Multi-focus thermal image fusion

TL;DR

This paper introduces a new algorithm for multi-focus thermal image fusion that enhances object temperature measurement accuracy and is evaluated through various error metrics and visual inspection.

Contribution

It presents the first dedicated approach to multi-focus thermal image fusion using local activity analysis and image pre-selection.

Findings

Improved temperature measurement error up to 5°C

Validated by error rate, RMS error, and cross-correlation metrics

Demonstrated on six thermal image sets with varying focus depths

Abstract

This paper proposes a novel algorithm for multi-focus thermal image fusion. The algorithm is based on local activity analysis and advanced pre-selection of images into fusion process. The algorithm improves the object temperature measurement error up to 5 Celsius degrees. The proposed algorithm is evaluated by half total error rate, root mean squared error, cross correlation and visual inspection. To the best of our knowledge, this is the first work devoted to multi-focus thermal image fusion. For testing of proposed algorithm we acquire six thermal image set with objects at different focal depth.