Query method and device

Abstract

The invention provides a query method and device, and relates to the technical field of monitoring, and the method comprises the steps: obtaining a portrait query request which comprises at least twodifferent space-time information query conditions; for each space-time information query condition, searching a face file set matched with the space-time information query condition from a face imagelibrary; wherein the face archives are determined by clustering face images captured by the monitoring equipment; clustering the face archives in each face archive set, and determining each face archive with the similarity meeting a set requirement as the same face archive; and for the clustered face archives, if it is determined that a first face archive exists in the face archive set corresponding to each space-time information query condition, determining the first face archive as a query result of the portrait query request. Through the clustering method, the information of the same suspect with a plurality of files cannot be missed, so that the query accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of monitoring, in particular to a query method and device. Background technique [0002] With the rapid development of information technology, monitoring technology has been widely used in various industries and places, providing many conveniences for people's daily work and life. But at the same time, there are many problems in the single monitoring application mode. The image content analysis of the monitoring network still needs to rely on manual real-time viewing and manual retrieval. [0003] With the expansion of the surveillance network scale and the massive growth of video data, image monitoring and retrieval take up a lot of manpower, and it is becoming more and more difficult to obtain useful information or intelligence from massive surveillance videos. [0004] In addition, most of the current surveillance video applications are only the reproduction and playback of surveillance scenes, which is ...

AI Technical Summary

Problems solved by technology

But at the same time, there are many problems in the single monitoring application mode. The image content analysis of the monitoring network still needs to rely on manual real-time viewing and manual retrieval.

[0003] With the expansion of the surveillance network scale and the massive growth of video data, image monitoring and retrieval take up a lot of manpower, and it is becoming more and more difficult to obtain useful information or intelligence from massive surveillance videos

[0004] In addition, most of the current surveillance video applications are only the reproduction and playback of surveillance scenes, which is difficult to meet the needs of modern public security prevention and control applications

Images