Image Warping and Mosaicing
by Kimberly Kao cs196-26-aas
The goal of this project is to create a system for automatic stitching of images into a mosaic. This is similar to project 6A, except instead of manually defining correspondence points, we can automatically find good feature points through the 5-step framework described below.
Automatic Feature Detection Framework:
Original Images
Harris Interest Points
After ANMS
Feature Matching
RANSAC
Final Mosaic: Manual (left) vs Automatic (right)
Original Images
Harris Interest Points
After ANMS
Feature Matching
RANSAC
Final Mosaic: Manual (left) vs Automatic (right)
Original Images
Harris Interest Points
After ANMS
Feature Matching
RANSAC
Final Mosaic: Manual (left) vs Automatic (right)
The coolest part of this project was learning about the different ideas to improve automatic feature detection such as ANMS and RANSAC. It's amazing how the most important feature points can be detected by such a simple framework.