TY - GEN
T1 - An efficient dense descriptor applied to 3D vision implemented on parallel computing
AU - Rosas-Miranda, Dario I.
AU - Ponomaryov, Volodymyr I.
AU - Robles-Gonzalez, Cesar M.A.
N1 - Publisher Copyright:
© 2018 SPIE. Downloading of the abstract is permitted for personal use only.
PY - 2018
Y1 - 2018
N2 - In this study, we introduce a novel local image descriptor, which is very efficient to compute densely. We also present an algorithm to compute dense depth maps from image pairs using designed descriptor. Novel descriptor is based on visual primitives and relations between them, namely coplanarity, cocolority, distance, and angle. Designed feature descriptor covers both geometric and appearance information. The depth map estimation performance is evaluated using the established bad matched pixel metric. An analysis of the feature descriptor employing a parallel programming paradigm is included to develop a possible real-time mode. This is performed with help of hardware based on multi-core processors and GPU platform, using a NVIDIA ® GeForce ® GT640 graphic card and Matlab over a PC with Windows 10.
AB - In this study, we introduce a novel local image descriptor, which is very efficient to compute densely. We also present an algorithm to compute dense depth maps from image pairs using designed descriptor. Novel descriptor is based on visual primitives and relations between them, namely coplanarity, cocolority, distance, and angle. Designed feature descriptor covers both geometric and appearance information. The depth map estimation performance is evaluated using the established bad matched pixel metric. An analysis of the feature descriptor employing a parallel programming paradigm is included to develop a possible real-time mode. This is performed with help of hardware based on multi-core processors and GPU platform, using a NVIDIA ® GeForce ® GT640 graphic card and Matlab over a PC with Windows 10.
KW - Disparity Map
KW - Features Descriptors
KW - Image Descriptor
KW - Parallel Computing
UR - http://www.scopus.com/inward/record.url?scp=85049585330&partnerID=8YFLogxK
U2 - 10.1117/12.2303667
DO - 10.1117/12.2303667
M3 - Contribución a la conferencia
AN - SCOPUS:85049585330
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Real-Time Image and Video Processing 2018
A2 - Kehtarnavaz, Nasser
A2 - Carlsohn, Matthias F.
PB - SPIE
T2 - Real-Time Image and Video Processing 2018
Y2 - 16 April 2018 through 17 April 2018
ER -