Compensated visual hull for defective segmentation and occlusion
Compensated visual hull for defective segmentation and occlusion
We propose an advanced visual hull technique to compensate for outliers using the reliabilities of the silhouettes. The proposed method consists of a foreground extraction technique based on the Generalized Gaussian Family model and a compensated shape-from-silhouette algorithm. They are connected by the intra-/inter-silhouette reliabilities to compensate for carving errors from defective segmentation or partial occlusion which may occur in a real environment. The 3D reconstruction process is implemented on a graphics processing unit (GPU) to accelerate the processing speed by using the huge computational power of modern graphics hardware. Experimental results show that the proposed method provides reliable silhouette information and an accurate visual hull in real environments at a very high speed on a common PC.
Color image processing, Gait analysis, Image reconstruction, Speed, Virtual reality, 3-D reconstructions, Computational power, Foreground extraction, Generalized Gaussian, Graphics hardware, Graphics processing unit, High speeds, International conferences, Partial occlusions, Processing speeds, Real environments, Shape from silhouettes, Visual Hull, Three dimensional
210-217
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Sakamoto, R.
6cdb329c-4cb0-42d6-b4b0-68b448304398
Kitahara, I.
13b48c1f-8b52-4b65-9f98-e00c2bee22df
Orman, N.
4751c1a7-88ba-429a-87c5-dc4cc67f5cd5
Toriyama, T.
060a3980-f003-4b15-b0fb-7e9e99acc471
Kogure, K.
9862d198-bf93-48a3-a954-dd8bce232b8b
2007
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Sakamoto, R.
6cdb329c-4cb0-42d6-b4b0-68b448304398
Kitahara, I.
13b48c1f-8b52-4b65-9f98-e00c2bee22df
Orman, N.
4751c1a7-88ba-429a-87c5-dc4cc67f5cd5
Toriyama, T.
060a3980-f003-4b15-b0fb-7e9e99acc471
Kogure, K.
9862d198-bf93-48a3-a954-dd8bce232b8b
Kim, H., Sakamoto, R., Kitahara, I., Orman, N., Toriyama, T. and Kogure, K.
(2007)
Compensated visual hull for defective segmentation and occlusion.
17th International Conference on Artificial Reality and Telexistence (ICAT 2007), , Esbjerg, Jylland, Denmark.
28 - 30 Nov 2007.
.
(doi:10.1109/ICAT.2007.23).
Record type:
Conference or Workshop Item
(Paper)
Abstract
We propose an advanced visual hull technique to compensate for outliers using the reliabilities of the silhouettes. The proposed method consists of a foreground extraction technique based on the Generalized Gaussian Family model and a compensated shape-from-silhouette algorithm. They are connected by the intra-/inter-silhouette reliabilities to compensate for carving errors from defective segmentation or partial occlusion which may occur in a real environment. The 3D reconstruction process is implemented on a graphics processing unit (GPU) to accelerate the processing speed by using the huge computational power of modern graphics hardware. Experimental results show that the proposed method provides reliable silhouette information and an accurate visual hull in real environments at a very high speed on a common PC.
This record has no associated files available for download.
More information
Published date: 2007
Additional Information:
Cited By :9
Export Date: 30 April 2020
Venue - Dates:
17th International Conference on Artificial Reality and Telexistence (ICAT 2007), , Esbjerg, Jylland, Denmark, 2007-11-28 - 2007-11-30
Keywords:
Color image processing, Gait analysis, Image reconstruction, Speed, Virtual reality, 3-D reconstructions, Computational power, Foreground extraction, Generalized Gaussian, Graphics hardware, Graphics processing unit, High speeds, International conferences, Partial occlusions, Processing speeds, Real environments, Shape from silhouettes, Visual Hull, Three dimensional
Identifiers
Local EPrints ID: 440547
URI: http://eprints.soton.ac.uk/id/eprint/440547
PURE UUID: 7dfb64dc-de89-49a6-9793-ee7aca0aba44
Catalogue record
Date deposited: 07 May 2020 16:31
Last modified: 17 Mar 2024 04:01
Export record
Altmetrics
Contributors
Author:
H. Kim
Author:
R. Sakamoto
Author:
I. Kitahara
Author:
N. Orman
Author:
T. Toriyama
Author:
K. Kogure
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics