Automated 3D room mapping and real-time corner detection for Android-based AR systems

Automated 3D room mapping and real-time corner detection for Android-based AR systems

Augmented Reality (AR) is the transformation of human interaction with physical space by incorporating digital content into the real world. Among the most crucial factors in AR application success lies the accurate mapping of 3D space and correct corner detection. Existing solutions often pose signi...

Full description

Saved in:
Bibliographic Details
Main Authors: Balakrishnan Ramalingam, Abraham Sudharson Ponraj, Mukund Sharma, Rishabh Sharma, Mohamed Nabeel, Shivanshu Upadhyay, Mahapatra Aditya, Siddhant Arora, Mohanaprasad Kothandaraman
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
AR foundation
Unity engine
Augmented reality
Spatial mapping
Room detection
Corner localization
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025024715
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Augmented Reality (AR) is the transformation of human interaction with physical space by incorporating digital content into the real world. Among the most crucial factors in AR application success lies the accurate mapping of 3D space and correct corner detection. Existing solutions often pose significant challenges due to their reliance on specialized sensors like LiDAR, significant user intervention, and poor optimization for Android devices, which account for a significant portion of the global smartphone market. To address these limitations, this work proposes an Android-based AR system utilizing Unity AR Foundation's advanced technologies and integrated computer vision tools. The proposed framework enables dynamic spatial mapping and real-time recognition on standard Android devices with minimal user input, eliminating the need for high-end hardware. The system's efficiency is demonstrated through real-time digital content mapping within 3D environments, achieving a Dice Similarity Coefficient (DSC) of 0.87 and a Hausdorff Distance of 0.05 meters, ensuring high room mapping and object placement accuracy of 94.43%. By leveraging advanced software techniques, the framework overcomes hardware constraints typical of Android smartphones, enabling scalable AR applications in architecture, interior design, and robotic navigation.
ISSN:2590-1230

Similar Items