To see the other types of publications on this topic, follow the link: Road scene understanding.
Journal articles on the topic 'Road scene understanding'
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 'Road scene understanding.'
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
Zhou, Wujie, Sijia Lv, Qiuping Jiang, and Lu Yu. "Deep Road Scene Understanding." IEEE Signal Processing Letters 26, no. 4 (April 2019): 587–91. http://dx.doi.org/10.1109/lsp.2019.2896793.
Full text
2
Huang, Wenqi, Fuzheng Zhang, Aidong Xu, Huajun Chen, and Peng Li. "Fusion-based holistic road scene understanding." Journal of Engineering 2018, no. 16 (November 1, 2018): 1623–28. http://dx.doi.org/10.1049/joe.2018.8319.
Full text
3
Wang, Chao, Huan Wang, Rui Li Wang, and Chun Xia Zhao. "Robust Zebra-Crossing Detection for Autonomous Land Vehicles and Driving Assistance Systems." Applied Mechanics and Materials 556-562 (May 2014): 2732–39. http://dx.doi.org/10.4028/www.scientific.net/amm.556-562.2732.
Full textAbstract:
Road scene understanding is critical for driving assistance systems and autonomous land vehicles. The main function of road scene understanding is robustly detecting useful visual objects existing in a road scene. A zebra crossing is a typical pedestrian crossing used in many countries around the world. When detecting a zebra crossing, an autonomous lane vehicle is normally required to automatically slow down its speed and to trigger a path-planning strategy for passing the zebra crossing. Also, most of driving assistance systems can send an early-warning signal to remind drivers to be more careful. This paper proposes a robust zebra-crossing detection algorithm for autonomous land vehicles and driving assistance systems. Firstly, an inverse perspective map is generated by utilizing camera calibration parameters to obtain a bird-eye view road image. Secondly, a course-to-fine detection process is applied to obtain a candidate zebra-crossing region and finally a true zebra-crossing region is recognized by combining appearance and shape features. Experiments on several kinds of real road videos which also include several challenge scenes demonstrate the effectiveness and efficiency of the proposed method.
4
Liu, Huajun, Cailing Wang, and Jingyu Yang. "Vanishing points estimation and road scene understanding based on Bayesian posterior probability." Industrial Robot: An International Journal 43, no. 1 (January 18, 2016): 12–21. http://dx.doi.org/10.1108/ir-05-2015-0095.
Full textAbstract:
Purpose – This paper aims to present a novel scheme of multiple vanishing points (VPs) estimation and corresponding lanes identification. Design/methodology/approach – The scheme proposed here includes two main stages: VPs estimation and lane identification. VPs estimation based on vanishing direction hypothesis and Bayesian posterior probability estimation in the image Hough space is a foremost contribution, and then VPs are estimated through an optimal objective function. In lane identification stage, the selected linear samples supervised by estimated VPs are clustered based on the gradient direction of linear features to separate lanes, and finally all the lanes are identified through an identification function. Findings – The scheme and algorithms are tested on real data sets collected from an intelligent vehicle. It is more efficient and more accurate than recent similar methods for structured road, and especially multiple VPs identification and estimation of branch road can be achieved and lanes of branch road can be identified for complex scenarios based on Bayesian posterior probability verification framework. Experimental results demonstrate VPs, and lanes are practical for challenging structured and semi-structured complex road scenarios. Originality/value – A Bayesian posterior probability verification framework is proposed to estimate multiple VPs and corresponding lanes for road scene understanding of structured or semi-structured road monocular images on intelligent vehicles.
5
Yasrab, Robail. "ECRU: An Encoder-Decoder Based Convolution Neural Network (CNN) for Road-Scene Understanding." Journal of Imaging 4, no. 10 (October 8, 2018): 116. http://dx.doi.org/10.3390/jimaging4100116.
Full textAbstract:
This research presents the idea of a novel fully-Convolutional Neural Network (CNN)-based model for probabilistic pixel-wise segmentation, titled Encoder-decoder-based CNN for Road-Scene Understanding (ECRU). Lately, scene understanding has become an evolving research area, and semantic segmentation is the most recent method for visual recognition. Among vision-based smart systems, the driving assistance system turns out to be a much preferred research topic. The proposed model is an encoder-decoder that performs pixel-wise class predictions. The encoder network is composed of a VGG-19 layer model, while the decoder network uses 16 upsampling and deconvolution units. The encoder of the network has a very flexible architecture that can be altered and trained for any size and resolution of images. The decoder network upsamples and maps the low-resolution encoder’s features. Consequently, there is a substantial reduction in the trainable parameters, as the network recycles the encoder’s pooling indices for pixel-wise classification and segmentation. The proposed model is intended to offer a simplified CNN model with less overhead and higher performance. The network is trained and tested on the famous road scenes dataset CamVid and offers outstanding outcomes in comparison to similar early approaches like FCN and VGG16 in terms of performance vs. trainable parameters.
6
Topfer, Daniel, Jens Spehr, Jan Effertz, and Christoph Stiller. "Efficient Road Scene Understanding for Intelligent Vehicles Using Compositional Hierarchical Models." IEEE Transactions on Intelligent Transportation Systems 16, no. 1 (February 2015): 441–51. http://dx.doi.org/10.1109/tits.2014.2354243.
Full text
7
Qin, Yuting, Yuren Chen, and Kunhui Lin. "Quantifying the Effects of Visual Road Information on Drivers’ Speed Choices to Promote Self-Explaining Roads." International Journal of Environmental Research and Public Health 17, no. 7 (April 3, 2020): 2437. http://dx.doi.org/10.3390/ijerph17072437.
Full textAbstract:
Roads should deliver appropriate information to drivers and thus induce safer driving behavior. This concept is also known as “self-explaining roads” (SERs). Previous studies have demonstrated that understanding how road characteristics affect drivers’ speed choices is the key to SERs. Thus, in order to reduce traffic casualties via engineering methods, this study aimed to establish a speed decision model based on visual road information and to propose an innovative method of SER design. It was assumed that driving speed is determined by road geometry and modified by the environment. Lane fitting and image semantic segmentation techniques were used to extract road features. Field experiments were conducted in Tibet, China, and 1375 typical road scenarios were picked out. By controlling variables, the driving speed stimulated by each piece of information was evaluated. Prediction models for geometry-determined speed and environment-modified speed were built using the random forest algorithm and convolutional neural network. Results showed that the curvature of the right boundary in “near scene” and “middle scene”, and the density of roadside greenery and residences play an important role in regulating driving speed. The findings of this research could provide qualitative and quantitative suggestions for the optimization of road design that would guide drivers to choose more reasonable driving speeds.
8
Jeong, Jinhan, Yook Hyun Yoon, and Jahng Hyon Park. "Reliable Road Scene Interpretation Based on ITOM with the Integrated Fusion of Vehicle and Lane Tracker in Dense Traffic Situation." Sensors 20, no. 9 (April 26, 2020): 2457. http://dx.doi.org/10.3390/s20092457.
Full textAbstract:
Lane detection and tracking in a complex road environment is one of the most important research areas in highly automated driving systems. Studies on lane detection cover a variety of difficulties, such as shadowy situations, dimmed lane painting, and obstacles that prohibit lane feature detection. There are several hard cases in which lane candidate features are not easily extracted from image frames captured by a driving vehicle. We have carefully selected typical scenarios in which the extraction of lane candidate features can be easily corrupted by road vehicles and road markers that lead to degradations in the understanding of road scenes, resulting in difficult decision making. We have introduced two main contributions to the interpretation of road scenes in dense traffic environments. First, to obtain robust road scene understanding, we have designed a novel framework combining a lane tracker method integrated with a camera and a radar forward vehicle tracker system, which is especially useful in dense traffic situations. We have introduced an image template occupancy matching method with the integrated vehicle tracker that makes it possible to avoid extracting irrelevant lane features caused by forward target vehicles and road markers. Second, we present a robust multi-lane detection by a tracking algorithm that incudes adjacent lanes as well as ego lanes. We verify a comprehensive experimental evaluation with a real dataset comprised of problematic road scenarios. Experimental result shows that the proposed method is very reliable for multi-lane detection at the presented difficult situations.
9
Sun, Jee-Young, Seung-Won Jung, and Sung-Jea Ko. "Lightweight Prediction and Boundary Attention-Based Semantic Segmentation for Road Scene Understanding." IEEE Access 8 (2020): 108449–60. http://dx.doi.org/10.1109/access.2020.3001679.
Full text
10
Deng, Yanzi, Zhaoyang Lu, and Jing Li. "Coarse-to-fine road scene segmentation via hierarchical graphical models." International Journal of Advanced Robotic Systems 16, no. 2 (March 1, 2019): 172988141983116. http://dx.doi.org/10.1177/1729881419831163.
Full textAbstract:
The road scene segmentation is an important problem which is helpful for a higher level of the scene understanding. This article presents a novel approach for image semantic segmentation of road scenes via a hierarchical graph-based inference. A deep encoder–decoder network is first applied for a fast pixel-wise classification. Then, hierarchical graph-based inference is performed to get an accurate segmentation result. In the inference process, all the object classes are grouped into fewer categories which contains at least one class. The category labels are assigned to image superpixels using Markov random field model. For each category, a pixel-level labeling based on fully connected conditional random fields is performed to divide image into different classes. After the inference for all categories, the results are integrated together to get the final segmentation. In additional to low-level affinity functions, the feature maps from network are integrated in pairwise potentials of the graphical models. This hierarchical inference scheme can alleviate the confusion of classes belonging to different categories. It performs well for small objects without adding more computational burden. Both qualitative and quantitative assessments are adopted to evaluate the proposed method. The results on benchmark data sets prove the effectiveness of the proposed hierarchical scheme, and the performance is competitive with the state-of-the-art methods.
11
Wang, Huan, YangYang Hou, and Mingwu Ren. "A Shape-Aware Road Detection Method for Aerial Images." International Journal of Pattern Recognition and Artificial Intelligence 31, no. 04 (February 2, 2017): 1750009. http://dx.doi.org/10.1142/s0218001417500094.
Full textAbstract:
Road detection in aerial images is a crucial technique for visual navigation and scene understanding in relation to unmanned aerial vehicles (UAVs). A shape-aware road detection method for aerial images is proposed in this paper. It first employs the stroke width transform (SWT) and a geodesic distance based superpixel clustering to generate proposal regions. Then, a shape classification is responsible for selecting all potential road segments from the proposal regions which appear to be long and with consistent width. All road segments selected are clustered into several groups based on width and color features. A global graph based labeling model is then applied based on each group to remove potential background clutters, as well as to generate the final output. Experiments on two public datasets demonstrate that the proposed method can handle more diverse and challenging road scenes and needs less pre-training, leading to better performance compared to conventional methods.
12
Wang, Haixia, Yehao Sun, Zhiguo Zhang, Xiao Lu, and Chunyang Sheng. "Depth estimation for a road scene using a monocular image sequence based on fully convolutional neural network." International Journal of Advanced Robotic Systems 17, no. 3 (May 1, 2020): 172988142092530. http://dx.doi.org/10.1177/1729881420925305.
Full textAbstract:
An advanced driving assistant system is one of the most popular topics nowadays, and depth estimation is an important cue for advanced driving assistant system. Depth prediction is a key problem in understanding the geometry of a road scene for advanced driving assistant system. In comparison to other depth estimation methods using stereo depth perception, determining depth relation using a monocular camera is considerably challenging. In this article, a fully convolutional neural network with skip connection based on a monocular video sequence is proposed. With the integration framework that combines skip connection, fully convolutional network and the consistency between consecutive frames of the input sequence, high-resolution depth maps are obtained with lightweight network training and fewer computations. The proposed method models depth estimation as a regression problem and trains the proposed network using a scale invariance optimization based on L2 loss function, which measures the relationships between points in the consecutive frames. The proposed method can be used for depth estimation of a road scene without the need for any extra information or geometric priors. Experiments on road scene data sets demonstrate that the proposed approach outperforms previous methods for monocular depth estimation in dynamic scenes. Compared with the currently proposed method, our method has achieved good results when using the Eigen split evaluation method. The obvious prominent one is that the linear root mean squared error result is 3.462 and the δ < 1.25 result is 0.892.
13
Billones, Robert Kerwin C., Argel A. Bandala, Laurence A. Gan Lim, Edwin Sybingco, Alexis M. Fillone, and Elmer P. Dadios. "Microscopic Road Traffic Scene Analysis Using Computer Vision and Traffic Flow Modelling." Journal of Advanced Computational Intelligence and Intelligent Informatics 22, no. 5 (September 20, 2018): 704–10. http://dx.doi.org/10.20965/jaciii.2018.p0704.
Full textAbstract:
This paper presents the development of a vision-based system for microscopic road traffic scene analysis and understanding using computer vision and computational intelligence techniques. The traffic flow model is calibrated using the information obtained from the road-side cameras. It aims to demonstrate an understanding of different levels of traffic scene analysis from simple detection, tracking, and classification of traffic agents to a higher level of vehicular and pedestrian dynamics, traffic congestion build-up, and multi-agent interactions. The study used a video dataset suitable for analysis of a T-intersection. Vehicle detection and tracking have 88.84% accuracy and 88.20% precision. The system can classify private cars, public utility vehicles, buses, and motorcycles. Vehicular flow of every detected vehicles from origin to destination are also monitored for traffic volume estimation, and volume distribution analysis. Lastly, a microscopic traffic model for a T-intersection was developed to simulate a traffic response based on actual road scenarios.
14
Yu, Chunlei, Veronique Cherfaoui, Philippe Bonnifait, and Dian-ge Yang. "Managing Localization Uncertainty to Handle Semantic Lane Information from Geo-Referenced Maps in Evidential Occupancy Grids." Sensors 20, no. 2 (January 8, 2020): 352. http://dx.doi.org/10.3390/s20020352.
Full textAbstract:
Occupancy grid is a popular environment model that is widely applied for autonomous navigation of mobile robots. This model encodes obstacle information into the grid cells as a reference of the space state. However, when navigating on roads, the planning module of an autonomous vehicle needs to have semantic understanding of the scene, especially concerning the accessibility of the driving space. This paper presents a grid-based evidential approach for modeling semantic road space by taking advantage of a prior map that contains lane-level information. Road rules are encoded in the grid for semantic understanding. Our approach focuses on dealing with the localization uncertainty, which is a key issue, while parsing information from the prior map. Readings from an exteroceptive sensor are as well integrated in the grid to provide real-time obstacle information. All the information is managed in an evidential framework based on Dempster–Shafer theory. Real road results are reported with qualitative evaluation and quantitative analysis of the constructed grids to show the performance and the behavior of the method for real-time application.
15
Trabelsi, Rim, Redouane Khemmar, Benoit Decoux, Jean-Yves Ertaud, and Rémi Butteau. "Recent Advances in Vision-Based On-Road Behaviors Understanding: A Critical Survey." Sensors 22, no. 7 (March 30, 2022): 2654. http://dx.doi.org/10.3390/s22072654.
Full textAbstract:
On-road behavior analysis is a crucial and challenging problem in the autonomous driving vision-based area. Several endeavors have been proposed to deal with different related tasks and it has gained wide attention recently. Much of the excitement about on-road behavior understanding has been the labor of advancement witnessed in the fields of computer vision, machine, and deep learning. Remarkable achievements have been made in the Road Behavior Understanding area over the last years. This paper reviews 100+ papers of on-road behavior analysis related work in the light of the milestones achieved, spanning over the last 2 decades. This review paper provides the first attempt to draw smart mobility researchers’ attention to the road behavior understanding field and its potential impact on road safety to the whole road agents such as: drivers, pedestrians, stuffs, etc. To push for an holistic understanding, we investigate the complementary relationships between different elementary tasks that we define as the main components of road behavior understanding to achieve a comprehensive understanding of approaches and techniques. For this, five related topics have been covered in this review, including situational awareness, driver-road interaction, road scene understanding, trajectories forecast, driving activities, and status analysis. This paper also reviews the contribution of deep learning approaches and makes an in-depth analysis of recent benchmarks as well, with a specific taxonomy that can help stakeholders in selecting their best-fit architecture. We also finally provide a comprehensive discussion leading us to identify novel research directions some of which have been implemented and validated in our current smart mobility research work. This paper presents the first survey of road behavior understanding-related work without overlap with existing reviews.
16
Kiy, K. I., and D. A. Anokhin. "A NEW TECHNIQUE FOR OBJECT DETECTION AND TRACKING AND ITS APPLICATION TO ANALYSIS OF ROAD SCENE." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIV-2/W1-2021 (April 15, 2021): 119–24. http://dx.doi.org/10.5194/isprs-archives-xliv-2-w1-2021-119-2021.
Full textAbstract:
Abstract. In this paper, a new technique for real-time object detection and tracking is presented. This technique is based on the geometrized histograms method (GHM) for segmenting and describing color images (frames of video sequences) and on the facilities for global image analysis provided by this method. Basic elements of the technique that make it possible to solve image understanding problems almost without using the pixel arrays of images are introduced and discussed.A real-time parallel software implementation of the developed technique is briefly discussed. This technique is applied to solving problems of road scene analysis. The application to finding small contrast objects in images, like traffic signals and signal zones of vehicles is given. The developed technique is applied also to detecting other vehicles in the frame. The results of processing different frame of videos of road scenes are presented and discussed.
17
Wang, Kewei, Fuwu Yan, Bin Zou, Luqi Tang, Quan Yuan, and Chen Lv. "Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles." Sensors 19, no. 21 (October 30, 2019): 4711. http://dx.doi.org/10.3390/s19214711.
Full textAbstract:
The deep convolutional neural network has led the trend of vision-based road detection, however, obtaining a full road area despite the occlusion from monocular vision remains challenging due to the dynamic scenes in autonomous driving. Inferring the occluded road area requires a comprehensive understanding of the geometry and the semantics of the visible scene. To this end, we create a small but effective dataset based on the KITTI dataset named KITTI-OFRS (KITTI-occlusion-free road segmentation) dataset and propose a lightweight and efficient, fully convolutional neural network called OFRSNet (occlusion-free road segmentation network) that learns to predict occluded portions of the road in the semantic domain by looking around foreground objects and visible road layout. In particular, the global context module is used to build up the down-sampling and joint context up-sampling block in our network, which promotes the performance of the network. Moreover, a spatially-weighted cross-entropy loss is designed to significantly increases the accuracy of this task. Extensive experiments on different datasets verify the effectiveness of the proposed approach, and comparisons with current excellent methods show that the proposed method outperforms the baseline models by obtaining a better trade-off between accuracy and runtime, which makes our approach is able to be applied to autonomous vehicles in real-time.
18
Tapiro, Hagai, Avinoam Borowsky, Tal Oron-Gilad, and Yisrael Parmet. "Where do older pedestrians glance before deciding to cross a simulated two-lane road? A pedestrian simulator paradigm." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 60, no. 1 (September 2016): 11–15. http://dx.doi.org/10.1177/1541931213601003.
Full textAbstract:
Knowing where to older pedestrians allocate their glances before deciding to cross the road can contribute to understanding the causes that lead them to make bad road crossing decisions. Research on older drivers suggest that they are over involved in crashes that involve navigation through intersections mainly because they focused on their travel path and rarely on other areas in the scene from where a hazard might appear. Yet, it is less known how older pedestrians spread their attention on their expected travel path. Eleven older participants (over 65) and ten younger adults were asked to make a road crossing decision in a simulated environment, while wearing an eye-tracker. Results exemplify significant differences between the younger and older adults; the older adults, in comparison to the younger, spent more time focusing on the central area of the scene and even less so in the last five seconds before making the crossing decision. These findings are consistent with older drivers’ behavior at intersections, suggesting that older pedestrians might be overly focused on their travel path.
19
Yang, Yuanfeng, Husheng Dong, Gang Liu, Liang Zhang, and Lin Li. "Cross-Domain Traffic Scene Understanding by Integrating Deep Learning and Topic Model." Computational Intelligence and Neuroscience 2022 (March 18, 2022): 1–15. http://dx.doi.org/10.1155/2022/8884669.
Full textAbstract:
Understanding cross-domain traffic scenarios from multicamera surveillance network is important for environmental perception. Most of existing methods select the source domain which is most similar to the target domain by comparing entire domains for cross-domain similarity and then transferring the motion model learned in the source domain to the target domain. The cross-domain similarity between overall different scenarios with similar local layouts is usually not utilized to improve any automatic surveillance tasks. However, these local commonalities, which may be shared across multiple traffic scenarios, can be transferred across scenarios as prior knowledge. To address these issues, we present a novel framework for cross-domain traffic scene understanding by integrating deep learning and topic model. This framework leverages the labeled samples with activity attribute labels from the source domain to annotate the target domain, where each label represents the local activity of some objects in the scene. When labeling the activity attributes of the target domain, there is no need to select the source domain, which avoids the phenomenon of performance degradation or even negative transfer due to wrong source domain selection. The effectiveness of the proposed framework is verified by extensive experiments carried out using public road traffic data.
20
Hylander, Johan, Britt-Inger Saveman, and Lina Gyllencreutz. "A Sense of Trust, the Norwegian Way of Improving Medical On-Scene Managing Major Tunnel Incidents: An Interview Study." Prehospital and Disaster Medicine 34, s1 (May 2019): s166. http://dx.doi.org/10.1017/s1049023x19003790.
Full textAbstract:
Introduction:Norway is a country with many road tunnels and therefore also has experience with rescue operations in tunnel environments. Major incidents always challenge involved emergency services’ management skills. Oslo, Norway has a specially trained medical on-scene commander, a function already existing in police and rescue service. Intra-agency communication and management of personnel are essential factors for a successful rescue effort.Aim:To investigate the medical management provided by the specially trained Norwegian medical on-scene commander in relation to tunnel incidents.Methods:Interviews were conducted with six of the seven medical on-scene commanders in Oslo. The collected data were analyzed using qualitative content analysis.Results:An overarching theme emerged: A need for mutual understanding of the tunnel incident. The medical on-scene commanders established guidelines for response in collaboration with the other emergency services. By creating a sense of trust, the collaboration between the emergency services became more fluent. Socializing outside of work resulted in improved reliance on their counterparts in the other services. The management also included that the medical on-scene commander supervised his personnel on site by providing support using knowledge of the risk object and surrounding area.Discussion:A forum for the emergency services on-scene commanders where they share ideas and knowledge, improve the on-scene intra-agency communication, and trust is desirable. A culture of trust between the organizations is needed for a mutual understanding. Further research on this subject is needed in other contexts and countries.
21
Cai, Ying Feng, Hai Wang, and Wei Gong Zhang. "Learning Patterns of Motion Trajectories Using Real-Time Tracking." Advanced Materials Research 403-408 (November 2011): 2768–71. http://dx.doi.org/10.4028/www.scientific.net/amr.403-408.2768.
Full textAbstract:
The understanding and description of behaviors for road vehicles is a hot topic of intelligent visual surveillance system. Trajectory analysis is one of the basic problems in behavior understanding, from which anomalies can be detected and also accidents can be predicted. In this paper, we proposed a hierarchical self-organizing neural network model to learn trajectory distribution pattern and a probability model for accident recognition. Sample data including motion trajectories are first get by real-time vehicle tracking. The self-organizing neural network algorithm is then applied to learn activity patterns from the sample trajectories. Using the learned patterns, we consider anomaly detection as well as object behavior prediction. Experiments in actual road scene show the effectiveness of the proposed algorithm.
22
Mauri, Antoine, Redouane Khemmar, Benoit Decoux, Madjid Haddad, and Rémi Boutteau. "Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility." Journal of Imaging 7, no. 8 (August 12, 2021): 145. http://dx.doi.org/10.3390/jimaging7080145.
Full textAbstract:
For smart mobility, autonomous vehicles, and advanced driver-assistance systems (ADASs), perception of the environment is an important task in scene analysis and understanding. Better perception of the environment allows for enhanced decision making, which, in turn, enables very high-precision actions. To this end, we introduce in this work a new real-time deep learning approach for 3D multi-object detection for smart mobility not only on roads, but also on railways. To obtain the 3D bounding boxes of the objects, we modified a proven real-time 2D detector, YOLOv3, to predict 3D object localization, object dimensions, and object orientation. Our method has been evaluated on KITTI’s road dataset as well as on our own hybrid virtual road/rail dataset acquired from the video game Grand Theft Auto (GTA) V. The evaluation of our method on these two datasets shows good accuracy, but more importantly that it can be used in real-time conditions, in road and rail traffic environments. Through our experimental results, we also show the importance of the accuracy of prediction of the regions of interest (RoIs) used in the estimation of 3D bounding box parameters.
23
Sun, Zhongyu, Wangping Zhou, Chen Ding, and Min Xia. "Multi-Resolution Transformer Network for Building and Road Segmentation of Remote Sensing Image." ISPRS International Journal of Geo-Information 11, no. 3 (February 25, 2022): 165. http://dx.doi.org/10.3390/ijgi11030165.
Full textAbstract:
Extracting buildings and roads from remote sensing images is very important in the area of land cover monitoring, which is of great help to urban planning. Currently, a deep learning method is used by the majority of building and road extraction algorithms. However, for existing semantic segmentation, it has a limitation on the receptive field of high-resolution remote sensing images, which means that it can not show the long-distance scene well during pixel classification, and the image features is compressed during down-sampling, meaning that the detailed information is lost. In order to address these issues, Hybrid Multi-resolution and Transformer semantic extraction Network (HMRT) is proposed in this paper, by which a global receptive field for each pixel can be provided, a small receptive field of convolutional neural networks (CNN) can be overcome, and the ability of scene understanding can be enhanced well. Firstly, we blend the features by branches of different resolutions to keep the high-resolution and multi-resolution during down-sampling and fully retain feature information. Secondly, we introduce the Transformer sequence feature extraction network and use encoding and decoding to realize that each pixel has the global receptive field. The recall, F1, OA and MIoU of HMPR obtain 85.32%, 84.88%, 85.99% and 74.19%, respectively, in the main experiment and reach 91.29%, 90.41%, 91.32% and 84.00%, respectively, in the generalization experiment, which prove that the method proposed is better than existing methods.
24
Zhang, Jie, Chunfang Liu, and Kuk Chol Ri. "Big Sur: Kerouac’s Spiritual Drop Scene." English Language and Literature Studies 12, no. 3 (July 12, 2022): 17. http://dx.doi.org/10.5539/ells.v12n3p17.
Full textAbstract:
Big Sur is an important novel in Kerouac’s late period. The origin, content and purpose of this novel are significantly different from his previous works. Through analyzing the symbolic images in the novel, we can understand Kerouac’s painful reflection on his resistance against the American mainstream culture, his deep understanding of the failure to convey his spiritual appeals and his inability to compromise with the society. The study of Big Sur not only shows Kerouac’s spiritual collapse, but also reveals the spiritual trajectory of the Beats from fanaticism to decay.
Big Sur, on the coast of California, is a 99-mile-long rugged and beautiful waterfront. “Big Sur is fabulously romantic, … with its rugged terrain, its treacherous sea, and its challenging climate” (Wallraff, 2002). Kerouac, the soul of the Beat Generation, finishes his novel Big Sur there. The agony and desperation shown in the novel helps to understand the ideological doom of the Beats. While On the Road, Kerouac’s best-known work, records the height of Beat Generation, Big Sur, which was published in 1962, written 7 years before Kerouac’s death, accurately summarizes the spiritual end of the Beat Generation. After Big Sur, Kerouac has never written works shown his spiritual pursuit and agony, which makes this novel the one that reveals his deep frustration and desperation over his spiritual struggle. In Big Sur, though the “spontaneous prose method” Kerouac has developed is applied, the symbols in Big Sur can still impress the readers by their concise and direct relation with Kerouac’s crushed feelings (Kostas, 2002). He never tries to escape from his true feelings for his definite failure, so the symbols pave the way for a thorough understanding of Kerouac’s spiritual journey and the ineluctable collapse of his dream. As Aram Saroyan said in the preface to Big Sur: “In Big Sur, we have the plaintive but magnificent aftermath” (Aram, 1992).
25
Li, Yongfu, Yingkai Long, Mingming Du, Xiping Jiang, and Xianfu Liu. "Navigation and Positioning Analysis of Electric Inspection Robot Based on Improved SVM Algorithm." Journal of Sensors 2022 (July 25, 2022): 1–6. http://dx.doi.org/10.1155/2022/4613931.
Full textAbstract:
In order to improve the accuracy of electric inspection robot navigation and positioning, an improved SVM algorithm was proposed to improve the accuracy of inspection. The research focuses on sensor calibration technology, lane line detection and robot positioning technology, obstacle detection and tracking technology, and substation road scene understanding technology. The results show that the radar measurement results have great fluctuation and deviation due to the existence of noise, but the results are smoother after EKF estimation. Secondly, the accuracy of the improved SVM classifier in this paper is much higher than that of the traditional method, and the improvement effect is obvious.
26
GIRLESCU, Nona, Madalina Maria DIAC, Iuliana HUNEA, Simona Irina DAMIAN, Anton KNIELING, and Diana BULGARU ILIESCU. "COMPLEX MECHANISMS IN ROAD TRAFFIC ACCIDENTS CONCERNING PEDESTRIANS. A CASE STUDY." Medicine and Materials 1, no. 1 (June 15, 2021): 11–22. http://dx.doi.org/10.36868/medmater.2021.01.01.011.
Full textAbstract:
Pedestrian injuries vary according to vehicle type, position during the accident, and pedestrian’s age, thus determining complex aspects by associating multiple types of traumas. In forensic practice, it should be noted that the lesion-producing mechanisms recorded among pedestrians are most frequently mixed, reason for which a correct and careful examination of the victim must be supported by the characteristics of the vehicle involved in the accident, as well as by other elements at the crime scene. It is necessary to thoroughly examine the injuries, an analysis that should always be characterized by a dynamic interpretation, directly related to the mechanism of accident occurrence, with case-by-case individualization, to result in the clarification of conditions difficult to grasp at a superficial interpretation. This article aims to briefly review the main lesion mechanisms in case of pedestrians, to emphasize on the importance of understanding the complexity of these injuries, in order to elucidate – as accurately as possible – the circumstances of such an ill-fated event.
27
MAYA, MARGARITA LÓPEZ. "The Venezuelan Caracazo of 1989: Popular Protest and Institutional Weakness." Journal of Latin American Studies 35, no. 1 (February 2003): 117–37. http://dx.doi.org/10.1017/s0022216x02006673.
Full textAbstract:
27 February 1989 saw a popular revolt, which was to escalate dramatically, break out in Venezuela. Both Caracas and most of the main and secondary cities of the country were the scene of barricades, road closures, the stoning of shops, shooting and widespread looting. This article describes the events occurring during the Caracazo or Sacudón, as the episode is known, in order to show the key role played by the weakness of a set of social and political institutions in the violent forms of collective action that prevailed. This data, on a comparative basis, may enrich our understanding of other similar uprisings in the region and worldwide.
28
Paliska, Dejan, Milan Batista, Roman Starin, and Daša Fabjan. "An Attempt to Attain New Information in Reconstruction of Road Traffic Accidents Applying Digital Image Processing." PROMET - Traffic&Transportation 23, no. 2 (January 26, 2012): 113–19. http://dx.doi.org/10.7307/ptt.v23i2.138.
Full textAbstract:
Court expertise dealing with the reconstruction of road traffic accidents often have to take into account the possibility that an accident could have been a set-up. Such suspicions can be eliminated only by considering all the evidence material from the accident scene. In case of photographic material experts come across the missing material, bad lighting, lack of contrast, different angle perspectives, blurring, omitting important details, etc. Therefore, different methods in forensics image processing have been developed. Most of these methods are primarily used in the processing of different types of photographic material, but some can be applied in the field of road accidents analyses. This paper shows the implementation of digital image processing methods used for processing of remotely sensed imagery. Even though the photographic evidence is incomplete, it is possible to determine the position and dispersion of different materials. This gives the experts additional information that can help in understanding with relatively high probability if the collision between vehicles occured at all and if it did, where. The paper consists of the presentation and description of methods used for digital image processing in a real case study while reconstructing the road accident. KEY WORDS: road traffic accidents, forensics, induced traffic accidents, image classification, digital image processing
29
Kovács, Réka, and Andrada Savin. "Music Autobiographies – Performing Selves." Acta Universitatis Sapientiae, Philologica 14, no. 3 (December 1, 2022): 127–42. http://dx.doi.org/10.2478/ausp-2022-0029.
Full textAbstract:
Abstract The article pays tribute to four artists of the music scene, i.e. Bob Dylan, Bruce Springsteen, Patti Smith, and John Luther Adams. It walks in their footsteps through their autobiographies and features the major landmarks in their artistic and creative evolution. Despite the various incongruent traits in their music style, background, or gender, music autobiographies prove to be valuable assets, based on which correlations and contrasts can be elucidated, the road to growing into an artist can be followed, and the creative spirit can be grasped. We hereby conclude that autobiographies can constitute a bridge towards the artistic soul and deepen the understanding of how these musicians project themselves as performers and position themselves in society.
30
Chen, Rung-Ching, Vani Suthamathi Saravanarajan, Long-Sheng Chen, and Hui Yu. "Road Segmentation and Environment Labeling for Autonomous Vehicles." Applied Sciences 12, no. 14 (July 17, 2022): 7191. http://dx.doi.org/10.3390/app12147191.
Full textAbstract:
In autonomous vehicles (AVs), LiDAR point cloud data are an important source to identify various obstacles present in the environment. The labeling techniques that are currently available are based on pixel-wise segmentation and bounding boxes to detect each object on the road. However, the Avs’ decision on motion control and trajectory path planning depends on the interaction among the objects on the road. The ability of the Avs to understand the moving and non-moving objects is the key to scene understanding. This paper presents a novel labeling method to combine moving and non-moving objects. This labeling technique is named relational labeling. Autoencoders are used to reduce the dimensionality of the data. A K-means model provides pseudo labels by clustering the data in the latent space. Each pseudo label is then converted into unary and binary relational labels. These relational labels are used in the supervised learning methods for labeling and segmenting the LiDAR point cloud data. A backpropagation network (BPN), along with traditional gradient descent-based learning methods, are used for labeling the data. Our study evaluated the labeling accuracy of two as well as three layers of BPN. The accuracy of the two-layer BPN model was found to be better than the three-layer BPN model. According to the experiments, our model showed competitive accuracy of 75% compared to the weakly supervised techniques in a similar area of study, i.e., the accuracy for S3DIS (Area 5) is 48.0%.
31
Tian, Renran, Stanley Chien, Yaobin Chen, and Rini Sherony. "Pedestrian Moving Patterns during Potential Conflicts with 110 On-Road Driving Vehicles." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 63, no. 1 (November 2019): 2036–40. http://dx.doi.org/10.1177/1071181319631434.
Full textAbstract:
As the most commonly seen vulnerable road users, protection and interaction with pedestrians are key functionalities in vehicle active safety and self-driving research areas. Development and evaluation of such systems require deeper understanding of pedestrian behaviors, especially motion patterns, in different driving environments. Traditionally, most of the pedestrian movement studies rely on fixed roadside cameras in specific road locations with higher pedestrian density, like intersections and junctions. Although these studies can provide information to describe pedestrian walking behavior and vehicle-pedestrian interactions in micro and macro levels, there are two main limitations. Firstly, pedestrian movement data are rarely collected from the vehicle’s point of view, which makes some critical variables difficult to be collected related to pedestrian initial appearance situation. Secondly, insufficient data are acquired to cover low- pedestrian-density road environments like mid-block, rural areas, and small un-controlled intersections. In this study, we focus on three important pedestrian movement variables including appearance distances, initial time-to-collision, and crossing speed under different driving and road scenarios. Based on a large-scale naturalistic driving study, crossing pedestrians were randomly captured in the scene videos from 110 passenger cars when potential ego-vehicle-to-pedestrian conflicts appeared during a one-year period. Motion data of these pedestrians were then analyzed to calculate the targeted behavior measurements, with the empirical results reported.
32
Han, Guodong, Shuanfeng Zhao, Pengfei Wang, and Shijun Li. "Driver Attention Area Extraction Method Based on Deep Network Feature Visualization." Applied Sciences 10, no. 16 (August 7, 2020): 5474. http://dx.doi.org/10.3390/app10165474.
Full textAbstract:
The current intelligent driving technology based on image data is being widely used. However, the analysis of traffic accidents occurred in intelligent driving vehicles shows that there is an explanatory difference between the intelligent driving system based on image data and the driver’s understanding of the target information in the image. In addition, driving behavior is the driver’s response based on the analysis of road information, which is not available in the current intelligent driving system. In order to solve this problem, our paper proposes a driver attention area extraction method based on deep network feature visualization. In our method, we construct a Driver Behavior Information Network (DBIN) to map the relation between image information and driving behavior. Then we use the Deep Network Feature Visualization method (DNFV) to determine the driver’s attention area. The experimental results show that our method can extract effective road information from a real traffic scene picture and obtain the driver’s attention area. Our method can provide a useful theoretical basis and related technology of visual perception for future intelligent driving systems, driving training and assisted driving systems.
33
Fratini, Elena, Ruth Welsh, and Pete Thomas. "Ranking Crossing Scenario Complexity for eHMIs Testing: A Virtual Reality Study." Multimodal Technologies and Interaction 7, no. 2 (February 2, 2023): 16. http://dx.doi.org/10.3390/mti7020016.
Full textAbstract:
External human–machine interfaces (eHMIs) have the potential to benefit AV–pedestrian interactions. The majority of studies investigating eHMIs have used relatively simple traffic environments, i.e., a single pedestrian crossing in front of a single eHMI on a one-lane straight road. While this approach has proved to be efficient in providing an initial understanding of how pedestrians respond to eHMIs, it over-simplifies interactions which will be substantially more complex in real-life circumstances. A process is illustrated in a small-scale study (N = 10) to rank different crossing scenarios by level of complexity. Traffic scenarios were first developed for varying traffic density, visual complexity of the road scene, road geometry, weather and visibility conditions, and presence of distractions. These factors have been previously shown to increase difficulty and riskiness of the crossing task. The scenarios were then tested in a motion-based, virtual reality environment. Pedestrians’ perceived workload and objective crossing behaviour were measured as indirect indicators of the level of complexity of the crossing scenario. Sense of presence and simulator sickness were also recorded as a measure of the ecological validity of the virtual environment. The results indicated that some crossing scenarios were more taxing for pedestrians than others, such as those with road geometries where traffic approached from multiple directions. Further, the presence scores showed that the virtual environments experienced were found to be realistic. This paper concludes by proposing a “complex” environment to test eHMIs under more challenging crossing circumstances.
34
Mohamed, Mohamed Gomaa, and Nicolas Saunier. "Behavior Analysis Using a Multilevel Motion Pattern Learning Framework." Transportation Research Record: Journal of the Transportation Research Board 2528, no. 1 (January 2015): 116–27. http://dx.doi.org/10.3141/2528-13.
Full textAbstract:
The increasing availability of video data, through existing traffic cameras or dedicated field data collection, and the development of computer vision techniques pave the way for the collection of massive data sets about the microscopic behavior of road users. Analysis of such data sets helps in understanding normal road user behavior and can be used for realistic prediction of motion and computation of surrogate safety indicators. A multilevel motion pattern learning framework was developed to enable automated scene interpretation, anomalous behavior detection, and surrogate safety analysis. First, points of interest (POIs) were learned on the basis of the Gaussian mixture model and the expectation maximization algorithm and then used to form activity paths (APs). Second, motion patterns, represented by trajectory prototypes, were learned from road users' trajectories in each AP by using a two-stage trajectory clustering method based on spatial then temporal (speed) information. Finally, motion prediction relied on matching at each instant partial trajectories to the learned prototypes to evaluate potential for collision by using computing indicators. An intersection case study demonstrates the framework's ability in many ways: it helps reduce the computation cost up to 90%; it cleans the trajectory data set from tracking outliers; it uses actual trajectories as prototypes without any pre- and postprocessing; and it predicts future motion realistically to compute surrogate safety indicators.
35
Garg, Prateek, Anirudh Srinivasan Chakravarthy, Murari Mandal, Pratik Narang, Vinay Chamola, and Mohsen Guizani. "ISDNet: AI-enabled Instance Segmentation of Aerial Scenes for Smart Cities." ACM Transactions on Internet Technology 21, no. 3 (August 31, 2021): 1–18. http://dx.doi.org/10.1145/3418205.
Full textAbstract:
Aerial scenes captured by UAVs have immense potential in IoT applications related to urban surveillance, road and building segmentation, land cover classification, and so on, which are necessary for the evolution of smart cities. The advancements in deep learning have greatly enhanced visual understanding, but the domain of aerial vision remains largely unexplored. Aerial images pose many unique challenges for performing proper scene parsing such as high-resolution data, small-scaled objects, a large number of objects in the camera view, dense clustering of objects, background clutter, and so on, which greatly hinder the performance of the existing deep learning methods. In this work, we propose ISDNet (Instance Segmentation and Detection Network), a novel network to perform instance segmentation and object detection on visual data captured by UAVs. This work enables aerial image analytics for various needs in a smart city. In particular, we use dilated convolutions to generate improved spatial context, leading to better discrimination between foreground and background features. The proposed network efficiently reuses the segment-mask features by propagating them from early stages using residual connections. Furthermore, ISDNet makes use of effective anchors to accommodate varying object scales and sizes. The proposed method obtains state-of-the-art results in the aerial context.
36
Wang, Bokun, and Caiqian Yang. "Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder." Sensors 22, no. 12 (June 20, 2022): 4647. http://dx.doi.org/10.3390/s22124647.
Full textAbstract:
As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a Convolutional Recurrent AutoEncoder (CR-AE), which combines an attention-based Convolutional Long–Short-Term Memory (ConvLSTM) network and a Convolutional AutoEncoder. The ConvLSTM network and the Convolutional AutoEncoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively.
37
Triebel, Rudolph, Rohan Paul, Daniela Rus, and Paul Newman. "Parsing Outdoor Scenes from Streamed 3D Laser Data Using Online Clustering and Incremental Belief Updates." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 2088–95. http://dx.doi.org/10.1609/aaai.v26i1.8378.
Full textAbstract:
In this paper, we address the problem of continually parsing a stream of 3D point cloud data acquired from a laser sensor mounted on a road vehicle. We leverage an online star clustering algorithm coupled with an incremental belief update in an evolving undirected graphical model. The fusion of these techniques allows the robot to parse streamed data and to continually improve its understanding of the world. The core competency produced is an ability to infer object classes from similarities based on appearance and shape features, and to concurrently combine that with a spatial smoothing algorithm incorporating geometric consistency. This formulation of feature-space star clustering modulating the potentials of a spatial graphical model is entirely novel. In our method, the two sources of information: feature similarity and geometrical consistency are fed continu- ally into the system, improving the belief over the class distributions as new data arrives. The algorithm obviates the need for hand-labeled training data and makes no apriori assumptions on the number or characteristics of object categories. Rather, they are learnt incrementally over time from streamed input data. In experiments per- formed on real 3D laser data from an outdoor scene, we show that our approach is capable of obtaining an ever- improving unsupervised scene categorization.
38
Park, Myoung-Ok. "Development of a Web-Based Mini-Driving Scene Screening Test (MDSST) for Clinical Practice in Driving Rehabilitation." International Journal of Environmental Research and Public Health 19, no. 6 (March 17, 2022): 3582. http://dx.doi.org/10.3390/ijerph19063582.
Full textAbstract:
(1) Background: For the elderly and disabled, self-driving is very important for social participation. An understanding of changing driving conditions is essential in order to drive safely. This study aimed to develop a web-based Korean Mini-Driving Scene Screening Test (MDSST) and to verify its reliability and validity for clinical application. (2) Methods: We developed a web-based MDSST, and its content validity was verified by an expert group. The tests were conducted with 102 elderly drivers to verify the internal consistency and reliability of items, and the validity of convergence with the existing Korean-Safe Driving Behavior Measure (K-SDBM) and the Korean-Adelaide Driving Self-Efficacy Scale (K-ADSES) driving tests was also verified. The test–retest reliability was verified using 54 individuals who participated in the initial test. (3) Results: The average content validity index of MDSST was 0.90, and the average internal consistency of all items was 0.822, indicating high content validity and internal consistency. The exploratory factor analysis for construct validity, the KOM value of the data, was 0.658, and Bartlett’s sphericity test also showed a strongly significant result. The four factors were road traffic and signal perception, situation understanding, risk factor recognition, and situation prediction. The explanatory power was reliable at 61.27%. For the convergence validation, MDSST and K-SDBM showed r = 0.435 and K-ADSES showed r = 0.346, showing a moderate correlation. In the evaluation–reevaluation reliability verification, the reliability increased to r = 0.952. (4) Conclusions: The web-based MDSST test developed in this study is a useful tool for detecting and understanding real-world driving situations faced by elderly drivers. It is hoped that the MDSST test can be applied more widely as a driving ability test that can be used in the clinical field of driving rehabilitation.
39
Martinelli, Francesco. "Establishing Italian Jazz on the International Scene 1960-1980." European Journal of Musicology 16, no. 1 (December 31, 2017): 136–57. http://dx.doi.org/10.5450/ejm.2017.16.5785.
Full textAbstract:
This paper sheds new light on the developments in Italian jazz in the two decades 1960-1980. It opens by touching on context and antecedents: the relationships with Italian musical traditions in early American jazz, the acceptance and refusal of jazz by Italian cultural institutions and movements before 1960, and the late '50s key developments both in jazz and arts/media. In the early '60s, Italian jazz was characterized by two small scenes with marked differences in Rome and Milan and with a few further relevant events. An active and well rooted specialist magazine (Musica Jazz) provides relatively good documentation on these beginnings, quite detached from other general movements in music. By the end of the decade several ideological, cultural, political ruptures will have changed this panorama, and while Italian jazz was active in these changes, its exponents also had to deal with the complex situation they created from the point of view of artistic challenges, working conditions, and relationships with the recording industry. In order to discuss these changes and the different strategies adopted by musicians, four case studies will be examined to gain a better understanding of the process. Nunzio Rotondo, while almost unknown outside of Italy, was one of the first Italian musicians to successfully perform internationally after the war. He subsequently worked within the Rome jazz scene, with limited exposure both live and on record. Giorgio Gaslini's ground-breaking work of the late 50s, his training in ‘classical' music, and his unflagging commitment to exploration made him a personality similar to Portal and Gulda. However, his artistic successes did not close the chasm between ‘serious' music and jazz in Italy. Enrico Rava took the opposite road to Rotondo, widely performing abroad and paying dues in Buenos Aires, New York, and Paris before gaining acceptance worldwide and in his own country. He has been instrumental in the creation of an international image of Italian jazz and even of an Italian sound, opening the doors to many others. Perigeo was a ‘jazz-rock' group of the early 70s. Their recordings are still extremely popular. The reaction to their music by the jazz establishment and then their curt dismissal by the industry led to their disbanding, after which the single members—Franco D'Andrea, Claudio Fasoli, Giovanni Tommaso—produced and still produce some of the most exciting Italian jazz.
40
Broome, Michael, Matthew Gadd, Daniele De Martini, and Paul Newman. "On the Road: Route Proposal from Radar Self-Supervised by Fuzzy LiDAR Traversability." AI 1, no. 4 (December 2, 2020): 558–85. http://dx.doi.org/10.3390/ai1040033.
Full textAbstract:
This is motivated by a requirement for robust, autonomy-enabling scene understanding in unknown environments. In the method proposed in this paper, discriminative machine-learning approaches are applied to infer traversability and predict routes from Frequency-Modulated Contunuous-Wave (FMCV) radar frames. Firstly, using geometric features extracted from LiDAR point clouds as inputs to a fuzzy-logic rule set, traversability pseudo-labels are assigned to radar frames from which weak supervision is applied to learn traversability from radar. Secondly, routes through the scanned environment can be predicted after they are learned from the odometry traces arising from traversals demonstrated by the autonomous vehicle (AV). In conjunction, therefore, a model pretrained for traversability prediction is used to enhance the performance of the route proposal architecture. Experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community. Our key finding is that joint learning of traversability and demonstrated routes lends itself best to a model which understands where the vehicle should feasibly drive. We show that the traversability characteristics can be recovered satisfactorily, so that this recovered representation can be used in optimal path planning, and that an end-to-end formulation including both traversability feature extraction and routes learned by expert demonstration recovers smooth, drivable paths that are comprehensive in their coverage of the underlying road network. We conclude that the proposed system will find use in enabling mapless vehicle autonomy in extreme environments.
41
Alam, Afroj. "A Review of Automatic Driving System by Recognizing Road Signs Using Digital Image Processing." Journal of Informatics Electrical and Electronics Engineering (JIEEE) 2, no. 2 (June 2, 2021): 1–9. http://dx.doi.org/10.54060/jieee/002.02.003.
Full textAbstract:
In this review, the paper furnishes object identification's relationship with video investigation and picture understanding, it has pulled in much exploration consideration as of late. Customary item identification strategies are based on high-quality highlights and shallow teachable models. This survey paper presents one such strategy which is named as Optical Flow method. This strategy is discovered to be stronger and more effective for moving item recognition and the equivalent has been appeared by an investigation in this review paper. Applying optical stream to a picture gives stream vectors of the focus-es comparing to the moving items. Next piece of denoting the necessary moving object of interest checks to the post preparation. Post handling is the real commitment of the review paper for moving item identification issues. Their presentation effectively deteriorates by developing complex troupes which join numerous low-level picture highlights with significant level setting from object indicators and scene classifiers. With the fast advancement in profound learning, all the more useful assets, which can learn semantic, significant level, further highlights, are acquainted with address the issues existing in customary designs. These models carry on contrastingly in network design, preparing system, and advancement work, and so on In this review paper, we give an audit on pro-found learning-based item location systems. Our survey starts with a short presentation on the historical backdrop of profound learning and its agent device, in particular Convolutional Neural Network (CNN).
42
Kolekar, Suresh, Shilpa Gite, Biswajeet Pradhan, and Abdullah Alamri. "Explainable AI in Scene Understanding for Autonomous Vehicles in Unstructured Traffic Environments on Indian Roads Using the Inception U-Net Model with Grad-CAM Visualization." Sensors 22, no. 24 (December 10, 2022): 9677. http://dx.doi.org/10.3390/s22249677.
Full textAbstract:
The intelligent transportation system, especially autonomous vehicles, has seen a lot of interest among researchers owing to the tremendous work in modern artificial intelligence (AI) techniques, especially deep neural learning. As a result of increased road accidents over the last few decades, significant industries are moving to design and develop autonomous vehicles. Understanding the surrounding environment is essential for understanding the behavior of nearby vehicles to enable the safe navigation of autonomous vehicles in crowded traffic environments. Several datasets are available for autonomous vehicles focusing only on structured driving environments. To develop an intelligent vehicle that drives in real-world traffic environments, which are unstructured by nature, there should be an availability of a dataset for an autonomous vehicle that focuses on unstructured traffic environments. Indian Driving Lite dataset (IDD-Lite), focused on an unstructured driving environment, was released as an online competition in NCPPRIPG 2019. This study proposed an explainable inception-based U-Net model with Grad-CAM visualization for semantic segmentation that combines an inception-based module as an encoder for automatic extraction of features and passes to a decoder for the reconstruction of the segmentation feature map. The black-box nature of deep neural networks failed to build trust within consumers. Grad-CAM is used to interpret the deep-learning-based inception U-Net model to increase consumer trust. The proposed inception U-net with Grad-CAM model achieves 0.622 intersection over union (IoU) on the Indian Driving Dataset (IDD-Lite), outperforming the state-of-the-art (SOTA) deep neural-network-based segmentation models.
43
Ben-Yami, Maya, Hilke Oetjen, Helen Brindley, William Cossich, Dulce Lajas, Tiziano Maestri, Davide Magurno, Piera Raspollini, Luca Sgheri, and Laura Warwick. "Emissivity retrievals with FORUM's end-to-end simulator: challenges and recommendations." Atmospheric Measurement Techniques 15, no. 6 (March 23, 2022): 1755–77. http://dx.doi.org/10.5194/amt-15-1755-2022.
Full textAbstract:
Abstract. Spectral emissivity is a key property of the Earth's surface, of which only very few measurements exist so far in the far-infrared (FIR) spectral region, even though recent work has shown that the FIR is important for accurate modelling of the global climate. The European Space Agency's 9th Earth Explorer, FORUM (Far-infrared Outgoing Radiation Understanding and Monitoring) will provide the first global spectrally resolved measurements of the Earth's top-of-the-atmosphere (TOA) spectrum in the FIR. In clear-sky conditions with low water vapour content, these measurements will provide a unique opportunity to retrieve spectrally resolved FIR surface emissivity. In preparation for the FORUM mission with an expected launch in 2027, this study takes the first steps towards the development of an operational emissivity retrieval for FORUM by investigating the sensitivity of the emissivity product of a full spectrum optimal estimation retrieval method to different physical and operational parameters. The tool used for the sensitivity tests is the FORUM mission's end-to-end simulator. These tests show that the spectral emissivity of most surface types can be retrieved for dry scenes in the 350–600 cm−1 region, with an absolute uncertainty ranging from 0.005 to 0.01. In addition, the quality of the retrieval is quantified with respect to the precipitable water vapour content of the scene, and the uncertainty caused by the correlation of emissivity with surface temperature is investigated. Based on these investigations, a road map is recommended for the development of the operational emissivity product.
44
Armstrong, John. "Gothic Matters of De-Composition: The Pastoral Dead in Contemporary American Fiction." Text Matters, no. 6 (November 23, 2016): 127–43. http://dx.doi.org/10.1515/texmat-2016-0008.
Full textAbstract:
In Alice Walker’s vignette “The Flowers,” a young black girl’s walk in the woods is interrupted when she treads “smack” into the skull of a lynched man. As her name predicates, Myop’s age and innocence obstruct her from seeing deeply into the full implications of the scene, while the more worldly reader is jarred and confronted with a whole history of racial violence and slavery. The skeleton, its teeth cracked and broken, is a temporal irruption, a Gothic “smack” that shatters the transience of the pastoral scene with the intrusion of a deeper past from which dead matter/material de-composes (disturbs, unsettles, undoes) the story’s present with the violent matter/issue of racism. Walker’s story is representative of an important trope in fiction, where the pastoral dead speak through the details of their remains, and the temporal fabric of text is disrupted by the very substance of death.
Against the backdrops of Terry Gifford’s post-pastoral and Fred Botting’s Gothic understanding of the literary corpse as “negative[ly] sublime,” this essay explores the fictional dead as matter unfettered by genre, consistently signifying beyond their own inanimate silences, revealing suppressed and unpalatable themes of racial and sexual violence, child abuse and cannibalistic consumerism. Along with Walker’s story, this study considers these ideas through new readings of Stephen King’s novella The Body, Raymond Carver’s story “So Much Water So Close to Home,” and The Road by Cormac McCarthy. While these writers may form an unlikely grouping in terms of style, each uses pastoral remains as significant material, deploying the dead as Gothic entities that force the reader to confront America’s darkest social and historical matters.
45
Calsavara, Felipe, Felipe Issa Kabbach Junior, and Ana Paula C. Larocca. "Effects of Fog in a Brazilian Road Segment Analyzed by a Driving Simulator for Sustainable Transport: Drivers’ Visual Profile." Sustainability 13, no. 16 (August 23, 2021): 9448. http://dx.doi.org/10.3390/su13169448.
Full textAbstract:
Visibility is a critical factor for drivers to perceive roadway information, and fog is an inclement weather condition that directly impacts their vision, since it reduces both overall contrast and visibility of the driving scene. Visual attention has been considered a contributing factor to traffic crashes, and fog-related accidents are prone to be more severe and involve multiple vehicles. The literature lacks studies on the influence of fog on drivers’ visual performance and environment’s infrastructure design. This article investigates the effects of fog on drivers’ performance in a Brazilian curved road segment through a driving simulator experiment – more precisely, whether the presence of fog (foggy scenario) or its absence (clear scenario) significantly affects the visual profile. In the foggy scenario, the results showed the tracked area was concentrated in a smaller region, despite an increase in the number of fixations compared with the clear scenario. The fixation duration did not change between the scenarios and the pupil dilation was shorter in the foggy one. The study shows the influence of environmental conditions on the driver’s performance and is one of the first on the use of driving simulators with realistic representations of the road infrastructure and its surrounding for the understanding of driving under fog in the Brazilian scenario. Besides roadway geometry elements, driving simulator studies enable analyses of features related to the interaction between route environment and driver’s answer, and can improve safety in places with visibility problems caused by fog, reducing their environmental impact and preserving drivers’ lives.
46
Lu, Wenjie, Sergio A. Rodríguez F., Emmanuel Seignez, and Roger Reynaud. "Lane Marking-Based Vehicle Localization Using Low-Cost GPS and Open Source Map." Unmanned Systems 03, no. 04 (October 2015): 239–51. http://dx.doi.org/10.1142/s2301385015400014.
Full textAbstract:
Autonomous Vehicle applications and Advanced Driving Assistance Systems (ADAS) need scene understanding processes, allowing high-level systems to carry out decision. For such systems, the localization of a vehicle evolving in a structured dynamic environment constitutes a complex problem of crucial importance. However, the low accuracy of the global positioning system (GPS) system in urban environments makes its localization unreliable for further treatments. The combination of GPS data and additional sensors (WSS, IMU or Camera) can improve the localization precision. More and more, digital maps are also used in this process. Generally, these maps are customized or built for a specific application, asking high-cost to design and upgrade. In this paper, we propose a low-cost localization system based on camera, GPS and open map. Starting from the road marking, detected by a multi-kernel estimation method, a particle filter generates the samples taking advantage of lane markings to predict the most probable trajectory of the vehicle and the low-cost GPS position. Then, the accuracy of the localization is improved using an open map. This process was validated through several scenarios with a public database and our experimental platform.
47
Ballardini, Augusto Luis, Álvaro Hernández Saz, Sandra Carrasco Limeros, Javier Lorenzo, Ignacio Parra Alonso, Noelia Hernández Parra, Iván García Daza, and Miguel Ángel Sotelo. "Urban Intersection Classification: A Comparative Analysis." Sensors 21, no. 18 (September 18, 2021): 6269. http://dx.doi.org/10.3390/s21186269.
Full textAbstract:
Understanding the scene in front of a vehicle is crucial for self-driving vehicles and Advanced Driver Assistance Systems, and in urban scenarios, intersection areas are one of the most critical, concentrating between 20% to 25% of road fatalities. This research presents a thorough investigation on the detection and classification of urban intersections as seen from onboard front-facing cameras. Different methodologies aimed at classifying intersection geometries have been assessed to provide a comprehensive evaluation of state-of-the-art techniques based on Deep Neural Network (DNN) approaches, including single-frame approaches and temporal integration schemes. A detailed analysis of most popular datasets previously used for the application together with a comparison with ad hoc recorded sequences revealed that the performances strongly depend on the field of view of the camera rather than other characteristics or temporal-integrating techniques. Due to the scarcity of training data, a new dataset is created by performing data augmentation from real-world data through a Generative Adversarial Network (GAN) to increase generalizability as well as to test the influence of data quality. Despite being in the relatively early stages, mainly due to the lack of intersection datasets oriented to the problem, an extensive experimental activity has been performed to analyze the individual performance of each proposed systems.
48
Manchev, V., JL Bruce, GV Oosthuizen, GL Laing, and DL Clarke. "The incidence, spectrum and outcome of paediatric trauma managed by the Pietermaritzburg Metropolitan Trauma Service." Annals of The Royal College of Surgeons of England 97, no. 4 (May 2015): 274–78. http://dx.doi.org/10.1308/003588414x14055925061595.
Full textAbstract:
Introduction The Pietermaritzburg Metropolitan Trauma Service (PMTS) has run a systematic quality improvement programme since 2006. A key component included the development and implementation of an effective surveillance system in the form of an electronic surgical registry (ESR). This study used data from the ESR to review the incidence, spectrum and outcome of paediatric trauma in Pietermaritzburg, South Africa. Methods The ESR was reviewed, and all cases of paediatric trauma managed between 1 January 2012 and 30 July 2014 were retrieved for analysis. Results During the study period, 1,041 paediatric trauma patients (724 male, 69.5%) were managed by the PMTS, averaging a monthly admission of 36. The mean age was 10.9 years (standard deviation: 5.4 years). The mechanism of injury (MOI) was blunt trauma in 753 patients (72.3%) and penetrating trauma in 170 (16.3%). Pedestrian vehicle collisions accounted for 21% of cases and motor vehicle collisions for a further 11%. Intentional trauma accounted for 282 patients (27.1%) and self-inflicted trauma for 14 cases (1.3%). Ninety patients admitted to the intensive care unit and fifty-one required high dependency unit admission. There were 17 deaths, equating to an in-hospital mortality rate of 1.7%. A total of 172 children died on the scene of an incident. There were 35 road traffic related deaths, 26 suicides by hanging, 27 deaths from blunt assault and 23 deaths from penetrating assault. The overall mortality rate for paediatric trauma was 18.2%. Conclusions The ESR has proved to be an effective surveillance system and has enabled the accurate quantification of the burden of paediatric trauma in Pietermaritzburg. This has improved our understanding of the mechanisms and patterns of injury, and has identified a high incidence of intentional and penetrating trauma as well as road traffic collisions. These data can be used to guide strategies to reduce the burden of paediatric trauma in our environment.
49
Obradović, Žarko. "Elements of global superiority of The People's Republic of China in the 21st century." Napredak 2, no. 2 (2021): 77–102. http://dx.doi.org/10.5937/napredak2-32694.
Full textAbstract:
The Chinese state has existed for more than five thousand years and in the history of human society it has always presented its own specific civilizational attainment, which exerted a considerable influence on the Asian region. In the years since its creation on October 1, 1949, and especially in the last decade, New China has stepped out beyond the region of Asia onto the global scene. With its economic power and international development projects (amongst which the Belt and Road projects stands out), China has become a leader of development and the promoter of the idea of international cooperation in the interests of peace and security in the world and the protection of the future of mankind. This paper will attempt to delineate the elements of the development of the People's Republic of China in the 21st century, placing a special focus on the realization of the Belt and Road initiative and the results of the struggle against the Covid-19 pandemic, all of which have made China an essential factor in the power relations between great global forces and the resultant change of attitude of the United States of America and the European Union towards China. Namely, China has always been a large country in terms of the size of its territory and population, but it is in the 21st century that the PR of China has become a strong state with the status of a global power. Such results in the organization of society and the state, the promotion of new development ideas and the achievement of set goals, would not have been possible without the Communist Party of China, as the main ideological, integrative and organizational factor within Chinese society. In its activities, the Chinese state sublimates the experiences of China's past with an understanding of the present moment in the international community and the need of Chinese citizens to improve the quality of life and to ensure stable development of the country. The United States and the European Union are taking various measures to oppose the strengthening of the People's Republic of China. These include looking after their interests and preserving their position in the international community, while simultaneously trying, if possible, to avoid jeopardizing their economic cooperation with China.
50
Liu, Lu. "Scene Classification in the Environmental Art Design by Using the Lightweight Deep Learning Model under the Background of Big Data." Computational Intelligence and Neuroscience 2022 (June 13, 2022): 1–9. http://dx.doi.org/10.1155/2022/9066648.
Full textAbstract:
On the basis of scene visual understanding technology, the research aims to further improve the classification efficiency and classification accuracy of art design scenes. The lightweight deep learning (DL) model based on big data is used as the main method to achieve real-time detection and recognition of multiple targets and classification of the multilabel scene. This research introduces the related foundations of the DL network and the lightweight object detection involved. The data for a multilabel scene classifier are constructed and the design of the convolutional neural network (CNN) model is described. On public datasets, the effectiveness of the lightweight object detection algorithm is verified to ensure its feasibility in the classification of actual scenes. The simulation results indicate that compared with the YOLOv3-Tiny model, the improved IRDA-YOLOv3 model reduces the number of parameters by 56.2%, the amount of computation by 46.3%, and the forward computation time of the network by 0.2 ms. It means that the IRDA-YOLOv3 network obtained after the improvement can realize the lightweight of the network. In the scene classification of complex traffic roads, the classification model of the multilabel scene can predict all kinds of semantic information of a single image and the classification accuracy for the four scenes is more than 90%. In summary, the discussed classification method based on the lightweight DL model is suitable for complex practical scenes. The constructed lightweight network improves the representational ability of the network and has certain research value for scene classification problems.