基于智能监控的中小人群异常行为检测

doi:10.11772/j.issn.1001-9081.2016.06.1724

计算机应用 ›› 2016, Vol. 36 ›› Issue (6): 1724-1729.DOI: 10.11772/j.issn.1001-9081.2016.06.1724

基于智能监控的中小人群异常行为检测

何传阳¹, 王平¹, 张晓华², 宋丹妮¹

1. 西华大学电气与电子信息学院, 成都 611700;
2. 广岛工业大学信息学院, 日本广岛 731-5193

收稿日期:2015-10-30 修回日期:2016-01-08 出版日期:2016-06-10 发布日期:2016-06-08
通讯作者: 何传阳
作者简介:何传阳(1991-),男,四川资中人,硕士研究生,主要研究方向:模式识别、计算机视觉;王平(1970-),男,四川绵阳人,教授,博士,主要研究方向:图像处理、信息融合、传感器系统集成;张晓华(1971-),男,副教授,博士,主要研究方向:数字内容制作、由拍摄图像生成手绘图像、3D建模及渲染;宋丹妮(1991-),女,浙江绍兴人,硕士研究生,主要研究方向:模式识别、计算机视觉。
基金资助:
教育部"春晖计划"项目(Z2012029);四川省信号与信息处理重点实验室开放基金资助项目(szjj2012-015);西华大学研究生创新基金资助项目(ycjj2015212)。

Abnormal behavior detection of small and medium crowd based on intelligent video surveillance

HE Chuanyang¹, WANG Ping¹, ZHANG Xiaohua², SONG Danni¹

1. School of Electrical Engineering and Electronic Information, Xihua University, Chengdu Sichuan 611700, China;
2. College of Information, Hiroshima Institute of Technology, Hiroshima 731-5193, Japan

Received:2015-10-30 Revised:2016-01-08 Online:2016-06-10 Published:2016-06-08
Supported by:
This work is partially supported by the Research Found for "Spring Sunshine Plan" Program of Higher Education of China (Z2012029), the Signal and Information Key Laboratory Open Fund of Sichuan Province (scjj2012-015), the Innovation Project of Xihua University Graduates (YCSZ2013068).

摘要/Abstract

摘要： 针对人群异常行为检测实时性较差、分类算法识别率不高、特征量较少的问题,提出一种基于智能监控的中小人群异常行为检测算法。首先,利用快速群体密度检测算法,提取人群数量变化信息;其次,利用改进的Lucas-Kanande光流法提取视频中人群的平均动能、人群方向熵、人群距离势能;最后,利用极限学习机(ELM)算法对人群行为进行分类。使用UMN公共数据集进行测试,ELM算法对中小人群异常行为分析比中高密度人群异常行为检测算法和基于KOD能量特征的群体异常行为检测算法识别率分别高出7.13个百分点和5.89个百分点,并且人数密度估计部分平均每帧图像处理耗时相比中高密度人群异常行为检测算法减少了106 ms(近1/3)。实验结果表明:基于智能监控的中小人群异常行为检测算法能有效提高异常帧识别率和实时性。

关键词: 群体密度, 特征量提取, Lucas-Kanade光流法, 极限学习机, 异常行为识别

Abstract: Focusing on the issues of poor real-time, low classification recognition rate and less features of the crowd abnormal detection, an abnormal behavior detection algorithm of small and medium crowd based on intelligent video surveillance was proposed. Firstly, the rapid population density detection algorithm was employed to extract the change information of crowd amount. Secondly, the improved Lucas-Kanade optical flow method was utilized to extract the average kinetic energy, the direction entropy and the distance potential energy of the crowd. Finally, the crowd behaviors were classified by using the Extreme Learning Machine (ELM) algorithm. UMN common data set was used for test, compared to abnormal crowd behavior detection algorithm in high and medium density and abnormal behavior detection algorithm based on Kinetic Orientation Distance (KOD) energy feature, the recognition rate of ELM algorithm in abnormal behavior detection of small and medium crowd increased by 7.13 percentage points and 5.89 percentage points respectively. On the part of the crowd density estimation, compared to the high and medium crowd density detection algorithm, the processing time for each frame of ELM algorithm reduced 106 ms almost 1/3, approximately. The experiments show that the proposed abnormal behavior detection of small and medium crowd based on intelligent video surveillance can effectively improve recognition rate and real-time performance of the abnormal behavior detection.

Key words: crowd density, feature extraction, Lucas-Kanade optical flow, Extreme Learning Machine (ELM), abnormal behavior detection

中图分类号:

TP391.41

何传阳, 王平, 张晓华, 宋丹妮. 基于智能监控的中小人群异常行为检测[J]. 计算机应用, 2016, 36(6): 1724-1729.

HE Chuanyang, WANG Ping, ZHANG Xiaohua, SONG Danni. Abnormal behavior detection of small and medium crowd based on intelligent video surveillance[J]. Journal of Computer Applications, 2016, 36(6): 1724-1729.

参考文献

[1] CHO S-H, KANG H-B. Abnormal behavior detection using hybrid agents in crowded scenes[J]. Pattern Recognition Letters, 2014, 44: 64-70.
[2] GU X, CUI J, ZHU Q. Abnormal crowd behavior detection by using the particle entropy[J]. Optik-International Journal for Light and Electron Optics, 2014, 125(14): 3428-3433.
[3] WANG T, SNOUSSI H. Detection of abnormal visual events via global optical flow orientation histogram[J]. IEEE Transactions on Information Forensics and Security, 2014, 9(6): 988-998.
[4] YUAN Y, FNAG J W, WANG Q. Online anomaly detection in crowd scenes via structure analysis[J]. IEEE Transations on Cybernetics, 2015, 45(3): 562-575.
[5] ROSTEN E, DRUMMOND T. Machine learning for high-speed corner detection[C]//ECCV 2006: Proceedings of the 9th European Conference on Computer Vision, LNCS 3951. Berlin:Springer, 2006: 430-443.
[6] ROSTEN E, PORTER R, DRUMMOND T, et al. Faster and better: a machine learning approach to corner detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(1): 105-119.
[7] 杨华,苏航,郑世宝.大规模群体密度估计算法[J].电视技术,2010,34(5): 113-116.(YANG H, SU H, ZHENG S B. Large-scale crowd density estimation[J]. Video Engineering, 2010, 34(5): 113-116).
[8] FRADI H, DUGELAY J L. Low level crowd analysis using frame-wise normalized feature for people counting[C]//Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security. Piscataway: IEEE, 2012: 246-251.
[9] 陈添丁,胡鉴,吴涤.稀疏光流快速计算的动态目标检测与跟踪[J].中国图象图形学报,2013,18(12):1593-1660.(CHEN T D, HU J, WU D. Dynamic target detection and tracking based on fast computation using sparse optical flow[J]. Journal of Image and Graphics, 2013, 18(12): 1593-1660).
[10] AHMAD M, TASLIMA T, LATA L, et al. A combined local-global optical flow approach for cranial ultrasonogram image sequence analysis[C]//Proceedings of the 200811th International Conference on Computer and Information Technology. Piscataway, NJ: IEEE, 2008: 323-328.
[11] 段晶晶,高琳,范勇,等.基于KOD能量特征的群体异常行为识别[J].计算机应用研究,2013,30(12):3836-3839.(DUAN J J,GAO L,FAN Y, et al. Abnormal crowd behavior recognition based on KOD energy model[J]. Application Research of Computers, 2013, 30(12): 3836-3839.)
[12] 王小川,史峰.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013:8.(WANG X C, SHI F. 43 Case Analysis of Neural Network in MATLAB[M]. Beijing: Beihang University Press, 2013: 8.)
[13] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.
[14] HUANG G B, ZHU Q Y, SIEW C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes[J].IEEE Transactions on Neural Networks, 2006,17(4): 879-892.
[15] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: a new learning scheme of feedforward neural networks[C]//Proceedings of the 2004 IEEE International Joint Conference on Neural Networks. Piscataway, NJ: IEEE, 2004: 985-990.
[16] ZHU Q Y,QIN A K, SUGANTHAN P N, et al. Evolutionary extreme learning machine[J]. Pattern Recognition, 2005, 38(10): 1759-1763.
[17] University of Minnesota. UMN abnormal events detection dataset[EB/OL]. (2009-04-12)[2015-8-30]. http://mha.cs.umn.edu/proj_events.shtml.
[18] 胡斌斌.中高密度人群异常行为检测[D].合肥:安徽大学,2013:13-23.(HU B B. Detection of abnormal crowd events in high density video[D]. Hefei: Anhui University, 2013: 13-23.)

基于智能监控的中小人群异常行为检测

Abnormal behavior detection of small and medium crowd based on intelligent video surveillance

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	孙浩艺, 王传美, 丁义明. 基于隐藏层输出矩阵的极限学习机算法优化[J]. 计算机应用, 2021, 41(9): 2481-2488.
[2]	唐延强, 李成海, 宋亚飞. 基于改进粒子群优化和极限学习机的网络安全态势预测[J]. 计算机应用, 2021, 41(3): 768-773.
[3]	牛春彦, 夏克文, 张江楠, 贺紫平. 基于云量子花朵授粉的极限学习机算法[J]. 计算机应用, 2020, 40(6): 1627-1632.
[4]	来杰, 王晓丹, 李睿, 赵振冲. 基于去噪自编码器的极限学习机[J]. 计算机应用, 2019, 39(6): 1619-1625.
[5]	程玉胜, 钱坤, 王一宾, 赵大卫. 融合萤火虫方法的多标签懒惰学习算法[J]. 计算机应用, 2019, 39(5): 1305-1311.
[6]	张芳艳, 王新, 许新征. 基于结构化遮挡编码和极限学习机的局部遮挡人脸识别[J]. 计算机应用, 2019, 39(10): 2893-2898.
[7]	颜宏文, 盛成功. 基于层次聚类和极限学习机的母线短期负荷预测[J]. 计算机应用, 2018, 38(8): 2437-2441.
[8]	范君, 王新, 徐慧. 粒子群优化混合核极限学习机的构造煤厚度预测方法[J]. 计算机应用, 2018, 38(6): 1820-1825.
[9]	张立优, 马珺, 贾华宇. PID补偿的完全在线序贯极限学习机控制器在输入扰动系统自适应控制中的应用[J]. 计算机应用, 2018, 38(4): 1213-1217.
[10]	翟俊海, 张素芳, 王聪, 沈矗, 刘晓萌. 基于MapReduce的大数据主动学习[J]. 计算机应用, 2018, 38(10): 2759-2763.
[11]	周馨, 王国胤, 于洪. 基于改进极限学习机的软测量建模[J]. 计算机应用, 2017, 37(3): 668-672.
[12]	杨绪兵, 冯哲, 顾一凡, 薛晖. 基于Plane-Gaussian神经网络的网络流状态监测[J]. 计算机应用, 2017, 37(3): 782-785.
[13]	朱林奇, 张冲, 周雪晴, 魏旸, 黄雨阳, 高齐明. 融合深度置信网络与与核极限学习机算法的核磁共振测井储层渗透率预测方法[J]. 计算机应用, 2017, 37(10): 3034-3038.
[14]	井诗博, 杨丽明, 李军会, 张思韫. 半监督极限学习机及其在近红外光谱数据分析中的应用[J]. 计算机应用, 2016, 36(2): 387-391.
[15]	卢涛, 杨威, 万永静. 基于图像超分辨极限学习机的极低分辨率人脸识别[J]. 计算机应用, 2016, 36(2): 580-585.