Classifying Glare Intensity in Airborne Imagery Acquired during Marine Megafauna Survey

This paper presents a classifier that takes airborne imagery acquired during marine megafauna surveys and classifies the glare intensity into four classes representing the severity of the glare. The objective of the classifier is to automate labour intensive and subjective components of the work performed by trained Marine Mammal Observers (MMOs). The proposed automatic method is based on a cascaded random forest architecture. The method uses features extracted from the histogram of the survey’s images and the metadata associated with respective images. The use of metadata is justified by the image formation model and we observed that it tends to improve the accuracy of the classifier. The proposed method provides results similar to that of trained MMOs. This is critical to the adoption of machine learning and machine vision technologies since introducing a change of methodology may impact the comparability of historic and future survey results when evaluating glare intensity.