Vehicle identity recognition model construction method and system based on deep learning and vehicle identity recognition method and system based on deep learning

Abstract

The invention belongs to the technical field of computer vision, and relates to a vehicle identity recognition model construction and recognition method and a system based on deep learning. Firstly, large-scale road monitoring pictures are used for carrying out model training of vehicle detection, and a multi-loss function staged joint training strategy is adopted for training; then, part extraction is carried out on the detected vehicle face image, and classification is carried out through a feature extraction and fusion network or a common classification network according to the vehicle facepart extraction situation; and finally, the identity feature vector of the vehicle face is extracted and filtered by using a multi-task network, and similarity measurement is performed on the featureof the image to be analyzed and the feature vector of the image in the vehicle information base to obtain a vehicle identity recognition result. According to the deep learning network framework provided by the invention, the feature extraction capability of the network model in different aspects can be improved according to requirements, so that the optimal model expression capability is realized, and the identification feature vector with significant discrimination is convenient to extract.

Description

technical field

[0001] The invention belongs to the technical field of computer vision, and more specifically, relates to a vehicle identity recognition model construction and recognition method and system based on deep learning. Background technique

[0002] In recent years, the computer vision theory based on neural network and machine learning has been redefined and developed qualitatively, breaking through the limitations of manual design and the traditional image feature extraction scheme with insufficient robustness, through multi-layer convolution pooling extraction The high-dimensional features fit a large amount of training data and regress the most suitable feature scheme to solve the problem. As a result, a large number of high-efficiency, strong applicability, and easy-to-adapt application examples have emerged in the field of computer vision. License plate recognition is one of the more mature applications with high value. It is widely used in traffic checkpoint...

Images