Recently, robust principal component analysis (RPCA) has been widely used in the detection of moving objects. However, this method fails to effectively utilize the low-rank prior information of the background and the spatiotemporal continuity prior of the moving object, and the target extraction effect is often poor when dealing with large-scale complex scenes. To solve the above problems, a new non-convex rank approximate RPCA model based on segmentation constraint is proposed. Firstly, the model adopts the low-rank sparse decomposition method to divide the original video sequence into three parts: low-rank background, moving foreground and sparse noise. Then, a new non-convex function is proposed to better constrain the low-rank characteristic of the video background. Finally, based on the spatiotemporal continuity of the foreground object, the video is segmented by the super-pixel segmentation technology, so as to realize the constraint of the motion foreground region. The augmented Lagrange multiplier method is used to solve the model. Experimental results show that the proposed model can effectively improve the accuracy of moving object detection, and has better visual effect of foreground object detection than existed methods. INDEX TERMS Moving object detection, robust principal component analysis, non-convex rank approximation, video segmentation.
Traditional robust principal component analysis (RPCA) is very prone to voids in the process of background/foreground separation of complex scene videos and easy to misjudge the dynamic background as a moving target, which makes the separation effect unideal. In order to address this problem, this paper introduces the super-pixel segmentation technique into the RPCA model. First, the Linear Spectral Clustering algorithm (LSC) is used to mark the super-pixel segmentation of the video sequence and a superpixel grouping matrix is obtained. Then a new video background/foreground separation model is proposed based on the non-convex rank approximation RPCA and super-pixel motion detection (SPMD) technique. The Otsu algorithm is used to obtain the motion mask matrix and the augmented lagrange alternating direction method is used to solve the improved RPCA model. The results of numerical experiment show that the method proposed in this paper has a higher accuracy in the detection of moving objects in dynamic background. INDEX TERMS Video background/foreground separation, RPCA, superpixel segmentation, linear spectral clustering algorithm, Otsu algorithm, motion mask.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.