TR2005-127

Covariance Tracking using Model Update Based on Lie Algebra


    •  Porikli, F., Tuzel, O., Meer, P., "Covariance Tracking using Model Update Based on Lie Algebra", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2006, vol. 1, pp. 728-735.
      BibTeX TR2005-127 PDF
      • @inproceedings{Porikli2006jun1,
      • author = {Porikli, F. and Tuzel, O. and Meer, P.},
      • title = {Covariance Tracking using Model Update Based on Lie Algebra},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2006,
      • volume = 1,
      • pages = {728--735},
      • month = jun,
      • issn = {1063-6919},
      • url = {https://www.merl.com/publications/TR2005-127}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

Abstract:

We propose a simple and elegant algorithm to track nonrigid objects using a covariance based object description and a Lie algebra based update mechanism. We represent an object window as the covariance matrix of features, therefore we manage to capture the spatial and statistical properties as well as their correlation within the same representation. The covariance matrix enables efficient fusion of different types of features and modalities, and its dimensionality is small. We incorporated a model update algorithm using the Lie group structure of the positive definite matrices. The update mechanism effectively adapts to the undergoing object deformations and appearance changes. The covariance tracking method does not make any assumption on the measurement noise and the motion of the tracked objects, and provides the global optimal solution. We show that it is capable of accurately detecting the nonrigid, moving objects in non-stationary camera sequences while achieving a promising detection rate of 97.4 percent.

 

  • Related News & Events

    •  NEWS    CVPR 2006: 3 publications by Oncel Tuzel, Amit Agrawal and Ramesh Raskar
      Date: June 17, 2006
      Where: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
      Research Area: Computer Vision
      Brief
      • The papers "Covariance Tracking using Model Update Based on Lie Algebra" by Porikli, F., Tuzel, O. and Meer, P., "Covariance Tracker" by Porikli, F. and Tuzel, O. and "Edge Suppression by Gradient Field Transformation using Cross-Projection Tensors" by Agrawal, A., Raskar, R. and Chellappa, R. were presented at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
    •