KEYWORDS: RGB color model, Data modeling, Image segmentation, 3D modeling, Unmanned aerial vehicles, Orthophoto maps, Process modeling, Convolutional neural networks, Visual process modeling, Remote sensing
Due to an increased occurrence frequency of drought events and pest infestations, large amounts of deadwood are a current issue in temperate forests. Accurate monitoring of deadwood and analysis of its spatial and temporal distribution is, therefore, more important than ever, as it facilitates faster response to pest outbreaks or increased risk of forest fires. As highlighted by previous studies, state-of-the-art remote sensing platforms, such as UAVs, provide great synergies for deadwood monitoring in combination with machine- and deep-learning approaches of computer vision. Key challenges that remain are the acquisition of sufficient amounts of labeled data for model training and identifying deadwood on the single-tree level, which is required to estimate the deadwood volume in an area. The presented work demonstrates how it is possible to obtain very accurate instance segmentation in the combined RGB and elevation domain and with limited training data. A high-performance Mask R-CNN model was trained to map standing and lying deadwood instances in German forests, achieving outstanding results with an overall accuracy of 92.4% and a mean average precision of 43.4%. To compensate for the possibly insufficient amount of annotated images, we performed experiments with a semi-supervised active learning pipeline. Here, each time after the model predicted a batch of new data, only the instances that achieved a high prediction score were added to the pool of training data to re-compute the model for the next iteration step. Even though the application of the fully supervised approach led to superior results, overall, this study proves that the proposed method can reliably map individual deadwood objects. The approach not only represents an end-to-end framework for image annotation, model acquisition, and large-scale mapping of deadwood, but also is adoptable with reasonable effort to solve similar problems in the future.
Tree surveys with the objective of establishing a tree cadastre or communal tree inventory is a time-consuming and expensive work.1 As cadastres are commonly acquired in laborious eld surveys and updating involves regular site inspection, the effort of keeping a cadastre up-to-date is often either too high,2 or a tree inventory is created only once or updated in a coarse temporal resolution. In the underlying study, we present a hybrid approach of merging data from different sources, to update a cadastre (shapefile) containing tree data. A classification of the four most frequent tree species in a study domain in Melville, Western Australia, was carried out. The considered tree species were Jacaranda Mimosifolia, Agonis Flexuosa, Callistemon KP Special, and Ulmus Parvifolia. The classification was performed on high-resolution airborne imagery, using Random Forests, and achieved outstanding results with an overall model accuracy of 93:44% and Cohen's of 89:93 %. This is a considerable step towards automated generation of communal tree cadastres in the contemplated geopgraphic domain. The proposed method demonstrates that (1) high-resolution aerial imagery has great potential in being a precise and efficient alternative for updating or creating communal tree cadastres, (2) updating requires minimal user interaction and can potentially be performed in a fully automated process, and (3) based on the excellent classification results, the considered tree species can now be detected and accurately mapped at scale.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.