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 conventional MRF. 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. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICIP.2010.5653951 | ICIP |
Keywords | Field | DocType |
mrf model,rough 3d information,stereo image pair,distribution statistics,random processes,3d augmented markov random field,3d distance,stereo,object recognition,energy function minimization,3d,markov random field,minimisation,stereo image processing,markov processes,image-based object recognition,solid modeling,global optimization,pixel | Computer vision,Markov process,3D single-object recognition,Random field,Pattern recognition,Computer science,Markov random field,Stochastic process,Probability distribution,Minimisation (psychology),Artificial intelligence,Cognitive neuroscience of visual object recognition | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-7993-1 | 978-1-4244-7993-1 | 1 |
PageRank | References | Authors |
0.35 | 3 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Yu | 1 | 259 | 14.78 |
Ahmed Bilal Ashraf | 2 | 131 | 10.47 |
Yao-jen Chang | 3 | 396 | 47.11 |
Congcong Li | 4 | 240 | 16.48 |
Tsuhan Chen | 5 | 4763 | 346.32 |