Loading...
Please wait, while we are loading the content...
Simultaneous recognition and homography extraction of local patches with a simple linear classifier (2008)
| Content Provider | CiteSeerX |
|---|---|
| Author | Hinterstoisser, Stefan Benhimane, Selim Lepetit, Vincent Fua, Pascal Navab, Nassir |
| Description | In BMVC We show that the simultaneous estimation of keypoint identities and poses is more reliable than the two separate steps undertaken by previous approaches. A simple linear classifier coupled with linear predictors trained during a learning phase appears to be sufficient for this task. The retrieved poses are subpixel accurate due to the linear predictors. We demonstrate the advantages of our approach on real-time 3D object detection and tracking applications. Thanks to the high accuracy, one single keypoint is often enough to precisely estimate the object pose. As a result, we can deal in real-time with objects that are significantly less textured than the ones required by state-of-the-art methods. 1 |
| File Format | |
| Language | English |
| Publisher Date | 2008-01-01 |
| Access Restriction | Open |
| Subject Keyword | Object Detection Single Keypoint State-of-the-art Method Local Patch Simultaneous Recognition Tracking Application Simultaneous Estimation Homography Extraction Simple Linear Classifier Object Pose Retrieved Pose Linear Predictor Subpixel Accurate Keypoint Identity Previous Approach Separate Step High Accuracy Learning Phase |
| Content Type | Text |
| Resource Type | Article |
