Title :
Stereocorrelation on the parallel OPENVISION system
Author :
Mazzoni, Christophe ; Essafi, Hassane ; Julien, Patrick ; Jamet, Olivier
Author_Institution :
LET, CEA-Technologies Avancees, Gif-sur-Yvette, France
Abstract :
The aim of this work is to reduce the computation time needed to produce the Digital Elevation Models (DEM) by using a parallel machine. It is made in collaboration between the French “Institut Geographique National” (IGN) and LETI-DEIN, a department of the French Atomic Energy Commission (CEA). The IGN has developed a system which provides accurate DEM, that is used to produce the commercialized topographic map. The kernel of this system is the correlator. The correlator is a part of software which automatically matches pairs of homologous points (i.e. a pair of points representing the same ground detail), and supplies disparities. Nevertheless the correlator is expensive in computing time. CEA-LETI. is involved in parallel architecture and image processing and has developed a SIMD (Single Instruction Multiple Data) parallel architecture called SYMPATI 2. This structure constitute the kernel of the parallel OPENVISION system that is commercialized by Centralp Automatisme. In order to reduce the computation time and to produce the DEM with the same accuracy than the scalar approach, this two partners tried to parallize the IGN´s correlator on the OPENVISION system
Keywords :
cartography; parallel programming; real-time systems; stereo image processing; SYMPATI 2; commercialized topographic map; computation time; digital elevation models; image processing; parallel OPENVISION system; parallel architecture; stereocorrelation; Collaborative work; Commercialization; Concurrent computing; Correlators; Digital elevation models; Image processing; Kernel; Parallel architectures; Parallel machines; Pixel;
Conference_Titel :
Algorithms and Architectures for Parallel Processing, 1995. ICAPP 95. IEEE First ICA/sup 3/PP., IEEE First International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-7803-2018-2
DOI :
10.1109/ICAPP.1995.472214