Real-time epipolar geometry estimation of binocular stereo heads

Stereo is an important cue for visually guided robots. While moving around in the world, such a robot can use dynamic fixation to overcome limitations in image resolution and field of view. In this paper, a binocular stereo system capable of dynamic fixation is presented. The external calibration is performed continuously taking temporal consistency into consideration, greatly simplifying the process. The essential matrix, which is estimated in real-time, is used to describe the epipolar geometry. It will be shown, how outliers can be identified and excluded from the calculations. An iterative approach based on a differential model of the optical flow, commonly used in structure from motion, is also presented and tested towards the essential matrix. The iterative method will be shown to be superior in terms of both computational speed and robustness, when the vergence angles are less than about 15. For larger angles, the differential model is insufficient and the essential matrix is preferably used instead.

1 Background

Stereo vision can be used for several tasks in the area of robotics. For applications, such as visually guided manipulation, stereo is a valuable cue in order to recognize shapes and pose. Stereopsis has also been used for visual navigation and obstacle detection [11], [18]. Such systems typically consist of two or more small cameras located in parallel with relatively short baselines, since they are expected to work for various distances. Objects located close to the observer might otherwise only be seen by one of cameras, greatly complicating depth estimation and making the system useless for behaviors such as obstacle avoidance. However, for manipulation, accuracy is crucial and a wider baseline is desired.