You have requested a machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Neither SPIE nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied representations or warranties of any kind, including, without limitation, representations and warranties as to the functionality of the translation feature or the accuracy or completeness of the translations.
Translations are not retained in our system. Your use of this feature and the translations is subject to all use restrictions contained in the Terms and Conditions of Use of the SPIE website.
9 June 2006Building 3D scenes from 2D image sequences
Sequences of 2D images, taken by a single moving video receptor, can be fused to generate a 3D representation. This
dynamic stereopsis exists in birds and reptiles, whereas the static binocular stereopsis is common in mammals, including
humans. Most multimedia computer vision systems for stereo image capture, transmission, processing, storage and
retrieval are based on the concept of binocularity. As a consequence, their main goal is to acquire, conserve and enhance
pairs of 2D images able to generate a 3D visual perception in a human observer. Stereo vision in birds is based on the
fusion of images captured by each eye, with previously acquired and memorized images from the same eye. The process
goes on simultaneously and conjointly for both eyes and generates an almost complete all-around visual field. As a
consequence, the baseline distance is no longer fixed, as in the case of binocular 3D view, but adjustable in accordance
with the distance to the object of main interest, allowing a controllable depth effect. Moreover, the synthesized 3D scene
can have a better resolution than each individual 2D image in the sequence. Compression of 3D scenes can be achieved,
and stereo transmissions with lower bandwidth requirements can be developed.
Paul Dan Cristea
"Building 3D scenes from 2D image sequences", Proc. SPIE 6252, Holography 2005: International Conference on Holography, Optical Recording, and Processing of Information, 62521D (9 June 2006); https://doi.org/10.1117/12.677057
The alert did not successfully save. Please try again later.
Paul Dan Cristea, "Building 3D scenes from 2D image sequences," Proc. SPIE 6252, Holography 2005: International Conference on Holography, Optical Recording, and Processing of Information, 62521D (9 June 2006); https://doi.org/10.1117/12.677057