✦ LIBER ✦
Real-time object tracking for soccer-robots without color information
✍ Scribed by André Treptow; Andreas Zell
- Publisher
- Elsevier Science
- Year
- 2004
- Tongue
- English
- Weight
- 351 KB
- Volume
- 48
- Category
- Article
- ISSN
- 0921-8890
No coin nor oath required. For personal study only.
✦ Synopsis
Objects in the RoboCup scenario (soccer playing robots) are identified by their unique color. These visual cues will be removed in the near future so that new vision algorithms are needed to cope with this. In this paper we present a method for detecting and tracking the ball in a RoboCup scenario without the need for color information. We use Haar-like features trained by an adaboost algorithm to get a colorless representation of the ball. Tracking is performed by a particle filter. It is shown that our algorithm is able to track the ball in real-time with 25 fps even in a cluttered environment.