Treffer: Multiway registration capability study in increasing the accuracy of registration results for infrastructure and mining pits terrestrial laser scanner (TLS) data point cloud.

Since the 1960s, 3D models have developed to meet various strategic needs such as scientific, technical, film, architecture, product design, and simulation applications, until they have expanded in various fields, including virtual reality (VR), augmented reality (AR), manufacturing, urban planning, and more. There are several methods for making 3D models that are known to the general public, but in the engineering field, making 3D models can be done using Laser Scanning methods and techniques, Close-range Photogrammetry, and Real-time 3D Capture. In mining work, the 3D Laser Scanning method is still an alternative for acquiring data for making 3D models. The 3D model produced by the laser scanning method depends highly on the registration method used in processing. The Multiway Registration method in 3D computer vision has proven reliable in increasing non-topographic registration accuracy. This study applies the multiway registration method to more complicated objects, namely pit holes and mining infrastructure, which have different characteristics of object complications, especially object variations. The research also examines the ability of the Multiway Registration method to register TLS point cloud data on pit objects and mining infrastructure in the registration process. This research began by building software using the ICP point-to-plane algorithm in Phycharm as an Integrated Development Environment (IDE) using the Python programming language. The registration results on the software that has been built are compared with comparative data. This research proves that the Multiway Registration method has better accuracy than comparable data in registering point cloud data of mining area objects. The RMSE value in the registration resultsusing the Multiway Registration method for the mining pit was 22.71 centimeters, and the fuel tank was 1.64 centimeters, while the comparative data was 27.8 centimeters for the mining pit and 2.4 centimeters for the fuel tank. The Multiway Registration method produces a fitness value for the mine pit object of 0.012 with a correspondence value of 7229 points and a fuel tank object of 0.403 meters with a correspondence value of 119,655 points. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)