6.1 Introduction
Imagery sensors have been widely used in the agricultural observation and monitoring systems. For example, a huge volume of remotely sensed image data is continuously acquired from various imaging sensors such as Moderate Resolution Imaging
Spectroradiometer (MODIS), Landsat Operational Land Imager (OLI), and Sentinel2 Multi-Spectral Instrument (MSI). These image data contain abundant fundamental information and have been extensively used to support decision making in
agriculture. The raw image data acquired from imaging sensors need to be processed
before being applied in agricultural applications. 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 fundamental of
digital image processing including its origins, definitions, image processing hardware/software, as well as state-of-the-art image processing technologies such
as mobile device-based image processing and cloud-based image processing.
Three main approaches for agricultural image data collection, in situ data collection,
airborne-based data collection, and space-borne-based data collection, are covered.
We also discuss the big data challenge in agro-geoinformatics. As the core operation
of image processing in the agricultural observation system, information extraction
aims to understand agro-geoinformation from the raw image data. This chapter
summarizes several image information extraction methods that are widely employed
used in agro-geoinformatics, including knowledge-based expert system, machine
learning-based decision tree, and artificial neural network approach. Furthermore, a
case study of the production of Cropland Data Layer (CDL) data is demonstrated.
6.2 The Fundamentals of Digital Image Processing
Agricultural image processing deals with digital images that are acquired by the
imaging sensor in agricultural monitoring systems. To process the agricultural
image data, we have to understand what is digital image and how digital image
processing works. This section will introduce the fundamentals of digital image
processing including its origins and definitions, fundamental steps, and basic terms
in the image processing flow including image acquisition, image enhancement,
image restoration, image compression, image segmentation, and image
representation.
6.2.1 Origins and Definitions
The origin of digital image processing could be traced back to a century ago when
the application of digital images was raised in the newspaper industry. With the
82
C. Zhang and L. Lin
Imagery sensors have been widely used in the agricultural observation and monitoring systems. For example, a huge volume of remotely sensed image data is continuously acquired from various imaging sensors such as Moderate Resolution Imaging
Spectroradiometer (MODIS), Landsat Operational Land Imager (OLI), and Sentinel2 Multi-Spectral Instrument (MSI). These image data contain abundant fundamental information and have been extensively used to support decision making in
agriculture. The raw image data acquired from imaging sensors need to be processed
before being applied in agricultural applications. 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 fundamental of
digital image processing including its origins, definitions, image processing hardware/software, as well as state-of-the-art image processing technologies such
as mobile device-based image processing and cloud-based image processing.
Three main approaches for agricultural image data collection, in situ data collection,
airborne-based data collection, and space-borne-based data collection, are covered.
We also discuss the big data challenge in agro-geoinformatics. As the core operation
of image processing in the agricultural observation system, information extraction
aims to understand agro-geoinformation from the raw image data. This chapter
summarizes several image information extraction methods that are widely employed
used in agro-geoinformatics, including knowledge-based expert system, machine
learning-based decision tree, and artificial neural network approach. Furthermore, a
case study of the production of Cropland Data Layer (CDL) data is demonstrated.
6.2 The Fundamentals of Digital Image Processing
Agricultural image processing deals with digital images that are acquired by the
imaging sensor in agricultural monitoring systems. To process the agricultural
image data, we have to understand what is digital image and how digital image
processing works. This section will introduce the fundamentals of digital image
processing including its origins and definitions, fundamental steps, and basic terms
in the image processing flow including image acquisition, image enhancement,
image restoration, image compression, image segmentation, and image
representation.
6.2.1 Origins and Definitions
The origin of digital image processing could be traced back to a century ago when
the application of digital images was raised in the newspaper industry. With the
82
C. Zhang and L. Lin