群体突发异常事件检测与事件源定位算法#br#

中国民航大学学报 ›› 2019, Vol. 37 ›› Issue (3): 49-53.

群体突发异常事件检测与事件源定位算法#br#

李海丰^1，2，姜子政¹，范龙飞¹，陈新伟²

（1.中国民航大学计算机科学与技术学院，天津300300；2.闽江学院福建省信息处理与智能控制重点实验室，福州350121）

出版日期:2019-06-27 发布日期:2020-04-01
作者简介:李海丰（1984—），男，内蒙古通辽人，讲师，博士，研究方向为计算机视觉、智能机器人.
基金资助:
国家自然科学基金项目（61305107）；福建省信息处理与智能控制重点实验室开放课题（MJUKF201732）；中央高校基本科研业务费专项（3122016B006）；中国民航大学科研启动基金项目（2012QD23X）

Abnormal crowd event detection and event source localization algorithm#br#

LI Haifeng^1,2, JIANG Zizheng¹, FAN Longfei¹, CHEN Xinwei²#br#

（1. College of Computer Science and Technology, CAUC, Tianjin 300300, China; 2. Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, Minjiang University, Fuzhou 350121, China）

Online:2019-06-27 Published:2020-04-01

摘要/Abstract

摘要： 提出一种群体突发异常事件检测与事件源定位算法以提高检测的准确性。算法分为群体异常行为检测和事件源定位两个阶段，在异常行为检测阶段，提出一种空间、时间联合的异常行为检测算法：在空间角度，提取平均动能分布直方图来描述人群的运动特征，并使用支持向量机分类器对不同状态的人群运动特征进行分类；在时间角度，构建隐马尔可夫模型，对场景中连续的人群行为状态进行异常检测。在事件源定位阶段，在随机抽样一致性算法框架下通过计算异常行为人群的反向延长线交点，实现了事件源位置的定位，并可同时标记多个事件源位置。在UMN 公共数据集上进行实验，并与传统光流法、SIFT 点检测法与社会力法进行对比，结果表明，该算法能够有效检测出群体异常行为，且AUC = 0.967，比上述3 种方法的AUC 分别提高0.127、0.074、0.007，并成功标记出事件源的合理位置。

关键词: 群体异常事件检测, 事件源定位, 空间、时间联合, 随机抽样一致性

Abstract: To improve the detection accuracy, an abnormal crowd event detection and localization method is proposed. This algorithm includes two phases: abnormal crowd event detection and event source localization. In the first phase,an algorithm combining with space and time is proposed. From the spatial perspective, the average kinetic energy distribution histogram is extracted to describe the crowd movement characteristics, and SVM classifier is used to classify the crowd movement characteristics; From the time perspective, the hidden Markov model is built to detect continuous crowd behaviors in the scene. In the second phase, under the framework of RANSAC, the event source location is realized by calculating the intersection point of the reverse extension line of abnormal behavior crowd movement, where the multiple event sources can be labeled simultaneously. Experimental results on UMN benchmarks show that this algorithm can effectively detect crowd anomaly behavior, and the value of AUC is 0.967, respectively increases by 0.127, 0.074 and 0.007 compared with traditional optical flow method,SIFT point detection method and social force method. Furthermore, this algorithm successfully localizes the event sources.

Key words: abnormal crowd event detection, event source localization, combination of space and time, RANSAC

中图分类号:

TP39
V19

李海丰, 姜子政, 范龙飞, 陈新伟. 群体突发异常事件检测与事件源定位算法#br#[J]. 中国民航大学学报, 2019, 37(3): 49-53.

LI Haifeng, JIANG Zizheng, FAN Longfei, CHEN Xinwei. Abnormal crowd event detection and event source localization algorithm#br#[J]. Journal of Civil Aviation University of China, 2019, 37(3): 49-53.

参考文献 10

[1]	MEHRAN R, OYAMA A, SHAH M. Abnormal crowd behavior detection
	using social force model[C]//2009 IEEE Conference on Computer
	Vision and Pattern Recognition, Miami, Florida, June 20-25, 2009: 935-
	942.
[1]	MEHRAN R, OYAMA A, SHAH M. Abnormal crowd behavior detection using social force model[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, June 20-25, 2009: 935-
	942.
[2]	XIONG GUOGANG, WU XINYU, CHEN YENLUN, et al. Abnormal crowd behavior detection based on the energy model[C]//2011 IEEE International Conference on Information and Automation, Shenzhen,Guangdong, June 6-8, 2011: 495-500.
[3]	RAGHAVENDRA R, BUE A D, CRISTANI M, et al. Optimizing Interaction Force for Global Anomaly Detection in Crowded Scenes[C]//2011 IEEE International Conference on Computer Vision Workshops, Barcelona,Spain, Nov 6-13, 2011:136-143.
[4]	CHAN M T, HOOGS A, SCHMIEDERER J, et al. Detecting Rare Events in Video Using Semantic Primitives with HMM[C]//Proceedings of the 17th International Conference on Pattern Recognition, Cambridge,UK, Aug 20-26, 2004:150-154.
[5]	CHEN CHUNYU, SHAO YU, BI XIAOJUN. Detection of anomalous crowd behavior based on the acceleration feature[J]. IEEE Sensors Journal,2015, 15(12):7252-7261.
[6]	WANG BO, YE MAO, ZHAO FENGJUAN. Abnormal crowd behavior detection using size-adapted spatio-temporal features[J]. International Journal of Control Automation & Systems, 2011, 9(5): 905-912.
[7]	SABOKROU M, FATHY M, HOSEINI M, et al. Real -time Anomaly Detection and Localization in Crowded Scenes[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston,MA, June 7-12, 2015, 56(7): 56-62.
[8]	DUAN SHISHI, WANG XIANGYANG, YU XIAOQING. Crowded Abnormal Detection Based on Mixture of Kernel Dynamic Texture[C]//2014 International Conference on Audio, Language and Image Processing,Shanghai, China, July 7-9, 2015: 931-936.
[9]	LI ANG, MIAO ZHENJIANG, CHEN YIGANG, et al. Abnormal Event Detection Based on Sparse Reconstruction in Crowded Scenes[C]//2016 IEEE International Conference on Acoustics, Speech and Signal Processing, Shanghai, China, March 20-25, 2016:733-739.
[10]	ZHANG DONGPING, XU KAIHANG, PENG HUAILIANG, et al.Abnormal crowd motion behaviour[J]. International Journal of Signal Processing, 2016, 9(1): 289-302.