Adaptive spatio‐temporal background subtraction using improved Wronskian change detection scheme in Gaussian mixture model framework. Issue 10 (14th August 2018)

• Record Type: Journal Article
• Authors: Panda, Deepak Kumar; Meher, Sukadev
• Is Part Of: IET image processing. Volume 12:Issue 10(2018)
• Page Start: 1832
• Page End: 1843
• Publication Date: 2018-08-14
• Subjects: spatiotemporal phenomena -- object detection -- video surveillance -- Gaussian processes -- learning (artificial intelligence) -- video signal processing -- image sequences -- image motion analysis; adaptive spatio‐temporal background subtraction -- improved Wronskian change detection scheme -- Gaussian mixture model framework -- fundamental step -- object detection -- video surveillance applications -- background variations -- real‐time constraints -- spatial relationship -- neighbouring pixels -- fixed learning rate -- parameter update -- Wronskian change detection model -- spatial‐domain BS technique -- Wronskian function -- fuzzy adaptive learning rate -- GMM framework -- WM directly -- background pixel -- weighted Wronskian -- dynamic background pixels -- framework yield better silhouette -- moving objects; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0595
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Background subtraction (BS) is a fundamental step for moving object detection in various video surveillance applications. Gaussian mixture model (GMM) is a widely used BS technique which provides a good compromise between robustness to the background variations and real‐time constraints. However, GMM does not support the spatial relationship among neighbouring pixels and it uses a fixed learning rate for every pixel during the parameter update. On the other hand, Wronskian change detection model (WM) is a spatial‐domain BS technique which solves misclassification of pixels but fails in the presence of dynamic background. In this study, a novel spatio‐temporal BS technique is proposed that exploits spatial relation of Wronskian function and employs it with a new fuzzy adaptive learning rate in a GMM framework. Instead of using WM directly, an improved WM is proposed by adaptively finding out the ratio of the current pixel to the background pixel or its reciprocal, and a weighted Wronskian is developed to mitigate the effect of dynamic background pixels. Additionally, a new fuzzy adaptive learning rate is employed in the GMM framework. Experimental results of the proposed framework yield better silhouette of the moving objects as compared with the state‐of‐the‐art techniques.