Massively Parallel Multiclass Object Recognition

Abstract

We present a massively parallel object recognition system based on a cortex-like structure. Due to its nature, this general, biologically motivated system can be parallelized efficiently on recent many-core graphics processing units (GPU). By implementing the entire pipeline on the GPU, by rigorously optimizing memory bandwidth and by minimizing branch divergence, we achieve significant speedup compared to both recent CPU as well as GPU implementations for reasonably sized feature dictionaries. We demonstrate an interactive application even on a less powerful laptop which is able to classify webcam images and to learn novel categories in real time.

DOI: 10.2312/PE/VMV/VMV10/251-257

Extracted Key Phrases

6 Figures and Tables

Cite this paper

@inproceedings{Sedding2010MassivelyPM, title={Massively Parallel Multiclass Object Recognition}, author={Helmut Sedding and Ferdinand Deger and Holger Dammertz and Jan Bouecke and Hendrik P. A. Lensch}, booktitle={VMV}, year={2010} }