caa a22 4500 469035994 CHVBK 20180323132756.0 cr unu---uuuuu 170328e19921001xx s 000 0 eng 10.1007/BF00163581 doi (NATIONALLICENCE)springer-10.1007/BF00163581 Computer vision based on a hypothesization and verification scheme by parallel relaxation [Elektronische Daten] [Koh Kakusho, Seiichiro Dan, Tadahiro Kitahashi, Norihiro Abe] Shape recovery from a monocular image is addressed. It is often said that the information conveyed by an image is insufficient to reconstruct 3D shapes of objects in the image. This implies that shape recovery from an image necessitates the use of additional plausible constraints on typical structures and features of the objects in an ordinary scene. We propose a hypothesization and verification method for 3D shape recovery based on geometrical constraints peculiar to man-made objects. The objective is to increase the robustness of computer vision systems. One difficulty with this method lies in the mutual dependency between proper assignment of constraints to the regions in a given image and recovery of a consistent 3D shape. A concurrent mechanism has been implemented which is based on energy minimization using a parallel network for relaxation. This mechanism is capable of maintaining consistency between constraint assignment and shape recovery. Kluwer Academic Publishers, 1992 Kakusho Koh The Institute of Scientific and Industrial Research, Osaka University, 567, Ibaraki, Osaka, Japan aut Dan Seiichiro The Institute of Scientific and Industrial Research, Osaka University, 567, Ibaraki, Osaka, Japan aut Kitahashi Tadahiro The Institute of Scientific and Industrial Research, Osaka University, 567, Ibaraki, Osaka, Japan aut Abe Norihiro Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology, 820, Iizuka, Fukuoka, Japan aut International Journal of Computer Vision Kluwer Academic Publishers 9/1(1992-10-01), 13-30 0920-5691 9:1<13 1992 9 11263 https://doi.org/10.1007/BF00163581 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00163581 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Kakusho Koh The Institute of Scientific and Industrial Research, Osaka University, 567, Ibaraki, Osaka, Japan aut NATIONALLICENCE 700 1- Dan Seiichiro The Institute of Scientific and Industrial Research, Osaka University, 567, Ibaraki, Osaka, Japan aut NATIONALLICENCE 700 1- Kitahashi Tadahiro The Institute of Scientific and Industrial Research, Osaka University, 567, Ibaraki, Osaka, Japan aut NATIONALLICENCE 700 1- Abe Norihiro Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology, 820, Iizuka, Fukuoka, Japan aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 9/1(1992-10-01), 13-30 0920-5691 9:1<13 1992 9 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer