Image matching techniques for vision-based indoor navigation systems: performance analysis for 3D map based approach

In this paper, we give an overview of image matching techniques for various vision-based navigation systems: stereo vision, structure from motion and map-based approach. Focused on map-based approach, which generally uses feature-based matching for localization, and based on our early developed system, a performance analysis has been carried out and three major problems have been identified: being vulnerable to illumination changes, drastic viewpoint changes and good percentage of mismatches. By introducing ASIFT into the system, the major improvement takes place on the epoch with large viewpoint changes. In order to deal with mismatches that are unable to be removed by RANSAC, we propose to use cross-correlation information to evaluate the quality of homography model and help select the proper one. The conducted experiments have proved that such an approach can reduce the chances of mismatches being included by RANSAC and final positioning accuracy can be improved.