Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916379241742336 |
|---|---|
| author | Liao, Haicheng Li, Yongkang Wang, Chengyue Lai, Songning Li, Zhenning Bian, Zilin Lee, Jaeyoung Cui, Zhiyong Zhang, Guohui Xu, Chengzhong |
| author_facet | Liao, Haicheng Li, Yongkang Wang, Chengyue Lai, Songning Li, Zhenning Bian, Zilin Lee, Jaeyoung Cui, Zhiyong Zhang, Guohui Xu, Chengzhong |
| contents | The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances the prediction capabilities beyond the current state-of-the-art (SOTA) 2D-based methods by incorporating monocular depth cues for sophisticated 3D scene modeling. Addressing the prevalent challenge of skewed data distribution in traffic accident datasets, we propose the Binary Adaptive Loss for Early Anticipation (BA-LEA). This novel loss function, together with a multi-task learning strategy, shifts the focus of the predictive model towards the critical moments preceding an accident. {We rigorously evaluate the performance of our framework on three benchmark datasets--Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D), and DADA-2000 Dataset--demonstrating its superior predictive accuracy through key metrics such as Average Precision (AP) and mean Time-To-Accident (mTTA). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01256 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling Liao, Haicheng Li, Yongkang Wang, Chengyue Lai, Songning Li, Zhenning Bian, Zilin Lee, Jaeyoung Cui, Zhiyong Zhang, Guohui Xu, Chengzhong Computer Vision and Pattern Recognition Artificial Intelligence The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that is pivotal for enhancing the safety and reliability of autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances the prediction capabilities beyond the current state-of-the-art (SOTA) 2D-based methods by incorporating monocular depth cues for sophisticated 3D scene modeling. Addressing the prevalent challenge of skewed data distribution in traffic accident datasets, we propose the Binary Adaptive Loss for Early Anticipation (BA-LEA). This novel loss function, together with a multi-task learning strategy, shifts the focus of the predictive model towards the critical moments preceding an accident. {We rigorously evaluate the performance of our framework on three benchmark datasets--Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D), and DADA-2000 Dataset--demonstrating its superior predictive accuracy through key metrics such as Average Precision (AP) and mean Time-To-Accident (mTTA). |
| title | Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.01256 |