Saved in:
Bibliographic Details
Main Authors: Wang, Meng, Noonan, Zach, Gershon, Pnina, Mehler, Bruce, Reimer, Bryan, Roberts, Shannon C.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.17886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912159621971968
author Wang, Meng
Noonan, Zach
Gershon, Pnina
Mehler, Bruce
Reimer, Bryan
Roberts, Shannon C.
author_facet Wang, Meng
Noonan, Zach
Gershon, Pnina
Mehler, Bruce
Reimer, Bryan
Roberts, Shannon C.
contents Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or vehicle kinematic features, but none have examined the combined influence of these factors. In this study, we term the integration of these features ``roadway complexity''. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating complexity-infused features. The second stage uses both original and complexity-infused features to predict crash likelihood, achieving an accuracy of 87.98\% with original features alone and 90.15\% with the added complexity-infused features. Ablation studies confirm that a combination of semantic, kinematic, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by the Large Language Model outperform those by Amazon Mechanical Turk, highlighting the potential of AI-based tools for accurate, scalable crash prediction systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17886
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Context of Crash Occurrence: A Complexity-Infused Approach Integrating Semantic, Contextual, and Kinematic Features
Wang, Meng
Noonan, Zach
Gershon, Pnina
Mehler, Bruce
Reimer, Bryan
Roberts, Shannon C.
Computer Vision and Pattern Recognition
Machine Learning
Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or vehicle kinematic features, but none have examined the combined influence of these factors. In this study, we term the integration of these features ``roadway complexity''. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating complexity-infused features. The second stage uses both original and complexity-infused features to predict crash likelihood, achieving an accuracy of 87.98\% with original features alone and 90.15\% with the added complexity-infused features. Ablation studies confirm that a combination of semantic, kinematic, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by the Large Language Model outperform those by Amazon Mechanical Turk, highlighting the potential of AI-based tools for accurate, scalable crash prediction systems.
title The Context of Crash Occurrence: A Complexity-Infused Approach Integrating Semantic, Contextual, and Kinematic Features
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.17886