Improving Deciduous Forest Inventory Plot Center Measurement Using Unoccupied Aerial Systems Imagery

Abstract

Field-based forest inventory plots are fundamental for many forest studies. These on-the-ground measurements of small samples of forested areas provide foresters with key information such as the size, abundance, health, and value of their forests. Recently, forest inventory plots have begun to be used as ground validation for tree features automatically extracted from remotely sensed data sets. Additionally, machine learning methods for feature extraction rely heavily on large quantities of training data and require these field forest inventory measurement datasets for algorithm training. Undermining the usefulness of forest inventory plot data as validation or training data is the positional uncertainty of plot location measurements. Because global navigation satellite systems (GNSS) cannot reliably measure plot center coordinates under thick tree canopy, plot center coordinates usually contain multiple meters of horizontal error. We present a method for reliably measuring plot center coordinates in which plot centers are individually marked with low-cost targets, allowing plot centers to be manually measured from orthoimagery captured during the leaf-off season. Our plot center measurements are shown to have less than 10 cm of horizontal error, an improvement of an order of magnitude over traditional GNSS methods. Study Implications: Recently, as unoccupied aerial systems (UASs) make high-resolution data easy to collect, researchers have begun to develop methods for measuring individual tree features automatically from remotely sensed data. The output from these methods must be compared to on-the-ground measurements, most commonly to forest inventories. Although forest inventories provide accurate per tree characteristics, there is no method for measuring the global position of these inventories accurately and reliably. This prevents the ground measurements from matching up with remotely sensed datasets. This study introduces a method for using UASs to reliably measure the coordinates of plot centers to within 10 cm of true position.