Low-Cost Urban Road Mapping Via Dual-View Fusion of Panoramic Images

Abstract

High-definition (HD) road maps are critical for autonomous navigation and intelligent transportation systems. However, single front-view pipelines suffer from unilateral occlusions and a narrow field of view (FoV), whereas conventional multi-sensor bird's-eye-view (BEV) systems improve coverage at the cost of increased hardware requirements, calibration complexity, and computation. This work addresses the problem of achieving robust, wide-coverage HD mapping under urban occlusions using a single, low-cost panoramic camera. A lightweight dual-view fusion framework is introduced for incremental road mapping from panoramic images. The method introduces three technical contributions: (1) a single-sensor dual-view construction that extracts front and rear perspective views from one panoramic camera via FoV-aware projection; (2) a geometry-consistent BEV fusion module that integrates inverse perspective mapping (IPM), pose-stabilized stitching, and patch-level merging to suppress parallax and motion jitter while recovering markings occluded in one view but visible in the other; and (3) a lightweight incremental pipeline that reduces deployment and inter-sensor calibration overhead relative to ring-camera systems. Experiments on a self-built dataset of 80 test panoramas with five road-element classes under unilateral or moderate occlusion show that dual-view fusion improves marking completeness by 33.3%, reduces geometric deviation (PSC) by 26.7%, and improves shape regularity (RARC) by 7.7% over a front-view-only baseline. The results support panoramic dual-view fusion as a practical low-cost compromise between limited single-view coverage and high-complexity multi-sensor platforms.