Name
Abstract | ||
|---|---|---|
The understanding of object's kinematic structure is one of main challenges in the area of computer vision. Especially, skeleton of deformable objects, which is familiar with human visual perception, visualizes its characteristic using few data. This paper describes an efficient approach for automatic skeleton extraction and its splitting in the space of diffusion tensor fields, which are generated from normalized gradient vector flow fields of a given image. Our method is based on two steps: Skeleton extraction using second order diffusion tensor fields, Splitting skeleton using dissimilarity measure between neighbor elements. The evaluation proofs the efficiency of our technique which might be applied to object retrieval, pose estimation and action recognition, object registration and visualization. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICIP.2009.5414139 | ICIP |
Keywords | Field | DocType |
normalized gradient vector flow fields,ngvf,order diffusion tensor field,splitting skeleton,dissimilarity measure,target objects splitting,kinematic structure,object registration,diffusion tensor field,second order diffusion tensor fields,automatic skeleton extraction,deformable object,feature extraction,gradient methods,skeleton,object detection,computer vision,visual perception,action recognition,skeleton extraction,tensor fields,target object,human visual perception,shape,diffusion tensor,tensile stress,pose estimation,noise,pixel,topology,second order | Computer vision,Object detection,Kinematics,Pattern recognition,Visualization,Computer science,Tensor field,Pose,Feature extraction,Vector flow,Pixel,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-5655-0 | 978-1-4244-5655-0 | 3 |
PageRank | References | Authors |
0.46 | 11 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sang Min Yoon | 1 | 129 | 19.66 |
| Holger Graf | 2 | 56 | 15.10 |