Loading...
Please wait, while we are loading the content...
Similar Documents
Efficient moving object detection based on statistical background modeling.
| Content Provider | CiteSeerX |
|---|---|
| Researcher | Kusuma., U. Shalini, S. T. Bibin |
| Abstract | Abstract — Tracking vehicles is an important and challenging problem in video-based Intelligent Transportation Systems, which has been broadly investigated in the past. A robust method for tracking vehicles is implemented in this thesis work. The proposed algorithm includes three stages: object detection, counting and tracking. Vehicle detection is a key step. The concept of moving object detection is built upon the segmentation method. Background subtraction method is used in this work. According to the segmented object shape, a predict method based on Kalman filter is proposed. By assuming that the vehicle moves with almost a constant acceleration from the current frame to the next, a Kalman filter model is used to tracking and predicting the trace of a vehicle. The model can be used in the traffic analysis as it is capable of tracking and counting multiple targets in a big area hence forming an effective, efficient, practical vehicle tracking system. The proposed method has been tested on few trafficimage sequences and the experimental results show that the algorithm is robust and can meet the requirement. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Object Detection Statistical Background Modeling Practical Vehicle Background Subtraction Method Kalman Filter Model Object Shape Constant Acceleration Multiple Target Big Area Hence Thesis Work Robust Method Vehicle Detection Trafficimage Sequence Abstract Tracking Vehicle Video-based Intelligent Transportation System Kalman Filter Key Step Current Frame Predict Method Segmentation Method Experimental Result Traffic Analysis |
| Content Type | Text |
| Resource Type | Thesis |
