Case study #1: find the ball
Load two color images of a ball in a room
Display images
Load pre-processed image of ball for Gaussian color model
Show image (for building color model)
Build Gaussian color model
Eliminate background pixels from data
Compute the mean μ and covariance matrix Σ over RGB pixel values
Gaussian color-model based ball detection: image #1
Select image
Display image
Gaussian distance image
Perform Gaussian-distance thresholding on original image
Blob finding on noisy threshold image
Clean up binary threshold image (w/Opening operator)
Blob finding on clenaed-up threshold image
Superimpose original image with cleaned-up threshold image
Gaussian color-model based ball detection: image #2
Select image
Display image
Gaussian distance image
Perform Gaussian-distance thresholding on original image
Blob finding on noisy threshold image
Clean up binary threshold image (w/Opening operator)
Blob finding on clenaed-up threshold image
Superimpose original image with cleaned-up threshold image
Created by Mathematica (February 5, 2004)