A Crowd Density Estimation Method Based on Convolutional Neural Network

Abstract

The invention discloses a crowd density estimation method based on convolutional neural network, comprising: step S1, establishing a training sample set; step S2, constructing a convolutional neural network model based on Mixed-Pooling; step S3, training the convolutional neural network Model: The stochastic gradient descent method is used to iteratively train the convolutional neural network model constructed in step S2, and the gradient and the value of the loss function are detected every iteration to obtain the optimal value of each weight value W and bias value b in the network structure. Optimal solution, obtain the optimal convolutional neural network model for this training after multiple iterations; step S4, crowd density estimation detection: the convolutional neural network classification model for the two partitions obtained through step S3, according to the new The detection and classification strategy estimates the population density of the overall area. The invention overcomes the problems of complex scene background interference and pedestrian occlusion, etc., and realizes accurate estimation of crowd density in the scene.

Description

technical field [0001] The invention relates to a crowd density estimation method, in particular to a crowd density estimation method based on a Mixed-Pooling convolutional neural network. Background technique [0002] In recent years, with the rapid development of the economy and the gradual improvement of people's living standards, more and more people will choose to travel during the holidays, resulting in a dramatic increase in the number of tourists visiting various scenic spots, and at the same time the safety caused by the overcrowded crowd. The hidden dangers become more and more obvious, and more and more safety accidents occur. Therefore, how to use computer vision and other technologies to intelligently monitor the crowd to make early warnings and take effective measures is of great significance for ensuring social stability and the safety of people's lives and property. At present, there are two main methods for estimating population density: [0003] 1. The me...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method for estimating crowd density based on convolutional neural network to overcome the background interference of complex scenes and pedestrian occlusion for the deficiencies of the existing technology, and then realize the estimation of crowd density in the scene. an accurate estimate of

Images