Image stitching is a research problem that aims to create an image with a larger field of view (FOV) by stitching multiple images together. One common application of image stitching is the generation of panorama, which features a wide-horizontal-angle view. In this project, we implemented an end-to-end algorithm that takes multiple images as input and creates a panorama as output.
The algorithm includes six different steps: 1) cylindrical projection, 2) feature detection, 3) feature matching, 4) image matching, 5) blending, and 6) seam carving. Each step contains several substeps. We adopted Multi-Scale Oriented Path to find feature points. To ensure that the feature points are spatially well distributed, we also used adaptive non-maximal suppression. Then we matched those features by comparing the similarities of different patches. To leverage the impact of outliers, we implemented RANSAC algorithm.