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

Sean Krisanski,Mohammad Sadegh Taskhiri,David Herries,Paul Turner,Susana Gonzalez Aracil

doi:10.3390/rs13081413

Sean Krisanski, Mohammad Sadegh Taskhiri + Show 3 more

Open Access

https://doi.org/10.3390/rs13081413

Copy DOI

Journal: Remote sensing	Publication Date: Apr 7, 2021
Citations: 33	License type: CC BY 4.0

Affiliation: University of Tasmania, Rotorua Hospital

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.

Highlights

Forest measurements are important in a number of fields including, but not limited to, forestry, climate science [1,2,3], fire risk management [4,5], and understanding habitat structural complexity [6,7,8]
The segmentation works described above were mostly designed with individual sensing methods in mind, such as Terrestrial Laser Scanning (TLS) [20,21,22,23,27,28,33,34], Mobile Laser Scanning (MLS) [25,28], or Aerial Laser Scanning (ALS) [26,28,29,30,31,32], resulting in limited transferability to point clouds captured using other methods with the exception of [28], whose approach was demonstrated on ALS, TLS, and MLS
The misclassification of some terrain points as stem points appears to mostly occur when the sample box region has cropped the terrain on the edges of the point cloud or partially cropped into the terrain with the upper or lower boundary of the box vertically. These cases can change the appearance of the terrain such that even a human may have difficulty identifying it correctly. We suggest that this problem is one of context, as when the sample is seen in context, it is easy for a human to identify these examples correctly as terrain, but without context, a small slice of terrain may look very similar to coarse woody debris (CWD), a branch/stem in the air, or vegetation

Summary

Introduction

Forest measurements are important in a number of fields including, but not limited to, forestry, climate science [1,2,3], fire risk management [4,5], and understanding habitat structural complexity [6,7,8]. Modern remote sensing techniques such as Light Detection and Ranging (LiDAR) and photogrammetry are enabling high-quality 3D reconstructions of forests to be collected by operators with little or no surveying training. Transformative are techniques such as close-range photogrammetry, which enable researchers and foresters to collect high accuracy and high-resolution 3D reconstructions of forests with low-cost, consumer-grade cameras [9,10] and low-cost Unoccupied Aircraft Systems (UAS) [11,12]. There are many challenges such as occlusions, complex structures, understory vegetation, and rugged terrain that are not yet well handled by existing approaches [18], resulting in applied forest studies commonly resorting to time-consuming manual methods of extracting measurements from forest point clouds [19]. Of particular note is that most point cloud tools are intended primarily for very high-quality Terrestrial Laser Scanning (TLS)

Objectives

Methods

Discussion

Conclusion