Статті в журналах з теми "Cyclist detection"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Cyclist detection.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Cyclist detection".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Wang, Kelong, and Wei Zhou. "Pedestrian and cyclist detection based on deep neural network fast R-CNN." International Journal of Advanced Robotic Systems 16, no. 2 (March 1, 2019): 172988141982965. http://dx.doi.org/10.1177/1729881419829651.
Повний текст джерелаАнотація:
In this article, a unified joint detection framework for pedestrian and cyclist is established to realize the joint detection of pedestrian and cyclist targets. Based on the target detection of fast regional convolution neural network, a deep neural network model suitable for pedestrian and cyclist detection is established. Experiments for poor detection results for small-sized targets and complex and changeable background environment; various network improvement schemes such as difficult case extraction, multilayer feature fusion, and multitarget candidate region input were designed to improve detection and to solve the problems of frequent false detections and missed detections in pedestrian and cyclist target detection. Results of experimental verification of the pedestrian and cyclist database established in Beijing’s urban traffic environment showed that the proposed joint detection method for pedestrians and cyclists can realize the stable tracking of joint detection and clearly distinguish different target categories. Therefore, an important basis for the behavior decision of intelligent vehicles is provided.
2
Shahraki, Farideh Foroozandeh, Ali Pour Yazdanpanah, Emma E. Regentova, and Venkatesan Muthukumar. "A Trajectory Based Method of Automatic Counting of Cyclist in Traffic Video Data." International Journal on Artificial Intelligence Tools 26, no. 04 (August 2017): 1750015. http://dx.doi.org/10.1142/s0218213017500154.
Повний текст джерелаАнотація:
Due to the growing number of cyclist accidents on urban roads, methods for collecting information on cyclists are of significant importance to the Department of Transportation. The collected information provides insights into solving critical problems related to transportation planning, implementing safety countermeasures, and managing traffic flow efficiently. Intelligent Transportation System (ITS) employs automated tools to collect traffic information from traffic video data. One of the important factors that influence cyclists safety is their counts. In comparison to other road users, such as cars and pedestrians, the automated cyclist data collection is relatively a new research area. In this work, we develop a vision-based method for gathering cyclist count data at intersections and road segments. We implement a robust cyclist detection method based on a combination of classification features. We implement a multi-object tracking method based on the Kernelized Correlation Filters (KCF) in cooperation with the bipartite graph matching algorithm to track multiple cyclists. Then, a trajectory rebuilding method and a trajectory comparison model are applied to refine the accuracy of tracking and counting. The proposed method is the first cyclist counting method, that has the ability to count cyclists under different movement patterns. The trajectory data obtained can be further utilized for cyclist behavioral modeling and safety analysis.
3
Drory, Ami, Hongdong Li, and Richard Hartley. "Estimating the projected frontal surface area of cyclists from images using a variational framework and statistical shape and appearance models." Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology 231, no. 3 (May 10, 2017): 169–83. http://dx.doi.org/10.1177/1754337117705489.
Повний текст джерелаАнотація:
We present a computer vision-based approach to estimating the projected frontal surface area (pFSA) of cyclists from unconstrained images. Wind tunnel studies show a reduction in cyclists’ aerodynamic drag through manipulation of the cyclist’s pose. Whilst the mechanism by which reduction is achieved remains unknown, it is widely accepted in the literature that the drag is proportional to the cyclist’s pFSA. This paper describes a repeatable automatic method for pFSA estimation for the study of its relationship with aerodynamic drag in cyclists. The proposed approach is based on finding object boundaries in images. An initialised curve dynamically evolves in the image to minimise an energy function designed to force the curve to gravitate towards image features. To overcome occlusions and pose variation, we use a statistical cyclist shape and appearance models as priors to encourage the evolving curve to arrive at the desired solution. Contour initialisation is achieved using a discriminative object detection method based on offline supervised learning that yields a cyclist classifier. Once an instance of a cyclist is detected in an image and segmented, the pFSA is calculated from the area of the final curve. Applied to two challenging datasets of cyclist images, for cyclist detection our method achieves precision scores of 1.0 and 0.96 and recall scores of 0.68 and 0.83 on the wind tunnel and cyclists-in-natura datasets, respectively. For cyclist segmentation, it achieves 0.88 and 0.92 scores for the mean dice similarity coefficient metric on the two datasets, respectively. We discuss the performance of our method under occlusion, orientation, and pose conditions. Our method successfully estimates pFSA of cyclists and opens new vistas for exploration of the relationship between pFSA and aerodynamic drag.
4
Ahmed, Sarfraz, M. Nazmul Huda, Sujan Rajbhandari, Chitta Saha, Mark Elshaw, and Stratis Kanarachos. "Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey." Applied Sciences 9, no. 11 (June 6, 2019): 2335. http://dx.doi.org/10.3390/app9112335.
Повний текст джерелаАнотація:
As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.
5
Radová, Zuzana, and Luboš Nouzovský. "Measuring of Cyclist Impact Dynamics." Applied Mechanics and Materials 821 (January 2016): 456–63. http://dx.doi.org/10.4028/www.scientific.net/amm.821.456.
Повний текст джерелаАнотація:
The contribution is aimed at detection of cyclists’ dynamics in standard and non-standard situations. From forensic experts point of view there are significant both, ie. riding dynamics of cyclist and also post-crash motion in case of collision with passenger car.To determine the riding trajectory, it is necessary to devise a measuring apparatus and devise methods for measuring and processing of the collected data. This pilot study involves suggestion of available combination of several procedures such as accelerometric measuring, photogrammetry and GPS use. In addition, the pilot measurement to prove this method was performed.In the term of post-crash motion the paper deals with the biomechanical analysis of load exerted on the child cyclist in configuration typical for cyclists (sudden enter the road or the case of non-giving way; the car front vs. the left side of the cyclists). Safety contribution of the bicycle helmet.
6
Eddy, Chris, Christopher de Saxe, and David Cebon. "Camera-based measurement of cyclist motion." Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 233, no. 7 (August 7, 2018): 1793–805. http://dx.doi.org/10.1177/0954407018789301.
Повний текст джерелаАнотація:
Heavy goods vehicles are overrepresented in cyclist fatality statistics in the United Kingdom relative to their proportion of total traffic volume. In particular, the statistics highlight a problem for vehicles turning left across the path of a cyclist on their inside. In this article, we present a camera-based system to detect and track cyclists in the blind spot. The system uses boosted classifiers and geometric constraints to detect cyclist wheels, and Canny edge detection to locate the ground contact point. The locations of these points are mapped into physical coordinates using a calibration system based on the ground plane. A Kalman Filter is used to track and predict the future motion of the cyclist. Full-scale tests were conducted using a construction vehicle fitted with two cameras, and the results compared with measurements from an ultrasonic-sensor system. Errors were comparable to the ultrasonic system, with average error standard deviation of 4.3 cm when the cyclist was 1.5 m from the heavy goods vehicles, and 7.1 cm at a distance of 1 m. When results were compared to manually extracted cyclist position data, errors were less than 4 cm at separations of 1.5 and 1 m. Compared to the ultrasonic system, the camera system requires simple hardware and can easily differentiate cyclists from stationary or moving background objects such as parked cars or roadside furniture. However, the cameras suffer from reduced robustness and accuracy at close range and cannot operate in low-light conditions.
7
Jia, Enzo C., Jianqiang Wang, and Daiheng Ni. "An Efficient Methodology for Calibrating Traffic Flow Models Based on Bisection Analysis." Journal of Applied Mathematics 2014 (2014): 1–12. http://dx.doi.org/10.1155/2014/949723.
Повний текст джерелаАнотація:
As urban planning becomes more sophisticated, the accurate detection and counting of pedestrians and cyclists become more important. Accurate counts can be used to determine the need for additional pedestrian walkways and intersection reorganization, among other planning initiatives. In this project, a camera-based approach is implemented to create a real-time pedestrian and cyclist counting system which is regularly accurate to 85% and often achieves higher accuracy. The approach retasks a state-of-the-art traffic camera, the Autoscope Solo Terra, for pedestrian and bicyclist counting. Object detection regions are sized to identify multiple pedestrians moving in either direction on an urban sidewalk and bicyclists in an adjacent bicycle lane. Collected results are processed in real time, eliminating the need for video storage and postprocessing. In this paper, results are presented for a pedestrian walkway for pedestrian flow up to 108 persons/min and the limitations of the implemented system are enumerated. Both pedestrian and cyclist counting accuracy of over 90% is achieved.
8
Jin, Wenqiang, Srinivasan Murali, Youngtak Cho, Huadi Zhu, Tianhao Li, Rachael Thompson Panik, Anika Rimu, et al. "CycleGuard." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, no. 4 (December 27, 2021): 1–30. http://dx.doi.org/10.1145/3494992.
Повний текст джерелаАнотація:
Every year 41,000 cyclists die in road traffic-related incidents worldwide [47]. One of the most startling and infuriating conflicts that cyclists experience is the so-called "right hook". It refers to a vehicle striking a cyclist heading in the same direction by turning right into the cyclist. To prevent such a crash, this work presents CycleGuard, an acoustic-based collision detection system using smartphones. It is composed of a cheap commercial off-the-shelf (COTS) portable speaker that emits imperceptible high-frequency acoustic signals and a smartphone for reflected signal reception and analysis. Since received acoustic signals bear rich information of their reflecting objects, CycleGuard applies advanced acoustic ranging techniques to extract those information for traffic analysis. Cyclists are alerted if any pending right hook crashes are detected. Real-time alerts ensure that cyclists have sufficient time to react, apply brakes, and eventually avoid the hazard. To validate the efficacy of CycleGuard, we implement a proof-of-concept prototype and carry out extensive in-field experiments under a broad spectrum of settings. Results show that CycleGuard achieves up to 95% accuracy in preventing right hook crashes and is robust to various scenarios. It is also energy-friendly to run on battery-powered smartphones.
9
NAMIHIRA, Yuki, Jun MIURA, and Shuji OISHI. "Pedestrian and cyclist detection by LIDAR-camera fusion." Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2016 (2016): 2P2–07b4. http://dx.doi.org/10.1299/jsmermd.2016.2p2-07b4.
Повний текст джерела
10
S, Anjali, and Nithin Joe. "Faster RCNN for Concurrent Pedestrian and Cyclist Detection." International Journal of Electronics and Communication Engineering 5, no. 5 (May 25, 2018): 21–24. http://dx.doi.org/10.14445/23488549/ijece-v5i5p105.
Повний текст джерела
11
De Angelis, Marco, Víctor Marín Puchades, Federico Fraboni, Luca Pietrantoni, and Gabriele Prati. "Negative attitudes towards cyclists influence the acceptance of an in-vehicle cyclist detection system." Transportation Research Part F: Traffic Psychology and Behaviour 49 (August 2017): 244–56. http://dx.doi.org/10.1016/j.trf.2017.06.021.
Повний текст джерела
12
Mehtab, Sabeeha, and Wei Qi Yan. "Flexible neural network for fast and accurate road scene perception." Multimedia Tools and Applications 81, no. 5 (January 25, 2022): 7169–81. http://dx.doi.org/10.1007/s11042-022-11933-0.
Повний текст джерелаАнотація:
AbstractAccurate object detection on the road is the most important requirement of autonomous vehicles. Extensive work has been accomplished for car, pedestrian, and cyclist detection; however, comparatively, very few efforts have been put into 2D object detection. In this article, a dynamic approach is investigated to design a perfect unified neural network that could achieve the best results based on our available hardware. The proposed architecture is based on CSPNet for feature extraction in an end-to-end way. The net extracts visual features by using backbone subnet, visual object detection is based on a feature pyramid network (FPN). In order to increase the net flexibility, an auto-anchor generating method is applied to the detection layer that makes the net suitable for any datasets. For fine-tuning the net, activation, optimization, and loss functions are considered along with multiple check points. The proposed net is trained and tested based on the benchmark KITTI dataset. Our extensive experiments show that the proposed model for visual object detection is superior to others, where other nets output very low accuracy for pedestrian and cyclist detection, our proposed model achieves 99.3% recall rate based on our dataset.
13
Li, Xiaofei, Lingxi Li, Fabian Flohr, Jianqiang Wang, Hui Xiong, Morys Bernhard, Shuyue Pan, Dariu M. Gavrila, and Keqiang Li. "A Unified Framework for Concurrent Pedestrian and Cyclist Detection." IEEE Transactions on Intelligent Transportation Systems 18, no. 2 (February 2017): 269–81. http://dx.doi.org/10.1109/tits.2016.2567418.
Повний текст джерела
14
Liu, Chunsheng, Yu Guo, Shuang Li, and Faliang Chang. "ACF Based Region Proposal Extraction for YOLOv3 Network Towards High-Performance Cyclist Detection in High Resolution Images." Sensors 19, no. 12 (June 13, 2019): 2671. http://dx.doi.org/10.3390/s19122671.
Повний текст джерелаАнотація:
You Only Look Once (YOLO) deep network can detect objects quickly with high precision and has been successfully applied in many detection problems. The main shortcoming of YOLO network is that YOLO network usually cannot achieve high precision when dealing with small-size object detection in high resolution images. To overcome this problem, we propose an effective region proposal extraction method for YOLO network to constitute an entire detection structure named ACF-PR-YOLO, and take the cyclist detection problem to show our methods. Instead of directly using the generated region proposals for classification or regression like most region proposal methods do, we generate large-size potential regions containing objects for the following deep network. The proposed ACF-PR-YOLO structure includes three main parts. Firstly, a region proposal extraction method based on aggregated channel feature (ACF) is proposed, called ACF based region proposal (ACF-PR) method. In ACF-PR, ACF is firstly utilized to fast extract candidates and then a bounding boxes merging and extending method is designed to merge the bounding boxes into correct region proposals for the following YOLO net. Secondly, we design suitable YOLO net for fine detection in the region proposals generated by ACF-PR. Lastly, we design a post-processing step, in which the results of YOLO net are mapped into the original image outputting the detection and localization results. Experiments performed on the Tsinghua-Daimler Cyclist Benchmark with high resolution images and complex scenes show that the proposed method outperforms the other tested representative detection methods in average precision, and that it outperforms YOLOv3 by 13.69 % average precision and outperforms SSD by 25.27 % average precision.
15
Liu, Xianpeng, Nan Xue, and Tianfu Wu. "Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (June 28, 2022): 1810–18. http://dx.doi.org/10.1609/aaai.v36i2.20074.
Повний текст джерелаАнотація:
Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D image. It is a highly challenging problem and remains open, especially when no extra information (e.g., depth, lidar and/or multi-frames) can be leveraged in training and/or inference. This paper proposes a simple yet effective formulation for monocular 3D object detection without exploiting any extra information. It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection. The key idea is that with the annotated 3D bounding boxes of objects in an image, there is a rich set of well-posed projected 2D supervision signals available in training, such as the projected corner keypoints and their associated offset vectors with respect to the center of 2D bounding box, which should be exploited as auxiliary tasks in training. The proposed MonoCon is motivated by the Cramer–Wold theorem in measure theory at a high level. In implementation, it utilizes a very simple end-to-end design to justify the effectiveness of learning auxiliary monocular contexts, which consists of three components: a Deep Neural Network (DNN) based feature backbone, a number of regression head branches for learning the essential parameters used in the 3D bounding box prediction, and a number of regression head branches for learning auxiliary contexts. After training, the auxiliary context regression branches are discarded for better inference efficiency. In experiments, the proposed MonoCon is tested in the KITTI benchmark (car, pedestrian and cyclist). It outperforms all prior arts in the leaderboard on the car category and obtains comparable performance on pedestrian and cyclist in terms of accuracy. Thanks to the simple design, the proposed MonoCon method obtains the fastest inference speed with 38.7 fps in comparisons. Our code is released at https://git.io/MonoCon.
16
Xu, Jun, Yanxin Ma, Songhua He, and Jiahua Zhu. "3D-GIoU: 3D Generalized Intersection over Union for Object Detection in Point Cloud." Sensors 19, no. 19 (September 22, 2019): 4093. http://dx.doi.org/10.3390/s19194093.
Повний текст джерелаАнотація:
Three-dimensional (3D) object detection is an important research in 3D computer vision with significant applications in many fields, such as automatic driving, robotics, and human–computer interaction. However, the low precision is an urgent problem in the field of 3D object detection. To solve it, we present a framework for 3D object detection in point cloud. To be specific, a designed Backbone Network is used to make fusion of low-level features and high-level features, which makes full use of various information advantages. Moreover, the two-dimensional (2D) Generalized Intersection over Union is extended to 3D use as part of the loss function in our framework. Empirical experiments of Car, Cyclist, and Pedestrian detection have been conducted respectively on the KITTI benchmark. Experimental results with average precision (AP) have shown the effectiveness of the proposed network.
17
Hollaus, Bernhard, Jasper C. Volmer, and Thomas Fleischmann. "Cadence Detection in Road Cycling Using Saddle Tube Motion and Machine Learning." Sensors 22, no. 16 (August 17, 2022): 6140. http://dx.doi.org/10.3390/s22166140.
Повний текст джерелаАнотація:
Most commercial cadence-measurement systems in road cycling are strictly limited in their function to the measurement of cadence. Other relevant signals, such as roll angle, inclination or a round kick evaluation, cannot be measured with them. This work proposes an alternative cadence-measurement system with less of the mentioned restrictions, without the need for distinct cadence-measurement apparatus attached to the pedal and shaft of the road bicycle. The proposed design applies an inertial measurement unit (IMU) to the seating pole of the bike. In an experiment, the motion data were gathered. A total of four different road cyclists participated in this study to collect different datasets for neural network training and evaluation. In total, over 10 h of road cycling data were recorded and used to train the neural network. The network’s aim was to detect each revolution of the crank within the data. The evaluation of the data has shown that using pure accelerometer data from all three axes led to the best result in combination with the proposed network architecture. A working proof of concept was achieved with an accuracy of approximately 95% on test data. As the proof of concept can also be seen as a new method for measuring cadence, the method was compared with the ground truth. Comparing the ground truth and the predicted cadence, it can be stated that for the relevant range of 50 rpm and above, the prediction over-predicts the cadence with approximately 0.9 rpm with a standard deviation of 2.05 rpm. The results indicate that the proposed design is fully functioning and can be seen as an alternative method to detect the cadence of a road cyclist.
18
Yang, Lina, Yingping Huang, Xing Hu, Hongjian Wei, and Qixiang Wang. "Multiclass obstacles detection and classification using stereovision and Bayesian network for intelligent vehicles." International Journal of Advanced Robotic Systems 17, no. 4 (July 1, 2020): 172988142094727. http://dx.doi.org/10.1177/1729881420947270.
Повний текст джерелаАнотація:
Intelligent vehicles should be able to detect various obstacles and also identify their types so that the vehicles can take an appropriate level of protection and intervention. This article presents a method of detecting and classifying multiclass obstacles for intelligent vehicles. A stereovision-based method is used to segment obstacles from traffic background and measure three-dimensional geometrical features. A Bayesian network (BN) model has been established to further classify them into five classes, including pedestrian, cyclist, car, van, and truck. The BN model is trained using substantial data samples. The optimized structure of the model is determined from the necessary path condition method with a presupposition constraint (NPC+PC). The conditional probability table of the discrete nodes and the conditional probability distribution of the continuous nodes are determined from expectation maximization (EM) training algorithm with consideration of prior domain knowledge. Experiments were conducted using the object detection data set on the public KITTI benchmark, and the results show that the proposed BN model exhibits an excellent performance for obstacle classification while the full pipeline of the method including detection and classification is in the upper middle level compared with other existing methods.
19
Lamberts, Robert P., Theresa N. C. Mann, Gerard J. Rietjens, and Hendrik H. Tijdink. "Impairment of 40-km Time-Trial Performance but Not Peak Power Output With External Iliac Kinking: A Case Study in a World-Class Cyclist." International Journal of Sports Physiology and Performance 9, no. 4 (July 2014): 720–22. http://dx.doi.org/10.1123/ijspp.2013-0040b.
Повний текст джерелаАнотація:
Iliac blood-flow restrictions causing painful and “powerless” legs are often attributed to overtraining and may develop for some time before being correctly diagnosed. In the current study, differences between actual performance parameters and performance parameters predicted from the Lamberts and Lambert Submaximal Cycle Test (LSCT) were studied in a world-class cyclist with bilateral kinking of the external iliac artery before and after surgery. Two performance-testing sessions, including a peak-poweroutput (PPO) test and a 40-km time trial (TT) were conducted before surgery, while 1 testing session was conducted after the surgery. Actual vs LSCT-predicted performance parameters in the world-class cyclists were compared with 82 symptom-free trained to elite male cyclists. No differences were found between actual and LSCT-predicted PPO before and after surgical intervention. However, there were differences between actual and LSCT-predicted 40-km TT time in the tests performed before the surgery (2:51and 2:55 min:s, respectively). These differences were no longer apparent in the postsurgery 40-km TT (2 s). This finding suggests that iliac blood-flow restrictions seem to mainly impair endurance performance rather than peak cycling performance. A standard PPO test without brachial ankle blood-pressure measurements might not be able to reflect iliac bloodflow restrictions. Differences between actual and LSCT-predicted 40-km TT time may assist in earlier referral to a cardiovascular specialist and result in earlier detection of iliac blood-flow restrictions.
20
Hu, Junping, Shitu Abubakar, Shengjun Liu, Xiaobiao Dai, Gen Yang, and Hao Sha. "Near-Infrared Road-Marking Detection Based on a Modified Faster Regional Convolutional Neural Network." Journal of Sensors 2019 (December 27, 2019): 1–11. http://dx.doi.org/10.1155/2019/7174602.
Повний текст джерелаАнотація:
Pedestrians, motorist, and cyclist remain the victims of poor vision and negligence of human drivers, especially in the night. Millions of people die or sustain physical injury yearly as a result of traffic accidents. Detection and recognition of road markings play a vital role in many applications such as traffic surveillance and autonomous driving. In this study, we have trained a nighttime road-marking detection model using NIR camera images. We have modified the VGG-16 base network of the state-of-the-art faster R-CNN algorithm by using a multilayer feature fusion technique. We have demonstrated another promising feature fusion technique of concatenating all the convolutional layers within a stage to extract image features. The modification boosts the overall detection performance of the model by utilizing the advantages of the shallow layers and the deep layers of the VGG-16 network. The training samples were augmented using random rotation and translation to enhance the heterogeneity of the detection algorithm. We have achieved a mean average precision (mAP) of 89.48% and 92.83% for the baseline faster R-CNN and our modified method, respectively.
21
Liang, Tianjiao, Hong Bao, Weiguo Pan, Xinyue Fan, and Han Li. "AspectNet: Aspect-Aware Anchor-Free Detector for Autonomous Driving." Applied Sciences 12, no. 12 (June 11, 2022): 5972. http://dx.doi.org/10.3390/app12125972.
Повний текст джерелаАнотація:
The anchor-free-based object detection method is a crucial part in an autonomous driving system because of its low computing cost. However, the under-fitting of positive samples and over-fitting of negative samples affect the detection performance. An aspect-aware anchor-free detector is proposed in this paper to address this problem. Specifically, it adds an aspect prediction head at the end of the detector, which can learn different distributions of aspect ratios between other objects. The sample definition method is improved to alleviate the problem of positive and negative sample imbalance. A loss function is designed to strengthen the learning weight of the center point of the network. The validation results show that the AP50 and AP75 of the proposed method are 97.3% and 93.4% on BCTSDB, and the average accuracies of the car, pedestrian, and cyclist are 92.7%, 77.4%, and 78.2% on KITTI, respectively. The comparison results demonstrate that the proposed algorithm is better than existing anchor-free methods.
22
Micucci, Mantecchini, and Sangermano. "Analysis of the Relationship between Turning Signal Detection and Motorcycle Driver’s Characteristics on Urban Roads; A Case Study." Sensors 19, no. 8 (April 15, 2019): 1802. http://dx.doi.org/10.3390/s19081802.
Повний текст джерелаАнотація:
The investigations on the effectiveness of the turn signal in motorcyclists understanding of motorists’ potential intentions in potentially dangerous car–motorcycle interactions and on the relationships among some variables that could influence the perception of rear and front turn signal status are examined in this paper. The investigations have been based on data pooled from the answers of a survey of 136 motorcycle riders, with special regards to the correct detection of turning indicators. Experimental videos have been realized during in-situ simulations, both in urban and suburban areas, recording vehicular interactions in three-leg road intersections, able to potentially generate crash risks, through a 360-camera mounted on a motorcyclist’s helmet. The blinkers detection rate has been combined with other factors related to motorcyclist’s characteristics and test context (e.g., age, gender, location of the test site, presence of a car behind tester vehicles and if the motorcyclist are also habitual car or bicycle drivers) in a stepwise logistic regression that modelled the odds of detecting the turn signal turned on as a function of significant factors. Within the limits of the proposed methodology, the results highlight the low percentage of correct sighting of the turn indicators and confirm the existence of a relation between the detection of the turn indicators aspect and some of the variables considered (e.g., age, being habitual cyclist or car driver and the presence of a car occluding the views), suggesting the opportunity to further investigate the phenomenon through the use of ad-hoc simulations, in order to highlight connections among the factors that can influence the perception of turning indicators in potentially dangerous contexts for cars and motorcycles.
23
Mimouna, Amira, Ihsen Alouani, Anouar Ben Khalifa, Yassin El Hillali, Abdelmalik Taleb-Ahmed, Atika Menhaj, Abdeldjalil Ouahabi, and Najoua Essoukri Ben Amara. "OLIMP: A Heterogeneous Multimodal Dataset for Advanced Environment Perception." Electronics 9, no. 4 (March 27, 2020): 560. http://dx.doi.org/10.3390/electronics9040560.
Повний текст джерелаАнотація:
A reliable environment perception is a crucial task for autonomous driving, especially in dense traffic areas. Recent improvements and breakthroughs in scene understanding for intelligent transportation systems are mainly based on deep learning and the fusion of different modalities. In this context, we introduce OLIMP: A heterOgeneous Multimodal Dataset for Advanced EnvIronMent Perception. This is the first public, multimodal and synchronized dataset that includes UWB radar data, acoustic data, narrow-band radar data and images. OLIMP comprises 407 scenes and 47,354 synchronized frames, presenting four categories: pedestrian, cyclist, car and tram. The dataset includes various challenges related to dense urban traffic such as cluttered environment and different weather conditions. To demonstrate the usefulness of the introduced dataset, we propose a fusion framework that combines the four modalities for multi object detection. The obtained results are promising and spur for future research.
24
Shuang, Feng, Hanzhang Huang, Yong Li, Rui Qu, and Pei Li. "AFE-RCNN: Adaptive Feature Enhancement RCNN for 3D Object Detection." Remote Sensing 14, no. 5 (February 27, 2022): 1176. http://dx.doi.org/10.3390/rs14051176.
Повний текст джерелаАнотація:
The point clouds scanned by lidar are generally sparse, which can result in fewer sampling points of objects. To perform precise and effective 3D object detection, it is necessary to improve the feature representation ability to extract more feature information of the object points. Therefore, we propose an adaptive feature enhanced 3D object detection network based on point clouds (AFE-RCNN). AFE-RCNN is a point-voxel integrated network. We first voxelize the raw point clouds and obtain the voxel features through the 3D voxel convolutional neural network. Then, the 3D feature vectors are projected to the 2D bird’s eye view (BEV), and the relationship between the features in both spatial dimension and channel dimension is learned by the proposed residual of dual attention proposal generation module. The high-quality 3D box proposals are generated based on the BEV features and anchor-based approach. Next, we sample key points from raw point clouds to summarize the information of the voxel features, and obtain the key point features by the multi-scale feature extraction module based on adaptive feature adjustment. The neighboring contextual information is integrated into each key point through this module, and the robustness of feature processing is also guaranteed. Lastly, we aggregate the features of the BEV, voxels, and point clouds as the key point features that are used for proposal refinement. In addition, to ensure the correlation among the vertices of the bounding box, we propose a refinement loss function module with vertex associativity. Our AFE-RCNN exhibits comparable performance on the KITTI dataset and Waymo open dataset to state-of-the-art methods. On the KITTI 3D detection benchmark, for the moderate difficulty level of the car and the cyclist classes, the 3D detection mean average precisions of AFE-RCNN can reach 81.53% and 67.50%, respectively.
25
Roemer, Felix, Marius Mrosek, Simon Schmalfuss, and Markus Lienkamp. "New Approach for an Easily Detachable Electric Drive Unit for Off-the-Shelf Bicycles." World Electric Vehicle Journal 9, no. 3 (August 23, 2018): 37. http://dx.doi.org/10.3390/wevj9030037.
Повний текст джерелаАнотація:
While an increasing number of electric bicycles are sold, the majority is still conventional, i.e., pedal powered.Electric bicycles could raise the share of people cycling in place of more inefficient modes of transportation. This paper investigates and proposes a new approach for an electric drive unit that can easily be attached and detached to a large majority of existing off-the-shelf bicycles to convert them into legal electric assisted bicycles (pedelecs). Different drive mechanisms were investigated and a design with a friction roller at the rear wheel showed the greatest potential. A good solution is achieved with a single unit that incorporates batteries, electronics, motors and sensors in a single enclosure to minimize the mounting time. With a fastening on the seat stay tube using a simple clamp mechanism it can assist the cyclist on most existing bicycles. The legally-required pedal detection is done with an integrated proximity sensor. A prototype is built to prove a simple and nonspecific installation and convenient usage.
26
Kim, Jin-Cheol, Hwi-Gu Jeong, and Seongwook Lee. "Simultaneous Target Classification and Moving Direction Estimation in Millimeter-Wave Radar System." Sensors 21, no. 15 (August 2, 2021): 5228. http://dx.doi.org/10.3390/s21155228.
Повний текст джерелаАнотація:
In this study, we propose a method to identify the type of target and simultaneously determine its moving direction in a millimeter-wave radar system. First, using a frequency-modulated continuous wave (FMCW) radar sensor with the center frequency of 62 GHz, radar sensor data for a pedestrian, a cyclist, and a car are obtained in the test field. Then, a You Only Look Once (YOLO)-based network is trained with the sensor data to perform simultaneous target classification and moving direction estimation. To generate input data suitable for the deep learning-based classifier, a method of converting the radar detection result into an image form is also proposed. With the proposed method, we can identify the type of each target and its direction of movement with an accuracy of over 95%. Moreover, the pre-trained classifier shows an identification accuracy of 85% even for newly acquired data that have not been used for training.
27
Pavlovic, Ratko, and Zhanneta Kozina. "Differences in Anthropometric Characteristics and Body Composition of Athletes in Cyclic Endurance-Type Activities: A Case Study." Journal of Advances in Sports and Physical Education 5, no. 10 (October 12, 2022): 225–34. http://dx.doi.org/10.36348/jaspe.2022.v05i10.003.
Повний текст джерелаАнотація:
Endurance-type disciplines (running, cycling, biathlon) define the cyclic structure of an athlete's movements, which, in addition to functional parameters, also includes an adequate morphological profile and body composition. Based on the detection, analysis and evaluation of these parameters, it is possible to define the body composition of the competitors as well as possible mutual differences even though it is endurance sports. The results are all the more relevant if the profile of top athletes with notable results is being evaluated. The current case study analyzes the morphological dimensions and body composition of competitors of three different disciplines (middle and long distances, cycling, biathlon) of top-level competitors, members of national teams. The study was conducted: Uroš Gutić (UG) - runner middle and long distances, member of AK "Sarajevo" and the BIH athletic national team; Milan Milivojević (MM) – cyclist, member of Cycling club "Borac" Čačak (Serbia), and the member Serbian national team; Stefan Lopatić (SL) – biathlete, member SK "Romanija" Pale, and BIH national team.
28
Hariharan, Sneha, and Ravishankar T. K. "Smart Helmet." International Journal for Research in Applied Science and Engineering Technology 10, no. 12 (December 31, 2022): 1365–67. http://dx.doi.org/10.22214/ijraset.2022.48212.
Повний текст джерелаАнотація:
Abstract: As the number of motorcyclists in our country rises, so do the number of traffic accidents and fatalities. The majority of these accidents are the result of drunk driving and a failure to wear a helmet. The majority of nations now require their residents to wear helmets while riding bikes and to never ride while intoxicated, but despite this, the laws are still broken. Drive Protection and Accident Detection Smart Helmet was developed in an effort to address this issue as engineers using the use of mechatronics. It is made up of an intelligent system that is built into the helmet and the vehicle. The helmet device makes sure the motorcyclist is wearing a helmet and is not drinking during the trip. If the aforementioned requirement is not met, it interacts with the vehicle unit to turn off the motorcycle's ignition system. Vehicle unit checks and intimates’ accident and SMS notifies of accident using geometric coordinates. Geometric coordinates can be used to locate the injured cyclist using a basic GPS monitoring software. The primary goal of the suggested idea is to offer a safe and affordable smart helmet. The smart helmet was designed using a Wi-Fi enabled processor and an integrated network of sensors for the engine control system, accident alert system, and alcohol detection. When it comes to the driver's safety, the suggested system is quite beneficial.
29
Hussain, Souhayla O. "Study on post-partum uterine involution by Ultrasonography and progesterone profile in local goats in Iraq." Iraqi Journal of Veterinary Medicine 40, no. 1 (June 5, 2016): 151–56. http://dx.doi.org/10.30539/iraqijvm.v40i1.153.
Повний текст джерелаАнотація:
The study was conducted to investigate and characteriz the time of uterine involution in local goats in Iraq by measuring the uterine diameter, uterine lumen (mm) and monitoring early post-partum ovarian activity as proved by Ultrasonography and progesterone assessment in local goats. 15 goats were submitted to examine from day 3 to 40 after kidding by Ultrasonography. Trans abdominal ultrasound approach was performed from day 3 to 5 after kidding and continued by trans rectal approach to follow up the uterine involution until day 40. Progesterone levels were measured starting from day of parturition, then a weekly measure until day 34 of post-partum period. Progesterone was assayed by Radio immune assay. The obtained results showed that complete of uterine involution started at day 26 (6.67) % and completed at day 34 post-partum in all does (100%). on the other hand involution of the uterus was completed at day 26, 27, 28, 29, 31, 33 after parturition with a percentage of 6.67%, 13.34%, 33.34%, 40%, 46.67%, 66.67%, 73.34% and 80% respectively. Average uterine lumen (mm) from days 3-7, 8- 14, 15- 21, 22- 28, 29 -35 and 36-40 were 9.02, 5.82, 5.14, 3.51, 2.66, and 2.0 (mm) respectively. Average uterine diameter (mm) was 40.25, 33.9, 31.4, 25.57, 20 .15 and 16.35 at day 3-7, 8- 14, 15-28, 29-35 and 36-40 respectively. Regarding progesterone profile, results indicated that the mean value of the hormone was 0.267±0.005 ng /ml at parturition and the values were 0.320±0.007, 0.414±00.5, 0.536 ±0.013, and 1.945 ±0.129 ng/ ml at day 7, 14, 21 and day 30, respectively. It could be concluded that Ultrasonography image proved to be a valuable and safe tool in monitoring uterine involution and measuring of progesterone is a precise biological marker for the detection of resumption of ovarian cyclist during post-partum period.
30
Beanland, Vanessa, and Lisa J. Hansen. "Do cyclists make better drivers? Associations between cycling experience and change detection in road scenes." Accident Analysis & Prevention 106 (September 2017): 420–27. http://dx.doi.org/10.1016/j.aap.2017.07.013.
Повний текст джерела
31
Xu, Xing, Xiang Wu, Yun Zhao, Xiaoshu Lü, and Aki Aapaoja. "3D Object Detection Algorithm Based on the Reconstruction of Sparse Point Clouds in the Viewing Frustum." Mobile Information Systems 2022 (October 15, 2022): 1–9. http://dx.doi.org/10.1155/2022/1611097.
Повний текст джерелаАнотація:
In response to the problem that the detection precision of the current 3D object detection algorithm is low when the object is severely occluded, this study proposes an object detection algorithm based on the reconstruction of sparse point clouds in the viewing frustum. The algorithm obtains more local feature information of the sparse point clouds in the viewing frustum through dimensional expansion, performs the fusion of local and global feature information of the point cloud data to obtain point cloud data with more complete semantic information, and then applies the obtained data to the 3D object detection task. The experimental results show that the precision of object detection in both 3D view and BEV (Bird’s Eye View) can be improved effectively through the algorithm, especially object detection of moderate and hard levels when the object is severely occluded. In the 3D view, the average precision of the 3D detection of cars, pedestrians, and cyclists at a moderate level can be increased by 7.1p.p., 16.39p.p., and 5.42p.p., respectively; in BEV, the average precision of the 3D detection of car, pedestrians, and cyclists at hard level can be increased by 6.51p.p., 16.57p.p., and 7.18p.p., respectively, thus indicating the effectiveness of the algorithm.
32
Koo, Helen S., and Xiao Huang. "Visibility aid cycling clothing: flashing light-emitting diode (FLED) configurations." International Journal of Clothing Science and Technology 27, no. 3 (June 1, 2015): 460–71. http://dx.doi.org/10.1108/ijcst-09-2014-0104.
Повний текст джерелаАнотація:
Purpose – The purpose of this paper is to investigate drivers’ differing psychological perceptions of cyclists’ conspicuity according to active visibility aid configurations on clothing. Design/methodology/approach – The flashing light-emitting diodes (FLEDs) were positioned on the major joints (shoulders, elbows, wrists, hips, knees, and ankles) in eight configurations and pre- and post-surveys were conducted. Findings – The results indicated that there were significant differences among the eight configurations in observers’ detection and recognition of cyclists, contributions of FLEDs, and visibility of cyclists (p<0.001). Among the eight different configurations on joints, FLEDs on the hips, knees, and ankles were the most detectable, recognizable, and visible. Originality/value – Most of the previous studies have investigated passive visibility aids and there is a lack of research on FLED configurations on major joints for cyclists. Thus, this study is expected to be beneficial to designers when developing active visibility aid clothing for cyclists.
33
Allebosch, Gianni, Simon Van den Bossche, Peter Veelaert, and Wilfried Philips. "Camera-Based System for Drafting Detection While Cycling." Sensors 20, no. 5 (February 25, 2020): 1241. http://dx.doi.org/10.3390/s20051241.
Повний текст джерелаАнотація:
Drafting involves cycling so close behind another person that wind resistance is significantly reduced, which is illegal during most long distance and several short distance triathlon and duathlon events. In this paper, a proof of concept for a drafting detection system based on computer vision is proposed. After detecting and tracking a bicycle through the various scenes, the distance to this object is estimated through computational geometry. The probability of drafting is then determined through statistical analysis of subsequent measurements over an extended period of time. These algorithms are tested using a static recording and a recording that simulates a race situation with ground truth distances obtained from a Light Detection And Ranging (LiDAR) system. The most accurate developed distance estimation method yields an average error of 0.46 m in our test scenario. When sampling the distances at periods of 1 or 2 s, simulations demonstrate that a drafting violation is detected quickly for cyclists riding at 2 m or more below the limit, while generally avoiding false positives during the race-like test set-up and five hour race simulations.
34
Wang, Chen, Yulu Dai, Wei Zhou, and Yifei Geng. "A Vision-Based Video Crash Detection Framework for Mixed Traffic Flow Environment Considering Low-Visibility Condition." Journal of Advanced Transportation 2020 (January 17, 2020): 1–11. http://dx.doi.org/10.1155/2020/9194028.
Повний текст джерелаАнотація:
In this paper, a vision-based crash detection framework was proposed to quickly detect various crash types in mixed traffic flow environment, considering low-visibility conditions. First, Retinex image enhancement algorithm was introduced to improve the quality of images, collected under low-visibility conditions (e.g., heavy rainy days, foggy days and dark night with poor lights). Then, a Yolo v3 model was trained to detect multiple objects from images, including fallen pedestrians/cyclists, vehicle rollover, moving/stopped vehicles, moving/stopped cyclists/pedestrians, and so on. Then, a set of features were developed from the Yolo outputs, based on which a decision model was trained for crash detection. An experiment was conducted to validate the model framework. The results showed that the proposed framework achieved a high detection rate of 92.5%, with relatively low false alarm rate of 7.5%. There are some useful findings: (1) the proposed model outperformed empirical rule-based detection models; (2) image enhancement method can largely improve crash detection performance under low-visibility conditions; (3) the accuracy of object detection (e.g., bounding box prediction) can impact crash detection performance, especially for minor motor-vehicle crashes. Overall, the proposed framework can be considered as a promising tool for quick crash detection in mixed traffic flow environment under various visibility conditions. Some limitations are also discussed in the paper.
35
Konishi, Yuichi, Kosuke Shigematsu, Takashi Tsubouchi, and Akihisa Ohya. "Detection of Target Persons Using Deep Learning and Training Data Generation for Tsukuba Challenge." Journal of Robotics and Mechatronics 30, no. 4 (August 20, 2018): 513–22. http://dx.doi.org/10.20965/jrm.2018.p0513.
Повний текст джерелаАнотація:
The Tsukuba Challenge is an open experiment competition held annually since 2007, and wherein the autonomous navigation robots developed by the participants must navigate through an urban setting in which pedestrians and cyclists are present. One of the required tasks in the Tsukuba Challenge from 2013 to 2017 was to search for persons wearing designated clothes within the search area. This is a very difficult task since it is necessary to seek out these persons in an environment that includes regular pedestrians, and wherein the lighting changes easily because of weather conditions. Moreover, the recognition system must have a light computational cost because of the limited performance of the computer that is mounted onto the robot. In this study, we focused on a deep learning method of detecting the target persons in captured images. The developed detection system was expected to achieve high detection performance, even when small-sized input images were used for deep learning. Experiments demonstrated that the proposed system achieved better performance than an existing object detection network. However, because a vast amount of training data is necessary for deep learning, a method of generating training data to be used in the detection of target persons is also discussed in this paper.
36
Valle-Melón, J. M., Á. Rodríguez-Miranda, and P. Pérez-Vidiella. "Detección del movimiento cíclico estacional en edificios históricos por métodos topográficos." Materiales de Construcción 61, no. 301 (March 11, 2011): 131–42. http://dx.doi.org/10.3989/mc.2011.54409.
Повний текст джерела
37
Tewson, Paul, Scott Martinka, Nathan Shaner, Catherine Berlot, Anne Marie Quinn та Thomas Hughes. "Assay for Detecting Gαi-Mediated Decreases in cAMP in Living Cells". SLAS DISCOVERY: Advancing the Science of Drug Discovery 23, № 9 (10 липня 2018): 898–906. http://dx.doi.org/10.1177/2472555218786238.
Повний текст джерелаАнотація:
Cell-based assays to detect Gαi signaling are often indirect, frequently involve complex pharmacological interventions, and are usually blind to the kinetics of the signaling. Our goal was to develop a simple, direct measure of Gαi signaling in living cells. We previously reported our fluorescent cADDis assay and showed that it reliably detects Gαs-mediated increases in cAMP levels. Agonists that stimulate a Gs-coupled receptor produce changes in the intensity of bright green or red fluorescent protein sensors that can be followed over time using automated fluorescence plate readers or fluorescence imaging systems. Since the cADDis sensors can monitor Gαs-mediated increases in adenylyl cyclase activity, in theory they should also be capable of detecting Gαi-mediated decreases. Here we apply our green fluorescent cADDis sensor to the detection of Gαi-mediated inhibition of adenylyl cyclase activity. We validated and optimized the assay in living HEK 293T cells using several known Gαi-coupled receptors and agonists, and we report robust Z′ statistics and consistent EC50 responses.
38
Yang, Jing, and Ming Gou. "Follow-Based Forward Obstacle Detection Using Vision Insensitive Feature for Road Cycling." Advanced Materials Research 718-720 (July 2013): 2427–31. http://dx.doi.org/10.4028/www.scientific.net/amr.718-720.2427.
Повний текст джерелаАнотація:
Paper proposes a method for detecting general obstacles on a road by subtracting present and past in road cycling camera images. The image-subtraction-based object detection approach can be applied to detect any kind of obstacles although the existing learning based methods detect only specific obstacles. To detect general obstacles, the proposed method first computes a frame-by-frame correspondence between the present and the past in-road cycling camera image sequences, and then registries road surfaces between the frames. Finally, obstacles are detected by applying image subtraction to the redistricted road surface regions with a vision insensitive feature for robust detection. Experiments were conducted by using several image sequences captured by an actual in-road cycling camera to confirm the effectiveness of the proposed method. The experimental results shows that the proposed method can detect general obstacles accurately at a distance enough to avoid them safely even with different situations.
39
Han, Guangjie, Yintian Zhu, Lyuchao Liao, Huiwen Yao, Zhaolin Zhao, and Qi Zheng. "Hybrid Attention-Based 3D Object Detection with Differential Point Clouds." Electronics 11, no. 23 (December 2, 2022): 4010. http://dx.doi.org/10.3390/electronics11234010.
Повний текст джерелаАнотація:
Object detection based on point clouds has been widely used for autonomous driving, although how to improve its detection accuracy remains a significant challenge. Foreground points are more critical for 3D object detection than background points; however, most current detection frameworks cannot effectively preserve foreground points. Therefore, this work proposes a hybrid attention-based 3D object detection method with differential point clouds, which we name HA-RCNN. The method differentiates the foreground points from the background ones to preserve the critical information of foreground points. Extensive experiments conducted on the KITTI dataset show that the model outperforms the state-of-the-art methods, especially in recognizing large objects such as cars and cyclists.
40
Olszewski, Piotr, Witold Czajewski, Beata Osińska, Piotr Szagała, and Paweł Włodarek. "Investigation of traffic conflicts at signalised intersections in Warsaw." MATEC Web of Conferences 262 (2019): 05009. http://dx.doi.org/10.1051/matecconf/201926205009.
Повний текст джерелаАнотація:
Although traffic safety situation in general is improving, the numbers of pedestrians and cyclists hit when crossing a road have not significantly decreased recently. Based on police accident records for years 2010-2014, some 735 pedestrians and 505 cyclists were hit by motor vehicles in Warsaw. Investigation reported in this paper is a part of the European project InDeV. One aim of the project is to find correlation between accidents and traffic conflicts and thus provide a solid base for using surrogate safety measures as safety diagnostic tools. Three typical signalised intersections in Warsaw were selected for video recording. Relevant encounters between motor vehicles and vulnerable road users (pedestrians and cyclists) were identified and analysed using programs RUBA and T-Analyst. The paper describes the semiautomatic video data processing and problems regarding some technical and methodological aspects of conflict detection. Based on video analysis of 24 hours of recording for each intersection, preliminary characteristics of encounters between pedestrians/cyclists and motorised vehicles have been developed. Statistical distributions of encounter parameters such as time-to-collision (TTC) and post-encroachment time (PET) are presented. These will be used in the development of appropriate safety indicators.
41
Peng, Hao, Guofeng Tong, Zheng Li, Yaqi Wang, and Yuyuan Shao. "3D object detection combining semantic and geometric features from point clouds." Cobot 1 (January 12, 2022): 2. http://dx.doi.org/10.12688/cobot.17433.1.
Повний текст джерелаАнотація:
Background: 3D object detection based on point clouds in road scenes has attracted much attention recently. The voxel-based methods voxelize the scene to regular grids, which can be processed with the advanced feature learning frameworks based on convolutional layers for semantic feature learning. The point-based methods can extract the geometric feature of the point due to the coordinate reservations. The combination of the two is effective for 3D object detection. However, the current methods use a voxel-based detection head with anchors for classification and localization. Although the preset anchors cover the entire scene, it is not suitable for detection tasks with larger scenes and multiple categories of objects, due to the limitation of the voxel size. Additionally, the misalignment between the predicted confidence and proposals in the Regions of the Interest (ROI) selection bring obstacles to 3D object detection. Methods: We investigate the combination of voxel-based methods and point-based methods for 3D object detection. Additionally, a voxel-to-point module that captures semantic and geometric features is proposed in the paper. The voxel-to-point module is conducive to the detection of small-size objects and avoids the presets of anchors in the inference stage. Moreover, a confidence adjustment module with the center-boundary-aware confidence attention is proposed to solve the misalignment between the predicted confidence and proposals in the regions of the interest selection. Results: The proposed method has achieved state-of-the-art results for 3D object detection in the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) object detection dataset. Actually, as of September 19, 2021, our method ranked 1st in the 3D and Bird Eyes View (BEV) detection of cyclists tagged with difficulty level ‘easy’, and ranked 2nd in the 3D detection of cyclists tagged with ‘moderate’. Conclusions: We propose an end-to-end two-stage 3D object detector with voxel-to-point module and confidence adjustment module.
42
Clark, Stephen D., and Matthew W. Page. "Cycling and Urban Traffic Management and Control Systems." Transportation Research Record: Journal of the Transportation Research Board 1705, no. 1 (January 2000): 77–84. http://dx.doi.org/10.3141/1705-12.
Повний текст джерелаАнотація:
Since the 1950s, cycling has been a declining mode of travel in the United Kingdom. During this same period, sophisticated techniques for managing traffic in the urban environment have been developed. Given these circumstances, the presence of cyclists is often ignored by urban traffic control (UTC) systems, which are dominated by consideration of the flows and journey times of private motorized vehicles. Authorities are enthusiastic about the promotion of cycling as a mode of travel and are looking to see if this can be assisted by use of traffic management systems. The fact that cyclists and potential cyclists vary considerably in their abilities and performance, as well as in their attitudes to timesaving and safety, is highlighted. The context of the problem is set, the specific issue of detection of cycles is examined, the potential for implementation of priority measures in different types of UTC systems is discussed, and the issue is illustrated with some actual installations. Limited European evidence would suggest that only minimum effort is needed to take explicit account of cycling when a UTC system is being implemented. This supports the idea that cyclists can be given a higher degree of consideration within a UTC system without incurring significant additional costs. Only when cycling achieves a near-dominant proportion of the trips within a city and is growing in volume, as is the case in China, is explicit consideration to cyclists given.
43
Werner, Christian, Bernd Resch, and Martin Loidl. "Evaluating Urban Bicycle Infrastructures through Intersubjectivity of Stress Sensations Derived from Physiological Measurements." ISPRS International Journal of Geo-Information 8, no. 6 (June 6, 2019): 265. http://dx.doi.org/10.3390/ijgi8060265.
Повний текст джерелаАнотація:
A continued shift of human mobility towards sustainable and active mobility modes is a major concern for society in order to reduce the human contribution to climate change as well as to improve liveability and health in urban environments. For this change to succeed, non-motorized modes of transport need to become more attractive. Cycling can play a substantial role for short to medium distances, but perceived safety and stress levels are still major concerns for cyclists. Therefore, a quantitative assessment of cyclists’ stress sensations constitutes a valuable input for urban planning and for optimized routing providing low-stress routes. This paper aims to investigate stress sensations of cyclists through quantifying physiological measurements and their spatial correlation as an intersubjective indicator for perceived bikeability. We developed an automated workflow for stress detection and aggregation, and validated it in a case study in the city of Salzburg, Austria. Our results show that measured stress generally matches reported stress perception and can thus be considered a valuable addition to mobility planning processes.
44
Diyan, Muhammad, Murad Khan, Bhagya Nathali Silva, and Kijun Han. "Scheduling Sensor Duty Cycling Based on Event Detection Using Bi-Directional Long Short-Term Memory and Reinforcement Learning." Sensors 20, no. 19 (September 25, 2020): 5498. http://dx.doi.org/10.3390/s20195498.
Повний текст джерелаАнотація:
A smart home provides a facilitated environment for the detection of human activity with appropriate Deep Learning algorithms to manipulate data collected from numerous sensors attached to various smart things in a smart home environment. Human activities comprise expected and unexpected behavior events; therefore, detecting these events consisting of mutual dependent activities poses a key challenge in the activities detection paradigm. Besides, the battery-powered sensor ubiquitously and extensively monitors activities, disputes, and sensor energy depletion. Therefore, to address these challenges, we propose an Energy and Event Aware-Sensor Duty Cycling scheme. The proposed model predicts the future expected event using the Bi-Directional Long-Short Term Memory model and allocates Predictive Sensors to the predicted event. To detect the unexpected events, the proposed model localizes a Monitor Sensor within a cluster of Hibernate Sensors using the Jaccard Similarity Index. Finally, we optimize the performance of our proposed scheme by employing the Q-Learning algorithm to track the missed or undetected events. The simulation is executed against the conventional Machine Learning algorithms for the sensor duty cycle, scheduling to reduce the sensor energy consumption and improve the activity detection accuracy. The experimental evaluation of our proposed scheme shows significant improvement in activity detection accuracy from 94.12% to 96.12%. Besides, the effective rotation of the Monitor Sensor significantly improves the energy consumption of each sensor with the entire network lifetime.
45
Patrona, Fotini, Paraskevi Nousi, Ioannis Mademlis, Anastasios Tefas, and Ioannis Pitas. "Visual Object Detection For Autonomous UAV Cinematography." Proceedings of the Northern Lights Deep Learning Workshop 1 (February 6, 2020): 6. http://dx.doi.org/10.7557/18.5099.
Повний текст джерелаАнотація:
The popularization of commercial, battery-powered, camera-equipped, Vertical Take-off and Landing (VTOL) Unmanned Aerial Vehicles (UAVs) during the past decade, has significantly affected aerial video capturing operations in varying domains. UAVs are affordable, agile and flexible, having the ability to access otherwise inaccessible spots. However, their limited resources burden computation cinematography techniques on operating with high accuracy and real-time speed on such devices. State-of-the-art object detectors and feature extractors are, thus, studied in this work, aiming to find a trade-off between performance and speed that will allow UAV exploitation for intelligent cinematography purposes. Experimental evaluation on three newly introduced datasets of rowing boats, cyclists and parkour athletes is performed and evidence is provided that even limited-resource autonomous UAVs can indeed be used for cinematography applications.
46
Lavrenko, Tetiana, Timo Gessler, Thomas Walter, Hubert Mantz, and Michael Schlick. "Radar Based Detection and Classification of Vulnerable Road Users." Engineering Proceedings 6, no. 1 (May 17, 2021): 67. http://dx.doi.org/10.3390/i3s2021dresden-10098.
Повний текст джерелаАнотація:
Radar sensors accurately detect different objects; however, the reliable classification of these objects remains challenging. In this contribution, new approaches to extracting and interpreting unique spectral features of pedestrians and cyclists are proposed. Both methods use range-Doppler maps, which contain information on the distance to and the velocity of a detected object. The detections originate from the local dynamic of the moving (body) parts, and therefore can be used to reconstruct a unique movement pattern, which is represented by a time dependent velocity distribution. Machine learning algorithms can also be applied to the obtained time series in order to automate the classification task.
47
Dejda, Agnieszka, Izabela Matczak, and Wojciech A. Gorczyca. "p19 detected in the rat retina and pineal gland is a guanylyl cyclase-activating protein (GCAP)." Acta Biochimica Polonica 49, no. 4 (December 31, 2002): 899–905. http://dx.doi.org/10.18388/abp.2002_3749.
Повний текст джерелаАнотація:
The Ca(2+)-dependent activation of retina-specific guanylyl cyclase (retGC) is mediated by guanylyl cyclase-activating proteins (GCAPs). Here we report for the first time detection of a 19 kDa protein (p19) with GCAP properties in extracts of rat retina and pineal gland. Both extracts stimulate synthesis of cGMP in rod outer segment (ROS) membranes at low (30 nM) but not at high (1 microM) concentrations of Ca(2+). At low Ca(2+), immunoaffinity purified p19 activates guanylyl cyclase(s) in bovine ROS and rat retinal membranes. Moreover, p19 is recognized by antibodies against bovine GCAP1 and, similarly to other GCAPs, exhibits a Ca(2+)-dependent electrophoretic mobility shift.
48
Battistini, Roberto, Alessandro Nalin, Andrea Simone, Claudio Lantieri, and Valeria Vignali. "How Do University Student Cyclists Ride? The Case of University of Bologna." Applied Sciences 12, no. 22 (November 14, 2022): 11569. http://dx.doi.org/10.3390/app122211569.
Повний текст джерелаАнотація:
In a general urban planning context, in which sustainable active mobility progressively takes up increasing attention, studies of cyclists’ attitudes and behaviors represent a relevant step to help any enhancing measures for urban cycling. Among different categories, university student cyclists represent a still unidentified class, despite the relevant impacts in terms of mass and variability of attitudes in urban areas. The novelty of this paper is to propose an innovative overview on the specific category of university student cyclists. The integrated methodology, based on direct observation through GPS detection, GIS processing, and qualitative survey, permits the evaluation of some interesting issues related to students’ propensity to cycling and their mobility patterns. The approach finds relevance in speed, frequency of movements, routing, and related infrastructure preferences. The methodology has been applied to a sample of more than 300 students of the University of Bologna who were allowed an original university-designed bicycle from February 2021 to June 2021. The analysis was applied in the Bologna urban area and allowed the evaluation of students’ preferences of using existing cycle paths, when available, the limited relevance of speed factors, the main distribution of commuter journeys concentrated in the main avenues directed to city center, and other behaviors.
49
Eckstein, Hans, and Heike Schlobohm. "A Particulate Guanylate Cyclase (EC 4.6.1.2) from Growing Yeast Cells {Saccharomyces cerevisiae)." Zeitschrift für Naturforschung C 52, no. 5-6 (June 1, 1997): 373–79. http://dx.doi.org/10.1515/znc-1997-5-616.
Повний текст джерелаАнотація:
Abstract The detection of cGMP in yeast (Eckstein 1988), but lacking hints at guanylate cyclase from sequencing of the yeast genome, raised questions about existence, isoform, and regulation of guanylate cyclase from this organism. We found a particulate guanylate cyclase activity in yeast extracts, exhibiting properties of an integral membrane protein. Characteristics are: pH-optimum at pH 6.8, temperature-optimum around 60 °C, only slight stimulation by Mn2+. Sigmoidal enzyme kinetics indicate allosteric regulation, ATP and Ca2+ act as negative allosteric effectors. The enzyme activity is increased by yeast alpha-1 mating factor, and by sodium nitrite, thus showing properties of particulate as well as of soluble isoforms from other eukaryotes. The activation by alpha-1 mating factor suggests receptor functions, and a role in ascospore conjugation.
50
Paz, M. A., R. Flückiger, A. Boak, H. M. Kagan, and P. M. Gallop. "Specific detection of quinoproteins by redox-cycling staining." Journal of Biological Chemistry 266, no. 2 (January 1991): 689–92. http://dx.doi.org/10.1016/s0021-9258(17)35225-0.
Повний текст джерела