KLT Revisited: Spatio-Temporal Affine Regression for Feature Tracking
Revista de Informática Teórica e Aplicada · 10.03.2026 · 33 (2) · 234-242
DOI: 10.22456/2175-2745.150903 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista de Informática Teórica e Aplicada, online erschienen am 10.03.2026. Verfasst von Nigel Joseph Bandeira Dias und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Feature association is an essential step for vision-based localization methods. These methods rely on feature matching to estimate relative motion between consecutive frames using projective geometry. Regardless of the advances in feature association, most existing methods still rely on pairwise feature matching approaches and ignore the rich temporal context in image sequences. In this paper, we revisit the well-known Kanade-Lucas-Tomasi (KLT) feature tracker algorithm and propose a differentiable tracker model. The Proposed method is a fully convolutional neural network that learns spatio-temporal features to track keypoints across videos. Experimental results show that the proposed method outperforms the KLT method, especially in challenging environments.
Zitieren
APA
Dias, N. J. B., Laureano, G. T., & Costa, R. M. D. (2026). KLT Revisited: Spatio-Temporal Affine Regression for Feature Tracking. Revista de Informática Teórica e Aplicada, 33(2), 234-242. https://doi.org/10.22456/2175-2745.150903
Vancouver
Dias NJB, Laureano GT, Costa RMD. KLT Revisited: Spatio-Temporal Affine Regression for Feature Tracking. Revista de Informática Teórica e Aplicada. 2026;33(2):234-242. doi:10.22456/2175-2745.150903
BibTeX
@article{Dias2026,
author = {Dias, Nigel Joseph Bandeira and Laureano, Gustavo Teodoro and Costa, Ronaldo Martins Da},
title = {KLT Revisited: Spatio-Temporal Affine Regression for Feature Tracking},
journal = {Revista de Informática Teórica e Aplicada},
year = {2026},
volume = {33},
number = {2},
pages = {234--242},
doi = {10.22456/2175-2745.150903}
}
EUVIMED