Smartphone Sensors-Based Abnormal Driving Behaviors Detection: Serial-Feature Network

Abstract

One of the important factors leading to traffic accidents is the abnormal driving behavior of drivers. Early detection of abnormal driving behaviors can effectively reduce the occurrence of traffic accidents. At present, most of the mainstream driving behavior detection methods are based on the data of a single moment, which separates the continuity of driving behavior. In this article, a driving behavior recognition algorithm based on Serial-Feature Network (SF-Net) and smart phone inertial sensor is proposed, which fully considers the continuity of driving events and uses adjacent multi time data to identify driving status. The data used in this article are collected from GPS data, 3-axis acceleration and gyroscope data of smart phone. Through the preprocessing operation, SF-net makes the input vector not only contain the current sensor data, but also fuse the relevant information of adjacent time. In SF-net, deep convolution neural network is used for feature extracting, and 10 different driving behaviors can be identified by fusing multi-level and multi-time feature information. The field test results show that the accuracy rate of the serial feature network is 97.1%, and the recall rate is 98.4%, which is better than other test network models. When the number of training samples is small, the sequential feature network can still maintain a high recognition rate, and the network model is relatively stable.