论文信息 - An Improved LBP Feature Based Moving Object Detection

An Improved LBP Feature Based Moving Object Detection

Moving object detection (MOD) is strongly restricted by the change of dynamic background. In this paper, a novel MOD algorithm based on improved Local Binary Patterns (LBP) is proposed. Firstly, the LBP is improved to overcome the shortcomings of LBP operator. Then the improved LBP is used in MOD to extract moving object in natural scenes. The experimental results show that the proposed MOD method can extract moving object more accurately.

[1] Shengcai Liao,et al. Moving Object Detection Revisited: Speed and Robustness , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[2] Van-Dung Hoang,et al. Moving Object Localization Using Optical Flow for Pedestrian Detection from a Moving Vehicle , 2014, TheScientificWorldJournal.

[3] Qi Zhang,et al. Moving Object Detection Based on Temporal Information , 2014, IEEE Signal Processing Letters.

[4] Kebin Jia,et al. A Moving Object Detection Algorithm Based on a Combination Optical Flow and Edge Detection , 2016, ECC.

[5] Marc Van Droogenbroeck,et al. ViBe: A Universal Background Subtraction Algorithm for Video Sequences , 2011, IEEE Transactions on Image Processing.

[6] J. H. Duan,et al. Moving object detection based on confidence factor and CSLBP features , 2016 .

[7] Larry S. Davis,et al. Non-parametric Model for Background Subtraction , 2000, ECCV.

[8] W. Eric L. Grimson,et al. Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[9] Sandeep Singh Sengar,et al. Moving object area detection using normalized self adaptive optical flow , 2016 .

[10] Ying Ding,et al. Robust moving object detection under complex background , 2010 .