Crowd counting method for real scene

Abstract

The invention discloses a crowd counting method for a real scene. The method is characterized by adopting a geometric Gaussian adaptive kernel function to generate a real crowd density map as a real value to guide training; inputting the crowd image into the convolution operation of the local receptive field, fusing the generated adaptive feature maps of different scales, inputting the fused feature maps into a deep neural network model, and obtaining the number of people in the scene through regression solution and an integral method according to the obtained estimated density map. Compared with the prior art, the method is simple and convenient, strong in real-time performance and high in accuracy of people counting, can quickly obtain a high-quality crowd density map by adopting a lightweight network structure, does not lose too much statistical precision, occupies a small memory space of model parameters, and is particularly suitable for various scenes with high real-time performance requirements, such as attendance systems, crowd monitoring systems and the like.

Description

technical field [0001] The invention relates to the technical field of crowd image counting, in particular to a crowd counting method in a real scene based on density map estimation. Background technique [0002] The goal of the crowd counting task is to estimate the number of people in a surveillance video or photo. Crowd counting from a single photo is of vital importance in areas such as traffic management, disaster warning, and public area management. In addition, this technology can also be applied to other research fields such as cell microscopy and vehicle counting. Crowd counting is an important research area in the field of computer vision and intelligent video surveillance due to its wide range of applications, and it has also received a lot of attention from both the computer vision research community and private companies in recent years. Like any other computer vision problem, crowd analysis faces many challenges, such as occlusions, high clutter, uneven distr...

AI Technical Summary

Problems solved by technology

Like any other computer vision problem, crowd analysis faces many challenges, such as occlusions, high clutter, uneven distribution of people, uneven lighting, appearance, scale, and perspective variations within and between scenes, etc., making the problem It is extremely complicated, which will lead to problems such as the decline in the accuracy of people counting

[0003] The crowd counting method in the prior art has difficulties such as low accuracy rate of people counting, poor real-time performance, many model parameters occupy a large memory space, and it is difficult to apply to real scenes.

Images