Journal articles on the topic 'Small target motion detector'
To see the other types of publications on this topic, follow the link: Small target motion detector.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Small target motion detector.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Guo, Baicheng, Li Miao, and Shilin Zhou. "Small target detection based on point cloud feature learning." Journal of Physics: Conference Series 2284, no. 1 (June 1, 2022): 012025. http://dx.doi.org/10.1088/1742-6596/2284/1/012025.
Full textAbstract:
Abstract Small target detection is an important means of target detection, the photoelectric detector of which mainly uses infrared and visible light band. In many issues, the targets imaging in optical detector can be seen as small targets. Taking the time domain of the single frame detection result of small target motion as the third-dimensional information input, the small target detection can be transformed into the problem of point cloud target detection. The purpose of this paper is to implement a small target detection neural network based on point cloud feature learning.
2
Uzair, Muhammad, Russell S. A. Brinkworth, and Anthony Finn. "Detecting Small Size and Minimal Thermal Signature Targets in Infrared Imagery Using Biologically Inspired Vision." Sensors 21, no. 5 (March 5, 2021): 1812. http://dx.doi.org/10.3390/s21051812.
Full textAbstract:
Thermal infrared imaging provides an effective sensing modality for detecting small moving objects at long range. Typical challenges that limit the efficiency and robustness of the detection performance include sensor noise, minimal target contrast and cluttered backgrounds. These issues become more challenging when the targets are of small physical size and present minimal thermal signatures. In this paper, we experimentally show that a four-stage biologically inspired vision (BIV) model of the flying insect visual system have an excellent ability to overcome these challenges simultaneously. The early two stages of the model suppress spatio-temporal clutter and enhance spatial target contrast while compressing the signal in a computationally manageable bandwidth. The later two stages provide target motion enhancement and sub-pixel motion detection capabilities. To show the superiority of the BIV target detector over existing traditional detection methods, we perform extensive experiments and performance comparisons using high bit-depth, real-world infrared image sequences of small size and minimal thermal signature targets at long ranges. Our results show that the BIV target detector significantly outperformed 10 conventional spatial-only and spatiotemporal methods for infrared small target detection. The BIV target detector resulted in over 25 dB improvement in the median signal-to-clutter-ratio over the raw input and achieved 43% better detection rate than the best performing existing method.
3
Wiederman, Steven D., and David C. O’Carroll. "Biologically Inspired Feature Detection Using Cascaded Correlations of off and on Channels." Journal of Artificial Intelligence and Soft Computing Research 3, no. 1 (January 1, 2013): 5–14. http://dx.doi.org/10.2478/jaiscr-2014-0001.
Full textAbstract:
Abstract Flying insects are valuable animal models for elucidating computational processes underlying visual motion detection. For example, optical flow analysis by wide-field motion processing neurons in the insect visual system has been investigated from both behavioral and physiological perspectives [1]. This has resulted in useful computational models with diverse applications [2,3]. In addition, some insects must also extract the movement of their prey or conspecifics from their environment. Such insects have the ability to detect and interact with small moving targets, even amidst a swarm of others [4,5]. We use electrophysiological techniques to record from small target motion detector (STMD) neurons in the insect brain that are likely to subserve these behaviors. Inspired by such recordings, we previously proposed an ‘elementary’ small target motion detector (ESTMD) model that accounts for the spatial and temporal tuning of such neurons and even their ability to discriminate targets against cluttered surrounds [6-8]. However, other properties such as direction selectivity [9] and response facilitation for objects moving on extended trajectories [10] are not accounted for by this model. We therefore propose here two model variants that cascade an ESTMD model with a traditional motion detection model algorithm, the Hassenstein Reichardt ‘elementary motion detector’ (EMD) [11]. We show that these elaborations maintain the principal attributes of ESTMDs (i.e. spatiotemporal tuning and background clutter rejection) while also capturing the direction selectivity observed in some STMD neurons. By encapsulating the properties of biological STMD neurons we aim to develop computational models that can simulate the remarkable capabilities of insects in target discrimination and pursuit for applications in robotics and artificial vision systems.
4
Li, Zhaoxu, Qiang Ling, Jing Wu, Zhengyan Wang, and Zaiping Lin. "A Constrained Sparse-Representation-Based Spatio-Temporal Anomaly Detector for Moving Targets in Hyperspectral Imagery Sequences." Remote Sensing 12, no. 17 (August 27, 2020): 2783. http://dx.doi.org/10.3390/rs12172783.
Full textAbstract:
At present, small dim moving target detection in hyperspectral imagery sequences is mainly based on anomaly detection (AD). However, most conventional detection algorithms only utilize the spatial spectral information and rarely employ the temporal spectral information. Besides, multiple targets in complex motion situations, such as multiple targets at different velocities and dense targets on the same trajectory, are still challenges for moving target detection. To address these problems, we propose a novel constrained sparse representation-based spatio-temporal anomaly detection algorithm that extends AD from the spatial domain to the spatio-temporal domain. Our algorithm includes a spatial detector and a temporal detector, which play different roles in moving target detection. The former can suppress moving background regions, and the latter can suppress non-homogeneous background and stationary objects. Two temporal background purification procedures maintain the effectiveness of the temporal detector for multiple targets in complex motion situations. Moreover, the smoothing and fusion of the spatial and temporal detection maps can adequately suppress background clutter and false alarms on the maps. Experiments conducted on a real dataset and a synthetic dataset show that the proposed algorithm can accurately detect multiple targets with different velocities and dense targets with the same trajectory and outperforms other state-of-the-art algorithms in high-noise scenarios.
5
Nordström, Karin, Douglas M. Bolzon, and David C. O'Carroll. "Spatial facilitation by a high-performance dragonfly target-detecting neuron." Biology Letters 7, no. 4 (January 26, 2011): 588–92. http://dx.doi.org/10.1098/rsbl.2010.1152.
Full textAbstract:
Many animals visualize and track small moving targets at long distances—be they prey, approaching predators or conspecifics. Insects are an excellent model system for investigating the neural mechanisms that have evolved for this challenging task. Specialized small target motion detector (STMD) neurons in the optic lobes of the insect brain respond strongly even when the target size is below the resolution limit of the eye. Many STMDs also respond robustly to small targets against complex stationary or moving backgrounds. We hypothesized that this requires a complex mechanism to avoid breakthrough responses by background features, and yet to adequately amplify the weak signal of tiny targets. We compared responses of dragonfly STMD neurons to small targets that begin moving within the receptive field with responses to targets that approach the same location along longer trajectories. We find that responses along longer trajectories are strongly facilitated by a mechanism that builds up slowly over several hundred milliseconds. This allows the neurons to give sustained responses to continuous target motion, thus providing a possible explanation for their extraordinary sensitivity.
6
Niven, Jeremy E. "Visual Motion: Homing in on Small Target Detectors." Current Biology 16, no. 8 (April 2006): R292—R294. http://dx.doi.org/10.1016/j.cub.2006.03.044.
Full text
7
Li, Biao, Xu Zhiyong, Jianlin Zhang, Xiangru Wang, and Xiangsuo Fan. "Dim-Small Target Detection Based on Adaptive Pipeline Filtering." Mathematical Problems in Engineering 2020 (May 30, 2020): 1–15. http://dx.doi.org/10.1155/2020/8234349.
Full textAbstract:
In order to improve the robustness of the pipeline target detection algorithm against strong noises and occlusion, this paper presents an adaptive pipeline filtering algorithm (APFA). In APFA, the velocity and the center of the target are firstly predicted based on the smooth motion trajectory after background suppression. Then, time-domain energy enhancement of targets is adopted to improve the obscure target detection, and adaptively updating the center and radius of the pipeline filter are carried out for targets’ motion variation. Experiments on five different typical scenes show that APFA can improve the robustness of the pipeline filter against strong noises and even when targets are temporarily obscured partially or completely. Simultaneously, APFA can significantly improve the energy and signal-to-noise ratio of targets, and as a result, the target detection rate is significantly promoted on all experiments.
8
O'Carroll, David C., and Steven D. Wiederman. "Contrast sensitivity and the detection of moving patterns and features." Philosophical Transactions of the Royal Society B: Biological Sciences 369, no. 1636 (February 19, 2014): 20130043. http://dx.doi.org/10.1098/rstb.2013.0043.
Full textAbstract:
Theories based on optimal sampling by the retina have been widely applied to visual ecology at the level of the optics of the eye, supported by visual behaviour. This leads to speculation about the additional processing that must lie in between—in the brain itself. But fewer studies have adopted a quantitative approach to evaluating the detectability of specific features in these neural pathways. We briefly review this approach with a focus on contrast sensitivity of two parallel pathways for motion processing in insects, one used for analysis of wide-field optic flow, the other for detection of small features. We further use a combination of optical modelling of image blur and physiological recording from both photoreceptors and higher-order small target motion detector neurons sensitive to small targets to show that such neurons operate right at the limits imposed by the optics of the eye and the noise level of single photoreceptors. Despite this, and the limitation of only being able to use information from adjacent receptors to detect target motion, they achieve a contrast sensitivity that rivals that of wide-field motion sensitive pathways in either insects or vertebrates—among the highest in absolute terms seen in any animal.
9
Li, Jing, Yanran Dai, Congcong Li, Junqi Shu, Dongdong Li, Tao Yang, and Zhaoyang Lu. "Visual Detail Augmented Mapping for Small Aerial Target Detection." Remote Sensing 11, no. 1 (December 21, 2018): 14. http://dx.doi.org/10.3390/rs11010014.
Full textAbstract:
Moving target detection plays a primary and pivotal role in avionics visual analysis, which aims to completely and accurately detect moving objects from complex backgrounds. However, due to the relatively small sizes of targets in aerial video, many deep networks that achieve success in normal size object detection are usually accompanied by a high rate of false alarms and missed detections. To address this problem, we propose a novel visual detail augmented mapping approach for small aerial target detection. Concretely, we first present a multi-cue foreground segmentation algorithm including motion and grayscale information to extract potential regions. Then, based on the visual detail augmented mapping approach, the regions that might contain moving targets are magnified to multi-resolution to obtain detailed target information and rearranged into new foreground space for visual enhancement. Thus, original small targets are mapped to a more efficient foreground augmented map which is favorable for accurate detection. Finally, driven by the success of deep detection network, small moving targets can be well detected from aerial video. Experiments extensively demonstrate that the proposed method achieves success in small aerial target detection without changing the structure of the deep network. In addition, compared with the-state-of-art object detection algorithms, it performs favorably with high efficiency and robustness.
10
Yano, Taihei, Naoteru Gouda, Yukiyasu Kobayashi, Takuji Tsujimoto, Yoshito Niwa, and Yoshiyuki Yamada. "The scientific goal of the Japanese small astrometric satellite, Small-JASMINE." Proceedings of the International Astronomical Union 8, S289 (August 2012): 433–36. http://dx.doi.org/10.1017/s1743921312021898.
Full textAbstract:
AbstractSmall-JASMINE is a small Japanese astrometric satellite, developed mainly at the National Astronomical Observatory of Japan. The target launch date of Small-JASMINE is around 2017. The satellite will be equipped with a telescope with an aperture size of 30 cm and a focal length of approximately 3.9 m. The operational wavelength will be centered on the infrared Hw band, between 1.1 and 1.7 μm, using a HgCdTe detector with 4k × 4k pixels. This will enable us to observe the central regions of our Galaxy and clarify the dynamical structure of the bulge region. A restricted region of the Galactic bulge will be observed using a frame-linking method, which is different from the approach taken by both Hipparcos and Gaia, both developed at ESA. The target accuracy of the annual parallax and proper motion is approximately 10 μas and 10 μas yr−1, respectively, in the central region of the survey area of 0.3 × 0.3 deg2. The target accuracy of the annual parallax, ~ 50 μas, and that of the proper motion, ~ 50 μas yr−1, will be obtained within a region of 2 × 2 deg2. The observing region covers a field of approximately 3 × 3 deg2. The mission is required to continue for around three years to obtain reliable measurements. In the winter season, the angular distance between the Sun and the Galactic bulge region is small. Accordingly, we may have the chance to observe different regions which contain scientifically interesting targets, such as Cygnus X-1. If we are successful in observing the object over the course of a few weeks, the orbital elements of the star accompanying Cygnus X-1 can be resolved by Small-JASMINE.
11
Xiangsuo, Fan, Hongwei Guo, Xu Zhiyong, and Biao Li. "Dim and Small Targets Detection in Sequence Images Based on Spatiotemporal Motion Characteristics." Mathematical Problems in Engineering 2020 (October 16, 2020): 1–19. http://dx.doi.org/10.1155/2020/7164859.
Full textAbstract:
In order to effectively enhance the low detection rates of dim and small targets caused by dynamic backgrounds, this paper proposes a detection algorithm for dim and small targets in sequence images based on spatiotemporal motion characteristics. With regard to the spatial domain, this paper proposes an improved anisotropic background filtering algorithm that makes full use of the gradient differences between the target and the background pixels in the eight directions of the spatial domain and selects the mean value of the three directions with the lowest diffusion function in the eight directions as the differential filter to obtain a differential image. Then, the paper proposes a directional energy correlation enhancement algorithm in the time domain. Finally, based on the above preprocessing operations, we construct a dim and small targets detection algorithm in sequence images with local motion characteristics, which achieves target detection by determining the number of occurrences of the target, the number of displacements, and the total cumulative area in these sequential images. Experiments show that the proposed detection algorithm in this paper can effectively improve the detection of dim and small targets in dynamic scenes.
12
Wu, Di, Lihua Cao, Pengji Zhou, Ning Li, Yi Li, and Dejun Wang. "Infrared Small-Target Detection Based on Radiation Characteristics with a Multimodal Feature Fusion Network." Remote Sensing 14, no. 15 (July 25, 2022): 3570. http://dx.doi.org/10.3390/rs14153570.
Full textAbstract:
Infrared small-target detection has widespread influences on anti-missile warning, precise weapon guidance, infrared stealth and anti-stealth, military reconnaissance, and other national defense fields. However, small targets are easily submerged in background clutter noise and have fewer pixels and shape features. Furthermore, random target positions and irregular motion can lead to target detection being carried out in the whole space–time domain. This could result in a large amount of calculation, and the accuracy and real-time performance are difficult to be guaranteed. Therefore, infrared small-target detection is still a challenging and far-reaching research hotspot. To solve the above problem, a novel multimodal feature fusion network (MFFN) is proposed, based on morphological characteristics, infrared radiation, and motion characteristics, which could compensate for the deficiency in the description of single modal characteristics of small targets and improve the recognition precision. Our innovations introduced in the paper are addressed in the following three aspects: Firstly, in the morphological domain, we propose a network with the skip-connected feature pyramid network (SCFPN) and dilated convolutional block attention module integrated with Resblock (DAMR) introduced to the backbone, which is designed to improve the feature extraction ability for infrared small targets. Secondly, in the radiation characteristic domain, we propose a prediction model of atmospheric transmittance based on deep neural networks (DNNs), which predicts the atmospheric transmittance effectively without being limited by the complex environment to improve the measurement accuracy of radiation characteristics. Finally, the dilated convolutional-network-based bidirectional encoder representation from a transformers (DC-BERT) structure combined with an attention mechanism is proposed for the feature extraction of radiation and motion characteristics. Finally, experiments on our self-established optoelectronic equipment detected dataset (OEDD) show that our method is superior to eight state-of-the-art algorithms in terms of the accuracy and robustness of infrared small-target detection. The comparative experimental results of four kinds of target sequences indicate that the average recognition rate Pavg is 92.64%, the mean average precision (mAP) is 92.01%, and the F1 score is 90.52%.
13
Zhang, Junpeng, Xiuping Jia, and Jiankun Hu. "Local Region Proposing for Frame-Based Vehicle Detection in Satellite Videos." Remote Sensing 11, no. 20 (October 12, 2019): 2372. http://dx.doi.org/10.3390/rs11202372.
Full textAbstract:
Current new developments in remote sensing imagery enable satellites to capture videos from space. These satellite videos record the motion of vehicles over a vast territory, offering significant advantages in traffic monitoring systems over ground-based systems. However, detecting vehicles in satellite videos are challenged by the low spatial resolution and the low contrast in each video frame. The vehicles in these videos are small, and most of them are blurred into their background regions. While region proposals are often generated for efficient target detection, they have limited performance on satellite videos. To meet this challenge, we propose a Local Region Proposing approach (LRP) with three steps in this study. A video frame is segmented into semantic regions first and possible targets are then detected in these coarse scale regions. A discrete Histogram Mixture Model (HistMM) is proposed in the third step to narrow down the region proposals by quantifying their likelihoods towards the target category, where the training is conducted on positive samples only. Experiment results demonstrate that LRP generates region proposals with improved target recall rates. When a slim Fast-RCNN detector is applied, LRP achieves better detection performance over the state-of-the-art approaches tested.
14
Zhang, Lu Ping, Biao Li, and Lu Ping Wang. "A Infrared Small Moving Object Extraction Method in the Context of Complex Background Motion." Advanced Materials Research 760-762 (September 2013): 1879–83. http://dx.doi.org/10.4028/www.scientific.net/amr.760-762.1879.
Full textAbstract:
The detection of small moving target in the context of complex background is a difficult issue. A method combining interframe differential registration and adaptive wiener filtering aimed to suppress background to detect moving object in complex background is proposed. The fixed background in the fore-and-aft frames can be filtered out by the interframe registration which preserves the moving target, parts of background and noise due to interframe movement and the gray-scale fluctuation. On one hand the complex background is estimated by an adaptive wiener filter, and the background suppression leaves the high-frequency regions containing the moving target in image. On the other hand, most of the high-frequency regions corresponding to non-target area are eliminated by the inter-frame registration in the differential images. The motion of target is continual in image sequences, while the position of the leaked background is relatively fixed and the noise is of small size. The fusion of the background suppression and inter-frame registration makes the discrimination of targets, background and noise possible. The small moving target is detected by trajectory association based on its interframe trajectory continuity. Experiment results verify the feasibility of the method.
15
LIU Xiao, 刘. 晓., 崔光照 CUI Guang-zhao, 李正周 LI Zheng-zhou, and 熊伟奇 XIONG Wei-qi. "Small target motion detection based on layering of vision system." Optics and Precision Engineering 27, no. 10 (2019): 2251–62. http://dx.doi.org/10.3788/ope.20192710.2251.
Full text
16
REN, YING, CHIN SENG CHUA, and YEONG KHING HO. "MOTION DETECTION FROM TIME-VARIED BACKGROUND." International Journal of Image and Graphics 02, no. 02 (April 2002): 163–78. http://dx.doi.org/10.1142/s0219467802000561.
Full textAbstract:
This paper proposes a new background subtraction method for detecting moving objects (foreground) from a time-varied background. While background subtraction has traditionally worked well for stationary backgrounds, for a non-stationary viewing sensor, motion compensation can be applied but is difficult to realize to sufficient pixel accuracy in practice, and the traditional background subtraction algorithm fails. The problem is further compounded when the moving target to be detected/tracked is small, since the pixel error in motion compensating the background will subsume the small target. A Spatial Distribution of Gaussians (SDG) model is proposed to deal with moving object detection under motion compensation that has been approximately carried out. The distribution of each background pixel is temporally and spatially modeled. Based on this statistical model, a pixel in the current frame is classified as belonging to the foreground or background. For this system to perform under lighting and environmental changes over an extended period of time, the background distribution must be updated with each incoming frame. A new background restoration and adaptation algorithm is developed for the time-varied background. Test cases involving the detection of small moving objects within a highly textured background and a pan-tilt tracking system based on a 2D background mosaic are demonstrated successfully.
17
Ansari, Zahir Ahmed, Madhav Ji Nigam, and Avnish Kumar. "Accurate Tracking of Manoeuvring Target using Scale Estimation and Detection." Defence Science Journal 69, no. 5 (September 17, 2019): 495–502. http://dx.doi.org/10.14429/dsj.69.13042.
Full textAbstract:
Camera zoom operation and fast approaching/receding target causes scaling of acquired target in video frames. Fast moving target manifests in large inter-frame motion. In general, non-uniform background degrades performance of tracking algorithms. Fast Fourier transform (FFT)-based Correlation algorithms improve tracking in this scenario, but their applications is limited to small inter-frame motion. Increasing search region has implication on execution speed of the algorithms. Rapid target scaling, non-uniform background and large inter-frame motion of target hinder accurate and long term visual tracking. These challenges have been addressed for extended target tracking by augmenting fast discriminative scale space tracking (fDSST) algorithm with probable target location prediction and target detection. Localisation of fast motion has been achieved by applying fused outputs of Kalman filter and quadratic regression based prediction before applying fDSST. It has helped in accurate localisation of fast motion without increasing search region. In each frame, target location and size have been estimated using fDSST and further refined by target detection near this location. Smoothing and limiting of trajectory and size of detected target has enhanced tracking performance. Experimental results show considerable improvement of precision, success rate and centre location error tracking performance against state-of-the-art trackers in stringent conditions.
18
Bai, Qiu Chan, Chun Xia Jin, Ding Li Yang, and Ma Hua Wang. "The Target Motion Detection Algorithm Based on Gauss Mixture Model." Advanced Materials Research 468-471 (February 2012): 1421–25. http://dx.doi.org/10.4028/www.scientific.net/amr.468-471.1421.
Full textAbstract:
Background reduction technique not only has the characteristics of pixels identify changes and small time complexity, but also can provide better detection results. The paper puts forward the running average method constructing background image by Gaussian mixture mode detecting background region and foreground region, and then adopting background reduction realizes the detection of moving target. Experimental results show that the algorithm effectively may realize background extraction and updating, and then completely and accurately detects moving targets. The algorithm has been achieved good results in the video vehicle detection.
19
Ma, Xin, Yuzhao Zhang, Weiwei Zhang, Hongbo Zhou, and Haoran Yu. "SDWBF Algorithm: A Novel Pedestrian Detection Algorithm in the Aerial Scene." Drones 6, no. 3 (March 14, 2022): 76. http://dx.doi.org/10.3390/drones6030076.
Full textAbstract:
Due to the large amount of video data from UAV aerial photography and the small target size from the aerial perspective, pedestrian detection in drone videos remains a challenge. To detect objects in UAV images quickly and accurately, a small-sized pedestrian detection algorithm based on the weighted fusion of static and dynamic bounding boxes is proposed. First, a weighted filtration algorithm for redundant frames was applied using the inter-frame pixel difference algorithm cascading vision and structural similarity, which solved the redundancy of the UAV video data, thereby reducing the delay. Second, the pre-training and detector learning datasets were scale matched to address the feature representation loss caused by the scale mismatch between datasets. Finally, the static bounding extracted by YOLOv4 and the motion bounding boxes extracted by LiteFlowNet were subject to the weighted fusion algorithm to enhance the semantic information and solve the problem of missing and multiple detections in UAV object detection. The experimental results showed that the small object recognition method proposed in this paper enabled reaching an mAP of 70.91% and an IoU of 57.53%, which were 3.51% and 2.05% higher than the mainstream target detection algorithm.
20
Wang, Zhonghua, Yuan Liao, Qingping Liu, and Chunyong Li. "Motion estimation and spatial-temporal filter-based infrared small target detection algorithm." International Journal of Wireless and Mobile Computing 8, no. 3 (2015): 256. http://dx.doi.org/10.1504/ijwmc.2015.069388.
Full text
21
Fan, Xiangsuo, Zhiyong Xu, Jianlin Zhang, Yongmei Huang, Zhenming Peng, Ziran Wei, and Hongwei Guo. "Dim small target detection based on high-order cumulant of motion estimation." Infrared Physics & Technology 99 (June 2019): 86–101. http://dx.doi.org/10.1016/j.infrared.2019.04.008.
Full text
22
Bagheri, Zahra M., Steven D. Wiederman, Benjamin S. Cazzolato, Steven Grainger, and David C. O'Carroll. "Properties of neuronal facilitation that improve target tracking in natural pursuit simulations." Journal of The Royal Society Interface 12, no. 108 (July 2015): 20150083. http://dx.doi.org/10.1098/rsif.2015.0083.
Full textAbstract:
Although flying insects have limited visual acuity (approx. 1°) and relatively small brains, many species pursue tiny targets against cluttered backgrounds with high success. Our previous computational model, inspired by electrophysiological recordings from insect ‘small target motion detector’ (STMD) neurons, did not account for several key properties described from the biological system. These include the recent observations of response ‘facilitation’ (a slow build-up of response to targets that move on long, continuous trajectories) and ‘selective attention’, a competitive mechanism that selects one target from alternatives. Here, we present an elaborated STMD-inspired model, implemented in a closed loop target-tracking system that uses an active saccadic gaze fixation strategy inspired by insect pursuit. We test this system against heavily cluttered natural scenes. Inclusion of facilitation not only substantially improves success for even short-duration pursuits, but it also enhances the ability to ‘attend’ to one target in the presence of distracters. Our model predicts optimal facilitation parameters that are static in space and dynamic in time, changing with respect to the amount of background clutter and the intended purpose of the pursuit. Our results provide insights into insect neurophysiology and show the potential of this algorithm for implementation in artificial visual systems and robotic applications.
23
von Mühlenen, A., H. J. Müller, and R. Groner. "Perceptual Integration of Motion and Form in a Visual Search Task." Perception 26, no. 1_suppl (August 1997): 32. http://dx.doi.org/10.1068/v970145.
Full textAbstract:
Three visual search experiments were designed to investigate the processes involved in the efficient detection of motion - form conjunction targets. In experiment 1 the number of movement directions in the display were varied, and we tried to establish whether or not the target direction was predictable. Search was less efficient when items moved in multiple directions compared to just one direction; whether items moved in two, three, or four directions made relatively little difference. Pre-cuing of the target direction facilitated the search to a small, but non-negligible, extent; the facilitation was not due to better predictability of the display region that contained the target at the start of a trial. Experiment 2 was designed to estimate the relative contributions of stationary and moving nontargets to the search rate. Search rates were primarily determined by the number of moving nontargets; stationary nontargets sharing the target form also exerted a significant effect, but this was only about half as strong as that of moving nontargets; stationary nontargets not sharing the target form had little influence. In experiment 3 we examined the effects of movement speed and item size on search performance. Increasing the speed of the moving items (> 1.5 deg s−1) facilitated target detection when the task required segregation of the moving from the stationary items; when no segregation was necessary, increasing the movement speed impaired performance. When the display items were ‘large’, motion speed had little effect on target detection; but when the items were ‘small’, search efficiency declined with item movement faster than 1.5 deg s−1. A ‘parallel continuous processing’ account of motion form conjunction search is proposed.
24
Zhou, Yitong. "Research on Motion Target Detection Method Based on Machine Learning." Advances in Engineering Technology Research 3, no. 1 (December 6, 2022): 283. http://dx.doi.org/10.56028/aetr.3.1.283.
Full textAbstract:
In the development of modern science and technology, due to the small size, low cost, practical operation is very flexible, so the UAV has been fully used in environmental monitoring, geological survey, military exploration, agricultural plant protection and other fields. Among them, as one of the basic contents of UAV aerial photography research, moving target detection directly affects the quality and efficiency of UAV work. On the basis of understanding the research status of moving target detection methods, I choose random forest and kernel correlation filtering algorithms for experimental analysis, focusing on the application value of the algorithm in moving target detection. Finally, the experimental results show that the proposed algorithm is effective.
25
Wang, Hongxin, Jigen Peng, Xuqiang Zheng, and Shigang Yue. "A Robust Visual System for Small Target Motion Detection Against Cluttered Moving Backgrounds." IEEE Transactions on Neural Networks and Learning Systems 31, no. 3 (March 2020): 839–53. http://dx.doi.org/10.1109/tnnls.2019.2910418.
Full text
26
Milde, M. B., O. J. N. Bertrand, H. Ramachandran, M. Egelhaaf, and E. Chicca. "Spiking Elementary Motion Detector in Neuromorphic Systems." Neural Computation 30, no. 9 (September 2018): 2384–417. http://dx.doi.org/10.1162/neco_a_01112.
Full textAbstract:
Apparent motion of the surroundings on an agent's retina can be used to navigate through cluttered environments, avoid collisions with obstacles, or track targets of interest. The pattern of apparent motion of objects, (i.e., the optic flow), contains spatial information about the surrounding environment. For a small, fast-moving agent, as used in search and rescue missions, it is crucial to estimate the distance to close-by objects to avoid collisions quickly. This estimation cannot be done by conventional methods, such as frame-based optic flow estimation, given the size, power, and latency constraints of the necessary hardware. A practical alternative makes use of event-based vision sensors. Contrary to the frame-based approach, they produce so-called events only when there are changes in the visual scene. We propose a novel asynchronous circuit, the spiking elementary motion detector (sEMD), composed of a single silicon neuron and synapse, to detect elementary motion from an event-based vision sensor. The sEMD encodes the time an object's image needs to travel across the retina into a burst of spikes. The number of spikes within the burst is proportional to the speed of events across the retina. A fast but imprecise estimate of the time-to-travel can already be obtained from the first two spikes of a burst and refined by subsequent interspike intervals. The latter encoding scheme is possible due to an adaptive nonlinear synaptic efficacy scaling. We show that the sEMD can be used to compute a collision avoidance direction in the context of robotic navigation in a cluttered outdoor environment and compared the collision avoidance direction to a frame-based algorithm. The proposed computational principle constitutes a generic spiking temporal correlation detector that can be applied to other sensory modalities (e.g., sound localization), and it provides a novel perspective to gating information in spiking neural networks.
27
Liang, Dong Sheng, Zhao Hui Liu, and Wen Liu. "The Extracting System Design of Small Dim Targets in Complex Background." Advanced Materials Research 328-330 (September 2011): 2324–27. http://dx.doi.org/10.4028/www.scientific.net/amr.328-330.2324.
Full textAbstract:
For the moving small dim targets in visible image sequences with low SNR and complex background, whose contained characters are simple and poor, they are extracted difficultly. This paper proposes a new method to detect and extract positions of small dim moving targets. According to the features of moving targets, in a very short time interval, the target trajectory is considered as a straight line approximately. Firstly, it makes use of threshold segmentation methods to extract the positions of targets in each frame, then building the motion line equations after the joint of multi-frame processing results. Finally, the position of small dim targets are detected out and extracted, and false targets are eliminated accurately. Hardware system was designed and the algorithm is implemented on hardware systems successfully. The experiment results show related functions of the system and extracting algorithm is feasible, the system is stable and has a strong process ability, which can effectively detect and extract small and dim target in complex background correctly.
28
Vincent, Ashley Chey, Haley Furman, Rebecca C. Slepian, Kaitlyn R. Ammann, Carson Di Maria, Jung Hung Chien, Ka-Chun Siu, and Marvin J. Slepian. "Smart Phone-Based Motion Capture and Analysis: Importance of Operating Envelope Definition and Application to Clinical Use." Applied Sciences 12, no. 12 (June 17, 2022): 6173. http://dx.doi.org/10.3390/app12126173.
Full textAbstract:
Human movement is vital for life, with active engagement affording function, limiting disease, and improving quality; with loss resulting in disability; and the treatment and training leading to restoration and enhancement. To foster these endeavors a need exists for a simple and reliable method for the quantitation of movement, favorable for widespread user availability. We developed a Mobile Motion Capture system (MO2CA) employing a smart-phone and colored markers (2, 5, 10 mm) and here define its operating envelope in terms of: (1) the functional distance of marker detection (range), (2) the inter-target resolution and discrimination, (3) the mobile target detection, and (4) the impact of ambient illumination intensity. MO2CA was able to detect and discriminate: (1) single targets over a range of 1 to 18 ft, (2) multiple targets from 1 ft to 11 ft, with inter-target discrimination improving with an increasing target size, (3) moving targets, with minimal errors from 2 ft to 8 ft, and (4) targets within 1 to 18 ft, with an illumination of 100–300 lux. We then evaluated the utility of motion capture in quantitating regional-finger abduction/adduction and whole body–lateral flex motion, demonstrating a quantitative discrimination between normal and abnormal motion. Overall, our results demonstrate that MO2CA has a wide operating envelope with utility for the detection of human movements large and small, encompassing the whole body, body region, and extremity and digit movements. The definition of the effective operating envelope and utility of smart phone-based motion capture as described herein will afford accuracy and appropriate use for future application studies and serve as a general approach for defining the operational bounds of future video capture technologies that arise for potential clinical use.
29
Yan, Yongjiang. "Using the Improved SSD Algorithm to Motion Target Detection and Tracking." Computational Intelligence and Neuroscience 2022 (May 14, 2022): 1–10. http://dx.doi.org/10.1155/2022/1886964.
Full textAbstract:
Computer vision-based motion target detection and tracking, which is widely used in video surveillance, human-computer interaction, range interpretation, and other fields, is one of the current research hotspots in the field of computer vision. In engineering scenarios, the two are inseparable and need to work together to accomplish specific tasks. The related research is progressing rapidly, but there is still room for improving its timeliness, accuracy, and automation. In this paper, we summarize and classify some classical target detection methods, analyze the basic principles of convolutional neural networks, and analyze the classical detection algorithms based on region suggestion and deep regression networks. After that, we improve the SSD algorithm for the shortage of low-level feature convolution layers, which has insufficient feature extraction and leads to poor detection of small targets. For the motion target tracking problem, this paper studies the motion target tracking method based on support vector machine and proposes the tracking method of support vector regression and the corresponding online support vector regression solution method based on the analysis of support vector tracking method and structural support vector tracking method. In this paper, we propose a tracking method that fuses structural support vector machines and correlation filtering. The structure is based on the idea of Inception, which adds and replaces some feature convolution layers of the original network while maintaining the original lightweight backbone. The final experiments on the VOC data set demonstrate that the improved algorithm improves the average detection accuracy by 2.6% compared to the original algorithm and basically maintains the real-time speed as well. Experimental simulations on a subset of VOC data (human set) show a significant improvement in AP values and more effective and reliable detection tracking of moving targets. The stability and accuracy of motion target detection and tracking are improved by setting parameters, such as confidence level; the effectiveness and continuity of detection and tracking are judged by setting the interframe centroid distance.
30
Fan, Xiangsuo, Zhiyong Xu, Jianlin Zhang, Yongmei Huang, and Zhenming Peng. "Infrared Dim and Small Targets Detection Method Based on Local Energy Center of Sequential Image." Mathematical Problems in Engineering 2017 (2017): 1–16. http://dx.doi.org/10.1155/2017/4572147.
Full textAbstract:
In order to detect infrared (IR) dim and small targets in a strong clutter background, a method based on local energy center of sequential image is proposed. This paper began by using improved anisotropy for background prediction (IABP), followed by target enhancement by improved high-order cumulates (HOC). Finally, on the basis of image preprocessing, the paper constructs a sequential image energy center detection algorithm that integrates the neighborhood, continuity, area, and energy and other motion characteristics of the target. Experiments showed that the improved anisotropic background predication could be loyal to the true background of the original image to the maximum extent, presenting a superior overall performance to other background prediction methods; the improved HOC significantly increased the signal-noise ratio of images; when the signal-noise ratio (SNR) is lower than 2.5 dB, the proposed method could effectively eliminate noise and detect targets.
31
Kwan, Chiman, and Bence Budavari. "Enhancing Small Moving Target Detection Performance in Low-Quality and Long-Range Infrared Videos Using Optical Flow Techniques." Remote Sensing 12, no. 24 (December 9, 2020): 4024. http://dx.doi.org/10.3390/rs12244024.
Full textAbstract:
The detection of small moving objects in long-range infrared videos is challenging due to background clutter, air turbulence, and small target size. In this paper, we summarize the investigation of efficient ways to enhance the performance of small target detection in long-range and low-quality infrared videos containing moving objects. In particular, we focus on unsupervised, modular, flexible, and efficient methods for target detection performance enhancement using motion information extracted from optical flow methods. Three well-known optical flow methods were studied. It was found that optical flow methods need to be combined with contrast enhancement, connected component analysis, and target association in order to be effective for target detection. Extensive experiments using long-range mid-wave infrared (MWIR) videos from the Defense Systems Information Analysis Center (DSIAC) dataset clearly demonstrated the efficacy of our proposed approach.
32
Xu, Meng Xi, Xin Wang, Xi Jun Yan, Guo Fang Lv, Sheng Nan Zheng, and Hui Bin Wang. "Polarization Imaging Target Detection Method by Imitating Dragonfly Compound Eye LF-SF Mechanism." Applied Mechanics and Materials 347-350 (August 2013): 3881–84. http://dx.doi.org/10.4028/www.scientific.net/amm.347-350.3881.
Full textAbstract:
Recently, water surface target detection and tracking for sea, lake, or river are challenging research topics. This paper presents a framework of target detection and tracing based on three-channel synchronization polarization imaging and imitation dragonfly compound eye LF-SF (large field-small field) mechanism. This framework can make full use of the advantages of polarization sensitivity of the compound eyes of a dragonfly, and be useful for effective water surface target detection and motion vector estimation.
33
Park, Jaehong, Wonsang Hwang, Hyunil Kwon, Kwangsoo Kim, and Dong-il “Dan” Cho. "A novel line of sight control system for a robot vision tracking system, using vision feedback and motion-disturbance feedforward compensation." Robotica 31, no. 1 (April 12, 2012): 99–112. http://dx.doi.org/10.1017/s0263574712000124.
Full textAbstract:
SUMMARYThis paper presents a novel line of sight control system for a robot vision tracking system, which uses a position feedforward controller to preposition a camera, and a vision feedback controller to compensate for the positioning error. Continuous target tracking is an important function for service robots, surveillance robots, and cooperating robot systems. However, it is difficult to track a specific target using only vision information, while a robot is in motion. This is especially true when a robot is moving fast or rotating fast. The proposed system controls the camera line of sight, using a feedforward controller based on estimated robot position and motion information. Specifically, the camera is rotated in the direction opposite to the motion of the robot. To implement the system, a disturbance compensator is developed to determine the current position of the robot, even when the robot wheels slip. The disturbance compensator is comprised of two extended Kalman filters (EKFs) and a slip detector. The inputs of the disturbance compensator are data from an accelerometer, a gyroscope, and two wheel-encoders. The vision feedback information, which is the targeting error, is used as the measurement update for the two EKFs. Using output of the disturbance compensator, an actuation module pans the camera to locate a target at the center of an image plane. This line of sight control methodology improves the recognition performance of the vision tracking system, by keeping a target image at the center of an image frame. The proposed system is implemented on a two-wheeled robot. Experiments are performed for various robot motion scenarios in dynamic situations to evaluate the tracking and recognition performance. Experimental results showed the proposed system achieves high tracking and recognition performances with a small targeting error.
34
Chen, Xuewen, Yuanpeng Jia, Xiaoqi Tong, and Zirou Li. "Research on Pedestrian Detection and DeepSort Tracking in Front of Intelligent Vehicle Based on Deep Learning." Sustainability 14, no. 15 (July 28, 2022): 9281. http://dx.doi.org/10.3390/su14159281.
Full textAbstract:
In order to improve the tracking failure caused by small-target pedestrians and partially blocked pedestrians in dense crowds in complex environments, a pedestrian target detection and tracking method for an intelligent vehicle was proposed based on deep learning. On the basis of the YOLO detection model, the channel attention module and spatial attention module were introduced and were joined to the back of the backbone network Darknet-53 in order to achieve weight amplification of important feature information in channel and space dimensions and improve the representation ability of the model for important feature information. Based on the improved YOLO network, the flow of the DeepSort pedestrian tracking method was designed and the Kalman filter algorithm was used to estimate the pedestrian motion state. The Mahalanobis distance and apparent feature were used to calculate the similarity between the detection frame and the predicted pedestrian trajectory; the Hungarian algorithm was used to achieve the optimal matching of pedestrian targets. Finally, the improved YOLO pedestrian detection model and the DeepSort pedestrian tracking method were verified in the same experimental environment. The verification results showed that the improved model can improve the detection accuracy of small-target pedestrians, effectively deal with the problem of target occlusion, reduce the rate of missed detection and false detection of pedestrian targets, and improve the tracking failure caused by occlusion.
35
Perivolioti, Triantafyllia-Maria, Michal Tušer, Dimitrios Terzopoulos, Stefanos P. Sgardelis, and Ioannis Antoniou. "Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm." Water 13, no. 9 (May 7, 2021): 1304. http://dx.doi.org/10.3390/w13091304.
Full textAbstract:
DIDSON acoustic cameras provide a way to collect temporally dense, high-resolution imaging data, similar to videos. Detection of fish targets on those videos takes place in a manual or semi-automated manner, typically assisted by specialised software. Exploiting the visual nature of the recordings, tools and techniques from the field of computer vision can be applied in order to facilitate the relatively involved workflows. Furthermore, machine learning techniques can be used to minimise user intervention and optimise for specific detection and tracking scenarios. This study explored the feasibility of combining optical flow with a genetic algorithm, with the aim of automating motion detection and optimising target-to-background segmentation (masking) under custom criteria, expressed in terms of the result. A 1000-frame video sequence sample with sparse, smoothly moving targets, reconstructed from a 125 s DIDSON recording, was analysed under two distinct scenarios, and an elementary detection method was used to assess and compare the resulting foreground (target) masks. The results indicate a high sensitivity to motion, as well as to the visual characteristics of targets, with the resulting foreground masks generally capturing fish targets on the majority of frames, potentially with small gaps of undetected targets, lasting for no more than a few frames. Despite the high computational overhead, implementation refinements could increase computational feasibility, while an extension of the algorithms, in order to include the steps of target detection and tracking, could further improve automation and potentially provide an efficient tool for the automated preliminary assessment of voluminous DIDSON data recordings.
36
Keating, E. G., A. Pierre, and S. Chopra. "Ablation of the pursuit area in the frontal cortex of the primate degrades foveal but not optokinetic smooth eye movements." Journal of Neurophysiology 76, no. 1 (July 1, 1996): 637–41. http://dx.doi.org/10.1152/jn.1996.76.1.637.
Full textAbstract:
1. Neural pathology which impairs foveal smooth pursuit eye movements typically also degrades optokinetic pursuit of large textures, suggesting that the two kinds of pursuit share a common circuit. This study reports an exception. After sequential bilateral ablation of the pursuit area in the frontal lobe three monkeys displayed degraded pursuit of a small foveal target but performed normally on identical measures of optokinetic pursuit. 2. A related experiment in one subject demonstrated a pursuit deficit when the foveal target moved relative to the background, but not when background and target moved together. The frontal pursuit area may specifically control pursuit of relative motion, and do so by receiving signals primarily from motion detectors in the macular part of the visual field.
37
Milani, Ileana, Carlo Bongioanni, Fabiola Colone, and Pierfrancesco Lombardo. "Fusing Measurements from Wi-Fi Emission-Based and Passive Radar Sensors for Short-Range Surveillance." Remote Sensing 13, no. 18 (September 7, 2021): 3556. http://dx.doi.org/10.3390/rs13183556.
Full textAbstract:
In this work, we consider the joint use of different passive sensors for the localization and tracking of human targets and small drones at short ranges, based on the parasitic exploitation of Wi-Fi signals. Two different sensors are considered in this paper: (i) Passive Bistatic Radar (PBR) that exploits the Wi-Fi Access Point (AP) as an illuminator of opportunity to perform uncooperative target detection and localization and (ii) Passive Source Location (PSL) that uses radio frequency (RF) transmissions from the target to passively localize it, assuming that it is equipped with Wi-Fi devices. First, we show that these techniques have complementary characteristics with respect to the considered surveillance applications that typically include targets with highly variable motion parameters. Therefore, an appropriate sensor fusion strategy is proposed, based on a modified version of the Interacting Multiple Model (IMM) tracking algorithm, in order to benefit from the information diversity provided by the two sensors. The performance of the proposed strategy is evaluated against both simulated and experimental data and compared to the performance of the single sensors. The results confirm that the joint exploitation of the considered sensors based on the proposed strategy largely improves the positioning accuracy, target motion recognition capability and continuity in target tracking.
38
Tian, Zhongxin. "Motion Video Image Based on Sensor and Multiprocessing Technology in Track and Field Sports." Journal of Sensors 2022 (September 10, 2022): 1–14. http://dx.doi.org/10.1155/2022/7651539.
Full textAbstract:
In order to use motion video image processing technology to better guide and evaluate athletes’ technical and tactical ability, this paper first constructed a motion video image acquisition system. Secondly, a fuzzy kernel estimation method for uniform linear motion based on cepstrum property is proposed. Then, the motion blur areas to be processed are selected, and only these areas are deblurred. Finally, the effective removal of local motion blur is realized, and a clear scene image is obtained. Then, the maximum value of the total entropy of the image is calculated by using the information entropy theory, and the particle swarm optimization algorithm is introduced to find the maximum threshold of image segmentation. Finally, small wave optical flow estimation algorithm and rectangular window scanning algorithm across scales of motion image target detection algorithm are proposed, to not only solve the traditional optical flow estimation for fast moving object detection accuracy but also improve the efficiency of the optical flow computation. Compared to many kinds of algorithms, this paper proposed an algorithm that can improve the accuracy of moving target detection and measurement accuracy. And, the detection accuracy of the proposed algorithm is up to 86.5%. The estimated accuracy was as high as 65%. The segmentation accuracy is up to 95%.
39
Liang, Chao, Zhipeng Zhang, Xue Zhou, Bing Li, and Weiming Hu. "One More Check: Making “Fake Background” Be Tracked Again." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 1546–54. http://dx.doi.org/10.1609/aaai.v36i2.20045.
Full textAbstract:
The one-shot multi-object tracking, which integrates object detection and ID embedding extraction into a unified network, has achieved groundbreaking results in recent years. However, current one-shot trackers solely rely on single-frame detections to predict candidate bounding boxes, which may be unreliable when facing disastrous visual degradation, e.g., motion blur, occlusions. Once a target bounding box is mistakenly classified as background by the detector, the temporal consistency of its corresponding tracklet will be no longer maintained. In this paper, we set out to restore the bounding boxes misclassified as ``fake background'' by proposing a re-check network. The re-check network innovatively expands the role of ID embedding from data association to motion forecasting by effectively propagating previous tracklets to the current frame with a small overhead. Note that the propagation results are yielded by an independent and efficient embedding search, preventing the model from over-relying on detection results. Eventually, it helps to reload the ``fake background'' and repair the broken tracklets. Building on a strong baseline CSTrack, we construct a new one-shot tracker and achieve favorable gains by 70.7 ➡ 76.4, 70.6 ➡ 76.3 MOTA on MOT16 and MOT17, respectively. It also reaches a new state-of-the-art MOTA and IDF1 performance. Code is released at https://github.com/JudasDie/SOTS.
40
Liu, Lili, Jinghua Li, Xiaoyi Feng, Haijie Shi, and Xiaobiao Zhang. "Research on underwater sound source ranging algorithm based on histogram filtering." Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University 39, no. 3 (June 2021): 492–501. http://dx.doi.org/10.1051/jnwpu/20213930492.
Full textAbstract:
Aiming at the distance measurement of moving sound sources in shallow seas, this paper proposes a method of histogram filtering to realize underwater distance estimation of moving sound sources in shallow seas. The algorithm used the transmission loss, target motion parameter in the sound propagation and receival signal as prior knowledge to updated the state vector of the sound source, so as to realize the distance estimation of the shallow sea sound source, and this paper used SwellEx-96 database for experimental verification. The experimental results shown that: the depth estimating error of moving sound source is small, and when the detected horizontal distance is in the range of 10 km, the maximum range error of the horizontal distance is ±10 m, meanwhile the accuracy of ranging can be improved by improving the prior knowledge of the target motion parameters, which verifies that the histogram filtering algorithm can achieve better ranging for underwater moving targets.
41
Zhou, Tong, and Yilei Wang. "The Application and Development Trend of Youth Sports Simulation Based on Computer Vision." Wireless Communications and Mobile Computing 2022 (August 21, 2022): 1–9. http://dx.doi.org/10.1155/2022/8500869.
Full textAbstract:
Based on computer vision technology, this paper presents a human motion analysis and target tracking technology based on computer vision. In terms of moving target detection, the current moving target detection technology is summarized, and some experimental results of the algorithm are given. The background difference method under monocular camera is emphatically analyzed. The preliminary human contour is obtained by the background difference method. In order to obtain a smoother target contour, the mathematical morphology is used to remove the noise, and the judgment algorithm of the size of the image connected domain is added. A specific threshold is set to remove the connected domain of the noise block less than the threshold. In the aspect of human motion recognition, this paper selects human motion features, including minimum external rectangle aspect ratio, rectangularity, circularity, and moment invariant. The criteria for selecting human motion features are strong noise resistance and obvious distinction. Then, the three types of human motion images are classified and recognized. After cross-validation and parameter optimization, the recognition accuracy is significantly improved. The experimental results show that the video sequence collected in the field has a total of 376 frames, and the frame rate is 10 frames/s. Due to the small traffic, the mean shift algorithm based on adaptive feature fusion is used to track the target every 2-3 frames. And set the inverse X direction as the direction of entering the scene and the X direction as the direction of moving out of the scene so that the allowable error of the distance between the detection and tracking results is 10. The weight of each feature is dynamically updated by the similarity between the candidate model and the target model, which solves the problem that the mean shift algorithm is not robust enough when similar objects are occluded and interfered and achieves more accurate tracking.
42
Fu, Qinbing, Hongxin Wang, Cheng Hu, and Shigang Yue. "Towards Computational Models and Applications of Insect Visual Systems for Motion Perception: A Review." Artificial Life 25, no. 3 (August 2019): 263–311. http://dx.doi.org/10.1162/artl_a_00297.
Full textAbstract:
Motion perception is a critical capability determining a variety of aspects of insects' life, including avoiding predators, foraging, and so forth. A good number of motion detectors have been identified in the insects' visual pathways. Computational modeling of these motion detectors has not only been providing effective solutions to artificial intelligence, but also benefiting the understanding of complicated biological visual systems. These biological mechanisms through millions of years of evolutionary development will have formed solid modules for constructing dynamic vision systems for future intelligent machines. This article reviews the computational motion perception models originating from biological research on insects' visual systems in the literature. These motion perception models or neural networks consist of the looming-sensitive neuronal models of lobula giant movement detectors (LGMDs) in locusts, the translation-sensitive neural systems of direction-selective neurons (DSNs) in fruit flies, bees, and locusts, and the small-target motion detectors (STMDs) in dragonflies and hoverflies. We also review the applications of these models to robots and vehicles. Through these modeling studies, we summarize the methodologies that generate different direction and size selectivity in motion perception. Finally, we discuss multiple systems integration and hardware realization of these bio-inspired motion perception models.
43
Hou, A.-Hui, Yi-Hua Hu, Jia-Jie Fang, Nan-Xiang Zhao, and Shi-Long Xu. "Photon echo probability distribution characteristics and range walk error of small translational target for photon ranging." Acta Physica Sinica 71, no. 7 (2022): 074205. http://dx.doi.org/10.7498/aps.71.20211998.
Full textAbstract:
<sec>The photon counting Lidar enhances the signal-to-noise ratio of the echo signal and reduces the number of photons required for signal analysis, thereby improving the detection range and measurement accuracy. At present, the photon counting Lidar is mainly used to detect stationary targets, and the mechanism of the influence of long-distance target motion characteristics on the photon echo probability distribution is still unclear. Therefore, it is urgent to study the photon ranging performance of long-distance moving targets.</sec><sec>In this paper, the probability distribution model of photon detection echo of moving targets is established, and a Monte Carlo model for photon detection of arbitrary targets is given. Through experimental comparison, the correctness of the Monte Carlo simulation model is verified. Furthermore, the probability distribution characteristics of the laser echo and photon echo of a small rectangular target in translation within a detection period are compared. And the variation law of the probability distribution of photon detection under different translational speeds is analyzed. In addition, the relationship between the photon ranging error and the translational speed of the target is discussed.</sec><sec>The results show that the photon echo probability distribution of the translational target is more forward and the width is narrower than the laser pulse echo probability distribution. Compared with the extended target, the detection probability of the translational small target is significantly reduced, and the maximum average echo photon number is <inline-formula><tex-math id="M6">\begin{document}$ 1/10 $\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M6.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M6.png"/></alternatives></inline-formula> times that of the extended target, as a result, the photon detection of the translational target requires higher laser pulse energy. When the length of target is 1m, the range walk error reaches a maximum value at a speed of <inline-formula><tex-math id="M7">\begin{document}$25\;{\text{m/s}}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M7.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M7.png"/></alternatives></inline-formula>, i.e. <inline-formula><tex-math id="M8">\begin{document}$6.72\;{\text{ cm}}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M8.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M8.png"/></alternatives></inline-formula>, which is <inline-formula><tex-math id="M9">\begin{document}$ 1/2 $\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M9.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="7-20211998_M9.png"/></alternatives></inline-formula> times that of the extended target. With the increase of the translational speed, the range walk error first increases and then turns stable with the light spot acting as the boundary.</sec><sec>The method proposed in this paper can be further extended to photon detection and ranging of targets with other shapes, materials and attitudes. The research results provide a theoretical basis for the correction and performance improvement of the photon ranging of moving target. Furthermore, it lays the foundation for the detection of moving targets and accurate acquisition of information by photon counting Lidar.</sec>
44
Chen, Junjie, Bo Huang, Jianan Li, Ying Wang, Moxuan Ren, and Tingfa Xu. "Learning Spatio-Temporal Attention Based Siamese Network for Tracking UAVs in the Wild." Remote Sensing 14, no. 8 (April 8, 2022): 1797. http://dx.doi.org/10.3390/rs14081797.
Full textAbstract:
The popularity of unmanned aerial vehicles (UAVs) has made anti-UAV technology increasingly urgent. Object tracking, especially in thermal infrared videos, offers a promising solution to counter UAV intrusion. However, troublesome issues such as fast motion and tiny size make tracking infrared drone targets difficult and challenging. This work proposes a simple and effective spatio-temporal attention based Siamese method called SiamSTA, which performs reliable local searching and wide-range re-detection alternatively for robustly tracking drones in the wild. Concretely, SiamSTA builds a two-stage re-detection network to predict the target state using the template of first frame and the prediction results of previous frames. To tackle the challenge of small-scale UAV targets for long-range acquisition, SiamSTA imposes spatial and temporal constraints on generating candidate proposals within local neighborhoods to eliminate interference from background distractors. Complementarily, in case of target lost from local regions due to fast movement, a third stage re-detection module is introduced, which exploits valuable motion cues through a correlation filter based on change detection to re-capture targets from a global view. Finally, a state-aware switching mechanism is adopted to adaptively integrate local searching and global re-detection and take their complementary strengths for robust tracking. Extensive experiments on three anti-UAV datasets nicely demonstrate SiamSTA’s advantage over other competitors. Notably, SiamSTA is the foundation of the 1st-place winning entry in the 2nd Anti-UAV Challenge.
45
Fan, Xiangsuo, Juliu Li, Huajin Chen, Lei Min, and Feng Li. "Dim and Small Target Detection Based on Improved Hessian Matrix and F-Norm Collaborative Filtering." Remote Sensing 14, no. 18 (September 8, 2022): 4490. http://dx.doi.org/10.3390/rs14184490.
Full textAbstract:
In order to effectively improve the dim and small target detection ability of photoelectric detection system to solve the high false rate issue under complex clouds scene in background modeling, a novelty Hessian matrix and F-norm collaborative filtering is proposed in this paper. Considering the influence of edge noise, we propose an improved Hessian matrix background modeling (IHMM) algorithm, where a local saliency function for adaptive representation of the local gradient difference between the target and background region is constructed to suppress the background and preserve the target. Because the target energy is still weak after the background modeling, a new local multi-scale gradient maximum (LMGM) energy-enhancement model is constructed to enhance the target signal, and with the help of LMGM, the target’s energy significant growth and the target’s recognition are clearer. Thus, based on the above preprocessing, using the motion correlation of the target between frames, this paper proposes an innovative collaborative filtering model combining F-norm and Pasteur coefficient (FNPC) to obtain the real target in sequence images. In this paper, we selected six scenes of the target size of 2 × 2 to 3 × 3 and with complex clouds and ground edge contour to finish experimental verification. By comparing with 10 algorithms, the background modeling indicators SSIM, SNR, and IC of the IHMM model are greater than 0.9999, 47.4750 dB, and 12.1008 dB, respectively. In addition, the target energy-enhancement effect of LMGM model reaches 17.9850 dB in six scenes, and when the false alarm rate is 0.01%, the detection rate of the FNPC model reaches 100% in all scenes. It shows that the algorithm proposed in this paper has excellent performance in dim and small target detection.
46
Yang, Degui, Zhengyang Bai, and Junchao Zhang. "Infrared Weak and Small Target Detection Based on Top-Hat Filtering and Multi-Feature Fuzzy Decision-Making." Electronics 11, no. 21 (October 31, 2022): 3549. http://dx.doi.org/10.3390/electronics11213549.
Full textAbstract:
Infrared weak and small target detection in a complex background has always been a research hotspot in the fields of area defense and long-range precision strikes. Among them, the single-frame infrared weak and small target detection technology is even more difficult to study due to factors such as lack of target motion information, complex background, and low signal-to-noise ratio. Aiming at the problem of a high false alarm rate in infrared weak and small target detection caused by the complex background edges and noise interference in infrared images, this paper proposes an infrared weak and small target detection algorithm based on top-hat filtering and multi-feature fuzzy decision-making. The algorithm first uses the multi-structural element top-hat operator to filter the original image and then obtains the suspected target area through adaptive threshold segmentation; secondly, it uses image feature algorithms, such as central pixel contrast, regional gradient, and directional gradient, to extract the feature information of the suspected target at multiple scales, and the fuzzy decision method is used for multi-feature fusion to achieve the final target detection. Finally, the performance of the proposed algorithm and several existing comparison algorithms are compared using the measured infrared sequence image data of five different scenarios. The results show that the proposed algorithm has obvious advantages in various performance indicators compared with the existing algorithms for infrared image sequences in different interference scenarios, especially for complex background types, and has a lower performance under the condition of ensuring the same detection rate and false alarm rate and in meeting the real-time requirements of the algorithm.
47
., Prateek, and Rajeev Arya. "Perturbation Propagation Models for Underwater Sensor Localisation using Semidefinite Programming." Defence Science Journal 71, no. 6 (October 22, 2021): 807–15. http://dx.doi.org/10.14429/dsj.71.16791.
Full textAbstract:
Real time Underwater sensor networks (UWSNs) suffer from localisation issues due to a dearth of incorporation of different geometric scenarios in UWSN scenarios. To address these issues, this paper visualises three specific scenarios of perturbation. First, small sized and large numbered particles of perturbance moving in a tangential motion to the sensor nodes; second, a single numbered and large-sized particle moving in a rectilinear motion by displacing the sensor nodes into sideward and forward direction, and third, a radially outward propagating perturbance to observe the influenced sensor nodes as the perturbance moves outwards. A novel target localisation and tracking is facilitated by including marine vehicle navigation as a source of perturbation. Using semidefinite programming, the proposed perturbation models minimise localisation errors, thereby enhancing physical security of underwater sensor nodes. By leveraging the spin, cleaving motion and radial cast-away behaviour of underwater sensor nodes, the results confirm that the proposed propagation models can be conveniently applied to real time target detection and estimation of underwater target nodes.
48
Popescu, Florin C., and W. Zev Rymer. "End Points of Planar Reaching Movements Are Disrupted by Small Force Pulses: An Evaluation of the Hypothesis of Equifinality." Journal of Neurophysiology 84, no. 5 (November 1, 2000): 2670–79. http://dx.doi.org/10.1152/jn.2000.84.5.2670.
Full textAbstract:
A single force pulse was applied unexpectedly to the arms of five normal human subjects during nonvisually guided planar reaching movements of 10-cm amplitude. The pulse was applied by a powered manipulandum in a direction perpendicular to the motion of the hand, which gripped the manipulandum via a handle at the beginning, at the middle, or toward the end the movement. It was small and brief (10 N, 10 ms), so that it was barely perceptible. We found that the end points of the perturbed motions were systematically different from those of the unperturbed movements. This difference, dubbed “terminal error,” averaged 14.4 ± 9.8% (mean ± SD) of the movement distance. The terminal error was not necessarily in the direction of the perturbation, although it was affected by it, and it did not decrease significantly with practice. For example, while perturbations involving elbow extension resulted in a statistically significant shift in mean end-point and target-acquisition frequency, the flexion perturbations were not clearly affected. We argue that this error distribution is inconsistent with the “equilibrium point hypothesis” (EPH), which predicts minimal terminal error is determined primarily by the variance in the command signal itself, a property referred to as “equifinality.” This property reputedly derives from the “spring-like” properties of muscle and is enhanced by reflexes. To ensure that terminal errors were not due to mid-course voluntary corrections, we only accepted trials in which the final position was already established before such a voluntary response to the perturbation could have begun, that is, in a time interval shorter than the minimum reaction time (RT) for that subject. This RT was estimated for each subject in supplementary experiments in which the subject was instructed to move to a new target if perturbed and to the old target if no perturbation was detected. These RT movements were found to either stop or slow greatly at the original target, then re-accelerate to the new one. The average latency of this second motion was used to estimate the voluntary RT for each subject (316 ms mean). Additionally, we found that the hand neither exerted target-oriented force against the handle nor drifted toward the desired end point just before coming to rest, making it unlikely that the mechanical properties of the manipulandum prevented the hand from reaching its intended target.
49
Davidson, R. M., and D. B. Bender. "Selectivity for relative motion in the monkey superior colliculus." Journal of Neurophysiology 65, no. 5 (May 1, 1991): 1115–33. http://dx.doi.org/10.1152/jn.1991.65.5.1115.
Full textAbstract:
1. Cells in the superficial layers of the colliculus were studied in immobilized monkeys anesthetized with nitrous oxide. We examined sensitivity to the relative motion between two stimuli: a small target in a cell's receptive field and a large random-dot background pattern that filled most of the visual field outside the receptive field. 2. Most cells were nonselective for either target direction or speed when the background pattern was stationary but were selective for both direction and speed relative to a moving background. Selectivity for relative motion was independent of the absolute direction and speed of both target and background. When both moved at the same speed in the same direction, the response evoked by the target was strongly suppressed. Changing the background direction relative to the target reduced the suppression; suppression was minimal when the two moved in opposite directions. Selectivity for relative direction was broad: the average tuning width at half-amplitude was 136 degrees. When target and background moved in the same direction, increasing or decreasing background speed relative to the target likewise reduced suppression. Average tuning width for relative speed was 1.4 log units. 3. Selectivity for relative motion was a global phenomenon. Suppression was present even when the background pattern was excluded from a region 10 times the receptive-field diameter. However, suppression gradually diminished with increasing distance between the receptive field and the background pattern. 4. Relative motion selectivity was most common in the deeper part of the superficial layers. Ninety percent of the cells below the middle of the stratum griseum superficiale were selective for relative direction, whereas above this level only 45% of the cells were. 5. Cells in the magnocellular and parvocellular layers of the lateral geniculate nucleus did not show selectivity for relative direction. 6. We suggest that the lower one-half of the superficial grey layer and the stratum opticum together constitute a subdivision of the superior colliculus that is specialized to detect strong discontinuities in relative motion. Descending input by way of the corticotectal tract is probably essential for the detection process. the projections from this tectal motion zone to the pulvinar, and from there to prestriate cortex, may provide a feedback pathway through which motion discontinuities such as occur at dynamic occlusion boundaries can influence local feature detection by cortical neurons.
50
Zhao, Linghua, and Zhihua Huang. "A Moving Object Detection Method Using Deep Learning-Based Wireless Sensor Networks." Complexity 2021 (April 12, 2021): 1–12. http://dx.doi.org/10.1155/2021/5518196.
Full textAbstract:
Aiming at the problem of real-time detection and location of moving objects, the deep learning algorithm is used to detect moving objects in complex situations. In this paper, based on the deep learning algorithm of wireless sensor networks, a novel target motion detection method is proposed. This method uses the deep learning model to extract visual potential representation features through offline similarity function ranking learning and online model incremental update and uses the hierarchical clustering algorithm to achieve target detection and positioning; the low-precision histogram and high-precision histogram cascade the method which determines the correct position of the target and achieves the purpose of detecting the moving target. In order to verify the advantages and disadvantages of the deep learning algorithm compared with traditional moving object detection methods, a large number of comparative experiments are carried out, and the experimental results were analyzed qualitatively and quantitatively from a statistical perspective. The results show that, compared with the traditional methods, the deep learning algorithm based on the wireless sensor network proposed in this paper is more efficient. The detection and positioning method do not produce the error accumulation phenomenon and has significant advantages and robustness. The moving target can be accurately detected with a small computational cost.