Three-dimensional convolutional neutral network training method and video anomalous event detection method and device

Abstract

The embodiment of the invention relates to the technical field of video images, in particular to a three-dimensional convolutional neutral network training method and a video anomalous event detection method and device based on a three-dimensional convolutional neutral network. The three-dimensional convolutional neutral network training method and the video anomalous event detection method and device based on the three-dimensional convolutional neutral network are used for detecting anomalous events occurring in a crowded situation. Each convolutional core on a convolutional layer of the Nth convolution and sampling layer convolves data of all characteristic patterns of all channels in a sampling layer of the Nth convolution and sampling layer in the forward transmission process of a three-dimensional convolutional neutral network, due to the fact that the last convolutional layer convolutes the data of all characteristic patterns of all the channels, characteristics with higher expressive ability can be extracted, and accordingly the anomalous events occurring in the crowd situation can be well described by means of the characteristics, and detection accuracy of the anomalous events can be improved.

Description

technical field [0001] The present invention relates to the technical field of video images, in particular to a training method for a three-dimensional convolutional neural network, a method and a device for detecting abnormal video events based on a three-dimensional convolutional neural network. Background technique [0002] With the rapid development of the economy, there is often a peak flow of people in public places such as shopping malls and stadiums, and these crowded people have brought great hidden dangers to public safety. If the abnormal behavior in the surveillance video can be detected in time, corresponding solutions can be taken in time to avoid major accidents. [0003] The existing methods for automatic detection of abnormal events in surveillance video need to be based on tracking of moving objects, that is, abnormal behavior detection is performed by continuously detecting the trajectory of moving objects. The abnormal behavior detection effect of this t...

AI Technical Summary

Problems solved by technology

The abnormal behavior detection effect of this type of method depends to a large extent on the results of moving object tracking, so this type of method is only suitable for non-crowded scenes, but for crowded scenes in public places such as shopping malls and stadiums, due to the mutual occlusion of objects It is quite serious with self-occlusion, which makes it difficult to effectively track moving objects. Therefore, in crowded scenes, the method based on moving object tracking is not applicable

Images