Stereo-motion estimation for visual object tracking
| Autor: | Xi Chen, Caihui Li, Lu Qiyong, Yan Sun |
|---|---|
| Rok vydání: | 2009 |
| Předmět: |
business.industry
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Object (computer science) Object detection Visualization Reduction (complexity) Stereopsis Video tracking Motion estimation Structure from motion Computer vision Artificial intelligence business ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | 2009 IEEE Youth Conference on Information, Computing and Telecommunication. |
| Popis: | Visual object tracking is a problem that has been studied by the computer community for decades. Computational stereo refers to the problem of determining 3-dimentional structure of a scene from two or more images taken from distinct viewpoints. An approach to detect stereo-moving objects with bio-cameras is presented in this thesis. Stereo and motion are detected simultaneously under a modified formulation of energy function. We extend the application from static stereo match and motion mono-camera detection to handle the whole problem together at a time, which results in a reduction of computation time and ability to handle more difficult situation. Experiments on several video-images, that showing convictive object detecting performances demonstrate its strong adaptability to stereo-motion application. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|