Unsupervised crowd abnormity monitoring and positioning method based on recurrent neural network modeling

Abstract

The invention discloses an unsupervised crowd abnormity monitoring and positioning method based on recurrent neural network modeling. The utilizes the combination of the time sequence characteristic of a monitoring video and the long time dependence of a recurrent neural network, individually models each grid after dividing a video scenario into grids, performs unsupervised learning on a crowd dynamic sequence in a normal case by selectively using optical flow statistical characteristics, trains a model by using a Hessian-Free Optimization method, loads abnormal data into the model, and monitors and positions a crowd scenario at a t+1 moment by measuring the distance between a histogram of optical flow at the t+1 moment and a histogram of optical flow at the t moment. The unsupervised crowd abnormity monitoring and positioning method achieves global modeling in the time and space, well keeps a relation among the crowd dynamic sequence characteristics at various moments, simplifies the complexity of the model, reduces RFF training difficulty, and has good abnormal event monitoring and positioning instantaneity and accuracy.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to an unsupervised crowd abnormality monitoring and positioning method based on recursive neural network modeling. Background technique [0002] Video surveillance detection technology is an image application technology that combines video technology and modern communication technology. At the same time, the detection of abnormal crowd events has also aroused the interest of more and more researchers around the world. [0003] Rao, S. et al[1] developed a stochastic model in 2003 to describe the behavior of normal people. When a new video is sent, the motion trajectory of the person is extracted to test whether there is any abnormality. In 2004, Shobhit Saxena[2] and others proposed a multi-frame feature point detection and tracking algorithm based on KLT tracking to realize crowd event modeling in specific crowd situations. Their proposed extended scene recognition engin...

AI Technical Summary

Problems solved by technology

However, in the actual research process, whether it is in the initial extraction of crowd dynamic features or in the later motion analysis, there are a series of problems that lead to a high false alarm rate in intelligent video detection, such as: different, the background is complex, and the definitions of basic events given are inconsistent; there are many types of abnormal events, which rely too much on manual definitions. For a large number of video surveillance, the workload of manual labeling is also increasing, and it is easy to ignore some specific Non-violent anomalous incidents such as onlookers or stepping on grass

So far, the research on the two basic problem-solving methods for the detection of abnormal crowd events is still in the immature stage, and further study, research, and improvement are needed.

Images