Human Motion Detection Based on Dual-Graph and Weighted Nuclear Norm Regularizations
This work addresses motion detection for surveillance and robotics, presenting an incremental improvement over existing regularization techniques.
The paper tackled the problem of separating moving objects from static background in videos by proposing a dual-graph and weighted nuclear norm regularization model, demonstrating effectiveness and robustness on realistic human motion datasets with potential for robotic applications.
Motion detection has been widely used in many applications, such as surveillance and robotics. Due to the presence of the static background, a motion video can be decomposed into a low-rank background and a sparse foreground. Many regularization techniques that preserve low-rankness of matrices can therefore be imposed on the background. In the meanwhile, geometry-based regularizations, such as graph regularizations, can be imposed on the foreground. Recently, weighted regularization techniques including the weighted nuclear norm regularization have been proposed in the image processing community to promote adaptive sparsity while achieving efficient performance. In this paper, we propose a robust dual graph regularized moving object detection model based on a novel weighted nuclear norm regularization and spatiotemporal graph Laplacians. Numerical experiments on realistic human motion data sets have demonstrated the effectiveness and robustness of this approach in separating moving objects from background, and the enormous potential in robotic applications.