Pedestrian re-identification method, pedestrian re-identification system, pedestrian re-identification device and storage medium

Abstract

The invention discloses a pedestrian re-identification method, a pedestrian re-identification system, a pedestrian re-identification device and a storage medium. The method comprises the steps of firstly, training an auto-encoder model by utilizing a pedestrian image database, optimizing a weight matrix, and obtaining an optimal model; calculating the feature score of each image by using the weight matrix of the hidden layer of the trained model, and sorting the features from high to low according to the scores to obtain high-score features; and 3, fusing the first three features of the scorein parallel to obtain the fusion feature with strong expression capability and low dimension; and finally, querying the similarity between the image and one target sequence in a database, and sortingaccording to the similarity from high to low to obtain an optimal matching result. Through the combination of the self-coding unsupervised feature selection and the parallel feature fusion, the unsupervised pedestrian re-identification is realized, the manpower and material resource input can be reduced, and the target searching task efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of intelligent video monitoring, in particular to a pedestrian re-identification method based on map and self-encoder unsupervised feature selection and its system, device and storage medium. Background technique [0002] With the improvement of people's living standards, the people's demand for public safety is increasing, and the heat of public place safety issues continues to rise. Among them, the use of cameras combined with human eye recognition and monitoring to report crimes and hunt down suspects has become one of the hot spots. [0003] The current recognition method relies on human eye recognition, which cannot meet the needs of practical applications. There are the following problems: First, in actual work, one person is often responsible for multiple monitoring areas at the same time, which exceeds the limit of ordinary humans, resulting in missed detection and false detection. . Second, long-t...

AI Technical Summary

Problems solved by technology

[0003] The current recognition method relies on human eye recognition, which cannot meet the needs of practical applications. There are the following problems: First, in actual work, one person is often responsible for multiple monitoring areas at the same time, which exceeds the limit of ordinary humans, resulting in missed detection and false detection.

Second, long-term identification work is harmful to the human body

Concentrating on observing the electronic screen for a long time will lead to visual fatigue, which in turn will cause vision loss. Whether it is visual fatigue or myopia, it is not conducive to investigation

Third, the labor

Images