Vehicle re-identification method, electronic equipment and related product

Abstract

The embodiment of the invention discloses a vehicle re-identification method, electronic equipment and a related product, the method is applied to the electronic equipment, and the method comprises the steps: inputting a first query image and a first base library image into a preset style conversion model, and obtaining a second query image and a second base library image; inputting the first vehicle training data into a preset style conversion model to obtain second vehicle training data; training a first feature extraction network through the first vehicle training data and the second vehicle training data to obtain a second feature extraction network; inputting the second query image into a second feature extraction network for feature extraction to obtain query image features; inputting the second base library image into a second feature extraction network for feature extraction to obtain a base library image feature; and matching the query image features with the base library image features to obtain a matching result, and displaying the matching result. According to the embodiment of the invention, the vehicle re-identification accuracy can be improved.

Description

technical field [0001] This application relates to the technical field of image processing, in particular to a vehicle re-identification method, electronic equipment and related products. Background technique [0002] Vehicle re-identification refers to given a vehicle image to identify the same vehicle in the vehicle image database. In a real traffic monitoring system, vehicle re-identification can play a role in positioning, monitoring, and criminal investigation of the target vehicle. There are usually multiple cameras in vehicle re-identification tasks, and due to various factors (environment, light, etc.), the image style captured by each camera of the same vehicle is usually different. In addition, even the same camera will capture images of different styles due to the time of day (morning, noon, afternoon, etc.). Therefore, the style of the image will change, which has a great influence on the final result of the vehicle re-identification task. In addition, the chan...

AI Technical Summary

Problems solved by technology

Therefore, the style of the image will change, which has a great influence on the result of the final vehicle re-identification task

In addition, the change of the relative position between the camera and the vehicle will cause the same vehicle to appear in different angles in different images, and the appearance of the vehicle has significant changes. In addition, because vehicles with different identities can have the same brand, model and Color, extracting discriminative features is very critical to the task of vehicle re-identification, and how to improve the accuracy of vehicle re-identification in real traffic monitoring scenarios needs to be solved urgently

Images