Carnegie Mellon Robotics Institute
A. Rowe, Chuck Rosenberg, and Illah Nourbakhsh
Tech sketch paper presented at CVPR 2001, October, 2001.
| Download |
|
| Abstract |
| In this paper we describe a functioning prototype of a simple low cost system which we have constructed and can perform a simple color blob tracking task at 16.7 frames per second. This system utilizes a low cost CMOS color camera module which eliminates the need for a separate frame grabber and all processing is performed by a high speed, low cost microcontroller. The resulting system makes it possible to utilize simple color vision algorithms in applications, like small mobile robotics, where a traditional vision system consisting of a separate camera, frame grabber, and high speed computer would be prohibitive. |
| Notes |
Associated Center(s) / Consortia:
Vision and Autonomous Systems Center Associated Lab(s) / Group(s):
CREATE: Community Robotics, Education and Technology Empowerment Associated Project(s):
The CMUcam Vision Sensor Number of pages: 4 Note: This is a revised version of the tech sketch paper accepted to CVPR
2001. A small number of revisions were made in October 2001 to re
flect the improved system performance achieved in the month following
the original paper submission and correct minor technical errors. |
| Text Reference |
| A. Rowe, Chuck Rosenberg, and Illah Nourbakhsh, "A Simple Low Cost Color Vision System," Tech sketch paper presented at CVPR 2001, October, 2001. |
| BibTeX Reference |
|
@inproceedings{Rosenberg_2001_4390, author = "A. Rowe and Chuck Rosenberg and Illah Nourbakhsh", title = "A Simple Low Cost Color Vision System", booktitle = "Tech sketch paper presented at CVPR 2001", month = "October", year = "2001", Notes = "This is a revised version of the tech sketch paper accepted to CVPR 2001. A small number of revisions were made in October 2001 to re flect the improved system performance achieved in the month following the original paper submission and correct minor technical errors." } |
| The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University. Contact Us | Update Instructions |