RI | Research | Projects | GPU-accelerated Computer Vision

Text only version of this site

GPU-accelerated Computer Vision Head: Takeo Kanade Contact: Philipp Michel (pmichel@cs.cmu.edu) Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 Associated centers: VASC and CFR Associated lab/group: Planning and Autonomy Lab

This page last updated - December 2006.

Project Description

This project seeks to exploit the computational resources and parallelism offered by modern programmable GPUs in the context of computer vision.

We have been implementing a robust model-based three-dimensional tracking system on the GPU, operating at frame-rate on a humanoid robot during walking. Leveraging the computational resources of the GPU for vision has enabled us to ensure our tracker’s robustness to the large camera displacements, camera shake and severe aspect changes typically encountered during humanoid navigation.

Personnel [Past Members]

	Name	Title	Email Address
	Satoshi Kagami	Visiting Faculty
	Takeo Kanade	U.A. and Helen Whitaker University Prof.	tk@cs.cmu.edu
	James Kuffner	Assistant Professor	kuffner@cs.cmu.edu
	Philipp Michel	PhD Student, RI	pmichel@cs.cmu.edu

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• GPU-accelerated Real-Time 3D Tracking for Humanoid Locomotion and Stair Climbing
  P. Michel, J. Chestnutt, S. Kagami, K. Nishiwaki, J. Kuffner, and T. Kanade
  Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'07), October, 2007, pp. 463-469. [Abstract]
  Download: pdf [1413 KB] copyrighted