A real-time pedestrian detection and re-identification method and device

Abstract

The present invention provides a method and device for real-time pedestrian detection and re-identification, which are used for real-time monitoring of specific pedestrians in multiple video streams of pedestrians. Perform face detection to obtain pedestrian faces; use the similarity discrimination model to calculate the similarity between pedestrian faces and specific pedestrian face database faces to obtain the face similarity value; when the face similarity value is greater than the specific face threshold, The pedestrian’s face is a specific pedestrian’s face; cut out a screenshot of a specific pedestrian from the pedestrian video stream, and store it in correspondence with the corresponding ID to obtain a specific pedestrian database; use the target detection model to perform pedestrian detection to obtain the pedestrian to be recognized, and cut out the pedestrian to be recognized Pedestrian screenshots; based on the screenshots of the pedestrians to be identified and the specific pedestrian database, the pedestrian similarity value is calculated through the similarity discrimination model; when the pedestrian similarity value is greater than the predetermined specific pedestrian threshold, the pedestrian to be identified is a specific pedestrian.

Description

technical field [0001] The invention belongs to the field of data identification, and in particular relates to a real-time pedestrian detection and re-identification method and device. Background technique [0002] Target detection technology is mainly used to detect targets in images or videos, and the detection content includes the category of the target and the coordinates of the target. In recent years, the target detection algorithm based on deep learning has made great progress. The more popular algorithms can be divided into two categories. One is the R-CNN algorithm based on Region Proposal (including R-CNN, Fast R-CNN, FasterR-CNN, etc.), they are Two-stage algorithms, which need to generate target candidate frames in advance, and then classify and return the candidate frames. The other type is One-stage algorithms such as YOLO and SSD, which can use a convolutional neural network (CNN) to directly predict the categories and positions of different targets. The Two...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, a pedestrian re-identification method and device are provided to solve the problem of low pedestrian re-identification rate caused by pedestrians changing clothing accessories, seasonal dressing styles and other differences through real-time updated pedestrian database. The present invention Adopted the following technical solutions:

Images