Boosting Rare Scenario Perception in Autonomous Driving: An Adaptive Approach With MoEs and LoRA

Y Li, Y Lin, L Zhong, R Yin, Y Ji… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
Autonomous driving technology has achieved remarkable advancements, offering
substantial potential to revolutionize traffic safety and smart mobility. However, when faced …

Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis

J Guo, M Wang, I Ilyankou, N Jongwiriyanurak… - arXiv preprint arXiv …, 2024 - arxiv.org
Panoramic cycling videos can record 360 {\deg} views around the cyclists. Thus, it is
essential to conduct automatic road user analysis on them using computer vision models to …

Hazards Prioritization With Cognitive Attention Maps for Supporting Driving Decision-Making

Y Huang, X Wang - IEEE Transactions on Intelligent …, 2024 - ieeexplore.ieee.org
Autonomous vehicles and driver assistance systems achieve satisfactory perception of
surroundings but lack cognitive capabilities to conduct knowledge-based risk assessment …

Leveraging Deep Learning and Multimodal Large Language Models for Near-Miss Detection Using Crowdsourced Videos

S Jaradat, M Elhenawy, HI Ashqar… - IEEE Open Journal of …, 2025 - ieeexplore.ieee.org
Near-miss traffic incidents, positioned just above" unsafe acts" on the safety triangle theory,
offer crucial predictive insights for preventing crashes. However, these incidents are often …

Machine Learning for Identifying Pedestrians and Vehicles in Low-Light Images: A Survey

S Sabaria, J Thangakumar - 2024 5th International Conference …, 2024 - ieeexplore.ieee.org
Pedestrian detection has applications in many areas, like autonomous vehicles, surveillance
systems, and robotics. This is quite a challenging problem in real-world scenarios, for …

[PDF][PDF] My Precious Crash Data: Barriers and Opportunities in Encouraging Autonomous Driving Companies to Share Safety-Critical Data

H SANDHAUS, AHCHI HWANG, W JU, Q YANG - haukesand.github.io
To date, AV companies rarely share safety-critical data externally. While policies mandate
sharing specific types of AV safety-critical data, companies rarely share beyond the minimal …

[引用][C] Semantic Editing of Traffic Near-Miss and Accident Dataset Using Tune-A-Video

EA Kusnanti, C Fatichah, HMA Pradana - IPTEK The Journal for Technology and …, 2025