Look to Locate: Vision-Based Multisensory Navigation with 3-D Digital Maps for GNSS-Challenged Environments

--In Global Navigation Satellite System (GNSS)- denied environments such as indoor parking structures or dense urban canyons, achieving accurate and robust vehicle positioning remains a significant challenge. This paper proposes a cost-effective, vision-based multi-sensor navigation system that integrates monocular depth estimation, semantic filtering, and visual map registration (VMR) with 3-D digital maps. Extensive testing in real-world indoor and outdoor driving scenarios demonstrates the effectiveness of the proposed system, achieving sub-meter accuracy 92% indoors and more than 80% outdoors, with consistent horizontal positioning and heading average root mean-square errors of approximately 0.98 m and 1.25 Compared to the baselines examined, the proposed solution significantly reduced drift and improved robustness under various conditions, achieving positioning accuracy improvements of approximately 88% on average. This work highlights the potential of cost-effective monocular vision systems combined with 3D maps for scalable, GNSS-independent navigation in land vehicles. OSITIONING is a cornerstone of autonomous driving, enabling vehicles to plan, control, and make decisions [1]. While global navigation satellite system (GNSS) technologies provide high accuracy positioning capabilities in open-sky environments [2], they become unreliable or even denied in environments such as dense urban areas, tunnels, and underground parking [3]. To compensate for GNSS limitations, some approaches employ high-resolution light detection and ranging (LiDAR)-based positioning systems [4] or integrate high-grade inertial navigation system (INS) [5]. Although these solutions can provide accurate and reliable positioning, their high cost hinders their practicality for consumer-level deployment. In contrast, cameras offer a cost-effective, lightweight, and widely available sensing modality. This research is supported by grants from the Natural Sciences and Engineering Research Council of Canada (NSERC) under grant numbers: RGPIN-2020-03900 and ALLRP-560898-20. Ola Elmaghraby and Paulo de Araujo are with the Department of Electrical and Computer Engineering, Queen's University, Kingston, ON K7L 3N6, Canada (e-mail: ola.elmaghraby.a@queensu.ca;