Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (4): 1164-1169.DOI: 10.11772/j.issn.1001-9081.2017092340

Previous Articles     Next Articles

Abnormal crowd behavior detection based on motion saliency map

HU Xuemin1, YI Chonghui1, CHEN Qin1, CHEN Xi1, CHEN Long2   

  1. 1. School of Computer Science and Information Engineering, Hubei University, Wuhan Hubei 430062, China;
    2. School of Data and Computer Science, Sun Yat-sen University, Guangzhou Guangdong 510275, China
  • Received:2017-09-28 Revised:2017-10-24 Online:2018-04-10 Published:2018-04-09
  • Supported by:
    This work is partially supported by the Youth Talent Project of Scientific Research Plan of Hubei Provincial Education Department.


胡学敏1, 易重辉1, 陈钦1, 陈茜1, 陈龙2   

  1. 1. 湖北大学 计算机与信息工程学院, 武汉 430062;
    2. 中山大学 数据科学与计算机学院, 广州 510275
  • 通讯作者: 胡学敏
  • 作者简介:胡学敏(1985-),男,湖南岳阳人,讲师,博士,主要研究方向:图像处理、计算机视觉;易重辉(1995-),男,湖北荆州人,主要研究方向:智能视频检测;陈钦(1995-),男,湖北黄冈人,主要研究方向:深度学习;陈茜(1996-),女,湖北黄陂人,主要研究方向:图像处理;陈龙(1985-),男,湖北襄阳人,副教授,博士,主要研究方向:计算机视觉、自动驾驶。
  • 基金资助:

Abstract: To deal with the crowd supervision issue of low accuracy and poor real-time performance in public places, an abnormal crowd behavior detection approach based on motion saliency map was proposed. Firstly, the Lucas-Kanade method was used to calculate the optical flow field of the sparse feature points, then the movement direction, velocity and acceleration of feature points were computed after filtering the optical flow field both in time and space. In order to precisely describe the crowd behavior, the amplitude of velocity, the direction change, and the amplitude of acceleration were mapped to three image channels corresponding to R, G, and B, respectively, and the motion saliency map for describing the characteristics of crowd movement was fused by this way. Finally, a convolution neural network model was designed and trained for the motion saliency map of crowd movement, and the trained model was used to detect abnormal crowd behaviors. The experimental results show that the proposed approach can effectively detect abnormal crowd behaviors in real time, and the detection rate in the datasets of UMN and PETS2009 are more than 97.9%.

Key words: abnormal crowd behavior detection, optical flow method, motion saliency map, Convolution Neural Network (CNN), video supervision

摘要: 针对公共场所中人群监控准确性和实时性低的问题,提出一种基于运动显著图的人群异常行为检测方法。该方法首先利用Lucas-Kanade法计算稀疏特征点的光流场,并对光流场进行时间和空间上的滤波处理,然后计算特征点的运动方向、速度和加速度。为了准确描述人群行为,将人群的速度幅值、运动方向变化量和加速度幅值分别映射为图像的R、G、B三个通道,并以此合成代表人群运动特征的运动显著图。最后,设计和训练面向人群运动显著图的卷积神经网络模型,并利用该模型检测人群中是否存在异常行为。实验结果表明,该方法能够有效、实时地检测人群异常行为,在UMN和PETS2009数据集的检测率均达到了97.9%以上。

关键词: 人群异常行为检测, 光流法, 运动显著图, 卷积神经网络, 视频监控

CLC Number: