Urban Vegetation Classification for Unmanned Aerial Vehicle Remote Sensing Combining Feature Engineering and Improved DeepLabV3+
Forests · 18.02.2024 · 15 (2) · 382
DOI: 10.3390/f15020382 ↗Kurz gefasst
Fachartikel in der Zeitschrift Forests, online erschienen am 18.02.2024. Verfasst von Qianyang Cao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guizhou Provincial Science and Technology Program Project—Natural Resource Statistics and Asset Value Assessment Based on Remote Sensing Big Data, Guizhou Provincial Science and Technology Program Project-Research on Key Technologies for Remote Sensing Monitoring of Natural Resources Assets in Karst Region.
Abstract (Originalsprache)
Addressing the problems of misclassification and omissions in urban vegetation fine classification from current remote sensing classification methods, this research proposes an intelligent urban vegetation classification method that combines feature engineering and improved DeepLabV3+ based on unmanned aerial vehicle visible spectrum images. The method constructs feature engineering under the ReliefF algorithm to increase the number of features in the samples, enabling the deep learning model to learn more detailed information about the vegetation. Moreover, the method improves the classical DeepLabV3+ network structure based on (1) replacing the backbone network using MoblieNetV2; (2) adjusting the atrous spatial pyramid pooling null rate; and (3) adding the attention mechanism and the convolutional block attention module. Experiments were conducted with self-constructed sample datasets, where the method was compared and analyzed with a fully convolutional network (FCN) and U-Net and ShuffleNetV2 networks; the migration of the method was tested as well. The results show that the method in this paper is better than FCN, U-Net, and ShuffleNetV2, and reaches 92.27%, 91.48%, and 85.63% on the accuracy evaluation indices of overall accuracy, MarcoF1, and mean intersection over union, respectively. Furthermore, the segmentation results are accurate and complete, which effectively alleviates misclassifications and omissions of urban vegetation; moreover, it has a certain migration ability that can quickly and accurately classify the vegetation.
Förderung
- Guizhou Provincial Science and Technology Program Project—Natural Resource Statistics and Asset Value Assessment Based on Remote Sensing Big Data
- Guizhou Provincial Science and Technology Program Project-Research on Key Technologies for Remote Sensing Monitoring of Natural Resources Assets in Karst Region
Zitieren
APA
Cao, Q., Li, M., Yang, G., Tao, Q., Luo, Y., Wang, R., & Chen, P. (2024). Urban Vegetation Classification for Unmanned Aerial Vehicle Remote Sensing Combining Feature Engineering and Improved DeepLabV3+. Forests, 15(2), 382. https://doi.org/10.3390/f15020382
Vancouver
Cao Q, Li M, Yang G, Tao Q, Luo Y, Wang R, et al. Urban Vegetation Classification for Unmanned Aerial Vehicle Remote Sensing Combining Feature Engineering and Improved DeepLabV3+. Forests. 2024;15(2):382. doi:10.3390/f15020382
BibTeX
@article{Cao2024,
author = {Cao, Qianyang and Li, Man and Yang, Guangbin and Tao, Qian and Luo, Yaopei and Wang, Renru and Chen, Panfang},
title = {Urban Vegetation Classification for Unmanned Aerial Vehicle Remote Sensing Combining Feature Engineering and Improved DeepLabV3+},
journal = {Forests},
year = {2024},
volume = {15},
number = {2},
pages = {382},
doi = {10.3390/f15020382}
}
EUVIMED