Abstract
The change of crowd energy is a fundamental measurement for describing a crowd behavior. In this paper, we present a crowd abnormal detection method based on the change of energy-level distribution. The method can not only reduce the camera perspective effect, but also detect crowd abnormal behavior in time. Pixels in the image are treated as particles, and the optical flow method is adopted to extract the velocities of particles. The qualities of different particles are distributed as different value according to the distance between the particle and the camera to reduce the camera perspective effect. Then a crowd motion segmentation method based on flow field texture representation is utilized to extract the motion foreground, and a linear interpolation calculation is applied to pedestrian’s foreground area to determine their distance to the camera. This contributes to the calculation of the particle qualities in different locations. Finally, the crowd behavior is analyzed according to the change of the consistency, entropy and contrast of the three descriptors for co-occurrence matrix. By calculating a threshold, the timestamp when the crowd abnormal happens is determined. In this paper, multiple sets of videos from three different scenes in UMN dataset are employed in the experiment. The results show that the proposed method is effective in characterizing anomalies in videos.
Highlights
Abnormal crowd analysis [1,2,3] has become a popular research topic in computer vision
The results report that the proposed method can be used to detect the abnormal crowd behavior
We propose an effective approach to detect crowd abnormal behavior in video streams using the change of energy-level distribution
Summary
Abnormal crowd analysis [1,2,3] has become a popular research topic in computer vision. It is difficult to accurately detect and track all the individuals in a dense crowd due to the occlusions among some individuals; (2) The macroscopic approach, which considers a large-scale crowd as a single entity [10] It treats each image pixel as a particle, and models the features of the particles to further identify the crowd behavior [11,12,13,14,15,16]. In [19], a gradient model based on space and time are proposed to detect partial abnormal crowd behavior. These types of methods do not require detection and tracking of the individual, which
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call