Quantitative Evaluation of OpenCV Visual Tracking Algorithms for Drawn Markers Under Dynamic Facial Deformation
Sensors · 2026
DOI: 10.3390/s26206653 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Konrad Tkaczyk und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Micromechanics and Photonics, Faculty of Mechatronics, Warsaw University of Technology, ul. Św. Andrzeja Boboli 8, 02-525 Warsaw, Poland. Hauptthemen laut MEDLINE: Algorithms, Face, Image Processing, Computer-Assisted. Die Arbeit nennt 86 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Warsaw University of Technology internal statutory funds.
Abstract (Originalsprache)
This study evaluates the eleven visual tracking algorithms available in OpenCV for tracking hand-drawn markers on deforming human faces. Using 41,641 multi-camera frames of seven subjects performing exaggerated phonetic and emotional movements, we assess each tracker’s deviation from an automated Blob Detection reference (four-marker sequences), its long-term marker identity retention (forty-marker sequences), and its throughput. Of the tested classical trackers, the Channel and Spatial Reliability Tracker (CSRT) performed best, retaining 96.2% of markers with a mean deviation of 1.94±1.29 pixels (approximately 0.46±0.31 mm) at 56.9 frames per second (FPS). The Kernelized Correlation Filter (KCF) matched this deviation at 445.4 FPS but failed under transient self-occlusion, retaining only 64.1%. Among the neural trackers, the Vision Transformer-based tracker (ViT) recorded the smallest deviation (1.06±1.03 pixels, approximately 0.25±0.25 mm) at 164.1 FPS, and the Distractor-Aware Siamese Region Proposal Network (DaSiamRPN) had the highest retention (92.4%, 1.35±1.26 pixels) at 11.6 FPS. Differences among the leading trackers were not significant at the subject level. The Minimum Output Sum of Squared Error (MOSSE) tracker reached about 12,500 FPS, but retained only 49.6%. Per-frame deviation and long-term retention are decoupled, meaning that both must inform tracker selection; scenario-based recommendations are provided.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Micromechanics and Photonics, Faculty of Mechatronics, Warsaw University of Technology, ul. Św. Andrzeja Boboli 8, 02-525 Warsaw, Poland.
ORCID-Profile: Robert Sitnik
Förderung
- Warsaw University of Technology internal statutory funds
Zitieren
APA
Tkaczyk, K., & Sitnik, R. (2026). Quantitative Evaluation of OpenCV Visual Tracking Algorithms for Drawn Markers Under Dynamic Facial Deformation. Sensors. https://doi.org/10.3390/s26206653
Vancouver
Tkaczyk K, Sitnik R. Quantitative Evaluation of OpenCV Visual Tracking Algorithms for Drawn Markers Under Dynamic Facial Deformation. Sensors. 2026. doi:10.3390/s26206653
BibTeX
@article{Tkaczyk2026,
author = {Tkaczyk, Konrad and Sitnik, Robert},
title = {Quantitative Evaluation of OpenCV Visual Tracking Algorithms for Drawn Markers Under Dynamic Facial Deformation},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26206653}
}
EUVIMED