Publication Date

Summer 2023

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Teng Moh

Keywords

Image Stitching, Homography Generation, Image Blending, Machine Learning, Randomized Algorithm, Superpixel Seam Detection..

Abstract

Image stitching algorithms are able to join sets of images together and provide a wider field of a vision when compared with an image from a single standard camera. Traditional techniques for accomplishing this are able to adequately produce a stitch for a static set of images, but suffer when differing lighting conditions exist between the two images. Additionally, traditional techniques suffer from processing times that are too slow for real time use cases. We propose a solution which resolves the issues encountered by traditional image stitching techniques. To resolve the issues with lighting difference, two blending schemes have been implemented, a standard approach and a superpixel approach. To verify the integrity of the cached solution, a validation scheme has been implemented. Using this scheme, invalid solutions can be detected, and the cache regenerated. Finally, these components are packaged together in a parallel processing architecture to ensure that frame processing is never interrupted.

Download

Share

COinS