A Crowd Density Estimation Method

Abstract

The invention discloses a crowd density estimation method. Including: preprocessing the image to be estimated to obtain a low-level feature map; inputting the first sub-network in the deep neural network model to obtain a high-level semantic feature map; inputting the fully connected layer in the deep neural network model to obtain the crowd density level; determining The corresponding sub-column of the second sub-network; input the low-level feature map into the corresponding sub-column to obtain the main feature map; input the high-level semantic feature map into the crowd position mask module to obtain the crowd position information mask; combine the main feature map with the crowd position The information mask is weighted and linked with the main feature map on the channel to obtain the feature map with crowd location information; input the dimension transformation layer to obtain the crowd density estimation map and the population estimation result. The present invention can effectively solve the problem of poor crowd density estimation performance due to multi-scale and uneven crowd distribution in different scenes in the crowd density estimation task, and has high accuracy and good robustness.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a crowd density estimation method. Background technique [0002] With the development of intelligent surveillance technology, crowd density estimation, as one of the most basic and difficult tasks in crowd anomaly detection, crowd analysis and scene understanding, has attracted extensive attention from academia and industry. Crowd density estimation refers to the estimation of the density of the crowd in the scene to obtain the number of pedestrians. [0003] At present, crowd density estimation methods are mainly divided into three categories: detection-based methods, regression-based methods and density map-based methods. Detection-based methods and regression-based methods are limited in performance due to phenomena such as severe crowd occlusion and multi-scale, while ignoring the key spatial information on the image. Therefore, in recent years, crowd density estimation task...

AI Technical Summary

Problems solved by technology

Most of the existing crowd density estimation methods use deep neural network models based on density maps, but these existing deep neural network models for crowd density estimation cannot suppress multi-scale images and uneven crowd distribution, resulting in accurate crowd density estimation. issues such as the impact of rate declines

Images