Next Article in Journal
Ground-Penetrating Radar and Photogrammetric Investigation on Prehistoric Tumuli at Parabita (Lecce, Italy) Performed with an Unconventional Use of the Position Markers
Next Article in Special Issue
Interpreting the Trends of Extreme Precipitation in Florida through Pressure Change
Previous Article in Journal
Unsupervised Generative Adversarial Network with Background Enhancement and Irredundant Pooling for Hyperspectral Anomaly Detection
Previous Article in Special Issue
Contribution of Climate Change and Grazing on Carbon Dynamics in Central Asian Pasturelands
 
 
Article

An Object-Based Genetic Programming Approach for Cropland Field Extraction

1
Key Laboratory of Agricultural Remote Sensing, Ministry of Agriculture and Rural Affairs, Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China
2
School of Engineering and Computer Science, Victoria University of Wellington, Wellington 6140, New Zealand
3
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, China
*
Author to whom correspondence should be addressed.
Academic Editors: Feng Gao, Berk Üstündağ, Liying Guo and Yahui Di
Remote Sens. 2022, 14(5), 1275; https://doi.org/10.3390/rs14051275
Received: 26 January 2022 / Revised: 2 March 2022 / Accepted: 3 March 2022 / Published: 5 March 2022
(This article belongs to the Special Issue Progresses in Agro-Geoinformatics)
Cropland fields are the basic spatial units for agricultural management, and information about their distribution is critical for analyzing agricultural investments and management. However, the extraction of cropland fields of smallholder farms is a challenging task because of their irregular shapes and diverse spectrum. In this paper, we proposed a new object-based Genetic Programming (GP) approach to extract cropland fields. The proposed approach used the multiresolution segmentation (MRS) method to acquire objects from a very high resolution (VHR) image, and extracted spectral, shape and texture features as inputs for GP. Then GP was used to automatically evolve the optimal classifier to extract cropland fields. The results show that the proposed approach has obtained high accuracy in two areas with different landscape complexities. Further analysis show that the GP approach significantly outperforms five commonly used classifiers, including K-Nearest Neighbor (KNN), Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). By using different numbers of training samples, GP can maintain high accuracy with any volume of samples compared to other classifiers. View Full-Text
Keywords: Genetic Programming; object-based; cropland fields Genetic Programming; object-based; cropland fields
Show Figures

Figure 1

MDPI and ACS Style

Wen, C.; Lu, M.; Bi, Y.; Zhang, S.; Xue, B.; Zhang, M.; Zhou, Q.; Wu, W. An Object-Based Genetic Programming Approach for Cropland Field Extraction. Remote Sens. 2022, 14, 1275. https://doi.org/10.3390/rs14051275

AMA Style

Wen C, Lu M, Bi Y, Zhang S, Xue B, Zhang M, Zhou Q, Wu W. An Object-Based Genetic Programming Approach for Cropland Field Extraction. Remote Sensing. 2022; 14(5):1275. https://doi.org/10.3390/rs14051275

Chicago/Turabian Style

Wen, Caiyun, Miao Lu, Ying Bi, Shengnan Zhang, Bing Xue, Mengjie Zhang, Qingbo Zhou, and Wenbin Wu. 2022. "An Object-Based Genetic Programming Approach for Cropland Field Extraction" Remote Sensing 14, no. 5: 1275. https://doi.org/10.3390/rs14051275

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop