Chapter 6
Image Processing Methods in Agricultural
Observation Systems
Chen Zhang and Li Lin
Abstract Image processing is an essential part of the agricultural observation system. This chapter is the first attempt to provide an overview of the image processing
methods, technologies, and tools from the perspective of agro-geoinformatics. First,
we introduce the origins, definitions, and basic steps of digital image processing.
Along with the traditional image processing hardware and software, the state-of-theart technologies for agricultural image processing, such as mobile device-based
image processing and cloud computing-based image processing, are covered.
Image data could be acquired by different sensors in different ways. We discuss
three common approaches to collect agricultural image data, in situ, airborne-based,
and space-borne-based data collection, as well as the big data challenge in agrogeoinformatics. As the core image processing operation in the agricultural observation system, information extraction aims to understand agro-geoinformation from
the raw image data. This chapter also illustrates several image information extraction
methods that are widely employed in agro-geoinformatics, such as knowledge-based
expert system, machine learning-based decision tree, and artificial neural network.
Furthermore, a case study of the production of Cropland Data Layer (CDL) data, a
comprehensive, raster-formatted, geo-referenced, annual crop-specific land cover
map produced by the U.S. Department of Agriculture (USDA) National Agricultural
Statistics Service (NASS), is demonstrated.
Keywords Image processing · Agricultural observation system · Agricultural
monitoring · Agricultural data collection · Agricultural information extraction ·
Big data · Machine learning · Land cover classification
C. Zhang (*) · L. Lin
Center for Spatial Information Science and Systems, George Mason University, Fairfax,
VA, USA
e-mail: czhang11@gmu.edu; llin2@gmu.edu
© Springer Nature Switzerland AG 2021
L. Di, B. Üstündağ (eds.), Agro-geoinformatics, Springer Remote Sensing/
Photogrammetry, https://doi.org/10.1007/978-3-030-66387-2_6
81
Image Processing Methods in Agricultural
Observation Systems
Chen Zhang and Li Lin
Abstract Image processing is an essential part of the agricultural observation system. This chapter is the first attempt to provide an overview of the image processing
methods, technologies, and tools from the perspective of agro-geoinformatics. First,
we introduce the origins, definitions, and basic steps of digital image processing.
Along with the traditional image processing hardware and software, the state-of-theart technologies for agricultural image processing, such as mobile device-based
image processing and cloud computing-based image processing, are covered.
Image data could be acquired by different sensors in different ways. We discuss
three common approaches to collect agricultural image data, in situ, airborne-based,
and space-borne-based data collection, as well as the big data challenge in agrogeoinformatics. As the core image processing operation in the agricultural observation system, information extraction aims to understand agro-geoinformation from
the raw image data. This chapter also illustrates several image information extraction
methods that are widely employed in agro-geoinformatics, such as knowledge-based
expert system, machine learning-based decision tree, and artificial neural network.
Furthermore, a case study of the production of Cropland Data Layer (CDL) data, a
comprehensive, raster-formatted, geo-referenced, annual crop-specific land cover
map produced by the U.S. Department of Agriculture (USDA) National Agricultural
Statistics Service (NASS), is demonstrated.
Keywords Image processing · Agricultural observation system · Agricultural
monitoring · Agricultural data collection · Agricultural information extraction ·
Big data · Machine learning · Land cover classification
C. Zhang (*) · L. Lin
Center for Spatial Information Science and Systems, George Mason University, Fairfax,
VA, USA
e-mail: czhang11@gmu.edu; llin2@gmu.edu
© Springer Nature Switzerland AG 2021
L. Di, B. Üstündağ (eds.), Agro-geoinformatics, Springer Remote Sensing/
Photogrammetry, https://doi.org/10.1007/978-3-030-66387-2_6
81