A structured storage and pre-retrieval method for pedestrian data in surveillance video

Abstract

The invention discloses a method for structured storage and pre-retrieval of pedestrian data in surveillance video. First, in the process of collecting surveillance video, the pedestrian detection method in video is used to detect pedestrians in video, and their coordinates and appearance time information are recorded. , and extract the pedestrian's color histogram feature, and then use the color histogram feature as an index to store the pedestrian data in a structured manner and associate it with the original video data. When you need to retrieve a pedestrian target in the surveillance video, you only need to input the color histogram information of the pedestrian, and you can quickly and roughly locate the time and position of the pedestrian in the surveillance video.

Description

technical field [0001] The invention mainly relates to the field of intelligent monitoring, in particular to a method for structured storage and pre-retrieval of pedestrian data in monitoring video. Background technique [0002] With the rapid development of network technology and high-definition camera technology, video surveillance is widely used in the security work of banks, squares, intersections, residential areas and other places. By recording videos in corresponding places around the clock, it provides a comprehensive solution for the accountability of accidents and the detection of criminal cases. important data support. But at the same time, due to the lack of intelligence of the traditional video surveillance system, it is necessary for the staff to continuously observe the dynamics in the surveillance scene, or rely on a large amount of manpower to browse the video data after the accident, and search for the accident or criminals. Time slices have great requirem...

AI Technical Summary

Problems solved by technology

[0005] (1) Video data generally needs to be compressed and stored. When the compression rate is too high, it will affect the video clarity and reduce the reliability of video data; Surveillance video storage cycle

[0006] (2) When the monitoring data is saved in a simple video format, a large amount of prior information is lost, the computing resources when collecting the video are wasted, the automation of monitoring data retrieval is hindered, and a large amount of human resources are wasted.

Images