Illumination-invariant image mosaic calculation based on logarithmic search

TL;DR

This paper presents an improved image mosaicking algorithm that enhances illumination invariance by integrating Jain's logarithmic search with Kourogi's matching method, resulting in more robust video sequence stitching.

Contribution

The paper introduces a novel combination of logarithmic search with existing image matching techniques to improve illumination invariance in mosaicking.

Findings

Enhanced robustness against illumination changes.

Better performance than optical-flow-based methods.

Effective in video sequence image matching.

Abstract

This technical report describes an improved image mosaicking algorithm. It is based on Jain's logarithmic search algorithm [Jain 1981] which is coupled to the method of Kourogi (1999} for matching images in a video sequence. Logarithmic search has a better invariance against illumination changes than the original optical-flow-based method of Kourogi.