Because of its attractive features, image segmentation has shown to be a promising tool in remote sensing. A known drawback about its implementation is computational complexity. Recently an efficient numerical method has been proposed for the minimization of a second-order variational approximation of the Blake-Zissermann functional. The method is an especially tailored version of the block-coordinate descent algorithm (BCDA). In order to enable the segmentation of large-size gridded data, such as Digital Surface Models, we combine a domain decomposition technique with BCDA and a parallel interconnection rule among blocks of variables. We aim to show that a simple tiling strategy enables us to treat large images even in a commodity multicore CPU, with no need of specific post-processing on tiles junctions. From the point of view of the performance, little computational effort is required to separate data in subdomains and the running time is mainly spent in concurrently solving the independent subproblems. Numerical results are provided to evaluate the effectiveness of the proposed parallel approach.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
Titolo: | A parallel approach for image segmentation by numerical minimization of a second-order functional |
Autori: | |
Data di pubblicazione: | 2016 |
Serie: | |
Abstract: | Because of its attractive features, image segmentation has shown to be a promising tool in remote sensing. A known drawback about its implementation is computational complexity. Recently an efficient numerical method has been proposed for the minimization of a second-order variational approximation of the Blake-Zissermann functional. The method is an especially tailored version of the block-coordinate descent algorithm (BCDA). In order to enable the segmentation of large-size gridded data, such as Digital Surface Models, we combine a domain decomposition technique with BCDA and a parallel interconnection rule among blocks of variables. We aim to show that a simple tiling strategy enables us to treat large images even in a commodity multicore CPU, with no need of specific post-processing on tiles junctions. From the point of view of the performance, little computational effort is required to separate data in subdomains and the running time is mainly spent in concurrently solving the independent subproblems. Numerical results are provided to evaluate the effectiveness of the proposed parallel approach. |
Handle: | http://hdl.handle.net/11392/2353948 |
ISBN: | 978-0-7354-1438-9 |
Appare nelle tipologie: | 04.2 Contributi in atti di convegno (in Volume) |