Assessing the performance of corner detectors for point feature tracking applications

In this paper we assess the performance of corner feature detecting algorithms for feature tracking applications. We analyze four different types of corner extractors, which have been widely used for a variety of applications. They are the Kitchen-Rosenfeld, the Harris, the Kanade-Lucas-Tomasi, and the Smith corner detectors. We use corner stability and corner localization properties as measures to evaluate the quality of the features extracted by the 4 detectors. For effective assessment of the corner detectors, we employed image sequences with no motion (simply static image sequences), so that the appearance and disappearance of corners in each frame is purely due to image plane noise and illumination conditions. Such a setup is ideal to analyze the stability and localization properties of the corners. The corners extracted from the initial frame are then matched through the sequence using a corner matching strategy. We employed 2 different types of matchers, namely the GVM (Gradient Vector Matcher) and the Product Moment Coefficient Matcher (PMCM). Each of the corner detectors was tested with each of the matching algorithms to evaluate their performance in tracking (matching) the features. The experiments were carried out on a variety of image sequences.