Crowd density estimation method

Abstract

The invention discloses a crowd density estimation method. The method comprises the following steps: preprocessing a to-be-estimated image to obtain a low-layer feature map; Inputting a first sub-network in the deep neural network model to obtain a high-level semantic feature map; Inputting a full connection layer in the deep neural network model to obtain a crowd density level; Determining a corresponding sub-column of the second sub-network; Inputting the low-layer feature map into a corresponding sub-column to obtain a main feature map; Inputting the high-level semantic feature map into a crowd position mask module to obtain a crowd position information mask; Weighting the main feature map and the crowd position information mask, and linking the main feature map with the main feature map on a channel to obtain a feature map added with the crowd position information; And inputting the data into a dimension conversion layer to obtain a crowd density estimation map and a number of people estimation result. According to the method, the problem of poor crowd density estimation performance caused by multi-scale and non-uniform crowd distribution in different scenes in the crowd density estimation task can be effectively solved, and the method has relatively high accuracy and relatively 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