Identity identification method and device for suspects based on large video data

Abstract

The invention provides an identity identification method and device for suspects based on large video data. The identity identification method comprises the following steps: receiving suspect characteristic information transmitted by a user; carrying out cluster retrieval on a moving target which is matched with the suspect characteristic information from a moving target characteristic database, and extracting characteristic information which is corresponding to the moving target; obtaining base station data corresponding to the characteristic information within a motion range according to the extracted characteristic information; extracting suspect identity information matched with the moving target from an identity information platform device according to the base station data corresponding to the characteristic information within the motion range. The identity identification method is combined with multi-aspect resources of the moving target characteristic database, the base station data, resident population data in the identity information platform device and the like to carry out comprehensive collision retrieval, so that accurate video suspect identity information can be obtained to greatly improve the accuracy and success rate of the suspect identity information identification; furthermore, a large data analysis and processing technology is used, so that a large number of high-speed changeable complex scenes can be dealt, and the timeliness is better.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a method and device for identifying a suspect based on video big data. Background technique [0002] In recent years, with the strengthening of the rule of law, surveillance cameras have been installed in various important public locations in cities in my country to obtain real-time video data within the monitoring range and store them to assist the public security organs in detecting cases. Ensure the safety of residents. In today's society, the main means for public security organs to detect cases is to use video surveillance information around the crime site, and use it to find and locate clues to suspects in related cases. In the above-mentioned case detection process, it is particularly important to identify and locate the identity information of the suspect in the relevant video. [0003] At present, the more advanced video suspect identity information ide...

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned method for identifying the video suspect's identity information by face recognition may have the following problems: First, due to the shooting angle of the camera, the video data collected by the video surveillance system may not include face data (or only include part of the face data). face data), so that the identity information of video suspects cannot be identified through the above-mentioned face recognition technology

Second, the shooting location of the video surveillance system as well as the resolution and exposure of the camera will cause a large deviation in the accuracy of the collected face data.

Images