Towards log-polar fixation for mobile robots - analysis of corner tracking on the log-polar camera

Abstract

Fixating on objects is fundamental to active vision tasks, such as reaching, navigation and docking. Most techniques generally have been designed for space-invariant cameras. This research proposes a new method for corner tracking to facilitate point fixation for a mobile robot using a foveated camera. When the target point is in the centre of the image, the fovea and its position can be accurately tracked at high resolution. At the same time, the periphery has a reduced pixel count thus reducing the image processing computation compared to a uniform camera with the same field of view. If the target point suddenly moves into the periphery, it still appears in the lower resolution part of the image and coarser control can bring it back into fovea. Our experiment results demonstrate the stability of the proposed method and the performance of our implementation is adequate for real-time tracking applications.