Sparselet Models for Efficient Multiclass Object Detection

  • Hyun Oh Song
  • Stefan Zickler
  • Tim Althoff
  • Ross Girshick
  • Mario Fritz
  • Christopher Geyer
  • Pedro Felzenszwalb
  • Trevor Darrell
Conference paper

DOI: 10.1007/978-3-642-33709-3_57

Volume 7573 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Song H.O. et al. (2012) Sparselet Models for Efficient Multiclass Object Detection. In: Fitzgibbon A., Lazebnik S., Perona P., Sato Y., Schmid C. (eds) Computer Vision – ECCV 2012. Lecture Notes in Computer Science, vol 7573. Springer, Berlin, Heidelberg

Abstract

We develop an intermediate representation for deformable part models and show that this representation has favorable performance characteristics for multi-class problems when the number of classes is high. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. This leads to a universal set of parts that are shared among all object classes. Reconstruction of the original part filter responses via sparse matrix-vector product reduces computation relative to conventional part filter convolutions. Our model is well suited to a parallel implementation, and we report a new GPU DPM implementation that takes advantage of sparse coding of part filters. The speed-up offered by our intermediate representation and parallel computation enable real-time DPM detection of 20 different object classes on a laptop computer.

Keywords

Sparse Coding Object Detection Deformable Part Models 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Hyun Oh Song
    • 1
  • Stefan Zickler
    • 2
  • Tim Althoff
    • 1
  • Ross Girshick
    • 3
  • Mario Fritz
    • 4
  • Christopher Geyer
    • 2
  • Pedro Felzenszwalb
    • 5
  • Trevor Darrell
    • 1
  1. 1.UC BerkeleyUSA
  2. 2.iRobotUSA
  3. 3.University of ChicagoUSA
  4. 4.Max Planck Institute for InformaticsGermany
  5. 5.Brown UniversityUSA