GPU deformable part model for object recognition

  • Etienne Gadeski
  • Hamidreza Odabai Fard
  • Hervé Le Borgne
Original Research Paper

DOI: 10.1007/s11554-014-0447-5

Cite this article as:
Gadeski, E., Fard, H.O. & Le Borgne, H. J Real-Time Image Proc (2014). doi:10.1007/s11554-014-0447-5

Abstract

We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. We do not take any prior assumptions on the scene and location of the objects. We provide a fast implementation and analyse the different modules of the state-of-the-art detector. Our implementation allows to accelerate both training and testing. While maintaining comparable classification performance, we report a speed-up of \(\times\)10.6 using a standard GPU card compared to a baseline implemented in C++ on a single core and \(\times\)5 compared to a multi-core OpenMP (8 threads) implementation.

Keywords

Deformable part model Object recognition GPU Pascal VOC Classification 

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Etienne Gadeski
    • 1
  • Hamidreza Odabai Fard
    • 1
  • Hervé Le Borgne
    • 1
  1. 1.CEA, LIST, Vision and Content Engineering LaboratoryGif-sur-YvetteFrance