MACHINE PERCEPTION AND ROBOTICS GROUP

機械知覚&ロボティクスグループ
中部大学

Stereo vision systems have been proposed and used in various fields. They require cameras to synchronize with each other for tracking objects accurately measuring depth. In this paper, we present a vision system which uses two normal, unsynchronized cameras for calculating 3D positions of objects. The unsynchronization in shutter timing of ameras has a merit that it processes faster than a synchronized camera system. 3D positions of an object are measured as a crossing point of lines in 3D space through the detected position on the last frame and estimated 3D position calculated by past frames. This makes it possible for our system to consist of two unsynchronized cameras and to calculate the 3D position of the moving object about twice faster than a synchronized method with similar precisions. This can be useful for controlling a robot as a fast visual feedback system.