Unsupervised moving object segmentation using background subtraction and optimal adversarial noise sample search
作者：
Highlights：
• Moving objects segmentation (MOS) is a fundamental task in many computer vision applications such as human activity analysis, visual object tracking, traffic monitoring, and surveillance.
• MOS becomes challenging due to abrupt illumination variations, dynamic backgrounds, camouflage and scenes with bootstrapping.
• To address these challenges we propose a MOS algorithm exploiting multiple adversarial regularizations including conventional as well as least squares losses.
• These loss functions force the generator to synthesize dynamic backgrounds similar to the test sequences which upon subtraction results in moving objects segmentation.
• Experimental evaluations on five benchmark datasets have shown excellent performance of the proposed algorithm compared to the 21 existing state-of-the-art methods.
摘要
•Moving objects segmentation (MOS) is a fundamental task in many computer vision applications such as human activity analysis, visual object tracking, traffic monitoring, and surveillance.•MOS becomes challenging due to abrupt illumination variations, dynamic backgrounds, camouflage and scenes with bootstrapping.•To address these challenges we propose a MOS algorithm exploiting multiple adversarial regularizations including conventional as well as least squares losses.•These loss functions force the generator to synthesize dynamic backgrounds similar to the test sequences which upon subtraction results in moving objects segmentation.•Experimental evaluations on five benchmark datasets have shown excellent performance of the proposed algorithm compared to the 21 existing state-of-the-art methods.
论文关键词：Moving objects segmentation,Generative adversarial network,Background subtraction
论文评审过程：Received 26 June 2020, Revised 17 April 2022, Accepted 18 April 2022, Available online 18 April 2022, Version of Record 27 April 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108719
