A Visual-Based Dual-Target Tracking System Using Independent Component Analysis
Detection and tracking of moving targets are major issues in visual surveillance and mobile robot navigation. However, segmentation of moving targets from background in a dynamic scene is still a challenging problem. Independent component analysis is a powerful statistical method for separating unknown signal sources from their linear mixtures into statistically independent components without prior knowledge. Recently, independent component analysis technique has also been successfully used in feature extraction and image segmentation. In this paper, we use the independent component analysis method to extract moving targets from complex background for development of a visual-based dual-target tracking system. The system incorporates two image tracking platforms and each consists of two cameras with two rotational degrees of freedom. First, the independent component analysis method is used for separating moving targets from complex background in a real-time video sequence. Next, after some image processing operations, we can calculate the centroid of detected moving targets in images, meanwhile, the relative position between moving targets and cameras can be estimated. Finally, with converting the relative position into actuating signals for driving motors, the two tracking platforms can track their own moving target and keep it in the middle of the surveillance image. Experimental results show that the proposed system works well for auto-tracking two walking persons in a surveillance zone.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
Document Type: Research Article
Publication date: 2012-05-01
More about this publication?
- The growing interest and activity in the field of sensor technologies requires a forum for rapid dissemination of important results: Sensor Letters is that forum. Sensor Letters offers scientists, engineers and medical experts timely, peer-reviewed research on sensor science and technology of the highest quality. Sensor Letters publish original rapid communications, full papers and timely state-of-the-art reviews encompassing the fundamental and applied research on sensor science and technology in all fields of science, engineering, and medicine. Highest priority will be given to short communications reporting important new scientific and technological findings.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites