Project 5: Fun with Homographies grad portion here

Julia Schwarz (grad)
andrew id: julenka

times square image from wikipedia.org.

skip to Image Rectification , Manual Panoramas, Automatic Panoramas, Bells & Whistles

Project Description

This project has two parts. In part 1 we make panoramas using manually defined correspondence points and perspective projections. In part 2 we make panoramas using automatically determined correspondence points.

Part 1A: Image Rectification

ORIGINAL
RECTIFIED		(cropped for size, see uncropped version here

Part 1B: Manual Panoramas

Stitching

Correspondences were manually determined then photos were warped and stitched automatically using some carefully worked out math.

Blending

I used a quadratic alpha blending function that performed alpha blending on overlapping regions of panoramas. Although such blending still produces ghosting (which could likely be eliminated using a LaPlacian pyramid), using quadratic as opposed to linear blending provided a mild improvement.

Discussion

For this portion I can really see how important it is to take photos with significant overlap! Many of my photos had less overlap than I had wanted and I noticed quite a bit of distortion on the edges. This is particularly apparent in my trees photo, where the field of view is near 180 degrees. Cylindrical projection would help here.

My Lab
Not bad, appropriate overlap
Flagstaff Hill, Cathedral of Learning
Should have had more overlap for rightmost image
Flagstaff Hill, trees
Way too little overlap.	(cropped, original (downsized) version here

Part 2: Automatic Panoramas

Manually specifying points is tiring. To create a panorama without manually specifying points, we can do it automatically! Here's how:

Source Images

First, our source images

Image 1	Image 2	Image 3

Step 1: Harris Points

First we extract 'interesting points' (implemented using the harris detector provided to us)

No points at edges because edge points were not allowed and the images for this particular example are small

Image 1	Image 2	Image 3

Step 2: Filter With Adaptive Non-Maximal Suppression

Then we pick a subset of these points using Adaptive Non-Maximal suppression (essentially, define a radius for each point which is the minimum distance to some other point that's larger than it, order the points by the size of the radius and pick the highest N points). I found 100 points to work well.

Image 1	Image 2	Image 3

Step 3: Features

We then compute features for this subset of points using an 8x8 blurred patch at every interest point.

Image 1	Image 2	Image 3

Step 4: RANSAC, and Output

Finally use RANSAC to find good correspondence points and compute homographies for these points to get interesting results. Below are examples of manual vs. automatically generated panoramas.

Manual
Automatic
Manual
Automatic

Some more automatically generated Panoramas...

More shots of the dev lab
More shots of the dev lab

Bells & Whistles

Playing With the Perspective Transform

Inspired by the billboards in Times Square, I create a light-hearted homage to our instructor using homographies. Click for a larger image.