Localized Harris-FAST interest point detector

摘要

Simultaneous Localization and Mapping (SLAM) requires both rotation and scale invariant features. Few algorithms have been developed with rotation and scale invariant features with few limitations. Thus, an algorithm has been proposed to address rotation and scaling invariance. Proposed algorithm Harris-FAST interest point detector is a fusion of Harris and FAST interest point detectors. The detector is optimized by localizing the interest point detector to preferred area, from which the execution time of the algorithm reduced to the order of one fourth. The results of the proposed algorithm are compared with available feature detectors for its performance. Localized-Harris-FAST algorithm has been developed with an interest point detector for use in real time applications like SLAM on a mobile robot, which have limited computational resources.