Fine-scale grassland land-cover classification using UAV RGB and multispectral imagery with staged feature selection
- 1College of Computer Science and Technology, Inner Mongolia Minzu University
- 2College of Information and Electrical Engineering, Shenyang Agricultural University
Abstract
Introduction: Accurate mapping of grassland vegetation and bare land is important for grassland degradation assessment and ecological management. This study investigated the effectiveness of integrating visible and multispectral imagery with staged feature selection for fine-scale grassland land-cover classification.
Methods: Four representative grassland land-cover classes, including Caragana microphylla, Artemisia scoparia, Agropyron cristatum, and bare land, were selected as classification categories. Spectral bands, vegetation indices, and texture metrics were combined to construct a multi-source feature pool, and different feature optimization strategies and classification models were systematically compared.
Results: Multi-source feature fusion improved the discrimination of spectrally similar land-cover classes, while staged feature selection provided a workflow for reducing cross-source feature redundancy while retaining complementary information. The model with the highest observed validation accuracy selected only ten features from the original feature pool and achieved an overall accuracy of 91.54% with a Kappa coefficient of 88.72%. Compared with direct feature fusion, the optimized feature subset substantially reduced feature dimensionality while maintaining comparable classification accuracy. The resulting classification maps showed broadly consistent spatial patterns, with differences mainly reflected in local boundary and fragmentation patterns.
Discussion: Under the conditions evaluated in this study, these findings indicate that staged feature selection provides a compact and interpretable feature optimization strategy for fine-scale UAV-based grassland land-cover classification. However, the data were acquired from a single study area during a single growing season, and the robustness of the framework across different regions, years, and phenological stages remains to be validated.
Related
- Rice multi-variety yield prediction using multi-temporal fusion of thermal infrared and multispectral UAV data based on random Forest feature selection
- Assessing the feasibility of up-scaling grapevine physiological trait estimation using multispectral UAV imagery
- Integrating UAV-based multispectral imagery and machine learning to classify glyphosate-resistant palmer amaranth and assess herbicide program efficacy in soybean
- Estimating the areal yield of forage nutritive components in a Mediterranean Sulla (Hedysarum coronarium L.) sward using UAV multispectral imagery
- Winter wheat yield prediction using temporal fusion of multispectral imagery and LiDAR point clouds acquired from a ground-based phenotyping platform
BibTeX
@article{liu2026finescale,
title = {{Fine-scale grassland land-cover classification using UAV RGB and multispectral imagery with staged feature selection}},
author = {Ying Liu and Mingyang Jiang and Haiyan Zhao and Mingyang Sun and Baoyou Qiao and Qiang Guan and Wen Du},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1956870},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1956870/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Fine-scale grassland land-cover classification using UAV RGB and multispectral imagery with staged feature selection
AU - Ying Liu
AU - Mingyang Jiang
AU - Haiyan Zhao
AU - Mingyang Sun
AU - Baoyou Qiao
AU - Qiang Guan
AU - Wen Du
PY - 2026
DA - 2026/10/06
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1956870
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1956870/full
AB - Introduction: Accurate mapping of grassland vegetation and bare land is important for grassland degradation assessment and ecological management. This study investigated the effectiveness of integrating visible and multispectral imagery with staged feature selection for fine-scale grassland land-cover classification. Methods: Four representative grassland land-cover classes, including Caragana microphylla, Artemisia scoparia, Agropyron cristatum, and bare land, were selected as classification categories. Spectral bands, vegetation indices, and texture metrics were combined to construct a multi-source feature pool, and different feature optimization strategies and classification models were systematically compared. Results: Multi-source feature fusion improved the discrimination of spectrally similar land-cover classes, while staged feature selection provided a workflow for reducing cross-source feature redundancy while retaining complementary information. The model with the highest observed validation accuracy selected only ten features from the original feature pool and achieved an overall accuracy of 91.54% with a Kappa coefficient of 88.72%. Compared with direct feature fusion, the optimized feature subset substantially reduced feature dimensionality while maintaining comparable classification accuracy. The resulting classification maps showed broadly consistent spatial patterns, with differences mainly reflected in local boundary and fragmentation patterns. Discussion: Under the conditions evaluated in this study, these findings indicate that staged feature selection provides a compact and interpretable feature optimization strategy for fine-scale UAV-based grassland land-cover classification. However, the data were acquired from a single study area during a single growing season, and the robustness of the framework across different regions, years, and phenological stages remains to be validated.
SN - 1664-462X
ER -