LNCS Homepage
ContentsAuthor IndexSearch

Sparselet Models for Efficient Multiclass Object Detection

Hyun Oh Song, Stefan Zickler2, Tim Althoff, Ross Girshick3, Mario Fritz4, Christopher Geyer2, Pedro Felzenszwalb5, and Trevor Darrell

1UC Berkeley, USA
song@eecs.berkeley.edu
althoff@eecs.berkeley.edu
darrell@eecs.berkeley.edu

2iRobot, USA
szickler@irobot.com
cgeyer@irobot.com

3University of Chicago, USA
rbg@cs.uchicago.edu

4Max Planck Institute for Informatics, Germany
mfritz@mpi-inf.mpg.de

5Brown University, USA
pff@brown.edu

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

LNCS 7573, p. 802 ff.

Full article in PDF | BibTeX


lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012