Scalable learning for object detection with GPU hardware

Adam Coates, Paul Baumstarck, Quoc V. Le, Andrew Y. Ng
Computer Science Department, Stanford University
IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009. IROS 2009. p.4287-4293


   title={Scalable learning for object detection with GPU hardware},

   author={Coates, A. and Baumstarck, P. and Le, Q. and Ng, A.Y.},

   booktitle={Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on},





Download Download (PDF)   View View   Source Source   



We consider the problem of robotic object detection of such objects as mugs, cups, and staplers in indoor environments. While object detection has made significant progress in recent years, many current approaches involve extremely complex algorithms, and are prohibitively slow when applied to large scale robotic settings. In this paper, we describe an object detection system that is designed to scale gracefully to large data sets and leverages upward trends in computational power (as exemplified by Graphics Processing Unit (GPU) technology) and memory. We show that our GPU-based detector is up to 90 times faster than a well-optimized software version and can be easily trained on millions of examples. Using inexpensive off-the-shelf hardware, it can recognize multiple object types reliably in just a few seconds per frame.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: