Optical Navigation by the Method of Differences

Abstract

The method of differences refers to a technique for image matching that uses the intensity gradient of the image to iteratively improve the match between the two images. Used in an iterative scheme combined with image smoothing, the method exhibits good accuracy and a wide convergence range. In this paper we show how the technique ran be used to directly solve for the parameters relating two cameras viewing the same scene. The resulting algorithm can be used for optical navigation, which has applications in robot arm guidance and autonomous roving vehicle navigation. Because of the regular structure of the algorithm, the prospects of carrying it out with specialpurpose hardware for real-time control of a robot seem good. We present experimental results demonstrating the accuracy and range of convergence that can be expected from the algorithm.