Scalable learning for object detection with GPU hardware

• Published in: 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 4287 - 4293
• Main Authors: Coates, A., Baumstarck, P., Quoc Le, Ng, A.Y.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2009
• Subjects: Clocks; Detectors; Graphics; Hardware; Indoor environments; Intelligent robots; Moore's Law; Object detection; Robot sensing systems; USA Councils
• ISBN: 9781424438037; 1424438039
• ISSN: 2153-0858
• DOI: 10.1109/IROS.2009.5354084

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.