数字农科院2.0

Comparative Analysis of Machine Learning Algorithms for Object-Based Crop Classification Using Multispectral Imagery

文献类型： 外文期刊

作者： Madjebi Collela Be;Antsa Sarobidy Randrianantenaina;James E. Kanneh;Yingchun Han;Yaping Lei;Xiaoyu Zhi;Shiwu Xiong;Yahui Jiao;Shilong Shang;Yunzhen Ma;Beifang Yang;Lin Tao;Yabing Li

作者机构：

关键词： ANN;crop identification;image processing;precision agriculture;SVM;UAV;XGBoost

期刊名称： Drones

ISSN： 2504-446X

年卷期： 2025 年 9 卷 11 期

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Highlights: What are the main findings? Unmanned aerial vehicle imagery and object-based image analysis identify crop types Five machine learning algorithms exhibit high Accuracy for crop type classification What is the implication of the main finding? Ensemble learning method outperformed a single model Index and grey-level co-occurrence matrix are important for crop identification Unmanned Aerial Vehicles (UAVs) offer enhanced spatial and temporal resolution for agricultural remote sensing, surpassing traditional satellite-based methods. Given the abundance of evolving machine-learning methods for crop recognition, this study evaluates and compares five machine learning algorithms (ML) and tests an Ensemble Learning method as a sixth approach, integrated with object-based image analysis (OBIA) for crop-type classification using UAV multispectral imagery, aiming to identify the most effective model and produce a classification map based on the best-performing method. Image segmentation was built using eCognition software, and spectral, index, and gray level co-occurrence matrix (GLCM) features were extracted from the segmented object. A machine learning model integrating multiple classification algorithms (SVM, ANN, RF, XGBoost, KNN, Ensemble Learning) with automated hyperparameter optimization was developed and executed in Google Colab using Python 3.10. All classifiers achieved accuracies exceeding 80% and Area Under the Curve (AUC) values above 0.9. SVM and ANN are the best classifiers, with the same value of accuracy (94%), followed by XGBoost (93%), RF (92%), and KNN (89%). The Ensemble Learning method (SVM + ANN) as a sixth approach outperformed all single models, with an accuracy value of 95%. Cotton, maize, peanut, and soybean were classified with the highest accuracy, with index and GLCM features contributing most significantly, followed by spectral features. The integration of high-resolution UAV imagery with ML and OBIA demonstrates strong potential for automated crop-type classification, offering valuable support for precision agriculture applications.

分类号：

  • 相关文献

[1]Prediction of wheat SPAD using integrated multispectral and support vector machines. Wei Wang,Na Sun,Bin Bai,Hao Wu,Yukun Cheng,Hongwei Geng,Ji Kun Song,Jin Ping Zhou,Zhiyuan Pang,Song Ting Qian,Wanyin Zeng. 2024

[2]Diagnostic model for wheat leaf conditions using image features and a support vector machine. K. Du, Z. Sun, Y. Li, F. Zheng, J. Chu, Y. Su. 2016

[3]Integrated UAV and Satellite Multi-Spectral for Agricultural Drought Monitoring of Winter Wheat in the Seedling Stage. Xiaohui Yang,Feng Gao,Hongwei Yuan,Xiuqing Cao. 2024

[4]Invasive plants detection and distribution patterns analysis through self-attention enhanced semantic segmentation in UAV imagery and Moran's index. Chao, Jun,Wang, Kaiwen,Xu, Beibei,Harty, Mary,Wang, Wensheng,Mcdonnell, Kevin. 2025

[5]GrapeSLAM: UAV-based monocular visual dataset for SLAM, SfM and 3D reconstruction with trajectories under challenging illumination conditions. Kaiwen Wang,Sergio Vélez,Lammert Kooistra,Wensheng Wang,João Valente. 2025

[6]UAV remote sensing-driven precision variable management in cotton: technological framework, applications, and research outlook. Lechun Zhang,Yingkuan Wang,Xinyu Xue,Wenjiang Huang,Tianye Yang,Hang Zhu,Yubin Lan. 2026

[7]UAV-assisted Multi-Object Tracking and Segmentation of Apples under Occlusions in Orchard Settings. Kaiwen Wang,Lammert Kooistra,Wensheng Wang,João Valente. 2025

[8]基于XGBoost算法的山东烟叶质量预测模型初探. 别瑞,周婷云,周显升,姜滨,周永,邱军,曹建敏. 2022

[9]基于无人机多源遥感数据和机器学习的高通量棉花估产研究. 冯美臣,苏悦,林涛,余汛,宋扬,金秀良. 2025

[10]应用近红外光谱分析技术检测豆粕中掺杂三聚氰胺和尿素的研究. 孙丹丹,谷旭,李俊,李军国,董颖超. 2014

[11]一种草地高光谱图像分类方法. 武林,马玉宝,潘新,闫伟红,段俊杰. 2018

[12]Oxidative stress and gene expression of earthworm (Eisenia fetida) to clothianidin. Liu, Tong,Wang, Xiuguo,You, Xiangwei,Chen, Dan,Li, Yiqiang,Wang, Fenglong.

[13]Origin verification of imported infant formula and fresh milk into China using stable isotope and elemental chemometrics. Xiuwen Zhou,Zhi Yan,Baohui Jin,Yingying Wu,Liqi Xie,Haiquan Chen,Guanghui Lin,Yan Zhao,Karyne M. Rogers,Hao Wu. 2021

[14]Crop specific inversion of PROSAIL to retrieve green area index (GAI) from several decametric satellites using a Bayesian framework. Jingwen Wang,Raul Lopez-Lozano,Marie Weiss,Samuel Buis,Wenjuan Li,Shouyang Liu,Frédéric Baret,Jiahua Zhang. 2022

[15]Using Various Models for Predicting Soil Organic Carbon Based on DRIFT-FTIR and Chemical Analysis. Fatma N. Thabit,Osama I.A. Negim,Mohamed A.E. AbdelRahman,Antonio Scopa,Ali R.A. Moursy. 2024

[16]A review of crop identification and area monitoring based on SAR image. Ding Yaping,Chen Zhongxin,Ding Yaping,Chen Zhongxin. 2012

[17]Discriminant models for crop identification of complex agricultural landscapes. You, Jiong,Pei, Zhiyuan,Wang, Dongliang. 2013

[18]Advances in research on crop identification using SAR. Di, Wang,Zhou Qingbo,Chen Zhongxin,Yan, Su. 2015

[19]Extending the Pairwise Separability Index for Multicrop Identification Using Time-Series MODIS Images. Hu, Qiong,Wu, Wenbin,Yu, Qiangyi,Lu, Miao,Yang, Peng,Tang, Huajun,Long, Yuqiao,Song, Qian,Song, Qian.

[20]How Do Temporal And Spectral F.eatures Matter In Crop C lassification In Heilongjiang Province, China?. Hu, Q, Wu, WB, Song, Q, Lu, M, Chen, D, Yu, QY, Tang, HJ. 2017

作者其他论文 更多>>