胡学敏, 余进, 邓重阳, 宋昇, 陈钦. 基于时空立方体的人群异常行为检测与定位[J]. 武汉大学学报 ( 信息科学版), 2019, 44(10): 1530-1537. DOI: 10.13203/j.whugis20170424
引用本文: 胡学敏, 余进, 邓重阳, 宋昇, 陈钦. 基于时空立方体的人群异常行为检测与定位[J]. 武汉大学学报 ( 信息科学版), 2019, 44(10): 1530-1537. DOI: 10.13203/j.whugis20170424
HU Xuemin, YU Jin, DENG Chongyang, SONG Sheng, CHEN Qin. Abnormal Crowd Behavior Detection and Location Based on Spatial-temporal Cube[J]. Geomatics and Information Science of Wuhan University, 2019, 44(10): 1530-1537. DOI: 10.13203/j.whugis20170424
Citation: HU Xuemin, YU Jin, DENG Chongyang, SONG Sheng, CHEN Qin. Abnormal Crowd Behavior Detection and Location Based on Spatial-temporal Cube[J]. Geomatics and Information Science of Wuhan University, 2019, 44(10): 1530-1537. DOI: 10.13203/j.whugis20170424

基于时空立方体的人群异常行为检测与定位

Abnormal Crowd Behavior Detection and Location Based on Spatial-temporal Cube

  • 摘要: 针对视频监控系统中人群异常行为检测准确率低的问题,提出了一种基于时空立方体的人群异常行为检测与定位方法。首先利用光流法计算等间距采样的特征点光流场,然后根据光流场计算特征点的运动速度、方向和方向熵3个特征量,并分别将其统计直方图投影到对应的三维立体空间中,构建描述人群行为的时空立方体特征。同时,将图像分成多个子区域,并计算各子区域的时空立方体特征;设计基于最近邻分类和支持向量机的级联分类器,完成人群异常行为的检测与定位。结果表明,该方法比现有方法能更准确地检测视频中的异常人群。

     

    Abstract: To handle the issue of low accuracy performance of crowd abnormal behavior detection in video surveillance systems, an abnormal crowd behavior detection and location approach based on spatial-temporal cube is proposed in this paper. The optical flow method is first used to calculate the optical flow field of feature points which are obtained by the equidistant sampling method. Then, the velocity, orientation and orientation entropy of the feature points are obtained. And statistical histograms of the three parameters are mapped into the corresponding cubic space to extract the spatial-temporal cube feature for describing the spatial-temporal features. A blocking method is used to divide the image into several sub regions, and the spatial-temporal cubes of each sub region are calculated. Finally, a cascade classifier based on nearest neighbor classification and support vector machine is designed to detect and locate crowd abnormal behaviors. Experimental results show that the proposed method can effectively detect and locate abnormal crowd behaviors in videos.

     

/

返回文章
返回