Articulo
A high-speed tracking algorithm for dense granular media
COMPUTER PHYSICS COMMUNICATIONS
Registro en:
1151029
1151029
Autor
Cerda, Mauricio
Navarro, Cristobal A
Silva, Juan
Waitukaitis, Scott R
Mujica, Nicolás
Hitschfeld, Nancy
Institución
Resumen
Many fields of study, including medical imaging, granular physics, colloidal physics, and active matter, require the precise identification and tracking of particle-like objects in images. While many algorithms exist to track particles in diffuse conditions, these often perform poorly when particles are densely packed together-as in, for example, solid-like systems of granular materials. Incorrect particle identification can have significant effects on the calculation of physical quantities, which makes the development of more precise and faster tracking algorithms a worthwhile endeavor. In this work, we present a new tracking algorithm to identify particles in dense systems that is both highly accurate and fast. We demonstrate the efficacy of our approach by analyzing images of dense, solid-state granular media, where we achieve an identification error of 5% in the worst evaluated cases. Going further, we propose a parallelization strategy for our algorithm using a GPU, which results in a speedup of up to 10x when compared to a sequential CPU implementation in C and up to 40x when compared to the reference MATLAB library widely used for particle tracking. Our results extend the capabilities of state-of-the-art particle tracking methods by allowing fast, high-fidelity detection in dense media at high resolutions. (C) 2018 Elsevier B.V. All rights reserved. Regular 2015 FONDECYT FONDECYT