Skip to content

Reflection-Aware Reasoning for Non-line-of-Sight Pedestrian Localization

Document Type
Publications · Conference Paper
Registered DB
Scopus
Journal Ranking
Scopus Q3
Journal
Lecture Notes in Computer Science17051 LNCS · pp.111 · 2026
Citation
Scopus 0
ISSN
0302-9743

Authors

  1. Park, ByeonggyuFirst authorSeoul National University, Seoul, Republic of Korea
  2. jeon, minguCorresponding authorPusan National University, Busan, Republic of Korea
  3. Kim, Seong-WooCorresponding authorSeoul National University, Seoul, Republic of Korea

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.

Keywords

collision avoidancemmWave radarmultimodal perceptionmultipath reflectionsNLOS perceptionpedestrian localization

Identifiers

Scopus EID
2-s2.0-105052136090