Art and Vision: Scene Layout from Pictorial Cues

Principal Investigator:Stella X. Yu
Project Span:2007 --- 2011
Project Sponsor:National Science Foundation CAREER IIS-0644204
Project Goal: Study art and vision together to find new solutions to fundamental problems in computer vision

1. Education

The interdisciplinary course, Art and Visual Perception, introduces neuroscience, psychology, visual art and computer science to college students at a very early stage so that they

  1. get exposed to various disciplines before making a knowing choice of an area of concentration
  2. learn how to visually communicate their ideas
  3. appreciate the challenge in visual perception and become inspired to study vision from various angles.

This course fulfills Fine Arts Core requirement starting from Fall 2007.

2. Experiments

We investigate human perception through a series of eye tracking experiments which reveal what visual information is essential for a human viewer to perform a detection or recognition task. Ongoing projects are:

  1. scene categorization
  2. change detection
  3. motion perception

The experimental data provide insights into what features and how they are computed in certain visual routines.

3. Computation

Understanding both the peculiarity of human vision and the universality of computational constraints allows us to better computation in the areas of:

  1. image and video compression
  2. brightness and color perception
  3. scene layout inference
  4. motion depiction

Check back on us as we make progress on these fronts.


Current Lab Members

Kyle Tierney,graduate student in Psychology
Callie McGrath,undergraduate in Psychology
Jeff Sun,undergraduate in Mathematics
David Tolioupov,undergraduate in Computer Science

Past Lab Members

Dr. Dimitri Lisin,now at VideoIQ.com
Marcus Woods,undergraduate in Communications and Psychology
Sebastian Skradal,undergraduate in Computer Science
Peter Sempolinski,undergraduate in Computer Science


Last updated on 17-Oct-2007.