EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LiDAR point cloud denoising for individual tree extraction based on the Noise4Denoise

Xiangfei Lu, Zongyu Ye, Liyong Fu, Huaiyi Wang, Kaiyu Wang, Yaquan Dou, Dongbo Xie, Xiaodi Zhao

Frontiers in Plant Science · 09.01.2025 · 15

DOI: 10.3389/fpls.2024.1490660 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 09.01.2025. Verfasst von Xiangfei Lu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Research Institute of Forest Policy and Information, Chinese Academy of Forestry, Beijing, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The processing of LiDAR point cloud data is of critical importance in the context of forest resource surveys, as well as representing a pivotal element in the realm of forest physiological and ecological studies.Nonetheless, conventional denoising algorithms frequently exhibit deficiencies with regard to adaptability and denoising efficacy, particularly when employed in relation to disparate datasets.To address these issues, this study introduces DEN4, an unsupervised, deep learning-based point cloud denoising algorithm designed to improve the accuracy of single tree segmentation in LiDAR point clouds.DEN4 introduces a multilevel noise separation module that effectively distinguishes between signal and noise, thereby improving the signal-to-noise ratio (SNR) and reducing the error.The experimental results demonstrate that DEN4 significantly outperforms traditional denoising methods in several key metrics, including mean square error (MSE), SNR, Hausdorff distance, and structural similarity index (SSIM).In the 60 sample dataset, DEN4 achieved the best mean and standard deviation on all metrics: Specifically, the MSE mean was found to be 0.0094, with a standard deviation of 0.0008, the SNR mean was 149.1570, with a standard deviation of 0.5628, the Hausdorff mean was 0.8503, with a standard deviation of 0.0947, and the SSIM mean was 0.8399, with a standard deviation of 0.0054. For instance, in the S10 dataset, DEN4 attained a 70.2% diminution in MSE and a 37.8% augmentation in SNR in comparison with PTD.The findings demonstrate the efficacy of DEN4 in multiple forest datasets, its ability to maintain geometric integrity, and its enhanced stability without the necessity for pre-labelled data. The algorithm's superior performance and robustness in diverse forest environments underscores its potential application in single tree segmentation and forest resource management.

Schlagwörter

Stichwörter der Autor:innen

LiDAR point cloudsdeep learningecological studyindividual tree extractionpoint cloud denoising

Autor:innen und Institutionen

  • Research Institute of Forest Policy and Information, Chinese Academy of Forestry, Beijing, China.
  • School of Mechanical and Materials Engineering, North China University of Technology, Beijing, China.
  • Research Institute of Forest Resource Information Technique, Chinese Academy of Forestry, Beijing, China.
  • Information Technology, Belarusian State University, Minsk, Belarus.

Zitieren

APA

Lu, X., Ye, Z., Fu, L., Wang, H., Wang, K., Dou, Y., Xie, D., & Zhao, X. (2025). LiDAR point cloud denoising for individual tree extraction based on the Noise4Denoise. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1490660

Vancouver

Lu X, Ye Z, Fu L, Wang H, Wang K, Dou Y, et al. LiDAR point cloud denoising for individual tree extraction based on the Noise4Denoise. Frontiers in Plant Science. 2025;15. doi:10.3389/fpls.2024.1490660

BibTeX
@article{Lu2025,
  author = {Lu, Xiangfei and Ye, Zongyu and Fu, Liyong and Wang, Huaiyi and Wang, Kaiyu and Dou, Yaquan and Xie, Dongbo and Zhao, Xiaodi},
  title = {LiDAR point cloud denoising for individual tree extraction based on the Noise4Denoise},
  journal = {Frontiers in Plant Science},
  year = {2025},
  volume = {15},
  doi = {10.3389/fpls.2024.1490660}
}
Kostenlos starten →