Abstract | ||
---|---|---|
Moving object detection plays a key role in video surveillance. A number of object detection methods have been proposed in the spatial domain. In this paper, we propose a compressed sensing (CS)-based algorithm for the detection of moving object in video sequences. First, we propose an object detection model to simultaneously reconstruct the foreground, background, and video sequence using the sampled measurement. Then, we use the reconstructed video sequence to estimate a confidence map to improve the foreground reconstruction result. Experimental results show that the proposed moving object detection algorithm outperforms the state-of-the-art approaches and is robust to the movement turbulence and sudden illumination changes. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1186/s13634-015-0194-1 | EURASIP Journal on Advances in Signal Processing |
Keywords | Field | DocType |
Compressed sensing, Low-rank optimization, Moving object detection, Moving turbulence mitigation | Computer vision,Object detection,Viola–Jones object detection framework,Video reconstruction,Object-class detection,Computer science,Video tracking,Artificial intelligence,Compressed sensing | Journal |
Volume | Issue | ISSN |
2015 | 1 | 1687-6180 |
Citations | PageRank | References |
2 | 0.38 | 30 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bin Kang | 1 | 22 | 6.57 |
Wei-Ping Zhu | 2 | 555 | 62.46 |
Jun Yan | 3 | 24 | 5.17 |