Accident Prediction Model Using Divergence Between Visual Attention and Focus of Expansion in Vehicle-Mounted Camera Images

Recently, accident prediction models, which predict the occurrence of traffic accidents through deep learning algorithms have been proposed. The application of these models demands both high precision and visualization of the decision basis applied. Current models use the motion features of objects...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2023, Vol.11, p.140116-140125
Main Authors: Maruyama, Yuta, Ohashi, Gosuke
Format: Article
Language:English
Subjects:
Accidents
Algorithms
Categories
Data models
Datasets
Deep learning
driver visual attention
Feature extraction
focus of expansion
Machine learning
Performance prediction
Prediction models
Predictive models
Risk factors
traffic accident prediction
Traffic accidents
Traffic accidents & safety
Traffic control
Vehicle safety
Visual aspects
Visualization
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, accident prediction models, which predict the occurrence of traffic accidents through deep learning algorithms have been proposed. The application of these models demands both high precision and visualization of the decision basis applied. Current models use the motion features of objects in the surrounding environment, but they do not predict well when the motion feature of the risk factor is small. Meanwhile, drivers can avoid accidents because they utilize visual attention functions. This study focuses on the divergence between visual attention and focus of expansion (FOE), which are highly correlated in normal driving situations, as the basis for an accident prediction method. The proposed model can visualize decision basis with high accuracy, even when the motion feature of the risk factors is small, by combining it with Dynamic-Spatial-Attention, a deep-learning-based accident prediction method. In this experiment, we classified data from the Dashcam Accident Dataset, a widely used accident dataset, into categories of accidents. Using the Dashcam Accident Dataset, the proposed method achieves higher accident prediction performance in categories for which the motion feature of risk factors tends to be small while maintaining the same accident prediction performance as achieved by the baseline Dynamic-Spatial-Attention method in categories for which the motion feature of risk factors tends to be large. In addition, the proposed method visualizes the risk factors using visual attention and FOE to provide a visual explanation of the decision basis.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2023.3339855