Exploring Driving Behavior for Autonomous Vehicles Based on Gramian Angular Field Vision Transformer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: You, Junwei, Chen, Ying, Jiang, Zhuoyu, Liu, Zhangchi, Huang, Zilin, Ding, Yifeng, Ran, Bin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914930416943104
author You, Junwei
Chen, Ying
Jiang, Zhuoyu
Liu, Zhangchi
Huang, Zilin
Ding, Yifeng
Ran, Bin
author_facet You, Junwei
Chen, Ying
Jiang, Zhuoyu
Liu, Zhangchi
Huang, Zilin
Ding, Yifeng
Ran, Bin
contents Effective classification of autonomous vehicle (AV) driving behavior emerges as a critical area for diagnosing AV operation faults, enhancing autonomous driving algorithms, and reducing accident rates. This paper presents the Gramian Angular Field Vision Transformer (GAF-ViT) model, designed to analyze AV driving behavior. The proposed GAF-ViT model consists of three key components: GAF Transformer Module, Channel Attention Module, and Multi-Channel ViT Module. These modules collectively convert representative sequences of multivariate behavior into multi-channel images and employ image recognition techniques for behavior classification. A channel attention mechanism is applied to multi-channel images to discern the impact of various driving behavior features. Experimental evaluation on the Waymo Open Dataset of trajectories demonstrates that the proposed model achieves state-of-the-art performance. Furthermore, an ablation study effectively substantiates the efficacy of individual modules within the model.
format Preprint
id arxiv_https___arxiv_org_abs_2310_13906
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exploring Driving Behavior for Autonomous Vehicles Based on Gramian Angular Field Vision Transformer
You, Junwei
Chen, Ying
Jiang, Zhuoyu
Liu, Zhangchi
Huang, Zilin
Ding, Yifeng
Ran, Bin
Computer Vision and Pattern Recognition
Image and Video Processing
Effective classification of autonomous vehicle (AV) driving behavior emerges as a critical area for diagnosing AV operation faults, enhancing autonomous driving algorithms, and reducing accident rates. This paper presents the Gramian Angular Field Vision Transformer (GAF-ViT) model, designed to analyze AV driving behavior. The proposed GAF-ViT model consists of three key components: GAF Transformer Module, Channel Attention Module, and Multi-Channel ViT Module. These modules collectively convert representative sequences of multivariate behavior into multi-channel images and employ image recognition techniques for behavior classification. A channel attention mechanism is applied to multi-channel images to discern the impact of various driving behavior features. Experimental evaluation on the Waymo Open Dataset of trajectories demonstrates that the proposed model achieves state-of-the-art performance. Furthermore, an ablation study effectively substantiates the efficacy of individual modules within the model.
title Exploring Driving Behavior for Autonomous Vehicles Based on Gramian Angular Field Vision Transformer
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2310.13906