Appearance models for occlusion handling
| Autor: | Andrew W. Senior, Arun Hampapur, Lisa M. Brown, Ruud M. Bolle, Sharath Pankanti, Yingli Tian |
|---|---|
| Rok vydání: | 2006 |
| Předmět: |
genetic structures
business.industry Computer science Track (disk drive) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Tracking system Video sequence Tracking (particle physics) GeneralLiterature_MISCELLANEOUS Visual tracking system Video tracking Signal Processing Occlusion Computer vision Computer Vision and Pattern Recognition Artificial intelligence business ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Image and Vision Computing. 24:1233-1243 |
| ISSN: | 0262-8856 |
| Popis: | Objects in the world exhibit complex interactions. When captured in a video sequence, some interactions manifest themselves as occlusions. A visual tracking system must be able to track objects, which are partially or even fully occluded. In this paper we present a method of tracking objects through occlusions using appearance models. These models are used to localize objects during partial occlusions, detect complete occlusions and resolve depth ordering of objects during occlusions. This paper presents a tracking system which successfully deals with complex real world interactions, as demonstrated on the PETS 2001 dataset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect