Traffic road network pedestrian density detection method and system and a server

Abstract

The embodiment of the invention provides a traffic road network pedestrian density detection method and system and a server, and the method comprises the steps: obtaining at least one video frame of a monitoring video corresponding to a query instruction as a to-be-detected image when the query instruction of the pedestrian density in the monitoring video of a traffic road network is received; inputting the to-be-detected image into a pedestrian density detection model obtained by pre-training, so that the pedestrian density detection model detects the density type of the to-be-detected image by using a classification sub-model, and detects the pedestrian density in the to-be-detected image by using a detection sub-model corresponding to the density type; based on the obtained pedestrian density, displaying a detection result of the pedestrian density of the monitoring video corresponding to the query instruction, wherein the density type of the to-be-detected image comprises a sparse type of which the pedestrian density is less than a first threshold value and a dense type of which the pedestrian density is greater than the first threshold value. According to the scheme, the accuracy of traffic network pedestrian density detection can be improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method, system and server for detecting pedestrian density in a traffic road network. Background technique [0002] Convolutional Neural Networks (CNN), as one of the most representative algorithms in the field of deep learning, has the characteristics of being able to pay attention to the subtle features of images, and has extremely high advantages in image processing. Therefore, many CNN-based pedestrian density detection methods have emerged. For example, the pedestrian density in the traffic road network can be obtained based on the CNN-based pedestrian density detection method, so as to analyze the driving risk through the pedestrian density reflected by the pedestrian density. [0003] However, the inventor found in the process of implementing the present invention that the above-mentioned CNN-based pedestrian density detection methods all have the problem that ...

Images