Enhanced DeepLabV3+ with OBIA and Lightweight Attention for Accurate and Efficient Tree Species Classification in UAV Images
Sensors · 2025
DOI: 10.3390/s25247501 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Xue Cheng und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China. Hauptthemen laut MEDLINE: Trees, Unmanned Aerial Devices, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangxi Province, Guangxi Key Laboratory of Spatial Information and Geomatics under Grant.
Abstract (Originalsprache)
Accurate tree species classification using high-resolution unmanned aerial vehicle (UAV) images is crucial for forest carbon cycle research, biodiversity conservation, and sustainable management. However, challenges persist due to high interspecies feature similarity, complex canopy boundaries, and computational demands. To address these, we propose an enhanced DeepLabV3+ model integrating Object-Based Image Analysis (OBIA) and a lightweight attention mechanism. First, an OBIA-based multiscale segmentation algorithm optimizes object boundaries. Key discriminative features, including spectral, positional, and vegetation indices, are then identified using Recursive Feature Elimination with Cross-Validation (RFECV). High-precision training labels are efficiently constructed by combining Random Forest classification with visual interpretation (RFVI). The DeepLabV3+ model is augmented with a lightweight attention module to focus on critical regions while significantly reducing model parameters. Evaluations demonstrate that the improved DeepLabV3+ model achieved overall accuracy (OA) of 94.91% and Kappa coefficient (Kappa) of 92.89%, representing improvements of 2.91% and 4.11% over the original DeepLabV3+ model, while reducing parameters to 5.91 M (78.35% reduction). It significantly outperformed U-Net, PSPNet, and the original DeepLabV3+. This study provides a high-accuracy yet lightweight solution for automated tree species mapping, offering vital technical support for forest carbon sink monitoring and ecological management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541004, China.
- Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541004, China.
ORCID-Profile: Jianjun Chen, Jiayuan Yin, Zizhen Chen, Haotian You, Xiaowen Han, Guoqing Zhou
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Guangxi Province
- Guangxi Key Laboratory of Spatial Information and Geomatics under Grant
- the Major Special Projects of High Resolution Earth Observation System
- Guangxi Key Laboratory of Spatial Information and Geomatics
- BaGui Young Outstanding Talents Cultivation Program of the provincial government of Guangxi
Zitieren
APA
Cheng, X., Chen, J., Li, J., Yin, J., Cheng, Q., Chen, Z., Li, X., You, H., Han, X., & Zhou, G. (2025). Enhanced DeepLabV3+ with OBIA and Lightweight Attention for Accurate and Efficient Tree Species Classification in UAV Images. Sensors. https://doi.org/10.3390/s25247501
Vancouver
Cheng X, Chen J, Li J, Yin J, Cheng Q, Chen Z, et al. Enhanced DeepLabV3+ with OBIA and Lightweight Attention for Accurate and Efficient Tree Species Classification in UAV Images. Sensors. 2025. doi:10.3390/s25247501
BibTeX
@article{Cheng2025,
author = {Cheng, Xue and Chen, Jianjun and Li, Junji and Yin, Jiayuan and Cheng, Qingmin and Chen, Zizhen and Li, Xinhong and You, Haotian and Han, Xiaowen and Zhou, Guoqing},
title = {Enhanced DeepLabV3+ with OBIA and Lightweight Attention for Accurate and Efficient Tree Species Classification in UAV Images},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25247501}
}
EUVIMED