Pedestrian re-identification method based on generative adversarial network image super-resolution technology

Abstract

The invention discloses a pedestrian re-identification method based on a generative adversarial network image super-resolution technology. The method includes the following steps: utilizing a Laplace pyramid generative adversarial network to generate a group of clear images, utilizing local maximum event expression and a Dense Correspondences algorithm to separately extract HSV color features, texture features and LAB color features of the images, carrying out fusion on the features, utilizing a cross vision quadratic discriminant analysis algorithm to conduct metric learning on the features, utilizing a Manhattan distance to calculate the distance between a probe set and a gallery set, and finally utilizing a multi-shot mode to carry out 1:N and N:N evaluation. A LAPGAN network is utilized to generate high-resolution image, and then a conventional method is utilized to obtain the features of the images and carry out corresponding matching. Deeping learning and the conventional method are combined to solve the problem of low image resolution caused by illumination, angle and other reasons, and an image matching rate is increased.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, in particular to a pedestrian re-identification method based on a generative confrontation network image super-resolution technology. Background technique [0002] Most of the current monitoring systems adopt the form of real-time shooting and manual monitoring, requiring the monitoring personnel to stare at the monitoring screen all the time and carefully distinguish the events in the video, but in fact it is difficult for human beings to be so meticulous, and there are omissions in the way of manual viewing and subjective errors. Considering the growing scale of surveillance video, the traditional method requires a lot of manpower, high cost, and low efficiency. Therefore, there is an urgent need for convenient and quick methods to improve the current surveillance shortage. Pedestrian re-identification is a multi-camera non-overlapping video surveillance environment, thro...

AI Technical Summary

Problems solved by technology

At present, pedestrian re-identification technology usually extracts features based on information such as pedestrian color and texture in images or videos. However, due to factors such as illumination, shooting angle, and occlusion, the resolution of pedestrians in images or videos is low, and the same person appears in different cameras. Large gap in characteristics

Images