Detection of Standing Deadwood from Aerial Imagery Products: Two Methods for Addressing the Bare Ground Misclassification Issue

Abstract

Deadwood mapping is of high relevance for studies on forest biodiversity, forest disturbance, and dynamics. As deadwood predominantly occurs in forests characterized by a high structural complexity and rugged terrain, the use of remote sensing offers numerous advantages over terrestrial inventory. However, deadwood misclassifications can occur in the presence of bare ground, displaying a similar spectral signature. In this study, we tested the potential to detect standing deadwood (h > 5 m) using orthophotos (0.5 m resolution) and digital surface models (DSM) (1 m resolution), both derived from stereo aerial image matching (0.2 m resolution and 60%/30% overlap (end/side lap)). Models were calibrated in a 600 ha mountain forest area that was rich in deadwood in various stages of decay. We employed random forest (RF) classification, followed by two approaches for addressing the deadwood-bare ground misclassification issue: (1) post-processing, with a mean neighborhood filter for “deadwood”-pixels and filtering out isolated pixels and (2) a “deadwood-uncertainty” filter, quantifying the probability of a “deadwood”-pixel to be correctly classified as a function of the environmental and spectral conditions in its neighborhood. RF model validation based on data partitioning delivered high user’s (UA) and producer’s (PA) accuracies (both > 0.9). Independent validation, however, revealed a high commission error for deadwood, mainly in areas with bare ground (UA = 0.60, PA = 0.87). Post-processing (1) and the application of the uncertainty filter (2) improved the distinction between deadwood and bare ground and led to a more balanced relation between UA and PA (UA of 0.69 and 0.74, PA of 0.79 and 0.80, under (1) and (2), respectively). Deadwood-pixels showed 90% location agreement with manually delineated reference to deadwood objects. With both alternative solutions, deadwood mapping achieved reliable results and the highest accuracies were obtained with deadwood-uncertainty filter. Since the information on surface heights was crucial for correct classification, enhancing DSM quality could substantially improve the results.

Detecting overmature forests with airborne laser scanning (ALS)

“…LiDAR data have proven their ability to characterize 3D structures, while optical imagery can inform on species composition or health status. Spectral properties in the near‐infrared region of the light spectrum or indices, like NDVI, based on combinations of reflectance in various bands, are useful to detect snags (Bütler & Schlaepfer, 2004; Zielewska‐Büttner et al., 2020). Combining spectral and textural information from optical data with 3D information from LiDAR data or stereo photogrammetry will lead to more and more efficient models and more reliable cartographic information.…”

A Survey of Computer Vision Techniques for Forest Characterization and Carbon Monitoring Tasks

“…The development of deadwood can be a consequence of the natural course of things or triggered by biotic and abiotic factors such as pest or pathogen outbreaks, changes in hydrologic regime due to climatic shifts, and windstorms [214,215]. Numerous studies are dedicated to find a difference between target object (deadwood occurred due to a specific reason) and other nontarget objects, or, for example, between damaged trees at different stages of factor influence, existing together and displaying similar spectral signatures [216,217]. For instance, in [218], it is recommended to apply a Neural Net with standard backpropagation and SVM among other supervised approaches for the deadwood detection in the case of Chilean Central-Patagonian Forests using high-resolution multi-spectral data (RGB+NIR) with the best algorithm performance of 98%.…”

Detection of standing retention trees in boreal forests with airborne laser scanning point clouds and multispectral imagery

“…Conversely, detecting individual standing dead trees generally presents a much more difficult task requiring relatively costly data. Nevertheless, promising results have been obtained with ALS data at a relatively low point density of 6.7 points/m 2 (Wing et al, 2015) and with aerial imagery at a ground sampling distance of 20 cm (Zielewska‐Büttner et al, 2020). Considering retention trees, their detection, compared with trees in a dense forest, might be facilitated by their positioning as they are often few and far between.…”