Real-time Accident Anticipation for Autonomous Driving Through Monocular Depth-Enhanced 3D Modeling

TL;DR

This paper presents AccNet, a real-time accident anticipation framework for autonomous driving that leverages monocular depth cues and a novel loss function to improve early prediction accuracy in traffic scenarios.

Contribution

The study introduces a monocular depth-enhanced 3D modeling framework and a Binary Adaptive Loss for Early Anticipation, advancing accident prediction capabilities over existing 2D methods.

Findings

Outperforms state-of-the-art methods on multiple datasets

Achieves higher Average Precision (AP) and earlier detection times

Demonstrates robustness across diverse traffic scenarios

Abstract

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).