Region Graph Based Method for Multi-Object Detection and Tracking using Depth Cameras

摘要

In this paper, we propose a multi-object detection and tracking method usingdepth cameras. Depth maps are very noisy and obscure in object detection. Wefirst propose a region-based method to suppress high magnitude noise whichcannot be filtered using spatial filters. Second, the proposed method detectRegion of Interests by temporal learning which are then tracked using weightedgraph-based approach. We demonstrate the performance of the proposed method onstandard depth camera datasets with and without object occlusions. Experimentalresults show that the proposed method is able to suppress high magnitude noisein depth maps and detect/track the objects (with and without occlusion).