Identifying Unobserved Road Regions in Bird’s-Eye View for Single-Vehicle Perception
- 13 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 2410-2417
Abstract
Visual Bird’s-Eye View (BEV) perception is a foundational paradigm in autonomous driving, enabling top-down semantic-spatial representations from multi-view inputs. However, current BEV methods struggle with occlusions, often generating hallucinated predictions in regions that are unobserved by the ego-vehicle. This mismatch between predictions and physical reality poses critical risks in safety-sensitive scenarios. To address this, we introduce a novel task: unobserved road segmentation, focusing on explicitly identifying road regions occluded from the ego-vehicle’s view. To tackle this task, we propose Polar Dual-Attention Cross-View Transformers (PDA-CVT), an efficient query-based framework that leverages polar-coordinate cross-view attention and local self-attention to improve occlusion reasoning efficiently. Additionally, an automated ground-truth generation process alleviates the need for manual annotation. Experimental results show that PDA-CVT outperforms existing methods in accurately segmenting unobservable road regions as well as conventional road layouts while maintaining efficiency. This work represents a critical step toward safer and more reliable autonomous driving through enhanced occlusion-aware perception.Keywords
This publication has 29 references indexed in Scilit:
- GraphBEV: Towards Robust BEV Feature Alignment for Multi-modal 3D Object Detection2024
- Learning Ego 3D Representation as Ray Tracing2022
- PETR: Position Embedding Transformation for Multi-view 3D Object Detection2022
- V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer2022
- PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark2022
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D2020
- End-to-End Object Detection with Transformers2020
- nuScenes: A Multimodal Dataset for Autonomous Driving2020
- Learning to Look around Objects for Top-View Representations of Outdoor Scenes2018
- Learning Motion Patterns in Videos2017