Crowd counting method based on multi-scale generative adversarial network

Abstract

According to the crowd counting method based on the multi-scale generative adversarial network, crowd density prediction is carried out by adopting an adversarial training mode. And the maximum and minimum problems of the generation model and the discrimination model are optimized by adopting a combined alternate iteration training mode, wherein the training generation network is used for generating an accurate crowd density map so as to cheat the discriminator, and on the contrary, the discriminator is trained to be used for discriminating the generated density map and a real density map label. Meanwhile, the output of the discriminator can provide feedback of the density map position and prediction precision for the generator. The two networks compete for training at the same time so asto improve the generation effect until the sample generated by the generator cannot be correctly judged by the discriminator. According to the crowd density detection algorithm provided by the invention, after adversarial loss is introduced, an adversarial training mode is adopted to enable the convolutional neural network to generate a density map with higher quality, so that the accuracy of network crowd counting is improved.

Description

technical field [0001] The invention relates to the fields of image processing and computer vision, in particular to a crowd counting algorithm based on a multi-scale generative confrontation network. Background technique [0002] With the continuous growth of my country's population, there are more and more occasions where large-scale crowds gather. In order to effectively control the number of people in public places and prevent accidents caused by crowd density overload, video surveillance has become the main means at present. In the field of video surveillance and security, crowd analysis has attracted the attention of more and more researchers, and has become a very hot research topic in the field of computer vision. The task of crowd counting is to accurately estimate the total number of crowds in the picture and at the same time give the distribution of crowd density. Image crowd counting can be used in many fields, such as accident prevention, space planning, analy...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems existing in the existing technology, this patent is based on the crowd counting method of the multi-scale generative confrontation network, which integrates the features of the single column convolutional neural network at different depths, and solves the problems of scale change and occlusion in the crowd image, and at the same time , the network model is added to the confrontation loss of the discriminator, and a confrontational training method is used to predict the crowd density and generate a higher quality density map

Images