A survey of appearance models in visual object tracking
Chinese Academy of Sciences · The University of Adelaide · +1 more institution
Abstract
Visual object tracking is a significant computer vision task which can be applied to many domains, such as visual surveillance, human computer interaction, and video compression. Despite extensive research on this topic, it still suffers from difficulties in handling complex object appearance changes caused by factors such as illumination variation, partial occlusion, shape deformation, and camera motion. Therefore, effective modeling of the 2D appearance of tracked objects is a key issue for the success of a visual tracker. In the literature, researchers have proposed a variety of 2D appearance models. To help readers swiftly learn the recent advances in 2D appearance models for visual object tracking, we…
Citation impact
- FWCI
- 69.59
- Percentile
- 100%
- References
- 217
Authors
6Topics & keywords
- Computer science
- Artificial intelligence
- Object (grammar)
- Computer vision
- Tracking (education)
- Eye tracking
- Human–computer interaction
- Reduced inequalities
Funding
- NNNational Natural Science Foundation of ChinaAward: 60935002
- MOMinistry of Science and Technology of the People's Republic of ChinaAwards: 2012CB316400, 2012AA012504
- NSNatural Science Foundation of Guangdong ProvinceAward: S2012020011081
- NSNatural Science Foundation of Beijing MunicipalityAward: 4121003
- ARAustralian Research Council
- DODivision of Computing and Communication FoundationsAward: IIS-0812114, CCF-1017828
- DODivision of Information and Intelligent SystemsAward: IIS-0812114, CCF-1017828