Abstract | ||
---|---|---|
Background cues mainly play a supplementary or accompanying role in most previous approaches for object tracking. If object tracking is treated as a binary target/background classification problem, then the similarity with the target and the difference from the background can be considered equally informative. This leads to an interesting question: is it possible to perform object tracking using background cues only? To answer this question, we propose an object tracking approach that utilizes background cues only. The extensive experimental results positively validate the possibility of performing object tracking using background cues only. The results revealed in this paper also provide a new reference in designing future object tracking methods. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TCSVT.2014.2317888 | IEEE Trans. Circuits Syst. Video Techn. |
Keywords | Field | DocType |
binary target classification problem,target tracking,background cues,image classification,background classification problem,object tracking,object detection | Deep-sky object,Computer vision,Pattern recognition,Computer science,Video tracking,Artificial intelligence | Journal |
Volume | Issue | ISSN |
24 | 11 | 1051-8215 |
Citations | PageRank | References |
4 | 0.37 | 22 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Annan Li | 1 | 4 | 3.08 |
Shuicheng Yan | 2 | 9701 | 359.54 |