Deep Ordinal Classification in Forest Areas Using Light Detection and Ranging Point Clouds
Alejandro Morales-Martín 
Pedro Antonio Gutiérrez 
Víctor Manuel Vargas-Yun 
César Hervás-Martínez Sensors
INSTRUMENTS & INSTRUMENTATION
Abstract
Recent advances in Deep Learning and aerial Light Detection And Ranging (LiDAR) have offered the possibility of refining the classification and segmentation of 3D point clouds to contribute to the monitoring of complex environments. In this context, the present study focuses on developing an ordinal classification model in forest areas where LiDAR point clouds can be classified into four distinct ordinal classes: ground, low vegetation, medium vegetation, and high vegetation. To do so, an effective soft labeling technique based on a novel proposed generalized exponential function (CE-GE) is applied to the PointNet network architecture. Statistical analyses based on Kolmogorov–Smirnov and Student’s t-test reveal that the CE-GE method achieves the best results for all the evaluation metrics compared to other methodologies. Regarding the confusion matrices of the best alternative conceived and the standard categorical cross-entropy method, the smoothed ordinal classification obtains a more consistent classification compared to the nominal approach. Thus, the proposed methodology significantly improves the point-by-point classification of PointNet, reducing the errors in distinguishing between the middle classes (low vegetation and medium vegetation).
Keywords
BibTex Citation
@article{Morales2024Deep,
author = {Morales-Mart{\' i}n, Alejandro and Mesas-Carrascosa, Francisco-Javier and Guti{\' e}rrez, Pedro Antonio and P{\' e}rez-Porras, Fernando-Juan and Vargas-Yun, V{\' i}ctor Manuel and Herv{\' a}s-Mart{\' i}nez, C{\' e}sar},
journal = {Sensors},
doi = {10.3390/s24072168},
number = {7},
year = {2024},
pages = {1--18},
title = {Deep {Ordinal} {Classification} in {Forest} {Areas} {Using} {Light} {Detection} and {Ranging} {Point} {Clouds}},
url = {https://www.mdpi.com/1424-8220/24/7/2168},
howpublished = {https://www.mdpi.com/1424-8220/24/7/2168},
volume = {24},
}
BibTex Unicode Citation
@article{Morales2024Deep,
author = {Morales-Martín, Alejandro and Mesas-Carrascosa, Francisco-Javier and Gutiérrez, Pedro Antonio and Pérez-Porras, Fernando-Juan and Vargas-Yun, Víctor Manuel and Hervás-Martínez, César},
journal = {Sensors},
doi = {10.3390/s24072168},
number = {7},
year = {2024},
pages = {1--18},
title = {Deep {Ordinal} {Classification} in {Forest} {Areas} {Using} {Light} {Detection} and {Ranging} {Point} {Clouds}},
url = {https://www.mdpi.com/1424-8220/24/7/2168},
howpublished = {https://www.mdpi.com/1424-8220/24/7/2168},
volume = {24},
}
APA Citation
Morales-Martín, A., Mesas-Carrascosa, F.-J., Gutiérrez, P. A., Pérez-Porras, F.-J., Vargas-Yun, V. M., & Hervás-Martínez, C. (2024). Deep Ordinal Classification in Forest Areas Using Light Detection and Ranging Point Clouds. Sensors, 24(7), 1–18. https://doi.org/10.3390/s24072168
RIS Citation
TY - JOUR
AU - Morales-Martín, Alejandro
AU - Mesas-Carrascosa, Francisco-Javier
AU - Gutiérrez, Pedro Antonio
AU - Pérez-Porras, Fernando-Juan
AU - Vargas-Yun, Víctor Manuel
AU - Hervás-Martínez, César
DA - 2024///
PY - 2024
DO - 10.3390/s24072168
ID - temp_id_410492609566
IS - 7
SP - 1-18
T2 - Sensors
TI - Deep Ordinal Classification in Forest Areas Using Light Detection and
Ranging Point Clouds
UR - https://www.mdpi.com/1424-8220/24/7/2168
VL - 24
ER -
CV Citation
A. Morales-Martín (CA), F. Mesas-Carrascosa, P.A. Gutiérrez, F. Pérez-Porras, V.M. Vargas-Yun, C. Hervás-Martínez (5/6). "Deep Ordinal Classification in Forest Areas Using Light Detection and Ranging Point Clouds". Sensors, Vol. 24(7), pp. 1-18, 2024. (Q2, IF: 3.5).