temperature, humidity, and NDVI (normalized difference vegetation index), from
various online sources (Sun et al. 2017). GPKG Mobile is developed as an iOS
mobile app to support field operations in agriculture, which provides the capability
to display, manage, and manipulate agricultural image data in GeoPackage format on
both Google Maps and OpenLayers by implementing GeoPackage Library and
CMAPI (Zhang et al. 2016a, b).
6.3.4 Cloud-Based Image Processing
The volume of the Earth observation data is growing in an exponential rate during
the past decades due to the rapid development of remote sensing technology and its
application. As the result, big data remote sensing is becoming a new idea in both
scientific and industrial communities.
To meet the challenge of big data remote sensing, Google has developed Earth
Engine as the next-generation Earth observation data analysis platform (Gorelick
et al. 2017). The major difference between the Google Earth Engine and traditional
remote sensing data platform is that the Google Earth Engine is powered by
Google’s cloud infrastructure, which means all data analyses and processing are
implemented in cloud instead of the user’s own desktop. The Google Earth Engine
provides the data catalogue contains the entire Landsat catalogue, MODIS satellite
datasets, Sentinel satellite data, precipitation data, elevation data, sea surface temperature, NAIP, and CHIRPS climate data. Which means users can directly analyze
data using web browser without finding and uploading Earth observation data by
themselves. On the other hand, the Google Earth Engine provides many derivative
products such as annual mosaics and a variety of environmental indices such as
NDVI, EVI, and NDWI (Padarian et al. 2015). Meanwhile, a variety of Google Earth
Engine-enabled web applications and toolkits have been developed to support agrogeoinformation and image processing (Yalew et al. 2016; Zhang et al. 2020a).
Compared with the conventional image processing system, cloud-based Earth
observation data processing system, which uses powerful cloud infrastructure as the
platform to process imagery data would considerably reduce the computation
times (Zhang et al. 2017).
6.4 Agricultural Image Data Collection
In an agricultural image processing system, data could be retrieved by the different
imaging sensors in different ways. This section introduces the three approaches for
agricultural image data collection including the situ data collection, airborne-based
data collection, and space-borne-based data collection. Also, the big data challenge
in agricultural image data collection would be discussed.
6 Image Processing Methods in Agricultural Observation Systems
87
various online sources (Sun et al. 2017). GPKG Mobile is developed as an iOS
mobile app to support field operations in agriculture, which provides the capability
to display, manage, and manipulate agricultural image data in GeoPackage format on
both Google Maps and OpenLayers by implementing GeoPackage Library and
CMAPI (Zhang et al. 2016a, b).
6.3.4 Cloud-Based Image Processing
The volume of the Earth observation data is growing in an exponential rate during
the past decades due to the rapid development of remote sensing technology and its
application. As the result, big data remote sensing is becoming a new idea in both
scientific and industrial communities.
To meet the challenge of big data remote sensing, Google has developed Earth
Engine as the next-generation Earth observation data analysis platform (Gorelick
et al. 2017). The major difference between the Google Earth Engine and traditional
remote sensing data platform is that the Google Earth Engine is powered by
Google’s cloud infrastructure, which means all data analyses and processing are
implemented in cloud instead of the user’s own desktop. The Google Earth Engine
provides the data catalogue contains the entire Landsat catalogue, MODIS satellite
datasets, Sentinel satellite data, precipitation data, elevation data, sea surface temperature, NAIP, and CHIRPS climate data. Which means users can directly analyze
data using web browser without finding and uploading Earth observation data by
themselves. On the other hand, the Google Earth Engine provides many derivative
products such as annual mosaics and a variety of environmental indices such as
NDVI, EVI, and NDWI (Padarian et al. 2015). Meanwhile, a variety of Google Earth
Engine-enabled web applications and toolkits have been developed to support agrogeoinformation and image processing (Yalew et al. 2016; Zhang et al. 2020a).
Compared with the conventional image processing system, cloud-based Earth
observation data processing system, which uses powerful cloud infrastructure as the
platform to process imagery data would considerably reduce the computation
times (Zhang et al. 2017).
6.4 Agricultural Image Data Collection
In an agricultural image processing system, data could be retrieved by the different
imaging sensors in different ways. This section introduces the three approaches for
agricultural image data collection including the situ data collection, airborne-based
data collection, and space-borne-based data collection. Also, the big data challenge
in agricultural image data collection would be discussed.
6 Image Processing Methods in Agricultural Observation Systems
87