15-869: Image Based Modeling and Rendering
Project Progress Report
Problem: Create a system for real-time motion capture for use as an
input device for a personal computer.
- W4: A Real Time System for Detecting and
Tracking People (Haritaoglu, Harwood & Davis)
- Subtraction by first 'learning' what range of values
each pixel has and thresholding according to that.
- Post processing to remove noise and correct the size of
- Method for human tracking assumes 'cardboard model'
Real-Time Tracking of the Human Body (Wren,
Azarbayejani, Darrel & Pentland)
- Subtraction takes 'learning' color distributions
modeled with a Gaussian, updated with a adaptive filter.
- New Pixels are compared to original model to see if
they are statistically different
- Humans identified by stored known human positions.
- Some of it's applications include gesture control of
- Real-time human
motion analysis by image skeletonization (Fujiyoshi
- Star skeletonization to identify extremal points.
- Use the thresholding method to gain an initial guess as
to what parts of the image are moving, because it is computationally
simple to perform.
- From this do a small amount of image processing to gain
a bounding silhouette and eliminate noise.
- Use the Gaussian on this image silhouette to more
precisely eliminate background pixels. (the method described in
the paper about Pfinder handles removing shadows).
- After obtaining this removed image, skeletonization
could be preformed
- Using the method in , find border positions that are
the farthest away and connect these to a centroid of the silhouette.
- Track the position of the object using the centroid,
and any gestures with the skeleton
I describe using a combination of algorithm to
do the image subtraction and skeletonization. Also, these methods were
used to identify human motion. I plan to use this algorithm as a hand
gesture tracker for use as an input to a personal computer.
After initially calibrating the system with
a background, check for new objects in the scene. The backgrounds I would
use would be simple, as well as have very few lighting changes. I will
then use add another object in the scene. My test case so far is a
cluttered desk with a drop cloth behind it and a ping pong ball moving through
it. Once I have the ability to track a new object in the scene, it will be
easy to test the image skeletonization by visualizing it on the computer
screen. I will attempt to get direct input to the computer of a hand and
attempt to track the 5 most extreme points - which should be the fingers.
Then test if I can save or match motions.