Object based 3-D motion and structure estimation
dc.citation.epage | 393 | en_US |
dc.citation.spage | 390 | en_US |
dc.contributor.author | Alatan, A. Aydın | en_US |
dc.contributor.author | Onural, Levent | en_US |
dc.coverage.spatial | Washington DC, USA | en_US |
dc.date.accessioned | 2016-02-08T12:01:00Z | |
dc.date.available | 2016-02-08T12:01:00Z | |
dc.date.issued | 1996 | en_US |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.description | Date of Conference: 23-26 October 1995 | en_US |
dc.description | Conference Name: International Conference on Image Processing, IEEE 1995 | en_US |
dc.description.abstract | Motion analysis is the most crucial part of object-based coding. A motion in 3-D environment can be analyzed better by using a 3-D motion model compared to its 2-D counterpart and hence may improve coding efficiency. Gibbs formulated joint segmentation and estimation of 2-D motion not only improves performance, but also generates robust point correspondences which are necessary for linear 3-D motion estimation algorithms. Estimated 3-D motion parameters are used to find the structure of the previously segmented objects by minimizing another Gibbs energy. Such an approach achieves error immunity compared to linear algorithms. Experimental results are promising and hence the proposed motion and structure analysis method is a candidate to be used in object-based (or even knowledge-based) video coding schemes. | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T12:01:00Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 1996 | en |
dc.identifier.doi | 10.1109/ICIP.1995.529728 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/27755 | |
dc.language.iso | English | en_US |
dc.publisher | IEEE | en_US |
dc.relation.isversionof | http://doi.org/10.1109/ICIP.1995.529728 | en_US |
dc.source.title | Proceedings of the International Conference on Image Processing, IEEE 1995 | en_US |
dc.subject | Algorithms | en_US |
dc.subject | Gibbs free energy | en_US |
dc.subject | Image compression | en_US |
dc.subject | Image segmentation | en_US |
dc.subject | Knowledge based systems | en_US |
dc.subject | Mathematical models | en_US |
dc.subject | Optical flows | en_US |
dc.subject | Parameter estimation | en_US |
dc.subject | Three dimensional | en_US |
dc.subject | Vectors | en_US |
dc.subject | Exponential joint distribution | en_US |
dc.subject | Motion analysis | en_US |
dc.subject | Motion estimation algorithms | en_US |
dc.subject | Object segmentation | en_US |
dc.subject | Image coding | en_US |
dc.title | Object based 3-D motion and structure estimation | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Object_based_3_D_motion_and_structure_estimation.pdf
- Size:
- 489.31 KB
- Format:
- Adobe Portable Document Format
- Description:
- View / Download