Sensor Agnostic Semantic Segmentation of Structurally Diverse and Complex Forest Point Clouds Using Deep Learning

Abstract

Forest inventories play an important role in enabling informed decisions to be made for the management and conservation of forest resources; however, the process of collecting inventory information is laborious. Despite advancements in mapping technologies allowing forests to be digitized in finer granularity than ever before, it is still common for forest measurements to be collected using simple tools such as calipers, measuring tapes, and hypsometers. Dense understory vegetation and complex forest structures can present substantial challenges to point cloud processing tools, often leading to erroneous measurements, and making them of less utility in complex forests. To address this challenge, this research demonstrates an effective deep learning approach for semantically segmenting high-resolution forest point clouds from multiple different sensing systems in diverse forest conditions. Seven diverse point cloud datasets were manually segmented to train and evaluate this model, resulting in per-class segmentation accuracies of Terrain: 95.92%, Vegetation: 96.02%, Coarse Woody Debris: 54.98%, and Stem: 96.09%. By exploiting the segmented point cloud, we also present a method of extracting a Digital Terrain Model (DTM) from such segmented point clouds. This approach was applied to a set of six point clouds that were made publicly available as part of a benchmarking study to evaluate the DTM performance. The mean DTM error was 0.04 m relative to the reference with 99.9% completeness. These approaches serve as useful steps toward a fully automated and reliable measurement extraction tool, agnostic to the sensing technology used or the complexity of the forest, provided that the point cloud has sufficient coverage and accuracy. Ongoing work will see these models incorporated into a fully automated forest measurement tool for the extraction of structural metrics for applications in forestry, conservation, and research.

Forest Structural Complexity Tool—An Open Source, Fully-Automated Tool for Measuring Forest Point Clouds

“…This work builds upon our previous paper [58], relying upon the semantically segmented point clouds as a starting point for our other algorithms. Figure 1 shows a schematic diagram of how FSCT is designed, and how it is connected to our previous semantic segmentation paper.…”

“…Suitable point clouds can be from MLS, TLS, both aerial and terrestrial close-range photogrammetry (AP/TP), and even high-resolution ALS. The "previously published" research refers to our previous paper on this project, which focused on the semantic segmentation of complex forest point clouds [58]. This open source tool is available here: https://github.com/SKrisanski/FSCT (accessed on 19 November 2021).…”

“…ns. 2021, 13, x FOR PEER REVIEW 4 of 30 earch refers to our previous paper on this project, which focused on the semantic segmentation of complex forest point uds [58]. This open source tool is available here: https://github.com/SKrisanski/FSCT (Date Accessed: 19 November 1).…”

“…This deep learning approach was trained with the goal of working on structurally diverse point clouds captured using most highresolution point cloud generation techniques. This approach was described and evaluated in our previous paper [58], and forms the starting point from which this paper continues. This paper describes how we exploit the segmented point cloud to extract highly detailed measurements from forest point clouds, both robustly and completely automatically on point clouds from multiple sensor types.…”

Computer Vision Techniques in Forest Inventory Assessment: Improving Accuracy of Tree Diameter Measurement Using Smartphone Camera and Photogrammetry

“…There is growing interest in using terrestrial laser scanning (TLS) and airborne laser scanning (ALS) systems to assess tree and forest biometric information based on 3D PCD. (15)(16)(17)(18) The 3D PCD generated from LIDAR sensors can not only provide DBH, tree height, and the volume of individual trees but is also valuable information for improving forest management and planning, (19)(20)(21)(22)(23)(24) including optimal forest inventory and biomass estimation. (25,26) However, the application of LIDAR systems in TLS and ALS is limited by the high cost of LIDAR systems and analysis tools.…”