Robust tracking for camera control on an irregular terrain vehicle

Tracking a target robustly by vision is very difficult for a mobile robot running on irregular terrain in a natural environment, because the image deformation caused by rolling and pitching of the camera, as well as relative movement between the target and the camera, affect the tracking ability. One approach to cope with such problems is matching the target image with many affine transformed candidate images while tracking. But when the number of candidate images gets larger, such approach becomes unfeasible because of computational cost. In this paper, we propose Robustness Analysis for Tracking (RAT) to improve the tracking ability. RAT is an analysis based on features of the object image, where three parameters - 'Detectability', 'Robustness for Depth (RBD)' and 'Robustness for Rotation (RBR)' - are defined. Much more robust templates can be found by analyzing the object image using RAT before the tracking task is performed. Experimental results verify the effectiveness of this method.