Urban tree <bold>s</bold>pecies <bold>c</bold>lassification based on multispectral <bold>a</bold>irborne LiDAR

Pei-Lun HU; Yu-Wei CHEN; Mohammad IMANGHOLILOO; Markus HOLOPAINEN; Yi-Cheng WANG; Juha HYYPPÄ

doi:10.11972/j.issn.1001-9014.2025.02.008

Journal of Infrared and Millimeter Waves, Volume. 44, Issue 2, 197(2025)

Urban tree species classification based on multispectral airborne LiDAR

Pei-Lun HU^1,2, Yu-Wei CHEN^1、*, Mohammad IMANGHOLILOO², Markus HOLOPAINEN², Yi-Cheng WANG^3、**, and Juha HYYPPÄ¹

Author Affiliations

¹Department of Remote Sensing and Photogrammetry，Finnish Geospatial Research Institute，Espoo 02150，Finland

²Department of Forest Sciences，University of Helsinki，Helsinki 00014，Finland

³Advanced Laser Technology Laboratory of Anhui Province，Hefei 230037，China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(7)

Fig. 1. Map of the study area and tree samples in the research area.

Download full size

View in Article

Fig. 2. Titan intensity image of Study area in Espoolahti（Red：Channel 1；Green：Channel 2；Blue：Channel 3）.

Download full size

View in Article

Fig. 3. The comparison of classification accuracy of 24 tree species：ET，RF，KNN，LR，LDA，CART，NB，SVM

Download full size

View in Article

Fig. 4. The confusion matrix of classification with geometric and intensity features for each species.

Download full size

View in Article

Table 1. List of all features from Multispectral ALS data (i refers to channel numbers, and subscript F represents the single-channel intensity feature used)

View table

View in Article

Table 1. List of all features from Multispectral ALS data (i refers to channel numbers, and subscript F represents the single-channel intensity feature used)

Feature	Definition
Single-channel Intensity（SCI）features
I_max	Maximum intensity
I_min	Minimum intensity
I_mean	Mean intensity
I_std	The standard deviation of intensity
I_cov	Coefficient of variation（i.e.，relative standard deviation）of intensity
I_sk	Skewness of intensity
I_range	Range of intensity
I_kut	Kurtosis of intensity
I₅ to I₉₅	Percentiles of intensity values of points above the ground threshold from 5% to 95% in 5% increments
Multi-channel Intensity（MCI）features
$R_{i}^{F} = I_{i}^{F} / (I_{1}^{F} + I_{2}^{F} + I_{3}^{F})$	Ratios of intensity features in each channel
$g N D V I^{F} = (I_{1}^{F} - I_{3}^{F}) / (I_{2}^{F} + I_{3}^{F})$	Green normalized differential vegetation index（gNDVI）
$g S R F = (I_{2}^{F} / I_{3}^{F})$	Green simple ratio vegetation index（gSR）
Geometric features
H_max	Maximum of the heights of all points
H_mean	Arithmetic mean of the height of all points above 1 m threshold
H_std	Standard deviation of height of all points above 1 m threshold
H_range	Range of normalized height of all points above 1 m threshold
P	Penetration as a ratio between the number of returns below 1 m and total returns
CA	Crown area as the area of the convex hull in 2D
CV	Crown volume as the convex hull in 3D
CD	Crown diameter calculated from crown area considering crown as a circle
HP₁₀to HP₉₀	Percentiles of the points above 1 m height from 10% to 90% at 10% incremental.
D₁to D₁₀	D_i = N_i/N_total，where i = 1 to 10，N_i is the number of points within the ith layer when tree height was divided into 10 intervals starting from 1 m，N_total is the number of all points.

Table 2. List of tree sample

View table

View in Article

Table 2. List of tree sample

Tree species	The index number	Number of Trees
Pinta-ala	1	2
Abies	2	13
Acer	3	249
Alnus	4	5
Betula	5	26
Fallopia	6	1
Fraxinus	7	2
Juglans	8	5
Larix	9	11
Malus	10	8
Picea	11	15
Pinus	12	84
Populus	13	16
Prunus	14	10
Quercus	15	23
Ribes	16	5
Salix	17	4
Sambucus	18	1
Sorbus	19	84
Syringa	20	1
Taxus	21	4
Thuja	22	2
Tilia	23	88
Ulmus	24	163

Table 3. The features have the most predictive power in different classification scenarios
View table
View in Article
Table 3. The features have the most predictive power in different classification scenarios
Cases Top 3 features
All features I²_min，P_1.5，I³_min

Tools

Get Citation

Copy Citation Text

Pei-Lun HU, Yu-Wei CHEN, Mohammad IMANGHOLILOO, Markus HOLOPAINEN, Yi-Cheng WANG, Juha HYYPPÄ. Urban tree species classification based on multispectral airborne LiDAR[J]. Journal of Infrared and Millimeter Waves, 2025, 44(2): 197

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Infrared Spectroscopy and Remote Sensing Technology

Received: Jun. 26, 2024

Accepted: --

Published Online: Mar. 14, 2025

The Author Email: Yu-Wei CHEN (chinaway.fgi@gmail.com), Yi-Cheng WANG (skl_wyc@163.com)

DOI:10.11972/j.issn.1001-9014.2025.02.008

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. List of all features from Multispectral ALS data (i refers to channel numbers, and subscript F represents the single-channel intensity feature used)

Table 1. List of all features from Multispectral ALS data (i refers to channel numbers, and subscript F represents the single-channel intensity feature used)

Table 2. List of tree sample

Table 2. List of tree sample

Table 3. The features have the most predictive power in different classification scenarios

Table 3. The features have the most predictive power in different classification scenarios