Entity

Time filter

Source Type


Yang Y.,Soochow University of China | Yang Y.,Jiangsu Province Support Software Engineering R and nter for Modern Information Technology Applied in Enterprise | Cui Z.,Soochow University of China | Cui Z.,Jiangsu Province Support Software Engineering R and nter for Modern Information Technology Applied in Enterprise | And 5 more authors.
Journal of Computational Information Systems | Year: 2012

Trajectory analysis is the basis of scene understanding. Currently, the most common trajectory analysis methods focus on the geometric characteristics of the whole trajectory and neglect the semantic information related to the common sub-trajectories. However, as we known the common sub-trajectories are often the important parts we are interested in for trajectory analysis and video event detection. In this paper, the trajectory firstly is segmented into sub-trajectories incorporated the Common Appearance Intervals (CAIS) into and propose an improved trajectory similarity measure method considering location, spatial and direction of trajectories. Then, we apply spectral clustering algorithm to group similar sub-trajectories in similar position and orientation into a cluster. Finally, a sequential pattern mining algorithm is attempted to identify the frequent trajectory patterns. Experiments on trajectory data set in true scene show the validity of the trajectory analysis method. © 2012 Binary Information Press. Source


Cao Y.,Soochow University of China | Cui Z.,Soochow University of China | Cui Z.,Jiangsu Yihe Traffic Engineering Co. | Wu J.,Soochow University of China | And 2 more authors.
Journal of Soochow University Engineering Science Edition | Year: 2011

Aiming at the existing untimely problems in urban road monitoring video of the incident detection and alarm which is not on time, we propose a kind of quick and effective method for detect violation vehicle route and position. This method does not rely on the traditional approach for detecting and segmenting multiple vehicles. We use the Harris corner detection method to extract vehicle corner, then use the pyramid of Lucas-Kanande tracking to track the Harris corner fast, then implement spectral clustering for the tracking Harris corner. We use the Bhattacharyya distance to measure and normalize. The Harris corner and clustering center we can judge whether the abnormally vehicle behavior happeneds with a predetermined threshold. The experimental results show that the method we proposed is robust and effective. Source


Yang Y.,Soochow University of China | Yang Y.,Center for Modern Information Technology Application in Enterprise | Yang Y.,Jiangsu Yihe Traffic Engineering Co. | Cui Z.,Soochow University of China | And 6 more authors.
Proceedings - 3rd International Symposium on Information Science and Engineering, ISISE 2010 | Year: 2011

Huge amount of Traffic video segmented into manageable shots is the key step of database storage and video analysis in Intelligent Transportation Systems (ITS). Then key frames are extracted for representing main visual content of each shot. This paper proposes a novel approach for the segmentation of traffic video by the judgment of motion trend and supported by the vehicle status changes. Considering the number of sub-shots in shots as the initialized clusters number, we apply an improved global k-means clustering algorithm to extract the key frame. With the numerical experiments on traffic surveillance video using the propose method in this paper, shot boundary detection can be made in an effective manner. The extracted key frames by our approach also show better representation for the visual content of the video shot compared with other methods. © 2010 IEEE. Source


Wu J.,Soochow University of China | Wu J.,Jiangsu Yihe Traffic Engineering Co. | Cui Z.-M.,Soochow University of China | Cui Z.-M.,Jiangsu Yihe Traffic Engineering Co. | And 3 more authors.
Journal of Multimedia | Year: 2012

Analysis of the Vehicle Behavior is mainly to analyze and identify the vehicles' motion pattern, and describe it by the use of natural language. It is a considerable challenge to analyze and describe the vehicles' behavior in a complex scene. This paper first hackles the development history of the intelligent transportation system and analysis of vehicles' behavior, and then conducts an indepth analysis of current situation of vehicle behavior analysis from the video processing, video analysis and video understanding, summarizes the achieved results and the key technical problems, and prospects the future development of vehicle behavior analysis. © 2012 ACADEMY PUBLISHER. Source


Zhang G.,Soochow University of China | Cui Z.,Soochow University of China | Cui Z.,Jiangsu Yihe Traffic Engineering Co. | Chen J.,Soochow University of China | And 3 more authors.
Journal of Computational Information Systems | Year: 2010

Traffic video key object research as an important part of intelligent transportation systems plays a significant role. Traditional traffic video key object information may express incompletely when extraction key frame at fixed interval, it can't meet the requirements of the recognition and tracking. In this paper, a novel fusion method which is combined beamlet transform with dynamic fuzzy logic is proposed. Firstly, beamlet transform was applied to decompose each incomplete key object into certain coefficients at different scales. Then dynamic fuzzy logic theory was applied to construct a series of membership functions to optimize these coefficients, the fusion coefficients from different scales were selected by these membership functions respectively. At last the key object was synthesized and reconstructed via inverse of the beamlet transform. By contrast, the efficiency of our method is better than other traditional fusion methods. Copyright © 2010 Binary Information Press. Source

Discover hidden collaborations