Deep learning-based crowd density detection method and system

Abstract

The invention discloses a deep learning-based crowd density detection method and system. The detection method comprises the following steps: firstly, obtaining background image information through background learning, and then extracting a target foreground image of each frame image through the background image information; establishing a low-density crowd model through an image from which the target foreground image is extracted and belonging to the low-density crowd level, and establishing a high-density crowd model through the image from which the target foreground image is extracted and belonging to the high-density crowd level; first inputting each frame image needing to detect the crowd density to the low-density crowd model, judging the crowd density level according to the crowd number when the low-density crowd model acquires that the crowd number result does not exceed a certain value; inputting the image into the high-density crowd model when the low-density crowd model acquires that the crowd number result exceeds a certain value, and judging the crowd density through the high-density crowd model. The detection method disclosed by the invention has the advantages of being high in detection precision and small in amount of calculation.

Description

Technical field [0001] The invention belongs to the field of machine vision, and particularly relates to a crowd density detection method and system based on deep learning. Background technique [0002] With the rapid development of my country's economy, population urbanization has become increasingly obvious. More and more people are pouring into the city, leading to an increasing population density in many public places (including subways, airports, commercial districts, stadiums, etc.) in the city. Especially during public holidays, crowd crowding is not uncommon. As a special management object, the crowd is receiving more and more attention from the society. Therefore, how to effectively monitor the crowd in real time and eliminate the hidden safety hazards caused by overcrowding is one of the problems that need to be solved urgently in today's society. As the subway is a component of the urban rail transit system, the demand for crowd density detection is even more urgent...

AI Technical Summary

Problems solved by technology

Moreover, the background image used in the image processing process in the crowd density detection method in the prior art is usually obtained by calculating the average value of each pixel, and the environmental illumination changes and the multimodality of the background are relatively sensitive. changes, its adaptability will become worse, which will affect the detection accuracy of crowd density

[0005] In addition, the systems for crowd density detection in the prior art usually transmit the acquired images to the remote control center through the network, and then detect them after analyzing the images through the remote control center. This kind of system communication needs to occupy Large bandwidth for image transmission, with defects such as slow image processing and poor real-time performance

Images