A comparison of global optimizers applied to point cloud registration

Pablo Barrios; Vicente Guzman; Martin Adams; Martin Rudorfer

A comparison of global optimizers applied to point cloud registration

Pablo Barrios, Vicente Guzman, Martin Adams, Martin Rudorfer

Universidad de Chile

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

The registration of point cloud data is essential in various applications, such as computer vision and robotics. The Iterative Closest Point (ICP) algorithm offered a solution to this problem, with several subsequent methods addressing problems including occlusions and variable point data overlap. To also account for detection errors, the Particle Swarm Optimization - Cardinalized Optimal Linear Assignment (PSO-COLA) point data registration algorithm was introduced. This algorithm offers robust registration solutions in the presence of data miss-detections and false alarms, but being based on a Particle Swarm Optimization (PSO) concept is susceptible to local minima problems. To address this problem, we propose the use of two additional meta-heuristic algorithms, namely Artificial Rabbit Optimisation (ARO) and Artificial Bee Colony (ABC), in
combination with the Cardinalized Optimal Linear Assignment (COLA) metric. Our experiments show that the resulting ARO-COLA algorithm reduces the execution time compared with the former PSO-COLA algorithm while maintaining high registration accuracy, especially in scenarios with cardinality and spatial errors. The results indicate that the ARO-COLA algorithm is
a promising alternative for efficient and accurate point cloud registration.

Original language	English
Title of host publication	Conference Proceedings of the 13th International Conference on Control, Automation and Information Sciences (ICCAIS)
Publisher	IEEE
Number of pages	5
Publication status	Published - 26 Nov 2024

Publication series

Name	Proceedings of the International Conference on Control, Automation and Information Sciences (ICCAIS)
ISSN (Print)	2475-7896
ISSN (Electronic)	2475-790X

Bibliographical note

Copyright © 2024, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Access to Document

a61-barrios stamped-e
Copyright © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Accepted author manuscript, 2.7 MBLicence: Unspecified

Cite this

@inproceedings{3c442d1d656f49cfa34f4a30cecba6fd,

title = "A comparison of global optimizers applied to point cloud registration",

abstract = "The registration of point cloud data is essential in various applications, such as computer vision and robotics. The Iterative Closest Point (ICP) algorithm offered a solution to this problem, with several subsequent methods addressing problems including occlusions and variable point data overlap. To also account for detection errors, the Particle Swarm Optimization - Cardinalized Optimal Linear Assignment (PSO-COLA) point data registration algorithm was introduced. This algorithm offers robust registration solutions in the presence of data miss-detections and false alarms, but being based on a Particle Swarm Optimization (PSO) concept is susceptible to local minima problems. To address this problem, we propose the use of two additional meta-heuristic algorithms, namely Artificial Rabbit Optimisation (ARO) and Artificial Bee Colony (ABC), incombination with the Cardinalized Optimal Linear Assignment (COLA) metric. Our experiments show that the resulting ARO-COLA algorithm reduces the execution time compared with the former PSO-COLA algorithm while maintaining high registration accuracy, especially in scenarios with cardinality and spatial errors. The results indicate that the ARO-COLA algorithm isa promising alternative for efficient and accurate point cloud registration.",

author = "Pablo Barrios and Vicente Guzman and Martin Adams and Martin Rudorfer",

note = "Copyright {\textcopyright} 2024, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. ",

year = "2024",

month = nov,

day = "26",

language = "English",

series = "Proceedings of the International Conference on Control, Automation and Information Sciences (ICCAIS)",

publisher = "IEEE",

booktitle = "Conference Proceedings of the 13th International Conference on Control, Automation and Information Sciences (ICCAIS)",

address = "United States",

}

A comparison of global optimizers applied to point cloud registration. / Barrios, Pablo; Guzman, Vicente; Adams, Martin et al.
Conference Proceedings of the 13th International Conference on Control, Automation and Information Sciences (ICCAIS). IEEE, 2024. (Proceedings of the International Conference on Control, Automation and Information Sciences (ICCAIS)).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - A comparison of global optimizers applied to point cloud registration

AU - Barrios, Pablo

AU - Guzman, Vicente

AU - Adams, Martin

AU - Rudorfer, Martin

N1 - Copyright © 2024, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2024/11/26

Y1 - 2024/11/26

N2 - The registration of point cloud data is essential in various applications, such as computer vision and robotics. The Iterative Closest Point (ICP) algorithm offered a solution to this problem, with several subsequent methods addressing problems including occlusions and variable point data overlap. To also account for detection errors, the Particle Swarm Optimization - Cardinalized Optimal Linear Assignment (PSO-COLA) point data registration algorithm was introduced. This algorithm offers robust registration solutions in the presence of data miss-detections and false alarms, but being based on a Particle Swarm Optimization (PSO) concept is susceptible to local minima problems. To address this problem, we propose the use of two additional meta-heuristic algorithms, namely Artificial Rabbit Optimisation (ARO) and Artificial Bee Colony (ABC), incombination with the Cardinalized Optimal Linear Assignment (COLA) metric. Our experiments show that the resulting ARO-COLA algorithm reduces the execution time compared with the former PSO-COLA algorithm while maintaining high registration accuracy, especially in scenarios with cardinality and spatial errors. The results indicate that the ARO-COLA algorithm isa promising alternative for efficient and accurate point cloud registration.

AB - The registration of point cloud data is essential in various applications, such as computer vision and robotics. The Iterative Closest Point (ICP) algorithm offered a solution to this problem, with several subsequent methods addressing problems including occlusions and variable point data overlap. To also account for detection errors, the Particle Swarm Optimization - Cardinalized Optimal Linear Assignment (PSO-COLA) point data registration algorithm was introduced. This algorithm offers robust registration solutions in the presence of data miss-detections and false alarms, but being based on a Particle Swarm Optimization (PSO) concept is susceptible to local minima problems. To address this problem, we propose the use of two additional meta-heuristic algorithms, namely Artificial Rabbit Optimisation (ARO) and Artificial Bee Colony (ABC), incombination with the Cardinalized Optimal Linear Assignment (COLA) metric. Our experiments show that the resulting ARO-COLA algorithm reduces the execution time compared with the former PSO-COLA algorithm while maintaining high registration accuracy, especially in scenarios with cardinality and spatial errors. The results indicate that the ARO-COLA algorithm isa promising alternative for efficient and accurate point cloud registration.

UR - https://ieeexplore.ieee.org/xpl/conhome/1802677/all-proceedings

UR - https://ami.gov.vn/2024iccais/

M3 - Conference publication

T3 - Proceedings of the International Conference on Control, Automation and Information Sciences (ICCAIS)

BT - Conference Proceedings of the 13th International Conference on Control, Automation and Information Sciences (ICCAIS)

PB - IEEE

ER -

A comparison of global optimizers applied to point cloud registration

Abstract

Publication series

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this