A vehicle type recognition method based on a multi-feature fusion neural network and a processing terminal

Abstract

The invention relates to a vehicle type identification method based on a multi-feature fusion neural network and a processing terminal. The method comprises the following steps: 1, training a preset neural network by using a training algorithm to obtain parameters of the neural network so as to determine the trained neural network; 2, obtaining an original image including vehicle type feature, preprocessing that original image to obtain a first image consistent with a preset pixel size, and extracting local features from the original image by adopting an object detection algorithm to obtain asecond image including the local features; 3, taking that first image as the data layer of the network, inputting the second image as the rois of the region of interest of the network to the trained neural network for feature extraction, obtaining fusion feature, classifying the fusion features by using a classification algorithm, and obtaining a classification result of a vehicle type and a probability of a corresponding vehicle type. The invention can effectively solve the problem of identifying similar vehicle types and improve the accuracy of vehicle type identification.

Description

technical field [0001] The invention relates to the technical field of vehicle identification, in particular to a vehicle identification method and a processing terminal based on a multi-feature fusion neural network. Background technique [0002] In the fields of security, transportation, etc., although the license plate recognition technology is becoming more and more mature, sometimes it is still impossible to accurately identify the license plate number due to reasons such as false license plates and blurred license plates, which brings troubles to related work, especially for This is especially true for public security. When the license plate cannot be recognized, it is also a known and commonly used technical means to identify it by means of the vehicle type. Car model recognition is a mixed recognition problem of coarse-grained and fine-grained. For example, the car model features of different brands of vehicles are very different, and the car model features of the sa...

AI Technical Summary

Problems solved by technology

[0002] In the fields of security, transportation, etc., although the license plate recognition technology is becoming more and more mature, sometimes it is still impossible to accurately identify the license plate number due to reasons such as false license plates and blurred license plates, which brings troubles to related work, especially for For the public security, this is even more so. In the case that the license plate cannot be recognized, it is also a known and commonly used technical means to use the vehicle model to identify it.

Car model recognition is a mixed recognition problem of coarse-grained and fine-grained. For example, the car model features of different brands of vehicles are very different, and the car model features of the same brand and the same car series are very different. There are thousands of common car models, and the sample distribution is extremely unbalanced. It is easy to make mistakes in the recognition of similar car models, and the recognition rate needs to be further improved.

Images