Abstract | ||
---|---|---|
In recent years, real-time direct detection of events by surveillance systems has attracted a great deal of attention. In this paper, we propose a new video-based surveillance system that can perform real-time event detection. In the background modeling phase, we adopt a mixture of Gaussian approach to determine the background. Meanwhile, we use color blob-based tracking to track foreground objects. Due to the self-occlusion problem,, the tracking module is designed as a multi-blob tracking process to obtain similar multiple trajectories. We devise an algorithm to merge these trajectories into a representative one. After applying the Douglas-Peucker algorithm to approximate a trajectory, we can compare two arbitrary trajectories. The above mechanism enables us to conduct real-time event detection if a number of wanted trajectories are pre-stored in a video surveillance system. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ISCAS.2006.1692634 | 2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS |
Keywords | Field | DocType |
mixture of gaussians,application software,information science,real time,douglas peucker algorithm,trajectory,tracking,real time systems,databases,algorithm design and analysis | Video recording,Computer vision,Ramer–Douglas–Peucker algorithm,Computer science,Video tracking,Gaussian,Artificial intelligence,Merge (version control),Trajectory | Conference |
ISSN | Citations | PageRank |
0271-4302 | 32 | 1.45 |
References | Authors | |
5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
h y m liao | 1 | 2353 | 198.72 |
Duan-Yu Chen | 2 | 296 | 28.79 |
Chih-Wen Su | 3 | 170 | 13.94 |
Hsiao-Rong Tyan | 4 | 248 | 25.53 |