Self-adaptive method for searching co-tour persons in scenic area

Abstract

The invention provides a self-adaptive method for searching co-tour persons in a scenic area, and the method comprises the following steps: 1, obtaining a pedestrian image of a person who reports a case; 2, searching a case reporting person in a pedestrian image database; 3, retrieving missing persons in the video frames containing the case reporting persons extracted in the step 2, and displaying the retrieved video frames; step 4, extracting pedestrian images of missing persons from the confirmed images; 5, retrieving missing persons in the pedestrian image database; 6, monitoring all the cameras in real time; 7, if the case reporting person requires to stop searching the person; and 8, ending. The beneficial effects of the invention are that the self-adaptive method is provided, and the missing person and pedestrian images are converted into different modes for matching the pedestrian images captured by the camera in the daytime and at night, so that the method can search people in the daytime environment and the night environment, and the application range of the method for searching people in the scenic spot is expanded.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence and computer vision, in particular to an adaptive method for finding fellow travelers in scenic spots. Background technique [0002] Touring scenic spots is one of people's leisure and entertainment methods, which can not only increase knowledge, but also help to strengthen the body. Most of the existing people-finding methods in scenic spots are based on manual search and face recognition, and the application environment is mostly daytime with good lighting environment. [0003] The methods of manual search include posting missing person information and querying surveillance video. Broadcasting missing person information includes posting missing person notices in scenic spots, distributing missing person leaflets, or disseminating missing person information by broadcasting or the Internet. The method of querying the surveillance video can accomplish two tasks: one is for the se...

AI Technical Summary

Problems solved by technology

At the same time, it is a difficult problem for all cameras to obtain clear images of faces

The face recognition method needs to point the camera at the entrance to shoot. After collecting clear face images, the final number of people is determined according to the similarity of face features, but this method cannot cover the entire scenic spot.

Moreover, some scenic spots have nocturnal activities, and most existing tracing schemes in scenic spots cannot effectively complete the task of tracing people at night

Images