Crowd density estimation method and device, electronic equipment and medium

Abstract

The invention provides a crowd density estimation method and device, electronic equipment and a computer readable medium. The crowd density estimation method comprises the following steps: obtaining amonitoring video for the crowd in the monitoring area, and extracting a key frame in the monitoring video, wherein the difference between image frames of the key frame is greater than a preset difference threshold value; and inputting the key frame into a convolutional neural network model for crowd analysis, and outputting a crowd density estimation graph and a people number estimation result corresponding to the key frame, the convolutional neural network model being established through deep learning training by taking different images and the crowd density estimation graph and the people number estimation result corresponding to the different images as a sample set. Since the crowd density estimation is performed after the key frame in the monitoring video is extracted, compared with the prior art, the crowd density estimation efficiency and accuracy can be improved.

Description

technical field

[0001] The present application relates to the technical field of image processing, in particular to a crowd density estimation method and device, an electronic device, and a computer-readable medium. Background technique

[0002] In major cities, with the increase of residential population density, the behavior of crowds gathering in large numbers is increasing and the scale is getting bigger and bigger. Although cameras are installed in almost every corner of the city, the current gathering of crowds still lacks effective management and control. Therefore, it becomes an important task in urban management to estimate the density of crowds in specific occasions.

[0003] Crowd density estimation plays an important role in disaster protection, design of public places, and intelligent scheduling of personnel. When a scene space accommodates too many pedestrians, stampede accidents are prone to occur, and crowd density estimation can give early warning to such ...

Images