Effective Venue Image Retrieval Using Robust Feature Extraction and Model Constrained Matching for Mobile Robot Localization

This paper describes a novel system for mobile robot localization in an indoor environment, using concepts like homography and matching borrowed from the context of stereo and content-based image retrieval techniques (CBIR). To deal with variations with respect to viewpoint and camera positions, a group of points of interest (POI) is extracted to represent the image for robust matching. To cope with illumination changes, we propose to produce a contrast image for each video frame by using the root mean square strategy, thus all the POIs are extracted from the corresponding contrast images to provide perceptually consistent measurement of image content. To achieve effective image matching, modeling of robot behavior for model constrained matching is proposed, where normalized cross correlation is employed for local matching to determine corresponding POI pairs followed by homography based global optimization using RANSAC. Meanwhile, application of specific constraints also helps to exclude irrelevant frames in the training set to further improve the efficiency and robustness. The proposed approach has been successfully applied to the Robot Vision task for the ImageCLEF workshop, and the experimental results have fully demonstrated the high-quality performance of our approaches in terms of both precision and robustness. The system and approach outlined in this paper was ranked the second best in the optional task group in ImageCLEF 2009. In addition to demonstrating the merits of our approach in isolation, we also illustrate the benefits of our proposed approach in comparison with other submissions.