期刊
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
卷 23, 期 9, 页码 15605-15615出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2022.3142672
关键词
Feature extraction; Accidents; Task analysis; Object detection; Detectors; Data mining; Roads; Unsafe maneuver classification; road scene understanding; dashcam; GPS; IMU; deep learning; attention; XAI
In this paper, a novel deep learning architecture is proposed to classify unsafe driving maneuvers using dashcam and IMU data. The architecture combines object detection algorithm output with raw video frames and GPS/IMU data, and utilizes a Spatio-Temporal Attention Selector (STAS) module to extract and select features for classification. Experimental results show that the proposed method outperforms other approaches applying attention over single frames.
In this paper, we propose a novel deep learning architecture to classify unsafe driving maneuvers from dashcam and IMU data. Such architecture processes the output of an object detection algorithm in combination with raw video frames and GPS/IMU data. At the core of the architecture there is a novel Spatio-Temporal Attention Selector (STAS) module, which (1) extracts features describing the evolution of each object in the scene over time and (2) leverages multi-head dot product attention to select the relevant ones, i.e., the dangerous ones or the ones in danger, to perform classification. We also introduce a simple but effective methodology to increase the benefit of fine-tuning the backbone network. Our method is shown to achieve higher performance than other approaches in the literature applying attention over single frames.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据