Lightweight Dangerous Driving Action Recognition Using Graph Convolutional Broad Learning

The dangerous driving action seriously affects traffic safety and may cause severe road disasters. Dangerous driving action recognition in Internet of Vehicles (IOV) has been widely exploited to reduce traffic accident risks by discovering and then transmitting the recognition results to autonomous machines or other vehicles. General action recognition models using deep learning networks usually have a large number of parameters and require a significant amount of memory and computational power, which cannot meet the lightweight and real-time requirements of action recognition models deployed on resource-limited onboard devices, e.g., vehicles. As a result, we introduce the broad learning system (BLS) into onboard dangerous driving action recognition tasks, classify actions based on skeleton data, and design the graph convolutional representation (GCR) algorithm and graph convolutional broad learning system (GCBLS) classification model to speed up the recognition process. We verified through ablation experiments that the GCR algorithm can effectively represent skeleton data and improve classification accuracy datasets. In addition, comparative experiments in State Farm and Driver Skeleton datasets show that the GCBLS model has the characteristics of lightweight, real-time, and high accuracy. We also designed a workflow for "noise" caused by poor pose estimations in practical applications, then deployed the proposed workflow on onboard devices, which can run at speeds above 27 FPS with high accuracy, which proves the effectiveness and practicability of our proposed algorithms and models for IOV.