DMCA
Pedestrian recognition with a learned metric
| Venue: | In Proc. Asian Conf. on Computer Vision |
| Citations: | 59 - 2 self |
BibTeX
@INPROCEEDINGS{Dikmen_pedestrianrecognition,
author = {Mert Dikmen and Emre Akbas and Thomas S. Huang and Narendra Ahuja},
title = {Pedestrian recognition with a learned metric},
booktitle = {In Proc. Asian Conf. on Computer Vision},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. This paper presents a new method for viewpoint invariant pedestrian recognition problem. We use a metric learning framework to obtain a robust metric for large margin nearest neighbor classification with rejection (i.e., classifier will return no matches if all neighbors are beyond a certain distance). The rejection condition necessitates the use of a uniform threshold for a maximum allowed distance for deeming a pair of images a match. In order to handle the rejection case, we propose a novel cost similar to the Large Margin Nearest Neighbor (LMNN) method and call our approach Large Margin Nearest Neighbor with Rejection (LMNN-R). Our method is able to achieve significant improvement over previously reported results on the standard Viewpoint Invariant Pedestrian Recognition (VIPeR [1]) dataset. 1
Keyphrases
pedestrian recognition viewpoint invariant pedestrian recognition problem approach large margin nearest neighbor significant improvement maximum allowed distance neighbor classification new method uniform threshold rejection condition metric learning framework standard viewpoint invariant pedestrian recognition large margin novel cost certain distance large margin nearest neighbor rejection case
