Vehicle attribute identification method based on multi-task convolutional neural network

Abstract

The invention provides a vehicle attribute identification method based on a multi-task convolutional neural network. The method comprises a training process and an identification process. Particularly the method comprises the steps of acquiring a picture of a to-be-identified vehicle, designing a multi-task convolutional neural network structure and training a network model vehicle attribute identification, identifying a vehicle model and returning vehicle window position coordinate of the vehicle, designing a vehicle image mask and generating a new vehicle image, extracting a multi-task convolutional neural network characteristic of the new vehicle image, training an SVM classification model, and identifying vehicle color. The vehicle attribute identification method is advantageous in that manual characteristic definition and re-classification by a user are not required; the multi-task convolutional neural network structure can simultaneously receive and process a plurality of tasks; and furthermore based on the multi-task convolutional neural network, structure information of the vehicle in the vehicle image is acquired for realizing an effective vehicle color identification method and improving identification accuracy, thereby supplying accurate basis for intelligent traffic.

Description

technical field [0001] This application relates to the field of intelligent transportation systems and computer vision technology, and in particular to a method for recognizing vehicle types and vehicle colors based on multi-task convolutional neural networks. Background technique [0002] At present, when identifying specific content in a picture, the following steps are usually included: [0003] The first step is to detect the position of the object of interest in the picture. For example, if you want to identify the attributes of the vehicle, you need to use a detector to detect the car from the picture. The output of the detector is that the car is in the picture. coordinates in [0004] The second step is to cut the car from the original picture according to the coordinate position, and put the cut picture into the classifier, and the output result of the classifier is the recognition result of the car. [0005] In the second step, the input original image pixel valu...

AI Technical Summary

Problems solved by technology

[0008] The embodiment of the present application proposes a vehicle attribute recognition method based on a multi-task convolutional neural network to solve the technical problem of low recognition accuracy of image recognition methods in the prior art

Images