基于场景语义先验和全局外观一致性的运动目标检测

doi:10.3969/j.issn.1006-2475.2016.11.010

计算机与现代化

基于场景语义先验和全局外观一致性的运动目标检测

安徽大学计算机科学与技术学院,安徽合肥230601

收稿日期:2016-04-08 出版日期:2016-11-15 发布日期:2016-11-23
作者简介:焦玉清（1992-），男，安徽宿州人，安徽大学计算机科学与技术学院硕士研究生，研究方向：图形图像处理；王文中（1978-），男，讲师，博士，研究方向：计算机视觉，计算机图形学与虚拟现实；罗文斌（1963-），男，教授，博士生导师，研究方向：数字图像处理与应用。

Moving Object Detection Based on Scene Semantic Prior and Global Appearance Consistency

School of Computer Science and Technology, Anhui University, Hefei 230601, China

Received:2016-04-08 Online:2016-11-15 Published:2016-11-23

摘要/Abstract

摘要： 在摄像机固定的视频监控中，动态背景下的运动目标检测是一个非常有挑战的基础问题。本文提出一种鲁棒的运动目标检测方法。首先，为有效利用场景区域的先验信息，把事先定义的语义区域信息融合到ViBe算法中，消除一些特定语义区域中的动态背景干扰。其次，根据改进的ViBe算法的结果估计背景和前景的全局外观GMM模型，利用该模型对每个像素进行进一步的分类，从而通过全局外观模型去除一些错误的检测结果。最后，使用超像素对结果进行后期处理，得到更加精确的检测结果。实验结果表明，本文方法在检测有强烈动态背景干扰的监控视频时，远远超过了其他的运动目标检测方法。


关键词: 动态背景, 场景语义先验, ViBe算法, 外观一致性, GMM模型

Abstract: Moving object detection in dynamic background is a very challenging fundamental problem in video surveillance. This paper presents a robust moving object detection method. First, we develop an effective ViBe algorithm against dynamic background by incorporating the scene prior information that is predefined in initial frame. Then, the global GMM models of foreground objects and background are estimated by foreground and background pixels detected by the improved ViBe algorithm. These GMM models are employed to classify every pixel effectively and remove some of the false results. For further alleviating the effects of noises, the superpixel-based refinement is adopted to obtain the final results. The experimental results on the collected video sequence with strongly dynamic background suggest that the method significantly outperforms other moving object detection methods.


Key words: dynamic background, scene semantic prior, ViBe algorithm, appearance consistency, GMM model

中图分类号:

TP391.41

焦玉清,王文中,罗斌. 基于场景语义先验和全局外观一致性的运动目标检测[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2016.11.010.

JIAO Yu-qing, WANG Wen-zhong, LUO Bin. Moving Object Detection Based on Scene Semantic Prior and Global Appearance Consistency[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2016.11.010.

参考文献

［1］ Bai Yan-cheng, Tang Ming. Robust tracking via weakly supervised ranking svm［C］// 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012:1854-1861.
［2］ Valera M, Velastin S A. Intelligent distributed surveillance systems: A review［J］. IEE Proceedings-Vision, Image and Signal Processing, 2005,152(2):192-204.
［3］ Horn B K P, Schunck B G. Determining optical flow［J］. Artificial Intelligence, 1981,17(1-3):185-203.
［4］ Haritaoglu I, Harwood D, Davis L S. W4: Real-time surveillance of people and their activities［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830.
［5］ Kato J, Watanabe T, Joga S, et al. An HMM/MRF-based stochastic framework for robust vehicle tracking［J］. IEEE Transactions on Intelligent Transportation Systems, 2004,5(3):142-154.
［6］ Monnet A, Mittal A, Paragios N, et al. Background modeling and subtraction of dynamic scenes［C］// Proceedings of the 9th IEEE International Conference on Computer Vision. 2003:1305-1312.
［7］ Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking［C］// IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999. 1999,2:2246-2252.
［8］ Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):747-757.
［9］赵光明,韩光,李晓飞,等. 基于融合帧间差的改进Vibe方法［J］. 计算机技术与发展, 2015,25(3):76-80.
［10］严红亮,王福龙,刘志煌,等. 基于ViBe算法的改进背景减去法［J］. 计算机系统应用, 2014,23(6):130-134.
［11］Barnich O, Van Droogenbroeck M. ViBe: A universal background subtraction algorithm for video sequences［J］. IEEE Transactions on Image Processing, 2011,20(6):1709-1724.
［12］Ren Xiaofeng, Malik J. Learning a classification model for segmentation［C］// Proceedings of the 9th IEEE International Conference on Computer Vision. 2003:10-17.
［13］Redner R A, Walker H F. Mixture densities, maximum likelihood and the EM algorithm［J］. SIAM Review, 1984,26(2):195-239.
［14］Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixel methods［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(11):2274-2282.
［15］Zhou Xiaowei, Yang Can, Yu Weichuan. Moving object detection by detecting contiguous outliers in the low-rank representation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(3):597-610.
［16］Elgammal A, Harwood D, Davis L. Non-parametric model for background subtraction［J］. Lecture Notes in Computer Science, 2000,1843:751-767.
［17］St-Charles P L, Bilodeau G A, Bergevin R. SuBSENSE: A universal change detection method with local adaptive sensitivity［J］. IEEE Transactions on Image Processing, 2015,24(1):359-373.

[1]	章伟明,周武能. 基于鬼影判断抑制和局部运动补偿的改进ViBe算法[J]. 计算机与现代化, 2018, 0(01): 51-55.
[2]	吴剑舞，翁玲瑜，童怀. 一种基于改进ViBe的运动目标检测方法[J]. 计算机与现代化, 2015, 0(7): 50-.
[3]	董云飞1，谢红松1，罗斌1,2，汤进1,2. 基于达芬奇平台的运动目标跟踪算法[J]. 计算机与现代化, 2015, 0(10): 45-49.
[4]	邓孝逸;曾庆化;徐贵力;朱华. 单目视觉室内无人飞行器运动目标测距技术研究[J]. 计算机与现代化, 2013, 1(3): 152-155,.

基于场景语义先验和全局外观一致性的运动目标检测

Moving Object Detection Based on Scene Semantic Prior and Global Appearance Consistency

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价