Semantic 3D Map Change Detection and Update based on Smartphone Visual Positioning System
This addresses the need for efficient and cost-effective map updates in applications like augmented reality and robotics, though it appears incremental by building on existing 3D maps and methods.
The paper tackles the problem of updating 3D maps for AI-based IoT applications by proposing a smartphone visual positioning system that detects and updates semantic changes in outdoor and indoor environments, achieving user positioning within 1.9m and object updates with an average error of 2.1m.
Accurate localization and 3D maps are increasingly needed for various artificial intelligence based IoT applications such as augmented reality, intelligent transportation, crowd monitoring, robotics, etc. This article proposes a novel semantic 3D map change detection and update based on a smartphone visual positioning system (VPS) for the outdoor and indoor environments. The proposed method presents an alternate solution to SLAM for map update in terms of efficiency, cost, availability, and map reuse. Building on existing 3D maps of recent years, a system is designed to use artificial intelligence to identify high-level semantics in images for positioning and map change detection. Then, a virtual LIDAR that estimates the depth of objects in the 3D map is used to generate a compact point cloud to update changes in the scene. We present an excellent performance of localization with respect to other state-of-the-art smartphone positioning solutions to accurately update semantic 3D maps. It is shown that the proposed solution can position users within 1.9m, and update objects with an average error of 2.1m.