Postprocesiranje rezultata 3D mapiranja pomoću ICP algoritma

undergraduate thesis

• Title (english): Postprocessing of 3D mapping data by ICP algorithm
• Author: Karmen Korić
• Mentor: Stjepan Bogdan (mentor)
• Committee member: Stjepan Bogdan (predsjednik povjerenstva)
• Committee member: Antonio Vasilijević (član povjerenstva)
• Committee member: Robert Milijaš (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-02-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad istražuje zamršeni proces 3D mapiranja pomoću različitih tehnologija i sveobuhvatnog procesa transformacije. Predstavlja metodologiju za obradu LiDAR podataka, detaljno opisujući proces ekstrakcije, transformaciju putanje i integraciju s modeliranjem temeljenim na URDF. Algoritam Iterativne najbliže točke (ICP) igra ključnu ulogu u obradi, usklađujući prikupljene podatke.

Prikupljanje podataka i prethodna obrada dalje naglašavaju izazove uključene u rukovanje velikim skupovima podataka, naglašavajući obradu podataka o putanji za točno usklađivanje i uključivanje modeliranja temeljenog na URDF-u. Korištenje ROS-a (Robot Operating System) i PCL-a (Point Cloud Library) u zadanim isječcima koda prikazuje ekstrakciju poruka oblaka točaka, ekstrakciju TF (Transform) poruka i transformaciju lidarskih podataka na temelju ekstrahiranih transformacija.

Implementacija ICP algoritma je detaljno objašnjena, pokrivajući parametre, postavke, integraciju s podacima lidara i postupke provjere valjanosti.

Rad zaključuje naglašavanjem važnosti takvog 3D mapiranja i transformacija uključujući robotiku, praćenje okoliša i urbano planiranje.

Abstract (english)

This paper explores the intricate process of 3D mapping using various technologies and a comprehensive transformation process. It introduces a methodology for LiDAR data processing, detailing the extraction process, trajectory transformation and integration with URDF-based modeling. The Iterative Closest Point (ICP) algorithm plays a key role in the processing, matching the collected data.

Data acquisition and preprocessing further highlight the challenges involved in handling large datasets, emphasizing the processing of trajectory data for accurate alignment and the inclusion of URDF-based modeling. Using ROS (Robot Operating System) and PCL (Point Cloud Library) in given code snippets shows extraction of point cloud messages, extraction of TF (Transform) messages and transformation of lidar data based on the extracted transforms.

The implementation of the ICP algorithm is explained in detail, covering parameters, settings, integration with lidar data, and validation procedures.

The paper concludes by emphasizing the importance of such 3D mapping and transformations including robotics, environmental monitoring and urban planning.

• Keywords: 3D mapiranje; LiDAR tehnologija; Iterativni algoritam najbliže točke (ICP); ROS (Robot Operating System); PCL (Knjižnica oblaka točaka); URDF modeliranje; Prikupljanje i prethodna obrada podataka; TF (Transform) poruke; Obrada oblaka točaka
• Keywords (english): 3D Mapping; LiDAR Technology; Iterative Closest Point (ICP) Algorithm; ROS (Robot Operating System); PCL (Point Cloud Library); URDF-based Modeling; Data Acquisition and Preprocessing; TF (Transform) Messages; Point Cloud Processing
• Language: croatian
• URN:NBN: urn:nbn:hr:168:840901
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-03-28 07:49:09