Parallel Computation of the Region-Based Level Set Method for Boundary Detection of Moving Objects

Abstract

We formulate a parallel, region-based level set model to speed up accurate boundary detection of moving objects in low-contrast images, applying parallelization and discretization to a Chan-Vese (CV) model. We implement the model in a column parallel vision (CPV) system that is one of parallel image processing systems we developed for robot vision. Using a microscopic image of moving paramecia as a sample of a low-contrast image, our model detects moving paramecia boundaries within 2 ms per image. Comparisons of our model to a CV model using the CPV system and a nonparallel PC, we found that our model cuts calculation time for a CV model while obtaining accuracy similar to the CV model in boundary detection of moving objects.