You have reached the homepage (dgray.info) of: Doug Gray
Publications

2009


D. Gray, I. Kozintsev, Y. Wu, and H. Haussecker, "WikiReality: Augmenting Reality with Community Driven Websites", In Proc. International Conference on Multimedia Expo (ICME), 2009.

2008


D. Gray, H. Tao, "Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features", In Proc. European Conference on Computer Vision (ECCV), 2008.

2007


D. Gray, S. Brennan, and H. Tao, "Evaluating Appearance Models for Recognition, Reacquisition, and Tracking", in Proc. IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), October 2007.

2006


D. Kong, D. Gray and H. Tao, "A Viewpoint Invariant Approach for Crowd Counting," International Conference on Pattern Recognition, 2006.

2005


D. Kong, D. Gray and H. Tao, "Counting Pedestrian in Crowds using view-invariant training," British Machine Vision Conference, 2005.

Research

Current Projects:




Viewpoint Invariant Pedestrian Recognition (VIPeR)

We are investigating methods of identifying pedestrians from arbitrary viewpoints. The dataset and a paper on performance evaluation can be found on our lab page at: http://vision.soe.ucsc.edu/?q=node/178

So far we've presented the dataset as a benchmark at PETS 2007 and a recognition algorithm with reasonable performance at ECCV 2008. More to come... 		Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features

Computational Beauty Analysis

Working with NEC Labs America to develop a system to predict female beauty ratings from images. This was a sumer/fall internship project that I'm still working on whenever I get a chance. Touchy subject, kinda hard to publish... Beauty Prediction Poster

Previous Projects:


Mobile Augmented Reality

This Intel project was to develop a prototype for performing tasks such as Augmented Reality on mobile internet devices (MIDs) powered by Intel Atom Processors. I wrote an ICME paper with some of my contributions just after leaving. More information to come...

Multiple object, multiple non-overlapping camera tracking

We worked with SAIC to implement tracking algorithms for multiple objects across multiple cameras with and without overlapping regions.
Sample tracking frame CCT application overview


Multi-scale Retinex with color restoration

An implementation of the retinex algorithm has been implemented for processing video sequences. Retinex is a general enhancement algorithm based on homomorphic filtering. It has the ability to compress dynamic range, remove illumination changes, and enhance sharpness and contrast.

Source code (ZIP) This was a graduate multimedia class project.

Right: Several examples of Retinex enhancement of video frames.
Unenhanced image of people walking by a mural Enhanced image of people walking by a mural
Unenhanced image of a plaza at night Enhanced image of a plaza at night
Unenhanced image of highway 680 Enhanced image of highway 680


Crowd Estimation from surveillance footage.

Methodology: Scalar information is obtained from various image-processing techniques and used to collect training data. Various fitting techniques (linear weights, neural networks, etc.) are used to fit the scalar data to the actual crowd size. We then use this model to estimate the crowd size in new images.

Files: BMVC Paper (PDF), ICPR Paper (PDF).

 Basic Estimation program Neural Net Training Application


HASTE: High Altitude Stratospheric Telemetry Explorer

Objective: Senior Design Project Class (CMPE 123A/B)

Methodology: The design and construction of a weather balloon equipped with various sensors, GPS and amateur radio equipment. The main goal of the project is the design of a differential thermocouple sensor which will be accurate enough to measure temperature differences across 1 meter with 0.001 degree centigrade accuracy. When sampled at 100 Hz, this measurement can be linked to the index of refraction structure parameter (C_n^2) of the air. Our experiment is to create a system of obtaining a profile of C_n^2 at a fraction of the current cost ($3k vs. $70k). While our balloon is currently missing in action in the vicinity of Fresno, we have succeeding in building a proof of concept.

The Lab, Spring 2005 PICT0661 What does cold smell like? Differential Thermocouple Sensor Back off! HASTE Circuit Boards Hardware Debugging Failure Not a bomb PICT1261 T-minus 5 seconds Laser Guide Star at Lick Observatory


Active Tracking

Objective: This was my project for CMPE 264 (Computer Vision and Image Analysis). The objective was to get a camera to follow people around the room.

Methodology: First an object is specified by the user (usually a persons face. A modified mean shift tracker then tracks the object around the image. When the object approaches the edge of the frame, a signal is sent to the camera to turn towards the object.

Files: Presentation Slides (PPT), Source Code (ZIP (updated 7-12-05)). Please note that I take no responsibility for anything this code is used for. It is unsupported and mostly undocumented. It contains code from OpenCV, an open source library sponsored by Intel. All the licensing restrictions that apply to OpenCV also apply to my code. (BSD style license)

 An example of active tracking

Smart as Bull
PICT2096
PICT1408
Smooth Sailing
7-6-2006-093
PICT1887
PICT1938
PICT2229
The Golfers Gray
Education
  • Ph.D. Computer Engineering, University of California, Santa Cruz, In progress... 2010 probably.
  • B.S. Computer Engineering, University of California, Santa Cruz, 2005

Experience
  • Research Associate, Smith-Kettlewell Eye Research Institute, April - August 2009
  • Intern, Intel Corporation (Intel>CTG>CTGLabs>MTL>ARL>AMT), June 2008 - January 2009
  • Intern, NEC Labs, July 2007 - March 2008
  • Graduate Student Researcher, Baskin School of Engineering, September 2006 - June 2007
  • Engineering Intern, Science Applications International Corporation (SAIC), July - September 2006
  • Teaching Assistant, Baskin School of Engineering
      Courses:
    • CMPE 185: Technical Writing, Winter 2009
    • AMS 27L: Engineering Math Lab (Matlab), Spring 2008
    • CMPE 80A: Universal Access, Winter 2008
    • CMPE 121/L: Microcontroller system design, Spring 2006
    • CMPE 107: Stochastics, Winter 2006
  • UC Regents Fellow, Baskin School of Engineering, Fall 2005
  • Undergraduate Research Assistant, Baskin School of Engineering, Professor Hai Tao (April 2004 - August 2005)
  • CFO, Art Director, Static Printing Inc. (June 2003 - January 2005)
  • Technical Assistant, Transfer Partnerships Program (January 2003 - September 2005)

Organizations
  • Visual Computing Lab, Graduate Student Researcher
  • Tau Beta Pi, California Alpha Delta Chapter, Charter Member
  • IEEE, Student Member
  • Graduate Student Association, UC Santa Cruz, Member

Skills
  • Research Interests: Computer Vision, Pattern Recognition, Machine Learning.
  • Computer Hardware, Microcontrollers and embedded systems, digital and analog circuit design, PCB layout, etc.
  • Computer Programming, C, C++, Matlab, Assembly, PHP, Perl, HTML, etc.
  • Computer Graphics, Photoshop, Powerpoint, LaTeX, etc.
  • Ham radio operator, Tech. class, KG6YZK

Interests
  • Sailing, brewing (beer), photography, snowboarding, xbox360, backpacking, traveling the globe, etc.

Contact

Links
  • My research group's new and improved website: vision.soe.ucsc.edu
  • I started a T-Shirt printing company when I was an undergrad. One of my partners bought everyone out when we graduated and turned our fledgling startup into a sucessful business. They do brand asset managment now: www.ylhonline.com
  • Baskin School of Engineering: www.soe.ucsc.edu