Delineation of Tree Crowns and Tree Species Classification From Full-Waveform Airborne Laser Scanning Data Using 3-D Ellipsoidal Clustering

Lindberg, Eva; Eysn, Lothar; Hollaus, Markus; Holmgren, Johan; Pfeifer, Norbert

doi:10.1109/jstars.2014.2331276

Cited by 70 publications

(54 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The higher accuracy when using combined feature sets is comparable with the results of earlier studies, e.g. : Lindberg et al (2014), who achieved an OA of 71% compared to 60% using solely geometric features. The usage of features related to the crown is only possible to a limited extent.…”

Section: Classificationsupporting

confidence: 86%

Urban Tree Classification Using Full-Waveform Airborne Laser Scanning

Koma¹,

Koenig²,

Höfle³

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Vegetation mapping in urban environments plays an important role in biological research and urban management. Airborne laser scanning provides detailed 3D geodata, which allows to classify single trees into different taxa. Until now, research dealing with tree classification focused on forest environments. This study investigates the object-based classification of urban trees at taxonomic family level, using full-waveform airborne laser scanning data captured in the city centre of Vienna (Austria). The data set is characterised by a variety of taxa, including deciduous trees (beeches, mallows, plane trees and soapberries) and the coniferous pine species. A workflow for tree object classification is presented using geometric and radiometric features. The derived features are related to point density, crown shape and radiometric characteristics. For the derivation of crown features, a prior detection of the crown base is performed. The effects of interfering objects (e.g. fences and cars which are typical in urban areas) on the feature characteristics and the subsequent classification accuracy are investigated. The applicability of the features is evaluated by Random Forest classification and exploratory analysis. The most reliable classification is achieved by using the combination of geometric and radiometric features, resulting in 87.5% overall accuracy. By using radiometric features only, a reliable classification with accuracy of 86.3% can be achieved. The influence of interfering objects on feature characteristics is identified, in particular for the radiometric features. The results indicate the potential of using radiometric features in urban tree classification and show its limitations due to anthropogenic influences at the same time.

show abstract

Section: Classificationsupporting

confidence: 86%

Urban Tree Classification Using Full-Waveform Airborne Laser Scanning

Koma¹,

Koenig²,

Höfle³

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The most demanding task using passive imaging systems has always been discriminating pines from spruces due to their spectral similarity. However, structural data from laser scanning has shown it can capture the structural differences of these species, such as the vertical extent of the leafy canopy [18,22,23].…”

Section: Introductionmentioning

confidence: 99%

Individual Tree Detection and Classification with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging

et al. 2017

View full text Add to dashboard Cite

Small unmanned aerial vehicle (UAV) based remote sensing is a rapidly evolving technology. Novel sensors and methods are entering the market, offering completely new possibilities to carry out remote sensing tasks. Three-dimensional (3D) hyperspectral remote sensing is a novel and powerful technology that has recently become available to small UAVs. This study investigated the performance of UAV-based photogrammetry and hyperspectral imaging in individual tree detection and tree species classification in boreal forests. Eleven test sites with 4151 reference trees representing various tree species and developmental stages were collected in June 2014 using a UAV remote sensing system equipped with a frame format hyperspectral camera and an RGB camera in highly variable weather conditions. Dense point clouds were measured photogrammetrically by automatic image matching using high resolution RGB images with a 5 cm point interval. Spectral features were obtained from the hyperspectral image blocks, the large radiometric variation of which was compensated for by using a novel approach based on radiometric block adjustment with the support of in-flight irradiance observations. Spectral and 3D point cloud features were used in the classification experiment with various classifiers. The best results were obtained with Random Forest and Multilayer Perceptron (MLP) which both gave 95% overall accuracies and an F-score of 0.93. Accuracy of individual tree identification from the photogrammetric point clouds varied between 40% and 95%, depending on the characteristics of the area. Challenges in reference measurements might also have reduced these numbers. Results were promising, indicating that hyperspectral 3D remote sensing was operational from a UAV platform even in very difficult conditions. These novel methods are expected to provide a powerful tool for automating various environmental close-range remote sensing tasks in the very near future.

show abstract

“…The shape and proportions of tree crowns differ somewhat between species and have been used for tree species classification [3][4][5][6][7]. Additionally, tree crowns can be separated from small trees below the top-most canopy to achieve better defined derived features [8,9].…”

Section: Introductionmentioning

confidence: 99%

Exploring Multispectral ALS Data for Tree Species Classification

2018

Self Cite

View full text Add to dashboard Cite

Multispectral Airborne Laser Scanning (ALS) is a new technology and its output data have not been fully explored for tree species classification purposes. The objective of this study was to investigate what type of features from multispectral ALS data (wavelengths of 1550 nm, 1064 nm and 532 nm) are best suited for tree species classification. Remote sensing data were gathered over hemi-boreal forest in southern Sweden (58 • 27 18.35 N, 13 • 39 08.03 E) on 21 July 2016. The field data consisted of 179 solitary trees from nine genera and ten species. Two new methods for feature extraction were tested and compared to features of height and intensity distributions. The features that were most important for tree species classification were intensity distribution features. Features from the upper part of the upper and outer parts of the crown were better for classification purposes than others. The best classification model was created using distribution features of both intensity and height in multispectral data, with a leave-one-out cross-validated accuracy of 76.5%. As a comparison, only structural features resulted in an highest accuracy of 43.0%. Picea abies and Pinus sylvestris had high user's and producer's accuracies and were not confused with any deciduous species. Tilia cordata was the deciduous species with a large sample that was most frequently confused with many other deciduous species. The results, although based on a small and special data set, suggest that multispectral ALS is a technology with great potential for tree species classification.

show abstract

Delineation of Tree Crowns and Tree Species Classification From Full-Waveform Airborne Laser Scanning Data Using 3-D Ellipsoidal Clustering

Cited by 70 publications

References 17 publications

Urban Tree Classification Using Full-Waveform Airborne Laser Scanning

Urban Tree Classification Using Full-Waveform Airborne Laser Scanning

Individual Tree Detection and Classification with UAV-Based Photogrammetric Point Clouds and Hyperspectral Imaging

Exploring Multispectral ALS Data for Tree Species Classification

Contact Info

Product

Resources

About