Registration of infrared transmission images using squared-loss mutual information

Sakai, Tomoya; Sugiyama, Masashi; Kitagawa, Katsuichi; Suzuki, Kazuyoshi

doi:10.1016/j.precisioneng.2014.09.001

Cited by 2 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When new algorithms are developed, registration accuracy is usually measured in a controlled environment where ground-truth camera movement is known or synthetically generated. In these cases, algorithm performance is assessed by comparing predicted and ground-truth registration transformations [39,44,[83][84][85][86]. However, this approach cannot be used for quality control in a general operational scenario where the ground-truth registration transformation is unknown.…”

Section: Discussionmentioning

confidence: 99%

Image Similarity Metrics Suitable for Infrared Video Stabilization during Active Wildfire Monitoring: A Comparative Analysis

et al. 2020

View full text Add to dashboard Cite

Aerial Thermal Infrared (TIR) imagery has demonstrated tremendous potential to monitor active forest fires and acquire detailed information about fire behavior. However, aerial video is usually unstable and requires inter-frame registration before further processing. Measurement of image misalignment is an essential operation for video stabilization. Misalignment can usually be estimated through image similarity, although image similarity metrics are also sensitive to other factors such as changes in the scene and lighting conditions. Therefore, this article presents a thorough analysis of image similarity measurement techniques useful for inter-frame registration in wildfire thermal video. Image similarity metrics most commonly and successfully employed in other fields were surveyed, adapted, benchmarked and compared. We investigated their response to different camera movement components as well as recording frequency and natural variations in fire, background and ambient conditions. The study was conducted in real video from six fire experimental scenarios, ranging from laboratory tests to large-scale controlled burns. Both Global and Local Sensitivity Analyses (GSA and LSA, respectively) were performed using state-of-the-art techniques. Based on the obtained results, two different similarity metrics are proposed to satisfy two different needs. A normalized version of Mutual Information is recommended as cost function during registration, whereas 2D correlation performed the best as quality control metric after registration. These results provide a sound basis for image alignment measurement and open the door to further developments in image registration, motion estimation and video stabilization for aerial monitoring of active wildland fires.

show abstract