Vehicle re-identification method based on capsule network

Abstract

The invention relates to a vehicle re-identification method based on a capsule network, and the method comprises the steps: obtaining a vehicle image data set, and dividing the vehicle image data set into a training set and a test set; constructing a capsule network model for vehicle re-identification; optimizing the capsule network model through a vehicle image in a training set; inputting a to-be-identified vehicle image and a vehicle image in a test set into the optimized capsule network model: firstly calculating feature vectors of the to-be-identified vehicle image and the vehicle image in the test set, then comparing the feature vectors of the to-be-identified vehicle image and the vehicle image in the test set, and calculating corresponding similarity; and finally, outputting a matching result according to high-low ranking of the similarities. According to the vehicle re-identification method based on the capsule network, the problems that a convolutional neural network cannot extract spatial position information and feature vectors are not aligned during feature matching can be effectively solved, so that the identification precision of vehicle re-identification can be improved.

Description

technical field [0001] The invention relates to the technical field of vehicle monitoring and tracking, in particular to a capsule network-based vehicle re-identification method. Background technique [0002] In recent years, smart cities and smart transportation have developed rapidly. Vehicles are an integral part of smart transportation, and vehicle re-identification is one of the core technologies of smart transportation. Vehicle re-identification refers to finding the same vehicle captured by other cameras given a vehicle image. The vehicle re-identification problem can be regarded as a sub-problem of image retrieval. Vehicle re-identification technology has certain practical value for road traffic video surveillance and traffic law enforcement departments. For example, it can quickly discover and locate the movement information of illegal vehicles in the monitoring area, so as to carry out relevant arrests or other processing, and improve the work of law enforcement of...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the above-mentioned prior art, the technical problem to be solved by the present invention is: how to provide a vehicle weight based on capsule network that can effectively overcome the problem that the convolutional neural network cannot extract spatial position information and feature vectors are not aligned during feature matching. Recognition method, so as to improve the recognition accuracy of vehicle re-identification

Images