[SCS dragon logo]

Programming Project #5 (second part)

15-463: Computational Photography

 

 

 

FEATURE MATCHING for AUTOSTITCHING

(second part of a larger project)

Due time: by 11:59pm on the due date

 

The goal of this project is to create a system for automatically stitching images into a mosaic.  A secondary goal is to learn how to read and implement a research paper.   The project will consist of the following steps:

  1. Detecting corner features in an image (10 pts)
  2. Extracting a Feature Descriptor for each feature point (10 pts)
  3. Matching these feature descriptors between two images (20 pts)
  4. Use a robust method (RANSAC) to compute a homography (30 pts)
  5. Proceed as in Project 3 to produce a mosaic (30 pts; you may use the same images from part A, but show both manually and automatically stitched results side by side) [produce at least three mosaics]
  6. Submit your results

 

Steps 1-3

For steps 1-3, we will follow the paper “Multi-Image Matching using Multi-Scale Oriented Patches” by Brown et al. but with several simplifications. Read the paper first and make sure you understand it.  Then implement the algorithm:

 

Step 4

For step 4, use 4-point RANSAC as described in class to compute a robust homography estimate.

 

Submit Your Results

You will need to submit all your code. Please include a README with your code describing where each of the steps was implemented. If you skipped a step, say so, to save your TA some time!

 

 

Bells & Whistles