Classification of Bark Beetle-Induced Forest Tree Mortality using Deep Learning

TL;DR

This paper presents a deep learning approach using RetinaNet architecture to accurately classify bark beetle attack stages on individual trees from UAV images, aiding early detection and forest management.

Contribution

It introduces a novel application of RetinaNet with data augmentation strategies for classifying bark beetle infestation stages at the tree level.

Findings

Achieved an average accuracy of 98.95%

Outperformed baseline by approximately 10%

Effective data augmentation improved classification robustness

Abstract

Bark beetle outbreaks can dramatically impact forest ecosystems and services around the world. For the development of effective forest policies and management plans, the early detection of infested trees is essential. Despite the visual symptoms of bark beetle infestation, this task remains challenging, considering overlapping tree crowns and non-homogeneity in crown foliage discolouration. In this work, a deep learning based method is proposed to effectively classify different stages of bark beetle attacks at the individual tree level. The proposed method uses RetinaNet architecture (exploiting a robust feature extraction backbone pre-trained for tree crown detection) to train a shallow subnetwork for classifying the different attack stages of images captured by unmanned aerial vehicles (UAVs). Moreover, various data augmentation strategies are examined to address the class imbalance problem, and consequently, the affine transformation is selected to be the most effective one for this purpose. Experimental evaluations demonstrate the effectiveness of the proposed method by achieving an average accuracy of 98.95%, considerably outperforming the baseline method by approximately 10%.