首页 > 论文 > 光学学报 > 38卷 > 8期(pp:815007--1)

视频监控中的人群异常行为检测与定位

Anomaly Detection and Location in Crowded Surveillance Videos

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

人群中的异常行为是一大潜在威胁,自动检测监控中的异常行为成为近年的研究热点之一。然而,由于异常的未知性与复杂性,已有的检测方法仍然存在检测率低、定位精度差的问题。为此,提出了对视频监控中的人群异常行为自动检测与定位的方法。结合灰度值与光流场的分布提取运动区域;对运动区域分割得到有效的运动块,从中提取表示外观和动态的两种特征,即局部H梯度方向直方图G和局部H光流方向直方图F特征;使用k-means方法对运动块进行聚类,对每类样本使用一类分类器进行建模。最后,加入运动连续性约束,以抑制干扰噪声。在两个复杂的异常行为数据集上的实验结果表明,本文方法明显优于已有的检测方法,且可以满足正确率高、抗干扰能力强等实际工程需求。

Abstract

The anomaly in the crowd is a great potential threat, and the automatic detection of abnormal behavior for surveillance has become a hot topic in recent years. However, because the anomaly is unknown and complex, the previous detection methods still suffer from a low detection rate and poor location accuracy. To this end, a method is proposed for anomaly detection and location in the crowded surveillance videos. First, the motion regions are extracted according to the distributions of the gray-scale value and the optical flow field. Second, the effective motion blocks are obtained by segmenting the motion regions. Two features, namely the local H histogram of gradient G and the local H histograms of flow F, are extracted from the motion blocks, representing the appearance and dynamics. Third, the motion blocks are clustered with the k-means method, and each cluster is modeled using a one-class classifiers. Finally, the motion continuity constraint is added to suppress the noisy noises. Experimental results on two complex abnormal behavior datasets show that the proposed method is obviously better than previous detection methods. It could meet the practical engineering needs such as high accuracy and strong anti-interference ability.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/aos201838.0815007

所属栏目:“机器视觉检测与应用”专题

基金项目:中国科学院国防科技创新基金(Y6A4160401)

收稿日期:2018-01-22

修改稿日期:2018-02-06

网络出版日期:2018-02-26

作者单位    点击查看

周培培:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院大学, 北京 100049中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016辽宁省图像理解与视觉计算重点实验室, 辽宁 沈阳 110016
丁庆海:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016航天恒星科技有限公司, 北京 100086
罗海波:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016辽宁省图像理解与视觉计算重点实验室, 辽宁 沈阳 110016
侯幸林:中国科学院沈阳自动化研究所, 辽宁 沈阳 110016中国科学院大学, 北京 100049中国科学院光电信息处理重点实验室, 辽宁 沈阳 110016辽宁省图像理解与视觉计算重点实验室, 辽宁 沈阳 110016

联系人作者:周培培(zhoupeipei@sia.cn); 丁庆海(13693689880@139.com);

【1】Cong Y, Yuan J, Liu J. Sparse reconstruction cost for abnormal event detection[C]. 2011 IEEE Conference on Computer Vision and Pattern Recognition, 2011: 3449-3456.

【2】Sodemann A A, Ross M P, Borghetti B J. A review of anomaly detection in automated surveillance[J]. IEEE Transactions on Systems Man and Cybernetics Part C, 2012, 42(6):1257-1272.

【3】Hmlinen W, Nyknen M. Efficient discovery of statistically significant association rules[C]. 8th IEEE International Conference on Data Mining, 2008:203-212.

【4】Kuettel D, Breitenstein M D, Gool L V, et al. What′s going on? Discovering spatio-temporal dependencies in dynamic scenes[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2010:1951-1958.

【5】Amraee S, Vafaei A, Jamshidi K, et al. Anomaly detection and localization in crowded scenes using connected component analysis[J]. Multimedia Tool sand Applications, 2018, 77(12): 14767-14782.

【6】Yuan Y, Feng Y, Lu X. Statisticalhy pothesis detector for abnormal event detection in crowded scenes[J]. IEEE Transactions on Cybernetics, 2017, 47(11): 3597-3608.

【7】Kwon J, Lee K M. A unified framework for event summarization and rare event detection from multiple views[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37(9): 1737-1750.

【8】Lee K M. A unified framework for event summarization and rare event detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2012:1266-1273.

【9】Wang X, Hou Z Q, Yu W S, et al. Target scale adaptive robust tracking based on fusion of multilayer convolutional features[J]. Acta Optica Sinica, 2017, 37(11): 1115005.
王鑫, 侯志强, 余旺盛, 等. 基于多层卷积特征融合的目标尺度自适应稳健跟踪[J]. 光学学报, 2017, 37(11): 1115005.

引用该论文

Zhou Peipei,Ding Qinghai,Luo Haibo,Hou Xinglin. Anomaly Detection and Location in Crowded Surveillance Videos[J]. Acta Optica Sinica, 2018, 38(8): 0815007

周培培,丁庆海,罗海波,侯幸林. 视频监控中的人群异常行为检测与定位[J]. 光学学报, 2018, 38(8): 0815007

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF