检索结果-南通市图书馆

Efficient Online vehicle tracking for Real-Virtual Mapping Systems

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2021年第5期26卷 598-606页

作者： CHEN Jiacheng LI Lin YANG Xubo School of Software Shanghai Jiao Tong UniversityShanghai 200240China Shanghai International Automobile City(Group)Co. Ltd.Shanghai 201805China

Multi-object tracking is a vital problem as many applications require better tracking *** learning-based detectors are becoming extremely powerful,there are few tracking methods designed to work with them in real *** explored an efficient flexible online vehicle tracking-by-detection framework suitable for real-virtual mapping systems,which combines a non-recursive temporal window search with delayed output and produces stable trajectories despite noisy detection *** computation speed meets the real-time requirements,whereas its performance is comparable with that of state-of-the-art online trackers on the DETRAC *** trajectories from our approach also contain the target class and color information important for virtual vehicle motion reconstruction.

关键词： multi-object tracking vehicle tracking tracklet association real-virtual mapping

vehicle tracking Based on Nonlinear Motion Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Vehicle Tracking Based on Nonlinear Motion Model

2013年中国智能自动化学术会议

作者： Fan Zhang Hong Li Kalilou Kone Wei Zhang School of Information Science and Engineering Central South University School of Architecture Hunan University

How to detect and track vehicle in nonlinear motion is a big problem in computer graphics *** vision is complete works like positioning with only one camera;it has a simple structure and a strong applicability. In this paper,we build and solve models of traffic video with nonlinear motion model,to locate and track vehicles in *** present a new nonlinear movement model using shape model and projection *** accurately calculated results of position and velocity of the vehicle is given by estimating the vehicle’s speed,posture,the last ***’s an effective solution to the problem that nonlinear movement is difficult to estimate by KALMAN filter and the tracking process is not stable and reliable *** experiments show that the new algorithm has better robustness than EKF and UKF algorithm.

关键词： Nonlinear motion vehicle tracking Motion model KALMAN filter

Video-based vehicle tracking considering occlusion

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Southeast University(English Edition) 2015年第2期31卷 266-271页

作者：朱周路小波东南大学交通学院南京210096 东南大学复杂工程系统测量与控制教育部重点实验室南京210096 东南大学自动化学院南京210096

To track the vehicles under occlusion, a vehicle tracking algorithm based on blocks is proposed. The target vehicle is divided into several blocks of uniform size, in which the edge block can overlap its neighboring blocks. All the blocks＇ motion vectors are estimated, and the noise motion vectors are detected and adjusted to decrease the error of motion vector estimation. Then, by moving the blocks based on the adjusted motion vectors, the vehicle is tracked. Aiming at the occlusion between vehicles, a Markov random field is established to describe the relationship between the blocks in the blocked regions. The neighborhood of blocks is defined using the Euclidean distance. An energy function is defined based on the blocks＇ histograms and optimized by the simulated annealing algorithm to segment the occlusion region. Experimental results demonstrate that the proposed algorithm can track vehicles under occlusion accurately.

关键词： vehicle tracking occlusion processing motionvector Markov random field

Vision-based vehicle tracking and Classification on the Highway

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science and Information 2007年第2期5卷 141-149页

作者： Guolian Yun Qimei Chen Bo Li Xindao Wang Department of Electronic Science and Engineering Nanjing University Nanjing 210093 China

This paper presents algorithms for vision-based tracking and classification of vehicles in image sequences of traffic scenes recorded by a stationary camera. In the algorithms, the central moment and extended Kalman filter of tracking processes optimizes the amount of spent computational resources. Moreover, it robust to many difficult situations such as partial or full occlusions of vehicles. vehicle classification performance is improved by Bayesian network, especially from incomplete data. The methods are test on a single Intel Pentium 4 processor 2.4 GHz and the frame rate is 25 frames/s. Experimental results from highway scenes are provided, which demonstrate the effectiveness and robust of the methods.

关键词： vision-based vehicle tracking Bayesian network vehicle classification

YOLOv2 Deep Learning Model and GIS Based Algorithms for vehicle tracking

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Geographic Information System 2021年第4期13卷 395-409页

作者： Mohamed El Imame Malaainine Hatim Lechgar Hassane Rhinane Hassania School of Public Works Casablanca Morocco FSAC-Hassan II University Casablanca Morocco

The latest advances in Deep Learning based methods and computational capabilities provide new opportunities for vehicle tracking. In this study, YOLOv2 (You Only Look Once—version 2) is used as an open source Convolutional Neural Network (CNN), to process high-resolution satellite images, in order to generate the spatio-temporal GIS (Geographic Information System) tracks of moving vehicles. At first step, YOLOv2 is trained with a set of images of 1024 × 1024 resolution from the VEDAI database. The model showed satisfactory results, with an accuracy of 91%, and then at second step, is used to process aerial images extracted from aerial video. The output vehicle bounding boxes have been processed and fed into the GIS based LinkTheDots algorithm, allowing vehicles identification and spatio-temporal tracks generation in GIS format.

关键词： Deep Learning YOLOv2 vehicle tracking GIS

A hierarchical clustering of features approach for vehicle tracking in traffic environments

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2016年第4期9卷 354-368页

作者： Anan Banharnsakun Supannee Tanathong CIR Laboratory Faculty of Engineering at SrirachaKasetsart University Sriracha CampusChonburiThailand Laboratory for Sensor and Modeling Department of GeoinformaticsUniversity of SeoulSeoulKorea

Purpose-Developing algorithms for automated detection and tracking of multiple objects is one challenge in the field of object *** in a traffic video monitoring system,vehicle detection is an essential and challenging *** the previous studies,many vehicle detection methods have been *** proposed approaches mostly used either motion information or characteristic information to detect *** these methods are effective in detecting vehicles,their detection accuracy still needs to be ***,the headlights and windshields,which are used as the vehicle features for detection in these methods,are easily obscured in some traffic *** paper aims to discuss these ***/methodology/approach-First,each frame will be captured from a video sequence and then the background subtraction is performed by using the Mixture-of-Gaussians background ***,the Shi-Tomasi corner detection method is employed to extract the feature points from objects of interest in each foreground scene and the hierarchical clustering approach is then applied to cluster and form them into feature *** feature blocks will be used to track the moving objects frame by ***-Using the proposed method,it is possible to detect the vehicles in both day-time and night-time scenarios with a 95 percent accuracy rate and can cope with irrelevant movement(waving trees),which has to be deemed as *** addition,the proposed method is able to deal with different vehicle shapes such as cars,vans,and ***/value-This paper presents a hierarchical clustering of features approach for multiple vehicles tracking in traffic environments to improve the capability of detection and tracking in case that the vehicle features are obscured in some traffic conditions.

关键词： Feature extraction Hierarchical clustering Mixture-of-Gaussians Multiple object detection Shi-Tomasi corner detection vehicle tracking Background model

Multiclass vehicle tracking Based on Local Feature

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Multiclass Vehicle Tracking Based on Local Feature

2013年中国智能自动化学术会议

作者： Zhiming Qian Jiakuan Yang Lianxin Duan Chuxiong Normal University

This paper presents a real time multiclass vehicle tracking *** method uses a combination of machine learning and feature analysis to track the vehicles on the *** SVM are trained using train samples to achieve detection and classification of vehicles in video sequences of traffic *** detection results provide the system used for *** class vehicle is tracked by SIFT *** results from highway scenes are provided which demonstrate the effectiveness of the method.

关键词： vehicle detection vehicle tracking Feature analysis

High Definition Map Assisted vehicle tracking with Lane Constraint

在线全文

cnki会议

学校读者我要写书评

暂无评论

High Definition Map Assisted Vehicle Tracking with Lane Cons...

第32届中国控制与决策会议

作者： Shenghao Su Mengxin Liu Ming Cen School of Automation Chongqing University of Posts and Telecommunications

vehicle target tracking is the key of auxiliary driving system and unmanned driving *** by traffic rules,vehicles on a multi-lane road always try to drive in the middle of the *** order to use this prior information to improve the performance of vehicle target tracking,a High Definition Map assisted vehicle tracking with lane constraint is *** the method,regarding the function of lane as a proportional-derivative controller,a new vehicle motion model considering the affection of the lane is *** measurement is transformed into the curvilinear-coordinate system,and the state estimation of the target is implemented in such coordinate system ***,to evaluate the influence of adjacent lanes to the vehicle,a DS-VSMM filter is designed to identify whether the vehicle is changing lane and which lane the vehicle would change *** results show that the proposed algorithm improved the vehicle tracking accuracy,reduced the time consumption,and effectively identified the lane change behavior of target vehicle.

关键词： vehicle tracking Lane Constraints High Definition Map DS-VSMM Filter

An Improved Method for Estimating Urban Traffic State via Probe vehicle tracking

在线全文

cnki会议

学校读者我要写书评

暂无评论

An Improved Method for Estimating Urban Traffic State via Pr...

第三十届中国控制会议

作者： ZHAO Qiankun~1,KONG Qingjie~1,XIA Yingjie~(1,2),LIU Yuncai~1 1.Department of Automation,Shanghai Jiao Tong University,and Key Laboratory of System Control and Information Processing,Ministry of Education of China,Shanghai,200240,P.R.China 2.Hangzhou Institute of Service Engineering,Hangzhou Normal University,Hangzhou,310012,P.R.China

＜正＞In order to estimate the state of urban traffic flow,a Probe-vehicle-tracking based method is proposed in this paper. The method collects traffic flow data with Global Positioning System（GPS）-equipped taxies,which are taken as the probe ***,the A* heuristic search algorithm is employed to judge the optimal vehicle tracking *** addition,the average velocities of road links are calculated by considering the velocities of vehicle tracks as well as their corresponding credibility ***,an experiment with massive real-world traffic data in the surface road network of Shanghai was carried out,and the ground truth of the average velocity was obtained by repeating the videos shot on the 24 links in Shanghai *** experiment results verify that the method has high accuracy and can be applied in engineering practice.

关键词： GPS probe vehicle Traffic state estimation vehicle tracking Intelligent Transportation Systems