Self-adaptive receptive field crowd density estimation method based on cavity convolution

Abstract

The invention discloses a self-adaptive receptive field crowd density estimation method based on cavity convolution, which belongs to the field of computer vision, and comprises the following steps: segmenting an original data set image and a crowd density map to obtain image blocks and crowd density map blocks; constructing and training an adaptive receptive field population density estimation network, wherein the model comprises a cavity convolution module and a classification module, the classification module is used for classifying the segmented image blocks, the cavity convolution moduleadaptively selects a cavity convolution sub-network corresponding to the receptive field according to the image block category output by the classification module, and performs feature extraction on the segmented image blocks to obtain a crowd density map; and inputting the picture to be predicted into the trained adaptive receptive field crowd density estimation model to obtain a crowd density estimation result. According to the method, the cavity convolution sub-network corresponding to the receptive field can be adaptively selected for crowd density estimation, and the problem of perspective distortion is solved, so that the accuracy of crowd density estimation is improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and more specifically relates to a method for estimating population density of an adaptive receptive field based on atrous convolution. Background technique [0002] In recent years, with the growth of urban population, people gather more frequently in public places, and a large number of people gathering in public places will bring a series of potential safety problems such as crowding and stampede. Therefore, the supervision and control of crowded public places is of great significance to the prevention of accidents, and crowd density estimation is one of the key measures. Crowd density estimation refers to accurately estimating the number of people in a video or image, and at the same time giving the distribution of the crowd in the picture. When the number of people in the image exceeds a certain threshold or the crowd distribution is too dense somewhere in the picture, a safety acci...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides an adaptive receptive field crowd density estimation method based on atrous convolution, which aims to solve the problem of perspective distortion in crowd images, thereby improving the accuracy of crowd density estimation. Accuracy

Images