Fast Pose Estimation with Parameter-Sensitive Hashing

  • Authors:
  • Gregory Shakhnarovich;Paul Viola;Trevor Darrell

  • Affiliations:
  • -;-;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.02

Visualization

Abstract

Example-based methods are effective for parameter estimationproblems when the underlying system is simple orthe dimensionality of the input is low. For complex andhigh-dimensional problems such as pose estimation, thenumber of required examples and the computational complexityrapidly become prohibitively high. We introduce anew algorithm that learns a set of hashing functions that efficientlyindex examples in a way relevant to a particularestimation task. Our algorithm extends locality-sensitivehashing, a recently developed method to find approximateneighbors in time sublinear in the number of examples. Thismethod depends critically on the choice of hash functions;we show how to find the set of hash functions that are optimallyrelevant to a particular estimation problem. Experimentsdemonstrate that the resulting algorithm, which wecall Parameter-Sensitive Hashing, can rapidly and accuratelyestimate the articulated pose of human figures from alarge database of example images.