aiqbench analysis
This research advances autonomous driving perception by fusing camera and radar data with physics-guided ray tracing to solve the complex problem of localizing pedestrians hidden from direct view. The framework's ability to reconstruct distorted reflection paths in dynamic outdoor environments represents a significant step toward safer urban mobility systems.
Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization
arXiv:2609.27346v1 Announce Type: new Abstract: Reliable localization of non-line-of-sight (NLOS) pedestrians is critical for safe urban autonomous driving, yet it remains highly challenging in ego-dynamic outdoor environments, where ego-vehicle motion makes radar multipath propagation complex and noisy. In this paper, we present a reflection-aware framework for NLOS pedestrian localization with a moving ego-vehicle in outdoor testbed scenarios. Our framework fuses front-view camera images and 2D radar point clouds to infer reflection orders and reflective surface distributions in bird's-eye-view space. It then uses physics-guided ray tracing to reconstruct distorted reflection paths and localize the hidden pedestrian. We validate the framework in outdoor testbed scenarios under ego-dynamic conditions. The results demonstrate the effectiveness of the proposed framework for NLOS pedestrian localization with a moving ego-vehicle.
Abstract:Reliable localization of non-line-of-sight (NLOS) pedestrians is critical for safe urban autonomous driving, yet it remains highly challenging in ego-dynamic outdoor environments, where ego-vehicle motion makes radar multipath propagation complex and noisy. In this paper, we present a reflection-aware framework for NLOS pedestrian localization with a moving ego-vehicle in outdoor testbed scenarios. Our framework fuses front-view camera images and 2D radar point clouds to infer reflection orders and reflective surface distributions in bird's-eye-view space. It then uses physics-guided ray tracing to reconstruct distorted reflection paths and localize the hidden pedestrian. We validate the framework in outdoor testbed scenarios under ego-dynamic conditions. The results demonstrate the effectiveness of the proposed framework for NLOS pedestrian localization with a moving ego-vehicle.
Robotics (cs.RO)
arXiv:2609.27346 [cs.RO]
(or arXiv:2609.27346v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.27346 arXiv-issued DOI via DataCite (pending registration)
Park, Byeonggyu, Mingu Jeon, and Seong-Woo Kim. "Reflection-Aware Reasoning for Non-line-of-Sight Pedestrian Localization." European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2026
https://doi.org/10.1007/978-3-032-37356-4_7 DOI(s) linking to related resources
Full text under the publisher's open licence · 164 words
