In this paper we address the problem of computing visibility information on digital terrain models in parallel. We propose a parallel algorithm for computing the visible region of an observation point located on the terrain. The algorithm is based on a sequential triangle-sorting visibility approach proposed in [4]. Static and dynamic parallelization strategies, both in terms of partitioning criteri a and scheduling policies, are discussed. The different parallelization strategies are implemented on an MIMD multicomputer and evaluated through experimental results. 1 Introd uction The problem of computing visibility information on a terrain has several important applications. One application. which has been studied in great depth. is terrain visualization, which consists l
Parallelizing visibility computations on triangulated terrains
Montani C;Scopigno R
1993
Abstract
In this paper we address the problem of computing visibility information on digital terrain models in parallel. We propose a parallel algorithm for computing the visible region of an observation point located on the terrain. The algorithm is based on a sequential triangle-sorting visibility approach proposed in [4]. Static and dynamic parallelization strategies, both in terms of partitioning criteri a and scheduling policies, are discussed. The different parallelization strategies are implemented on an MIMD multicomputer and evaluated through experimental results. 1 Introd uction The problem of computing visibility information on a terrain has several important applications. One application. which has been studied in great depth. is terrain visualization, which consists lFile | Dimensione | Formato | |
---|---|---|---|
prod_411838-doc_145000.pdf
accesso aperto
Descrizione: Parallelizing visibility computations on triangulated terrains
Dimensione
2.29 MB
Formato
Adobe PDF
|
2.29 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.