GHAR: GeoPose-based Handheld Augmented Reality for Architectural Positioning, Manipulation and Visual Exploration

2025-06-17

AI Summary

To address the deployment complexity, illumination sensitivity, and marker-design constraints of marker-based handheld AR systems in civil infrastructure, this paper proposes a markerless handheld augmented reality framework tailored for pre-construction planning. The framework centers on GeoPose—a geographic pose estimation technique—and integrates markerless SLAM, 7-degree-of-freedom natural gesture recognition, and mobile real-time rendering to enable precise registration and interactive visualization of CAD models onto real-world construction sites. User studies employing dual evaluation metrics (SUS and HARUS) demonstrate statistically significant improvements (p < 0.01) in usability, operability, and comprehensibility compared to conventional marker-based approaches. These results validate the framework’s practicality and technical advancement for requirements analysis and construction planning in civil engineering contexts.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Handheld Augmented Reality (HAR) is revolutionizing the civil infrastructure application domain. The current trend in HAR relies on marker tracking technology. However, marker-based systems have several limitations, such as difficulty in use and installation, sensitivity to light, and marker design. In this paper, we propose a markerless HAR framework with GeoPose-based tracking. We use different gestures for manipulation and achieve 7 DOF (3 DOF each for translation and rotation, and 1 DOF for scaling). The proposed framework, called GHAR, is implemented for architectural building models. It augments virtual CAD models of buildings on the ground, enabling users to manipulate and visualize an architectural model before actual construction. The system offers a quick view of the building infrastructure, playing a vital role in requirement analysis and planning in construction technology. We evaluated the usability, manipulability, and comprehensibility of the proposed system using a standard user study with the System Usability Scale (SUS) and Handheld Augmented Reality User Study (HARUS). We compared our GeoPose-based markerless HAR framework with a marker-based HAR framework, finding significant improvement in the aforementioned three parameters with the markerless framework.

Problem

• Proposes markerless HAR framework for architectural positioning
• Enables 7 DOF manipulation of virtual building models
• Improves usability over marker-based systems in construction planning

Innovation

• Markerless HAR framework with GeoPose tracking
• 7 DOF manipulation using different gestures
• Augments virtual CAD models for construction planning