TR2009-072

Object Detection Via Boosted Deformable Features


Abstract:

It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this context, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. We introduce using deformable features with boosted ensembles. A deformable feature adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. We empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection.

 

  • Related News & Events

    •  NEWS    ICIP 2009: 2 publications by Wei Sun, Anthony Vetro and Shantanu D. Rane
      Date: November 7, 2009
      Where: IEEE International Conference on Image Processing (ICIP)
      MERL Contact: Anthony Vetro
      Brief
      • The papers "Object Detection via Boosted Deformable Features" by Hussein, M.E., Porikli, F.M. and Davis, L. and "Secure Distortion Computation between Untrusting Parties using Homomorphic Encryption" by Rane, S.D., Sun, W. and Vetro, A. were presented at the IEEE International Conference on Image Processing (ICIP).
    •