Name
Abstract | ||
|---|---|---|
We propose a novel framework for contour based object detection and recognition, which we formulate as a joint contour fragment grouping and labeling problem. For a given set of contours of model shapes, we simultaneously perform selection of relevant contour fragments in edge images, grouping of the selected contour fragments, and their matching to the model contours. The inference in all these steps is performed using particle filters (PF) but with static observations. Our approach needs one example shape per class as training data. The PF framework combined with decomposition of model contour fragments to part bundles allows us to implement an intuitive search strategy for the target contour in a clutter of edge fragments. First a rough sketch of the model shape is identified, followed by fine tuning of shape details. We show that this framework yields not only accurate object detections but also localizations in real cluttered images. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICCV.2009.5459446 | ICCV |
Keywords | DocType | Volume |
contour fragment labeling problem,edge fragments,particle filtering (numerical methods),shape recognition,contour fragment grouping problem,target contour,intuitive search strategy,contour based object recognition,contour based object detection,object localization,cluttered images,edge images,shape guided contour grouping,object detection,object recognition,particle filters,model contour fragments,image segmentation,shape,pixel,particle filter,age groups,clutter | Conference | 2009 |
Issue | ISSN | ISBN |
1 | 1550-5499 E-ISBN : 978-1-4244-4419-9 | 978-1-4244-4419-9 |
Citations | PageRank | References |
56 | 1.48 | 26 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| ChengEn Lu | 1 | 71 | 2.76 |
| Longin Jan Latecki | 2 | 3301 | 176.88 |
| Nagesh Adluru | 3 | 208 | 20.57 |
| Xingwei Yang | 4 | 771 | 24.86 |
| Haibin Ling | 5 | 4531 | 215.76 |