🤖 AI Summary
This paper addresses the challenge of automatically detecting close-pass events—instances where motor vehicles pass dangerously near cyclists—in cycling safety assessment. We propose a two-tier detection paradigm: scene-level detection (determining whether a near-miss event occurs) and instance-level detection (localizing the causative vehicle). We formally define cycling near-miss events for the first time and introduce Cyc-CP, the first open-source, dual-modal benchmark dataset comprising both synthetic and real-world video sequences. Our method integrates temporal action recognition with multi-object spatial relation modeling within an end-to-end supervised learning framework. On real-world data, our approach achieves 88.13% accuracy for scene-level detection and 84.60% for instance-level detection. All data, annotations, and models are publicly released to support reproducible interdisciplinary research at the intersection of road safety and intelligent transportation systems.
📝 Abstract
Cycling is a healthy and sustainable mode of transport. However, interactions with motor vehicles remain a key barrier to increased cycling participation. The ability to detect potentially dangerous interactions from on-bike sensing could provide important information to riders and policy makers. Thus, automated detection of conflict between cyclists and drivers has attracted researchers from both computer vision and road safety communities. In this paper, we introduce a novel benchmark, called Cyc-CP, towards cycling close pass near miss event detection from video streams. We first divide this task into scene-level and instance-level problems. Scene-level detection asks an algorithm to predict whether there is a close pass near miss event in the input video clip. Instance-level detection aims to detect which vehicle in the scene gives rise to a close pass near miss. We propose two benchmark models based on deep learning techniques for these two problems. For training and testing those models, we construct a synthetic dataset and also collect a real-world dataset. Our models can achieve 88.13% and 84.60% accuracy on the real-world dataset, respectively. We envision this benchmark as a test-bed to accelerate cycling close pass near miss detection and facilitate interaction between the fields of road safety, intelligent transportation systems and artificial intelligence. Both the benchmark datasets and detection models will be available at https://github.com/SustainableMobility/cyc-cp to facilitate experimental reproducibility and encourage more in-depth research in the field.
