Driver behavior identification method based on multi-scale attention convolutional neural network

Abstract

The invention discloses a driver behavior identification method based on a multi-scale attention convolutional neural network. The method comprises the following steps: (1) shooting an image data setfor driver behavior identification; (2) carrying out data enhancement on the shot driver behavior data set and simultaneously bringing samples obtained by enhancement into training data; (3) constructing a neural network model which comprises three modules, namely a multi-scale convolution module, an attention module and a classification module; (4) training a multi-scale attention convolutional neural network; using a Pytorch open source tool i for building a network model, and using a random gradient descent method for optimizing network parameters; and (5) testing the multi-column convolutional neural network. According to the invention, the multi-scale model and the attention mechanism are introduced into the driver behavior identification task to extract the behavior fine-grained feature representation with the distinction degree, so that the driver behavior identification accuracy can be further improved.

Description

technical field [0001] The invention relates to the technical fields of image processing and pattern recognition, in particular to a driver behavior recognition method based on a multi-scale attention convolutional neural network. Background technique [0002] In recent years, with the continuous improvement of technology and living standards, cars have entered thousands of households. At present, the number of cars in China has reached 325 million, second only to the United States. The popularity of automobiles has brought a lot of convenience to people's travel, but it has also caused potential hidden dangers to traffic safety. According to relevant statistics from the Ministry of Communications of China, there were 212,846 traffic accidents nationwide in 2017, resulting in 63,093 deaths, and more than 80% of the traffic accidents were closely related to the illegal driving behavior of drivers. Due to the weak awareness of traffic regulations, bad driving behaviors such a...

AI Technical Summary

Problems solved by technology

[0005] (2) Different drivers have different driving habits, for example, there are obvious differences in the way of holding the steering wheel

This makes the driver present a large intra-class variance in the image pose, and at the same time, the occlusion of light also makes it difficult for accurate recognition

Images