RI | Research | Labs | Computational Sensor Laboratory

Text only version of this site

Computational Sensor Laboratory Head: Vladimir Brajovic Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 Location: NSH A401 (412) 268 3346 Associated center: VASC For more information, see this lab's homepage.

This page last updated - January 1999.

Lab Description

The Computational Sensor Lab creates specialty imaging sensors for improving robustness and capabilities of robot vision systems.

Rather than only miniaturizing existing capabilities, our goal is to bring new capabilities to vision systems. For most of our implementations there is no conventional system substitute. Simply, conventional systems cannot do what our sensors do because either the sensor signal is missing or the system is not fast enough to cope with continuous events in the physical world.

Our solutions manipulate parameters and arrangements in three areas:

1. image formation and sensing,
2. on-chip computation using analog and mixed-mode circuits, and
3. system integration using commercial embedded processors and networks.

Mainly, the superior performance of our sensors come from analog on-chip signal processing that enables low latency and rapid adaptation to environmental changes. Miniature size, low power and low cost are added benefits of our solutions.

Personnel [Past members]

	Name	Title	Email Address
	Takeo Kanade	U.A. and Helen Whitaker University Prof., RI/CS	tk@cs.cmu.edu

Current Projects

Reflectance Perception - We have developed Reflectance Perception - an image processing software that intelligently compensates for illumination problems in digital pictures.

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.

• Brightness Perception, Dynamic Range and Noise: A Unifying Model for Adaptive Image Sensors
  V. Brajovic
  Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '04), Vol. 2, June, 2004, pp. 189 - 196. [Abstract]
  Download: pdf [1878 KB] copyrighted

• Illumination-Invariant Imaging for Machine Vision Applications in Unconstrained Environments
  V. Brajovic
  Automation and Assembly Summit, Society of Manufacturing Engineers, May, 2004.

• Compound Eye Sensor for 3D Ego Motion Estimation
  J. Neumann, C. Fermuller, Y. Aloimonos, and V. Brajovic
  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '04), IEEE, April, 2004. [Abstract]

• Lossless Non-Arbitrated Address-Event Coding
  V. Brajovic
  Proceedings of the 2003 International Symposium on Circuits and Systems (ISCAS '03), Vol. 5, May, 2003, pp. 825 - 828. [Abstract]
  Download: pdf [271 KB] copyrighted

• An Object Tracking Computational Sensor
  V. Brajovic
  tech. report CMU-RI-TR-01-40, Robotics Institute, Carnegie Mellon University, December, 2001. [Abstract]
  Download: pdf [120 KB], ps.gz [169 KB] copyrighted

• A VLSI Sorting Image Sensor: Global Massively Parallel Intensity-to-Time Processing for Low-Latency, Adaptive Vision
  V. Brajovic and T. Kanade
  IEEE Transactions on Robotics and Automation, Vol. 15, No. 1, February, 1999, pp. 67-75. [Abstract]
  Download: pdf [1017 KB] copyrighted

• Temporal Photoreception for Adaptive Dynamic Range Image Sensing and Encoding
  V. Brajovic, R. Miyagawa, and T. Kanade
  Neural Networks (1998 Special Issue), Vol. 11, No. 7-8, October, 1998, pp. 1149-1158. [Abstract]
  Download: pdf [404 KB] copyrighted

• Computational Sensor for Visual Tracking with Attention
  V. Brajovic and T. Kanade
  IEEE Journal of Solid State Circuits, Vol. 33, No. 8, August, 1998, pp. 1199 - 1207. [Abstract]
  Download: pdf [186 KB] copyrighted

• A Sorting Image Sensor: An Example of Massively Parallel Intensity-to-Time Processing for Low-Latency Computational Sensors
  V. Brajovic and T. Kanade
  Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Vol. 2, 1996, pp. 1638 - 1643. [Abstract]
  Download: pdf [276 KB], ps.gz [583 KB] copyrighted

• Integration-Time Based Computational Image Sensors
  R. Miyagawa and T. Kanade
  ITE Technical Report, Vol. 19, No. 65, November, 1995, pp. 37 - 41. [Abstract]
  Download: pdf [177 KB] copyrighted