Graphics enhanced version of this site

Vladimir Brajovic
Project Scientist

No longer a member of RI.

Jump to: Research interests | Keywords | Labs & Groups | Projects | Publications

My research interests are in robot perception; more specifically, VLSI computational sensors and computer vision. I am interested in creating miniature, intelligent, task-oriented, self-contained, integrated sensing and processing components that enable a machine (e.g., an autonomous vehicle) to coherently interact with a changing environment and/or human user.

Perception plays a dominant role in an intelligent system -- an animal or machine. Computational sensors mimic one aspect of biological systems: they tightly integrate computation and sensing to improve performance and achieve new capabilities. The computational sensor is a new and exciting concept that offers a range of research topics:

• algorithms: discovering new sensing and computing strategies
• VLSI design: implement these strategies by designing and fabricating analog/digital integrated circuits sensitive to a stimulus (e.g., light, sound, etc.)
• applications; apply these integrated circuits in a system that intelligently interacts with the environment and/or human.

The sensors I have built so far are vision sensors. They detect images and compute useful quantities from those images very quickly. My specific projects include: a sorting computational sensor which senses an image and sorts pixel values by their intensities, a tracking computational sensor which selects and tracks visual stimulus within the field of view, an eye tracking computational sensor, and a road-following computational sensor.

biological vision, computational sensors, computer vision, sensors, and VLSI

• Computational Sensor Laboratory - We are developing specialty imaging sensors for improving robustness and capabilities of robot vision systems.

• Integrated Vision and Sensing for Human Sensory Augmentation - The project integrates vision algorithms with sensing technologies for low-power, low-latency, compact adaptive vision systems to provide augmentation of human sensory systems and enabling sensory driven information delivery
• Multidisciplinary University Research Initiative
• Reflectance Perception - We have developed Reflectance Perception - an image processing software that intelligently compensates for illumination problems in digital pictures.

• 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]

• Fast Row-Parallel CMOS Range Image Sensor
  V. Brajovic
  IEEE International Conference on Robotics and Automation, IEEE, April, 2004. [Abstract]
  Download: pdf [491 KB] copyrighted

• Shot Noise Suppression in Image Sensors
  V. Brajovic
  SPIE, Visual Information Processing, Defense&Security Symposium, SPIE, April, 2004. [Abstract]

• Reflectance Sensitive Retina
  V. Brajovic
  SPIE International Technical Group on Electronic Imaging Newsletter, SPIE, Vol. 14, No. 1, January, 2004.

• When are the Smart Vision Sensors Smart?
  V. Brajovic and T. Kanade
  Sensor Review, 2004.

• An Image Preprocessing Algorithm for Illumination Invariant Face Recognition
  R. Gross and V. Brajovic
  4th International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA), Springer, June, 2003. [Abstract]

• A Model for Reflectance Perception in Vision
  V. Brajovic
  SPIE, EMT03 - Microtechnologies for the New Millennium 2003, SPIE, May, 2003. [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