Simultaneous recognition and homography extraction of local patches with a simple linear classifier

DMCA

Simultaneous recognition and homography extraction of local patches with a simple linear classifier (2008)

Cached

Download Links

by Stefan Hinterstoisser , Selim Benhimane , Vincent Lepetit , Pascal Fua , Nassir Navab

Venue:	In BMVC
Citations:	9 - 4 self

BibTeX

@INPROCEEDINGS{Hinterstoisser08simultaneousrecognition,
    author = {Stefan Hinterstoisser and Selim Benhimane and Vincent Lepetit and Pascal Fua and Nassir Navab},
    title = {Simultaneous recognition and homography extraction of local patches with a simple linear classifier},
    booktitle = {In BMVC},
    year = {2008}
}

OpenURL

Abstract

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

Keyphrases

simple linear classifier simultaneous recognition local patch homography extraction linear predictor retrieved pose tracking application single keypoint separate step object pose subpixel accurate state-of-the-art method object detection high accuracy learning phase keypoint identity previous approach simultaneous estimation

DMCA