CONF Yao_CVPR-VS2007_2007/IDIAP Multi-Layer Background Subtraction Based on Color and Texture Yao, Jian Odobez, Jean-Marc EXTERNAL https://publications.idiap.ch/attachments/papers/2007/Yao_CVPR-VS2007_2007.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Yao_Idiap-RR-67-2007 Related documents CVPR 2007 Workshop on Visual Surveillance (VS2007) 2007 June 2007 In this paper, we propose a robust multi-layer background subtraction technique which takes advantages of local texture features represented by local binary patterns (LBP) and photometric invariant color measurements in RGB color space. LBP can work robustly with respective to light variation on rich texture regions but not so efficiently on uniform regions. In the latter case, color information should overcome LBP’s limitation. Due to the illumination invariance of both the LBP feature and the selected color feature, the method is able to handle local illumination changes such as cast shadows from moving objects. Due to the use of a simple layer-based strategy, the approach can model moving background pixels with quasiperiodic flickering as well as background scenes which may vary over time due to the addition and removal of long-time stationary objects. Finally, the use of a cross-bilateral filter allows to implicitly smooth detection results over regions of similar intensity and preserve object boundaries. Numerical and qualitative experimental results on both simulated and real data demonstrate the robustness of the proposed method. REPORT Yao_Idiap-RR-67-2007/IDIAP Multi-Layer Background Subtraction Based on Color and Texture Yao, Jian Odobez, Jean-Marc EXTERNAL https://publications.idiap.ch/attachments/reports/2007/Yao_Idiap-RR-67-2007.pdf PUBLIC Idiap-RR-67-2007 2007 Idiap May 2007 In this paper, we propose a robust multi-layer background subtraction technique which takes advantages of local texture features represented by local binary patterns (LBP) and photometric invariant color measurements in RGB color space. LBP can work robustly with respective to light variation on rich texture regions but not so efficiently on uniform regions. In the latter case, color information should overcome LBP’s limitation. Due to the illumination invariance of both the LBP feature and the selected color feature, the method is able to handle local illumination changes such as cast shadows from moving objects. Due to the use of a simple layer- based strategy, the approach can model moving background pixels with quasi-periodic flickering as well as background scenes which may vary over time due to the addition and removal of long-time stationary objects. Finally, the use of a cross-bilateral filter allows to implicitly smooth detection results over regions of similar intensity and preserve object boundaries. Numerical and qualitative experimental results on both simulated and real data demonstrate the robustness of the proposed method.