Improving matching performance of the keypoints in images of 3D scenes by using depth information

Keypoint detection is a basic step in many computer vision algorithms aimed at recognition of objects, automatic navigation, medicine and other application fields. Successful implementation of higher level image analysis tasks, however, is conditioned by reliable detection of characteristic image local regions termed keypoints. A large number of keypoint detection algorithms has been proposed and verified. The main part of this work is devoted to description of an original keypoint detection algorithm that incorporates depth information computed from stereovision cameras or other depth sensing devices. It was shown that filtering out keypoints that are context dependent, e.g. located on object boundaries can improve the matching performance of the keypoints which is the basis for object recognition tasks. This improvement was shown quantitatively by comparing the proposed algorithm to the widely accepted SIFT keypoint detector algorithm. Our study is motivated by a development of a system aimed at aiding the visually impaired in space perception and object identification.