Method for obtaining crowd spatial position in video

Abstract

The invention provides a method for obtaining a crowd spatial position in a video, and belongs to the technical field of urban space analysis. The method comprises the following steps: firstly, acquiring a to-be-analyzed space video, and extracting a corresponding image; performing target detection on each image by using a convolutional neural network model; and reserving a target identification box with an identification result being a person in the target detection result, and restoring the position of the person in each image to a coordinate in a planar graph or a top view by using a geometric algorithm to obtain crowd spatial position information in the video. The method has the advantages that the actual geographic position information of the crowd can be quickly and accurately obtained, and has a good application prospect in the aspects of urban space analysis, urban and rural planning evaluation and the like.

Description

technical field [0001] The invention belongs to the technical field of urban space analysis, and particularly proposes a method for obtaining the spatial position of crowds in a video. Background technique [0002] The continuous development of information technology provides conditions for large-scale data processing, especially in recent years, the development of deep learning technology has greatly promoted the research in the field of computer vision, making the data obtained from common video recording equipment, such as photos, videos Wait, there are new analytical tools. Video images contain very rich environmental characteristics and crowd behavior information. Using video to analyze crowd behavior can help us understand crowd behavior characteristics more intuitively. If the spatial location of the crowd in the video can be obtained, the accuracy and efficiency of urban spatial analysis will be greatly improved. [0003] The existing method of obtaining crowd info...

AI Technical Summary

Problems solved by technology

Therefore, there will be a large error in obtaining the crowd position using this method

However, the crowd information required for spatial planning and design is based on the geographic coordinate system or projected coordinate system. It is impossible to obtain the exact position of the crowd in the image or video in space, which will make it difficult for the crowd information in the video to be used to support related work.

Images