Estimation of Extent of Trees’ and Biomass’ Infestation of the Suburban Forest of Thessaloniki (Seich Sou) using UAV Imagery and Combining R-CNNs and Multichannel Texture Analysis

摘要

Given the urgent priority around protecting the forests and limiting the impacts of the climate change, the constantmonitoring of forests towards the achievement of accurate and timely detection of infestations and the catastrophic actionof invasive insects, pests and fungi is an important and challenging task. More precisely, new species of insects that areintroduced or already existing insect species whose population multiply uncontrollably into the forest area, affect treegrowth, their survival, as well as the quality of forest biomass and constitute a serious threat to the mechanisms of suchforest ecosystems. Thus, new concepts are needed that will overcome difficulties faced by existing remote sensingtechniques and that would allow the timely and accurate health determination process of forest regions, assistingscientists and authorities to take action in order to protect the forests. In this paper, we propose a monitoring approach,which uses high resolution RGB aerial images and combines different Region Convolution Neural Networks (R-CNNs)architectures, namely Faster R-CNN and Mask R-CNN and fuses their bounding box outcomes in order to moreaccurately localize candidate infected trees’ regions whilst increasing the number of the candidate trees that have beendetected as infected. Subsequently, the candidate detected trees are modelled through the higher order linear dynamicalsystems (h-LDS) and descriptors are extracted for each candidate region. Finally, the h-LDS descriptors are classifiedusing an SVM classifier for the estimation of the infected trees. The study area includes parts of the suburban pine forestof Thessaloniki city (Greece) named Seich Sou, which suffers the last months an infestation of high significance andintensity by a bark and wood destroying insect (Tomicus piniperda). Although this insect was recorded in the specificecosystem many years ago, its population increased uncontrollably after the degradation of the ecosystem due to humanintervention and lack of protection and management strategy. Experimental results, through their outperforming existingstate-of-the-art algorithms, demonstrate high potential and perspectives of the proposed methodology of low cost andtime consumed, to contribute to the sustainable management, protection and recovery of a forest ecosystem.