Moving Object Detection on RGB-D Videos Using Graph Regularized Spatiotemporal RPCA

Moving object detection is the fundamental step for various computer vision tasks. Many existing methods are still limited in accurately detecting the moving objects because of complex background scenes such as illumination condition, color saturation, and shadows etc. RPCA models have shown potential for moving object detection, where input data matrix is decomposed into a low-rank matrix representing the background image and a sparse component identifying moving objects. However, RPCA methods are not ideal for real-time processing because of the batch processing issues. These methods also show a performance degradation without encoding spatiotemporal and depth information. To address these problems, we investigate the performance of online Spatiotemporal RPCA (SRPCA) algorithm [1] for moving object detection using RGB-D videos. SRPCA is a graph regularized algorithm which preserves the low-rank spatiotemporal information in the form of dual spectral graphs. This graph regularized information is then encoded into the objective function which is solved using online optimization. Experiments show competitive results as compared to four state-of-the-art sub-space learning methods.