Video-Based Abnormal Driving Behavior Detection via Deep Learning Fusions

Abstract

Video-based abnormal driving behavior detection is becoming more and more popular for the time being, as it is highly important in ensuring safeties of drivers and passengers in the vehicle, and it is an essential step in realizing automatic driving at the current stage. Thanks to recent developments in deep learning techniques, this challenging detection task can be largely facilitated via the prominent generalization capability of sophisticated deep learning models as well as large volumes of video clips which are indispensable for thoroughly training these data-driven deep learning models. In this paper, deep learning fusion techniques are emphasized, and three novel deep learning-based fusion models inspired by the recently proposed and popular densely connected convolutional network (DenseNet) are introduced, to fulfill the video-based abnormal driving behavior detection task for the first time. These three new deep learning-based fusion models are named as the wide group densely (WGD) network, the wide group residual densely (WGRD) network, and the alternative wide group residual densely (AWGRD) network, respectively. Technically, WGD takes important issues of deep learning models, i.e., the depth, the width and the cardinality, into consideration when designing its model structure based on DenseNet. For the WGRD and AWGRD, they are more sophisticated as the important idea of residual networks with superpositions of previous layers is incorporated. The extensive experiments are conducted to verify the effectiveness of three new models. Their superiority has been suggested based on rigorous comparisons towards several popular deep learning models in this video-based abnormal driving behavior detection study.