Pedestrian Recognition with a Learned Metric

DIKMEN M., Akbas E., HUANG T. S. , Ahuja N.

10th Asian Conference on Computer Vision, Queenstown, Guyana, 8 - 12 November 2010, vol.6495, pp.501-512 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 6495
  • City: Queenstown
  • Country: Guyana
  • Page Numbers: pp.501-512
  • Middle East Technical University Affiliated: No


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.