Home
Uni-Logo
 

Training Deformable Object Models for Human Detection based on Alignment and Clustering

European Conference on Computer Vision (ECCV), 2014
Abstract: We propose a clustering method that considers non-rigid alignment of samples. The motivation for such a clustering is training of object detectors that consist of multiple mixture components. In particular, we consider the deformable part model (DPM) of Felzenszwalb et al., where each mixture component includes a learned deformation model. We show that alignment based clustering distributes the data better to the mixture components of the DPM than previous methods. Moreover, the alignment helps the non-convex optimization of the DPM find a consistent placement of its parts and, thus, learn more accurate part filters.


Other associated files : ECCV_BenjaminDrayer.pdf [7.8MB]   Poster_ECCV_2014_Benjamin.pdf [9.5MB]  

Images and movies

 

BibTex reference

@InProceedings{DB14,
  author       = "B.Drayer and T.Brox",
  title        = "Training Deformable Object Models for Human Detection based on Alignment and Clustering",
  booktitle    = "European Conference on Computer Vision (ECCV)",
  year         = "2014",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2014/DB14"
}

Other publications in the database