TR2005-111

Region Covariance: A Fast Descriptor for Detection and Classification


    •  Tuzel, O., Porikli, F., Meer, P., "Region Covariance: A Fast Descriptor for Detection and Classification", European Conference on Computer Vision (ECCV), May 2006.
      BibTeX TR2005-111 PDF
      • @inproceedings{Tuzel2006may,
      • author = {Tuzel, O. and Porikli, F. and Meer, P.},
      • title = {Region Covariance: A Fast Descriptor for Detection and Classification},
      • booktitle = {European Conference on Computer Vision (ECCV)},
      • year = 2006,
      • month = may,
      • url = {https://www.merl.com/publications/TR2005-111}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

Abstract:

We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore,we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance fetures is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix.

 

  • Related News & Events

    •  NEWS    ECCV 2006: 2 publications by Oncel Tuzel, Amit Agrawal and Ramesh Raskar
      Date: May 7, 2006
      Where: European Conference on Computer Vision (ECCV)
      Research Area: Computer Vision
      Brief
      • The papers "Region Covariance: A Fast Descriptor for Detection and Classification" by Tuzel, O., Porikli, F. and Meer, P. and "What is the Range of Surface Reconstructions from a Gradient Field?" by Agrawal, A., Raskar, R. and Chellappa, R. were presented at the European Conference on Computer Vision (ECCV).
    •