DMCA
A boundaryfragment-model for object detection (2006)
| Venue: | In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR06 |
| Citations: | 156 - 7 self |
BibTeX
@INPROCEEDINGS{Opelt06aboundaryfragment-model,
author = {Andreas Opelt and Andrew Zisserman},
title = {A boundaryfragment-model for object detection},
booktitle = {In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR06},
year = {2006}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. The objective of this work is the detection of object classes, such as airplanes or horses. Instead of using a model based on salient image fragments, we show that object class detection is also possible using only the object’s boundary. To this end, we develop a novel learning technique to extract class-discriminative boundary fragments. In addition to their shape, these “codebook ” entries also determine the object’s centroid (in the manner of Leibe et al. [19]). Boosting is used to select discriminative combinations of boundary fragments (weak detectors) to form a strong “Boundary-Fragment-Model ” (BFM) detector. The generative aspect of the model is used to determine an approximate segmentation. We demonstrate the following results: (i) the BFM detector is able to represent and detect object classes principally defined by their shape, rather than their appearance; and (ii) in comparison with other published results on several object classes (airplanes, cars-rear, cows) the BFM detector is able to exceed previous performances, and to achieve this with less supervision (such as the number of training images). 1
Keyphrases
object detection bfm detector object class codebook entry object boundary object class detection strong boundary-fragment-model boundary fragment object centroid salient image fragment discriminative combination several object class previous performance weak detector following result approximate segmentation novel learning technique training image class-discriminative boundary fragment generative aspect
