Generating realtime panorama using a generalized feature vector approach
Jhilik Bhattacharya, Saibal Majumder, Goutam Sanyal · 2011
This paper proposes a technique to generate a panoramic view in realtime by combining images acquired at different light exposures and camera orientations. A new framework termed as Generalized Feature Vector (GFV) is used to detect and match features for image alignment and stitching. A scale space filtering operation is further applied over the composite image inorder to remove the seamline and intensity discrepancies produced due to the varying light exposures of the individual images. Experimental results with a set of images demonstrate the effectiveness of the approach in generating seamless stitched images without visual artifacts.