Abstract | ||
---|---|---|
In this paper, a fuzzy feature-based method for online people tracking using an IP PTZ camera is proposed. It involves five steps: 1) target modeling, 2) track initialization, 3) blob extraction, 4) target localization using a fuzzy classifier, and 5) IP PTZ camera control. It selects the most similar target among candidate blobs found in the image using skin and motion detection. Results show that the proposed method has a good target detection precision ( 89%), low track fragmentation, and the target is almost always localized within 1/6th of the image diagonal from the image center. In addition, results suggest that our tracking method can cope with occlusion and large motion of the target. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-02611-9_65 | ICIAR |
Keywords | Field | DocType |
fuzzy tracking, feature-based, people tracking, low frame rate tracking, IP PTZ camera | Diagonal,Computer vision,Motion detection,Pattern recognition,Computer science,Fuzzy logic,Tracking system,Video tracking,Artificial intelligence,Initialization,Fuzzy classifier,Camera control | Conference |
Volume | ISSN | Citations |
5627 | 0302-9743 | 2 |
PageRank | References | Authors |
0.36 | 11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Parisa Darvish Zadeh Varcheie | 1 | 71 | 6.18 |
Guillaume-Alexandre Bilodeau | 2 | 667 | 51.02 |