Optimal target detection scale generation method in people flow statistics

Abstract

The invention discloses an optimal target detection scale generation method in people flow rate statistics. The generation method comprises the following steps: obtaining a video source and initializing a statistical target queue people_list to be null; reading current frame image of the video source, converting the image into a grayscale image Gk, and initializing a detection target queue head_list to be null; dividing the grayscale image Gk into n areas; carrying out target detection on the grayscale image Gk, updating the people_list by utilizing detection targets and track information and taking newly-appeared unassociated detection targets as new targets and add the new targets to the people_list; after processing a certain number of video frames, calculating a target detection scale distribution histogram of each area according to the current position information of all statistical targets in the people_list, and calculating the optimal target detection scale of each area by utilizing target detection scale distribution histogram information. The optimal target detection scale generation method promotes high detection rate and low false alarm rate in the people flow rate algorithm based on videos.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to a method for generating an optimal target detection scale in people flow statistics. Background technique [0002] People flow counting technology is widely used in shopping malls, subways, stations and other places, and the research on this technology also has extremely high market value. The traditional way of counting the flow of people mostly adopts manual counting method, which needs to hire a lot of manpower, resulting in a waste of resources. With the development of computer vision technology, people flow counting technology based on video images is gradually developing. It automatically processes and analyzes the video images acquired by the camera by using relevant theories in image processing and other disciplines to analyze the images in the images. The target is identified and tracked, so as to realize the function of automatic counting. This method sa...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method for generating the optimal target detection scale in people flow statistics, the purpose of which is to avoid the inconvenience of manually setting the target detection scale in the video-based people flow statistics algorithm. Accuracy and inconvenience issues, and can have a beneficial effect on the high detection rate and low false alarm rate of video-based people traffic algorithms

Images