Please use this identifier to cite or link to this item:
|Title:||3D augmented Markov random field for object recognition||Authors:||Yu W.
Markov random field
|Issue Date:||2010||Citation:||Yu W., Ashraf A.B., Chang Y.-J., Li C., Chen T. (2010). 3D augmented Markov random field for object recognition. Proceedings - International Conference on Image Processing, ICIP : 3889-3892. ScholarBank@NUS Repository. https://doi.org/10.1109/ICIP.2010.5653951||Abstract:||In this paper, we propose the use of 3D information to augment the Markov random field (MRF) model for object recognition. Conventional MRF for image-based object recognition usually uses appearance and 2D location as features in the model. We estimate rough 3D information from stereo image pairs, and incorporate this information into node and edge potential models in the conventiona lMRF. Introducing 3D information into the node potential allows to leverage the distribution statistics of 3D location for different classes. We solve the object recognition problem by finding the globally optimal class assignment that minimizes an energy function defined in the augmented MRF. We show that the introduction of 3D distance in the edge potential can help distinguish "true" neighbors from "fake" neighbors in 2D. We demonstrate improved recognition results by using the proposed technique.||Source Title:||Proceedings - International Conference on Image Processing, ICIP||URI:||http://scholarbank.nus.edu.sg/handle/10635/146170||ISBN:||9781424479948||ISSN:||15224880||DOI:||10.1109/ICIP.2010.5653951|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Oct 12, 2021
WEB OF SCIENCETM
checked on Oct 5, 2021
checked on Oct 14, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.