File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1117/12.674648
- Scopus: eid_2-s2.0-33750601052
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Segmentation of motion textures using mixed-state Markov Random Fields
Title | Segmentation of motion textures using mixed-state Markov Random Fields |
---|---|
Authors | |
Keywords | Image motion analysis Image texture analysis Markov random fields Segmentation |
Issue Date | 2006 |
Publisher | S P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml |
Citation | Proceedings Of Spie - The International Society For Optical Engineering, 2006, v. 6315 How to Cite? |
Abstract | The aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes (rivers, sea-waves, smoke, fire, grass etc) where some sort of stationarity and homogeneity of motion is present. We adopt the mixed-state Markov Random Fields models recently introduced to represent so-called motion textures. The approach consists in describing the distribution of some motion measurements which exhibit a mixed nature: a discrete component related to absence of motion and a continuous part for measurements different from zero. We propose several extensions on the spatial schemes. In this context, Gibbs distributions are analyzed, and a deep study of the associated partition functions is addressed. Our approach is valid for general Gibbs distributions. Some particular cases of interest for motion texture modeling are analyzed. This is crucial for problems of segmentation, detection and classification. Then, we propose an original approach for image motion segmentation based on these models, where normalization factors are properly handled. Results for motion textures on real natural sequences demonstrate the accuracy and efficiency of our method. |
Persistent Identifier | http://hdl.handle.net/10722/132616 |
ISSN | 2023 SCImago Journal Rankings: 0.152 |
References |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Crivelli, T | en_HK |
dc.contributor.author | CernuschiFrías, B | en_HK |
dc.contributor.author | Bouthemy, P | en_HK |
dc.contributor.author | Yao, JF | en_HK |
dc.date.accessioned | 2011-03-28T09:27:01Z | - |
dc.date.available | 2011-03-28T09:27:01Z | - |
dc.date.issued | 2006 | en_HK |
dc.identifier.citation | Proceedings Of Spie - The International Society For Optical Engineering, 2006, v. 6315 | en_HK |
dc.identifier.issn | 0277-786X | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/132616 | - |
dc.description.abstract | The aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes (rivers, sea-waves, smoke, fire, grass etc) where some sort of stationarity and homogeneity of motion is present. We adopt the mixed-state Markov Random Fields models recently introduced to represent so-called motion textures. The approach consists in describing the distribution of some motion measurements which exhibit a mixed nature: a discrete component related to absence of motion and a continuous part for measurements different from zero. We propose several extensions on the spatial schemes. In this context, Gibbs distributions are analyzed, and a deep study of the associated partition functions is addressed. Our approach is valid for general Gibbs distributions. Some particular cases of interest for motion texture modeling are analyzed. This is crucial for problems of segmentation, detection and classification. Then, we propose an original approach for image motion segmentation based on these models, where normalization factors are properly handled. Results for motion textures on real natural sequences demonstrate the accuracy and efficiency of our method. | en_HK |
dc.language | eng | en_US |
dc.publisher | S P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml | en_HK |
dc.relation.ispartof | Proceedings of SPIE - The International Society for Optical Engineering | en_HK |
dc.subject | Image motion analysis | en_HK |
dc.subject | Image texture analysis | en_HK |
dc.subject | Markov random fields | en_HK |
dc.subject | Segmentation | en_HK |
dc.title | Segmentation of motion textures using mixed-state Markov Random Fields | en_HK |
dc.type | Conference_Paper | en_HK |
dc.identifier.email | Yao, JF: jeffyao@hku.hk | en_HK |
dc.identifier.authority | Yao, JF=rp01473 | en_HK |
dc.description.nature | link_to_subscribed_fulltext | en_US |
dc.identifier.doi | 10.1117/12.674648 | en_HK |
dc.identifier.scopus | eid_2-s2.0-33750601052 | en_HK |
dc.relation.references | http://www.scopus.com/mlt/select.url?eid=2-s2.0-33750601052&selection=ref&src=s&origin=recordpage | en_HK |
dc.identifier.volume | 6315 | en_HK |
dc.publisher.place | United States | en_HK |
dc.identifier.scopusauthorid | Crivelli, T=25824832900 | en_HK |
dc.identifier.scopusauthorid | CernuschiFrías, B=7003558300 | en_HK |
dc.identifier.scopusauthorid | Bouthemy, P=7005146506 | en_HK |
dc.identifier.scopusauthorid | Yao, JF=7403503451 | en_HK |
dc.identifier.issnl | 0277-786X | - |