An Effective Deep Learning Framework for Detecting Misconduct of the Trucker

Abstract

The traffic risks include malfunction of gears in the vehicle and some human misconducts while on the road. These misconducts of driver contain using the mobile phone, smoking, watching videos, reading books, and so forth. To prevent drivers from danger, in this paper, we will present an effective system to detect whether the drivers are doing those behaviors while driving by using the deep learning technologies. The proposed system adopts two different neural network architectures to improve its accuracy rate that are multilayer perceptron (MLP) and convolutional neural network (CNN). As expected, by training the video data from cameras installed in the truck, the proposed system could possibly distinguish the misconduct if the drivers are doing danger behaviors. The result of this paper shows that the proposed system practically provides a solution to recognize misconducts of the trucker with 90% accuracy of detecting abnormal situations.