AI-assisted synchronization of maps from 2D to 3D: method and application
113 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.CSCE7.2023.37-48Keywords:
Map; Digital Map; 2D; 3D; Sand table; 3D digital sand table; Synchronization.Abstract
In this article, we introduce a method for synchronizing operations from 2D digital mapping software to 3D digital sand table software using AI technology. This method solves the challenges and difficulties of combining 2D and 3D in military applications, such as the difference between 2D and 3D space, the accuracy and efficiency of the synchronization process, and the user experience when working with three-dimensional space. This method also uses AI models to detect and classify objects on the terrain and estimate the Z coordinates of objects on 3D sand tables. This method has been applied in the T3BD system, including 2D (GISDesktop) and 3D (GlobeDeskop) applications, and has been used by several units in the military. Experimental results show that this method achieves low synchronization times for all types of objects, from simple to complex. This method can improve the accuracy and efficiency of the synchronization process and enhance the user experience when working with three-dimensional space.
References
[1]. Nguyen Duc Dinh, Hoang Van Toan. “System Design Documentation of T3BD System”, (2020).
[2]. “TerraExplorer Programmer Guide – Basic concepts”, Skyline Sofware Inc, (2017).
[3]. Nguyen Canh Hung, Nguyen Duc Dinh, Le Ngoc Tu “Application of the skyline technology platform in the construction of 3d digital sand table data for command and consultation work in sea and island warfare”, Academy of Military Science and Technology, (2019).
[4]. Le Van Diep, Hoang Van Toan. “Real-time distributed data transmission and application in data synchronization of sea and island battle plans based on digital charts and 3d digital sand tables”, Academy of Military Science and Technology, (2019).
[5]. w3sDesign.com. "The Command design pattern - Problem, Solution, and Applicability”. (2017).
[6]. Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao. “YOLOv4: Optimal Speed and Accuracy of Object Detection”, (2020).
[7]. Nikola M. Zivkovic. “Machine Learning with ML.NET – Object detection with YOLO”, (2021).
[8]. Mac Van Vien. “The method to determine position in 3d digital sand table”, (2022). DOI: https://doi.org/10.54939/1859-1043.j.mst.CSCE6.2022.16-27
