Smart RANSAC: A Robust Approach

Vinayak Raju; Chetana Pujari

doi:10.1109/CITDS62610.2024.10791379

Smart RANSAC: A Robust Approach

Vinayak Raju
, Chetana Pujari

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper introduces Smart RANSAC, an enhancement to the traditional Random Sample Consensus (RANSAC) algorithm, aimed at increasing robustness in outlier detection by incorporating a weighted selection mechanism for point consideration. Unlike the conventional RANSAC that selects points randomly, Smart RANSAC calculates a weighted average for the second point based on the proximity to previously fitted lines, promoting a bias towards denser point regions. Our experiments demonstrate faster convergence in line fitting tasks.

Original language	English
Title of host publication	2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350387889
DOIs	https://doi.org/10.1109/CITDS62610.2024.10791379
Publication status	Published - 2024
Event	3rd IEEE Conference on Information Technology and Data Science, CITDS 2024 - Hybrid, Debrecen, Hungary Duration: 26-08-2024 → 27-08-2024

Publication series

Name	2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings

Conference

Conference	3rd IEEE Conference on Information Technology and Data Science, CITDS 2024
Country/Territory	Hungary
City	Hybrid, Debrecen
Period	26-08-24 → 27-08-24

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems
Statistics, Probability and Uncertainty
Modelling and Simulation

Access to Document

10.1109/CITDS62610.2024.10791379

Cite this

@inproceedings{de7433f1cbff4d4fa461622e69d3d25a,

title = "Smart RANSAC: A Robust Approach",

abstract = "This paper introduces Smart RANSAC, an enhancement to the traditional Random Sample Consensus (RANSAC) algorithm, aimed at increasing robustness in outlier detection by incorporating a weighted selection mechanism for point consideration. Unlike the conventional RANSAC that selects points randomly, Smart RANSAC calculates a weighted average for the second point based on the proximity to previously fitted lines, promoting a bias towards denser point regions. Our experiments demonstrate faster convergence in line fitting tasks.",

author = "Vinayak Raju and Chetana Pujari",

note = "Publisher Copyright: {\textcopyright}2024 IEEE.; 3rd IEEE Conference on Information Technology and Data Science, CITDS 2024 ; Conference date: 26-08-2024 Through 27-08-2024",

year = "2024",

doi = "10.1109/CITDS62610.2024.10791379",

language = "English",

series = "2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings",

address = "United States",

}

Raju, V & Pujari, C 2024, Smart RANSAC: A Robust Approach. in 2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings. 2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 3rd IEEE Conference on Information Technology and Data Science, CITDS 2024, Hybrid, Debrecen, Hungary, 26-08-24. https://doi.org/10.1109/CITDS62610.2024.10791379

Smart RANSAC: A Robust Approach. / Raju, Vinayak; Pujari, Chetana.
2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2024. (2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Smart RANSAC

T2 - 3rd IEEE Conference on Information Technology and Data Science, CITDS 2024

AU - Raju, Vinayak

AU - Pujari, Chetana

PY - 2024

Y1 - 2024

N2 - This paper introduces Smart RANSAC, an enhancement to the traditional Random Sample Consensus (RANSAC) algorithm, aimed at increasing robustness in outlier detection by incorporating a weighted selection mechanism for point consideration. Unlike the conventional RANSAC that selects points randomly, Smart RANSAC calculates a weighted average for the second point based on the proximity to previously fitted lines, promoting a bias towards denser point regions. Our experiments demonstrate faster convergence in line fitting tasks.

AB - This paper introduces Smart RANSAC, an enhancement to the traditional Random Sample Consensus (RANSAC) algorithm, aimed at increasing robustness in outlier detection by incorporating a weighted selection mechanism for point consideration. Unlike the conventional RANSAC that selects points randomly, Smart RANSAC calculates a weighted average for the second point based on the proximity to previously fitted lines, promoting a bias towards denser point regions. Our experiments demonstrate faster convergence in line fitting tasks.

UR - https://www.scopus.com/pages/publications/85216426456

UR - https://www.scopus.com/pages/publications/85216426456#tab=citedBy

U2 - 10.1109/CITDS62610.2024.10791379

DO - 10.1109/CITDS62610.2024.10791379

M3 - Conference contribution

AN - SCOPUS:85216426456

T3 - 2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings

BT - 2024 IEEE 3rd Conference on Information Technology and Data Science, CITDS 2024 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 26 August 2024 through 27 August 2024

ER -

Smart RANSAC: A Robust Approach

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this