Pedestrian hybrid search method and system in video monitoring scene

Abstract

The invention discloses a pedestrian hybrid search method and system in a video monitoring scene, and belongs to the field of video content search. The method comprises the following steps: carrying out the video decoding to obtain a frame image; respectively carrying out face target detection and pedestrian target detection on the frame image to respectively obtain a face snapshot and a pedestrian snapshot of a pedestrian target; recognizing face snapshots and pedestrian snapshots belonging to the same pedestrian target in the same frame, and associating the face snapshots and the pedestriansnapshots together; extracting face features according to the face snapshots, extracting pedestrian re-recognition features according to the pedestrian snapshots, and matching the pedestrian targets in the current frame with the pedestrian targets in the processed frame images through feature matching so as to obtain tracks of the same pedestrian target; and storing the pedestrian target ID and the face snapshot, the pedestrian snapshot, the face feature, the pedestrian re-recognition feature and the track information of the pedestrian target into a database to obtain a search database. According to the method, multi-angle feature description of the pedestrian target can be provided, and reliable support is provided for application.

Description

technical field [0001] The invention belongs to the field of video content search, and more specifically relates to a pedestrian mixed search method and system in a video surveillance scene. Background technique [0002] Under the background of building "Safe City" and "Smart City", the number of cameras installed in the city has shown explosive growth, followed by massive video data. How to scientifically and efficiently use these video data to analyze and generate valuable information has become an important research topic. It is of great research significance and practical value to search for pedestrian targets in video, and then realize the recognition and tracking of pedestrian targets in video. [0003] Pedestrian detection and face detection are common methods for searching pedestrian objects in videos. The purpose of Person Detection is to determine whether there are pedestrians in the image, and if there are pedestrians, return the position of the image area conta...

AI Technical Summary

Problems solved by technology

[0004] In the existing methods of pedestrian target search for video surveillance scenes, only face detection or pedestrian detection is applied, and the search effect is not ideal.

In an actual application scenario, when the camera is fixed, pedestrians are in motion, and due to changes in environmental conditions, occlusion, etc., high-quality faces may not be detected, and the search results cannot be further used for target tracking and identity verification applications.

Pedestrian detection only obtains the appearance information of the target, and does not have enough discrimination ability to complete further applications. For example, when performing identity verification, the identity information is often corresponding to the facial features, and the search results are obtained through pedestrian detection. and cannot be used for authentication

In general, in video surveillance scenarios, existing pedestrian search methods have single search results and poor robustness, and cannot provide reliable support for subsequent applications.

Images