Context-aware embedded crowd counting method and system, medium and electronic equipment

Abstract

The invention provides a context-aware embedded crowd counting method, a context-aware embedded crowd counting system, a medium and electronic equipment, wherein the context-aware embedded network ismainly used for extracting low-level spatial features of an image, segmenting the image into super-pixels, fusing a result of segmenting the image into the super-pixels and an extraction result of thelow-level spatial features, and extracting global association of the features to finally generate a density map. According to the super-pixel network adopted by the invention, the pixels are groupedby utilizing the similarity of the characteristics among the pixels, and a small number of super-pixels are used for replacing a large number of pixels to represent the characteristics of the picture,so that the complexity is greatly reduced. The context-aware embedded network adopted by the method can extract global association between any two point features on the feature map, so the feature expression capability is enhanced; when complex and diverse scenes are processed, the complex crowd distribution condition in the crowded scene can be well processed, some errors are avoided, and the error influence is reduced, so that the total number of crowds can be better counted.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a context-aware embedded crowd counting method, system, medium and electronic equipment. Background technique [0002] With the increasing urban population, in subway stations, shopping malls, and various festival gatherings, excessive crowds bring potential dangers and easily cause tragedies such as stampedes and riots. In recent years, crowd counting and population density distribution estimation have become hot topics in the security field. At the same time, the algorithm performance of crowd counting has been greatly improved under the combination of deep learning. Therefore, crowd counting and crowd density estimation have important research value. [0003] The purpose of crowd counting is to find out the number of people in a specific scene, while crowd density distribution estimation needs to obtain spatial density information and number of people (summation of density map...

AI Technical Summary

Problems solved by technology

[0009] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a context-aware embedded crowd counting method, system, medium and electronic equipment, which are used to solve the ineffective and quasi-group crowd counting method in the prior art. estimated problem

Images