Improving Multi-view Object Recognition by Detecting Changes in Point Clouds

object recognition, change detection, reconstruction, hypotheses clustering, multi-view, point cloud, RGB-D data

This paper proposes the use of change detection in a multi-view object recognition system in order to improve its flexibility and effectiveness in dynamic environments. Multi-view recognition approaches are essential to overcome problems related to clutter, occlusion or camera noise, but the existing systems usually assume a static environment. The presence of dynamic objects raises another issue - the inconsistencies introduced to the internal scene model. We show that by incorporating the change detection and correction of the inherent scene inconsistencies, we can reduce false positive detections by 70% in average for moving objects when tested on the publicly available TUW dataset. To reduce time required for verifying a large set of accumulated object pose hypotheses, we further integrate a clustering approach into the original multi-view object recognition system and show that this reduces computation time by approximately 16%.