Framework for low-cost indoor smartphone camera-based localization using spherical panorama and BIM

Abstract

Abstract-This article presents a cost-effective framework for indoor localization that integrates spherical panoramas, smartphone cameras, and building information modeling (BIM). We propose two methods for panorama pose estimation: panorama pose estimation via attribute matching (PPEAM) and panorama pose estimation via genetic algorithm (PPE-GA). PPE-AM provides an initial pose estimate by matching attributes extracted from the panorama with those rendered from the BIM. PPE-GA refines this estimate using a genetic algorithm (GA) that aligns semantic and depth maps. Our approach eliminates the need for premapping and on-site data collection, offering a practical alternative to expensive solutions such as spherical panorama localization based on point cloud or 3-D line maps. Experimental results in a typical indoor environment demonstrate the system’s accuracy, with PPE-AM achieving a mean 3-D error of 0.74 m, and PPE-GA further improving it to 0.47 m. Smartphone pose estimation (SPE), leveraging the localized panoramas, achieved a mean 3-D error of 0.92 m. The proposed framework offers a robust and scalable solution for accurate indoor localization, with potential applications in augmented reality, facility management, and digital twin technologies.