Video-based moving vehicle detection and tracking are important parts of modern intelligent transportation system (ITS). They can provide valuable information such as vehicle velocity and trajectory for ITS. However, vehicle tracking at urban intersection is more challenging than that at highway, due to the complicated scenarios, such as the variety of vehicle moving direction, inter-vehicle clustering and occlusion. Many successful vehicle tracking systems developed for high way vehicle tracking based on the blob-tracking approach failed to provide acceptable performance at urban intersections when there are heavy vehicle occlusion or vehicles close to each other. This paper proposes a novel vehicle segmentation method for moving vehicle segmentation at urban intersection by seeking the spatial-temporal matching of feature points. Experimental results show that feature point may be taken as an important cue for moving vehicle segmentation and tracking under sophisticated traffic situation.

In modern intelligent transportation systems, the video image vehicle detection system (VIVDS) is gradually becoming one of the popular methods at signalized traffic intersection due to its convenient installation and rich information content provided. However, in the current VIVDS, the camera usually is installed at the roadside poles or traffic light poles, which not only requires more than one camera to cover the entire intersection, but also results in serious vehicle occlusions and adverse affects on the performance of the vehicle detection and tracking. Meanwhile, it is noted that the detection rate of the black, gray and dark color vehicles (such as red, blue, and green vehicles) are poor or incomplete detection by using the traditional background subtraction method in the RGB color model. To tackle these problems, this paper presents a novel VIVDS with the new camera installation, which only uses a single camera to cover the panorama view of the interested intersection. Furthermore, a robust vehicle detection algorithm with multi-information fusion has been developed to resolve problems of detecting incompletion, which plays a key role in enhancing the vehicle detection rate in the proposed VIVDS for urban traffic surveillance. The proposed system has been tested on a traffic image sequences recorded at typical urban intersections. The experimental results show that the system offers the flexibility to detect the different color vehicles, the robustness to noise and the efficiency of computation.

Traffic incident detection is one of the most important issues for intelligent transportation systems (ITS), especially in urban area which is full of signaled intersections. This paper presents the development of a novel traffic incident detection system based on image signal processing, feature extraction algorithms, and hidden Markov model (HMM) classifier. First, a traffic surveillance system was set up at a typical intersection of china, traffic videos were recorded and image sequences were extracted for image database forming. Second, several features extraction algorithms were used and compared. Finally, HMM was used for classification of traffic signal logics (East-West, West-East, South-North, North-South) and accident of crash. Feature generation with DCT-FFT process gives the best result with total correct rate of 91% and incident recognition rate of 95%.

This paper presents a robust traffic parameters extraction (RTPE) method for intelligent traffic system. Firstly a texture-based algorithm is introduced to solve the moving shadow problem, which occurs in traffic lane commonly. Secondly, we propose a robust exponential entropy-based and data-dependent threshold vehicle detection algorithm, named RVD-EXEN algorithm to extract vehicle's feature from raw visual information for vehicle detection. On this basis, we calculate some basic traffic parameters such as traffic flow, time occupancy ratio and space mean speed. The experiments show that proposed RTPE method has the flexibility to shadow situation, robustness to noise and efficiency of computation.

For an intelligent transportation system (ITS), traffic incident detection is one of the most important issues, especially for urban area which is full of signaled intersections. In this paper, we propose a novel traffic incident detection method based on the image signal processing and hidden Markov model (HMM) classifier. First, a traffic surveillance system was set up at a typical intersection of China, traffic videos were recorded and image sequences were extracted for image database forming. Second, compressed features were generated through several image processing steps, image difference with FFT was used to improve the recognition rate. Finally, HMM was used for classification of traffic signal logics (East-West, West-East, South-North, North-South) and accident of crash, the total correct rate is 74% and incident recognition rate is 84%. We believe, with more types of incident adding to the database, our detection algorithm could serve well for the traffic surveillance system.

For a typical urban intersection, moving vehicle shadow and vehicle-pedestrian mixed conditions exist in traffic scene commonly. These interfering factors lead to a very low correct rate of the traffic parameters extraction. This paper presents robust traffic parameters extraction (RTPE) approach for traffic surveillance system at an urban intersection, which contains three key algorithms. First, a texture-based vehicle segmentation (TVS) algorithm is introduced to solve the moving shadow problem. Second, we propose an image exponential entropy-based vehicle exist detection (IEE-VED) algorithm to reduce the noise interference by pedestrians at the intersection, and we extract vehicle features from raw visual information to determine whether there is a vehicle in the detection zone. On this basis, the traffic parameters measurement (TPM) algorithm is introduced to calculate some important traffic parameters of the intersection for traffic management and traffic jam detection, such as traffic flow, time occupancy ratio, space mean speed and the difference of IN/OUT traffic flow. Experimental results indicate that the proposed RTPE approach is effective for traffic parameters extraction, and these parameters can truly reflect the prevailing traffic condition.

基于视频的车辆跟踪技术已经成为车辆跟踪技术的主要研究方向。能否在复杂的交通场景下,鲁棒地、实时地对车辆进行跟踪成为衡量跟踪方法优劣的重要标准。本文介绍了四种主要的基于视频的车辆跟踪方法,并分别讨论了这些方法在复杂交通场景下的适用性和性能。文章着重介绍了一种基于区域特征匹配的车辆跟踪算法,运用该跟踪算法能有效地对交叉路口的车辆进行跟踪。

Video-based vehicle tracking techniques have become the main research direction of vehicle tracking. The studies of vehicles tracking focus on how to obtain robust and real-time vehicle tracking in complex traffic scenes. In this paper, four mainstream methods are introduced for video-based vehicle tracking, and the applicability and tracking capability of these methods are discussed in complex traffic scenes. Additionally, a vehicle tracking algorithm based on regional characteristic matching is mainly introduced, which can track vehicles efficiently at traffic intersections.

基于视频的运动车辆检测技术已经成为车辆检测技术的主要研究方向。随着这种技术的不断发展,能否在复杂背景下快速而准确地检测出运动车辆成为衡量基于视频的车辆检测技术的重要标准之一。本文着重介绍了三种主流的基于视频的运动车辆检测方法,并着重分别讨论了这些方法在复杂背景下的适用性和检测能力。文章的最后,详细地介绍了混合高斯背景建模算法的原理以及工作流程。

传统交通事件自动检测(AID)算法存在检测率较低、误报率较高、平均检测时间长等不足,未能在城市智能交通系统中获得成功应用。概述两种传统AID检测算法的基本原理,着重介绍了基于不同神经网络结构和支持向量机的AID算法及其性能分析比较。针对城市复杂交通场景,比较分析各种AID算法的优缺点和局限性。结果表明结合模糊理论和支持向量机AID技术有可能为城市交通事件自动检测提供解决方案。