License-plate-information-free vehicle re-identification method and system, medium and video monitoring system

Abstract

The invention belongs to the technical field of image processing, and discloses a license-plate-information-free vehicle re-identification method and system, a medium and a video monitoring system, and the license-plate-information-free vehicle re-identification method comprises the steps: obtaining a data set, and carrying out the data set division and preprocessing; taking ResNet-50 which is trained in advance as a backbone network, and extracting a basic feature tensor; adding a channel attention mechanism and a space attention mechanism to obtain a new feature tensor; designing four relatively independent networks for extracting higher-level semantic features respectively; utilizing the cross entropy loss function and the triple loss function to train and optimize the vehicle overall network to obtain a training model; testing the test image by using the trained model to obtain a re-identification initial sorting result; sorting the initial sorting result again by using a resortingalgorithm; and visualizing the final sorting result. According to the license-plate-information-free vehicle re-identification method, the vehicle re-identification rate under the condition of no license plate information is effectively improved, and the vehicle re-identification accuracy based on no license plate information under a complex scene is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a vehicle re-identification method, system, medium and video monitoring system without license plate information. Background technique [0002] At present, the vehicle re-identification technology is a technology that matches the same vehicle target captured by different external conditions and different cameras in the video surveillance system. This work began at the end of the 20th century. The vehicle re-recognition method based on license plate information was first used. This method requires the positioning of the license plate, followed by character segmentation and recognition. At present, the positioning function is mainly realized by grayscale information, color and texture information and neural network-based methods, and the segmentation and recognition function is mainly realized by template matching and neural network methods. The vehicle re-ide...

AI Technical Summary

Problems solved by technology

[0005] (1) The traditional manual feature extraction is single and the accuracy is low

[0006] (2) Influenced by factors such as light intensity, object occlusion, and shooting angle of traditional technologies, the effectiveness of deep appearance features extracted by some deep learning methods is poor, making many existing deep learning-based vehicle re-identification technologies less accurate.

[0007] (3) Traditional technology ignores the importance of vehicle local features for re-identification accuracy

[0008] (4) The top-1 accuracy rate of traditional technology vehicle re-identification results is too much lower than the top-5 accuracy rate

Therefore, it is of great theoretical significance and practical value to study and solve the problem of low recognition accuracy caused by the high environmental complexity of the vehicle re-identification method based on no license plate information.

Images