On the optical flow model selection through metaheuristics

Author(s)

Pereira, Danillo R. ; Delpiano, Jose ; Papa, Joao P.

• Document type: Journal article
• Source: EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING; v. N/A, p. 10-pg., 2015-05-09.

Abstract

Optical flow methods are accurate algorithms for estimating the displacement and velocity fields of objects in a wide variety of applications, being their performance dependent on the configuration of a set of parameters. Since there is a lack of research that aims to automatically tune such parameters, in this work, we have proposed an optimization-based framework for such task based on social-spider optimization, harmony search, particle swarm optimization, and Nelder-Mead algorithm. The proposed framework employed the well-known large displacement optical flow (LDOF) approach as a basis algorithm over the Middlebury and Sintel public datasets, with promising results considering the baseline proposed by the authors of LDOF. (AU)

• FAPESP's process: 14/16250-9 - On the parameter optimization in machine learning techniques: advances and paradigms
• Grantee: João Paulo Papa
• Support Opportunities: Regular Research Grants
• FAPESP's process: 13/20387-7 - Hyperparameter optimization in deep learning arquitectures
• Grantee: João Paulo Papa
• Support Opportunities: Scholarships abroad - Research