Contribution of Geometric Feature Analysis for Deep Learning Classification Algorithms of Urban LiDAR Data

Article


Tarsha Kurdi, Fayez, Amakhchan, Wijdan, Gharineiat, Zahra, Boulaassal, Hakim and Kharki, Omar El. 2023. "Contribution of Geometric Feature Analysis for Deep Learning Classification Algorithms of Urban LiDAR Data." Sensors. 23 (17). https://doi.org/10.3390/s23177360
Article Title

Contribution of Geometric Feature Analysis for Deep Learning Classification Algorithms of Urban LiDAR Data

ERA Journal ID34304
Article CategoryArticle
AuthorsTarsha Kurdi, Fayez, Amakhchan, Wijdan, Gharineiat, Zahra, Boulaassal, Hakim and Kharki, Omar El
Journal TitleSensors
Journal Citation23 (17)
Number of Pages30
Year2023
PublisherMDPI AG
Place of PublicationSwitzerland
ISSN1424-8220
1424-8239
Digital Object Identifier (DOI)https://doi.org/10.3390/s23177360
Web Address (URL)https://www.mdpi.com/1424-8220/23/17/7360
AbstractThe use of a Machine Learning (ML) classification algorithm to classify airborne urban Light Detection And Ranging (LiDAR) point clouds into main classes such as buildings, terrain, and vegetation has been widely accepted. This paper assesses two strategies to enhance the effectiveness of the Deep Learning (DL) classification algorithm. Two ML classification approaches are developed and compared in this context. These approaches utilize the DL Pipeline Network (DLPN), which is tailored to minimize classification errors and maximize accuracy. The geometric features calculated from a point and its neighborhood are analyzed to select the features that will be used in the input layer of the classification algorithm. To evaluate the contribution of the proposed approach, five point-clouds datasets with different urban typologies and ground topography are employed. These point clouds exhibit variations in point density, accuracy, and the type of aircraft used (drone and plane). This diversity in the tested point clouds enables the assessment of the algorithm’s efficiency. The obtained high classification accuracy between 89% and 98% confirms the efficacy of the developed algorithm. Finally, the results of the adopted algorithm are compared with both rule-based and ML algorithms, providing insights into the positioning of DL classification algorithms among other strategies suggested in the literature.
KeywordsLiDAR; point cloud; classification; buildings; vegetation; terrain; urban areas; deep learning; machine learning; geometric features
Article Publishing Charge (APC) Amount Paid2600.0
Article Publishing Charge (APC) FundingOther
Contains Sensitive ContentDoes not contain sensitive content
ANZSRC Field of Research 2020401304. Photogrammetry and remote sensing
461103. Deep learning
Byline AffiliationsSchool of Surveying and Built Environment
Abdelmalek Essaâdi University, Morocco
Permalink -

https://research.usq.edu.au/item/z26z4/contribution-of-geometric-feature-analysis-for-deep-learning-classification-algorithms-of-urban-lidar-data

Download files


Published Version
sensors-23-07360-v2.pdf
License: CC BY 4.0
File access level: Anyone

  • 5
    total views
  • 3
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as

Related outputs

Efficiency of Terrestrial Laser Scanning in Survey Works: Assessment, Modelling, and Monitoring
Tarsha Kurdi, Fayez, Reed, Paul, Gharineiat, Zahra and Awrangjeb, Mohammad. 2023. "Efficiency of Terrestrial Laser Scanning in Survey Works: Assessment, Modelling, and Monitoring." International Journal of Environmental Sciences and Natural Resources. 32 (2). https://doi.org/10.19080/IJESNR.2023.32.556334
3D LoD2 and LoD3 Modelling of Rotating Surface Building of Ornamental Towers starting from LiDAR Data
Lewandowicz, Elzbieta, Tarsha Kurdi, Fayez and Gharineiat, Zahra. 2023. "3D LoD2 and LoD3 Modelling of Rotating Surface Building of Ornamental Towers starting from LiDAR Data." Oniga, Valeria-Ersilia (ed.) Prime Archives in Remote Sensing. India. Vide Leaf.
Torsional behavior of GFRP-reinforced concrete pontoon decks with and without an edge cutout
Manalo, Allan, Yang, Xian, Alajarmeh, Omar, Benmokrane, Brahim, Gharineiat, Zahra, Ebrahimzadeh, Shahrad, Sorbello, Charles-Dean and Weerakoon, Senarath. 2023. "Torsional behavior of GFRP-reinforced concrete pontoon decks with and without an edge cutout." Marine Structures. 88. https://doi.org/10.1016/j.marstruc.2022.103345
Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data
Tarsha Kurdi, Fayez, Lewandowicz, Elzbieta, Gharineiat, Zahra and Shan, Jie. 2023. "Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data." Remote Sensing. 15 (13). https://doi.org/10.3390/rs15133324
Machine learning-based segmentation of aerial LiDAR point cloud data on building roof
Dey, Emon Kumar, Awrangjeb, Mohammad, Tarsha Kurdi, Fayez and Stantic, Bela. 2023. "Machine learning-based segmentation of aerial LiDAR point cloud data on building roof." European Journal of Remote Sensing. 56 (1). https://doi.org/10.1080/22797254.2023.2210745
Construction and Deconstruction: Materials and substances from 'waste'
Burey, Paulomi, Feldman, Jessica, Seligmann, Hannah, Song, Eric, Flynn, Matthew, Helwig, Andreas, Gharineiat, Zahra, Seneviratne, Dinuki, Whiteside, Eliza, Shelley, Tristan, Priesler, Nils, Manalo, Allan, Mirzaghorbanali, Ali, Nourizadeh, Hadi, Roberts, Michae, Nicol, Rose, Redmond, Petrea, Lynch, Mark, Dearnaley, John, ..., Germon, Geoff. 2023. "Construction and Deconstruction: Materials and substances from 'waste'." Chemistry in Australia. (June-August 2023), pp. 16-21.
CNN Based Image Classification of Malicious UAVs
Brown, Jason, Gharineiat, Zahra and Raj, Nawin. 2023. "CNN Based Image Classification of Malicious UAVs." Applied Sciences. 13 (1), pp. 1-13. https://doi.org/10.3390/app13010240
Crack Detection in Concrete Structures Using Deep Learning
Golding, Vaughn Peter, Gharineiat, Zahra, Munawar, Hafiz Suliman and Ullah, Fahim. 2022. "Crack Detection in Concrete Structures Using Deep Learning." Sustainability. 14 (13), pp. 1-25. https://doi.org/10.3390/su14138117
A Framework for Burnt Area Mapping and Evacuation Problem Using Aerial Imagery Analysis
Munawar, Hafiz Suliman, Gharineiat, Zahra, Akram, Junaid and Khan, Sara Imran. 2022. "A Framework for Burnt Area Mapping and Evacuation Problem Using Aerial Imagery Analysis." Fire. 5 (4), pp. 1-15. https://doi.org/10.3390/fire5040122
3D LoD2 and LoD3 Modeling of Buildings with Ornamental Towers and Turrets Based on LiDAR Data
Lewandowicz, Elzbieta, Tarsha Kurdi, Fayez and Gharineiat, Zahra. 2022. "3D LoD2 and LoD3 Modeling of Buildings with Ornamental Towers and Turrets Based on LiDAR Data." Remote Sensing. 14 (19), pp. 1-17. https://doi.org/10.3390/rs14194687
Review of Automatic Processing of Topography and Surface Feature Identification LiDAR Data Using Machine Learning Techniques
Gharineiat, Zahra, Tarsha Kurdi, Fayez and Campbell, Glenn. 2022. "Review of Automatic Processing of Topography and Surface Feature Identification LiDAR Data Using Machine Learning Techniques." Remote Sensing. 14 (19), pp. 1-24. https://doi.org/10.3390/rs14194685
Assessment and Prediction of Sea Level Trend in the South Pacific Region
Raj, Nawin, Gharineiat, Zahra, Ahmed, Abul Abrar Masrur and Stepanyants, Yury. 2022. "Assessment and Prediction of Sea Level Trend in the South Pacific Region." Remote Sensing. 14 (4), pp. 1-25. https://doi.org/10.3390/rs14040986
Comparative Approach of Unmanned Aerial Vehicle Restrictions in Controlled Airspaces
McTegg, Stephen, Kurdi, Fayez, Simmons, Shane and Gharineiat, Zahra. 2022. "Comparative Approach of Unmanned Aerial Vehicle Restrictions in Controlled Airspaces." Remote Sensing. 14 (4), pp. 1-30. https://doi.org/10.3390/rs14040822
Automatic Filtering of Lidar Building Point Cloud in Case of Trees Associated to Building Roof
Tarsha Kurdi, Fayez, Gharineiat, Zahra, Campbell, Glenn, Awrangjeb, Mohammad and Dey, Emon Kumar. 2022. "Automatic Filtering of Lidar Building Point Cloud in Case of Trees Associated to Building Roof." Remote Sensing. 14 (2), pp. 1-23. https://doi.org/10.3390/rs14020430
Full series algorithm of automatic building extraction and modelling from LiDAR data
Tarsha Kurdi, Fayez, Gharineiat, Zahra, Campbell, Glenn, Dey, Emon Kumar and Awrangjeb, Mohammad. 2021. "Full series algorithm of automatic building extraction and modelling from LiDAR data." Zhou, Jun, Salvado, Olivier, Sohel, Ferdous, Borges, Paulo and Wang, Shilin (ed.) 2021 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2021). Gold Coast, Australia 29 Nov - 01 Dec 2021 United States.
Anthocyanin retention in Queen Garnet plums during processing and bottling
Pahl, Jessica, Burey, Polly, Lynch, Mark, Helwig, Andreas and Gharineiat, Zahra. 2022. Anthocyanin retention in Queen Garnet plums during processing and bottling. Australia. Fight Food Waste Cooperative Research Centre.
Pressure beneath the foot for older adults using an improved approach
Al-Daffaie, Kadhem, Chong, Albert K. and Gharineiat, Zahra. 2019. "Pressure beneath the foot for older adults using an improved approach." 9th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE 2019). Kota Kinabalu, Malaysia 27 - 28 Apr 2019 United States. https://doi.org/10.1109/ISCAIE.2019.8743653
Evaluation of multivariate adaptive regression splines and artificial neural network for prediction of mean sea level trend around northern Australian coastlines
Raj, Nawin and Gharineiat, zahra. 2021. "Evaluation of multivariate adaptive regression splines and artificial neural network for prediction of mean sea level trend around northern Australian coastlines." Mathematics. 9 (21), pp. 1-20. https://doi.org/10.3390/math9212696
Random forest machine learning technique for automatic vegetation detection and modelling in LiDAR data
Tarsha Kurdi, Fayez, Amakhchan, Wijdan and Gharineiat, Zahra. 2021. "Random forest machine learning technique for automatic vegetation detection and modelling in LiDAR data." International Journal of Environmental Sciences and Natural Resources. 28 (2). https://doi.org/10.19080/IJESNR.2021.28.556234
Plantar Pressure Characteristics in Obese Individuals: A Proposed Methodology
Al-Daffaie, Kadhem, Chong, Albert K. and Gharineiat, Zahra. 2019. "Plantar Pressure Characteristics in Obese Individuals: A Proposed Methodology." 2019 3rd International Conference on Imaging, Signal Processing and Communication (ICISPC). Singapore 27 - 29 Jul 2019 United States. IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/ICISPC.2019.8935691
Spectral Analysis of Satellite Altimeters and Tide Gauges Data around the Northern Australian Coast
Gharineiat, Zahra and Deng, Xiaoli. 2020. "Spectral Analysis of Satellite Altimeters and Tide Gauges Data around the Northern Australian Coast." Remote Sensing. 12 (1), pp. 1-15. https://doi.org/10.3390/rs12010161
Description and assessment of regional sea-level trends and variability from altimetry and tide gauges at the northern Australian coast
Gharineiat, Zahra and Deng, Xiaoli. 2018. "Description and assessment of regional sea-level trends and variability from altimetry and tide gauges at the northern Australian coast." Advances in Space Research. 61 (10), pp. 2540-2554. https://doi.org/10.1016/j.asr.2018.02.038
Coastal altimetry for sea level changes in Northern Australian coastal oceans
Gharineiat, Zahra. 2017. Coastal altimetry for sea level changes in Northern Australian coastal oceans. PhD Thesis Doctor of Philosophy. University of Newcastle.
Observing and modelling the high water level from satellite radar altimetry during tropical cyclones
Deng, Xiaoli, Gharineiat, Zahra, Andersen, Ole B. and Stewart, Mark G.. 2016. "Observing and modelling the high water level from satellite radar altimetry during tropical cyclones." Rizos, Chris and Willis, Pascal (ed.) 2013 IAG Scientific Assembly. Postdam, Germany 01 - 06 Sep 2013 Switzerland. https://doi.org/10.1007/1345_2015_108
Application of the multi adaptive regression splines to integrate sea level data from altimetry and tide gauges for monitoring extreme sea level events
Gharineiat, Zahra and Deng, Xiaoli. 2015. "Application of the multi adaptive regression splines to integrate sea level data from altimetry and tide gauges for monitoring extreme sea level events." Marine Geodesy. 38 (3), pp. 261-276. https://doi.org/10.1080/01490419.2015.1036183