BOHR International Journal of Smart Computing

and Information Technology

2021, Vol. 2, No. 1, pp. 59–63
DOI: 10.54646/bijscit.2021.20
www.bohrpub.com

CASE STUDY

A case study: Grid services for satellite image processing

Patil Rushikesh 1* and Siddhi Mane 2
1 Department of Mechatronics Engineering, Chandigarh University, Punjab, India
2 Department of Computer Science and Engineering, Dr. J. J. Magdum College of Engineering, Maharashtra, India

*Correspondence:
Patil Rushikesh,
[email protected]

Received: 10 October 2021; Accepted: 23 October 2021; Published: 16 November 2021

Satellite image processing is an intricate task that requires vast computation and data processing, which cannot
be handled by a single computer. Furthermore, the processing of the massive amount of data accumulated by
the satellite is a huge challenge for the end user. Hence, grid computing is the essential platform to provide high
computing performance at the user end. This article reviews the grid services used for satellite image processing
and significant data processing.
Keywords: satellite, grid, image processing, remote sensing

1. Introduction MedioGrid is a type of service grid, but it is considerably used

with computational grid for high performance (3, 4).
Satellite image processing is an intensive process involving The components and structure of the computational,
extensive data analysis and computation. Real-time image data or instrument, and service grids are shown in
processing in remote sensing is a quite impossible task for Figures 1–3. Those figures explicitly show the components
a single computer. Furthermore, it involves reciprocation and workflow of grids.
of data and images from space to earth every second. This article reviews grid services used for satellite image
The computational analysis of this massive amount of data processing and other remote sensing applications like
requires efficient technology for remote sensing (1). Grid monitoring the earth and climate change and capturing
images of unknown celestial bodies. The next section tends
services are an essential platform that is anticipated to
to collect previous contributions in the satellite image
make reliable handling of data and distribution among users
processing. Section 3 specifies satellite image processing
simultaneously. Due to the unavailability of the required
using grids. Section 4 concludes the review, and the article
computing performance, grid services have become an
ends with references.
important platform for satellite image processing.
Grid computing is a procedure involving the use of
multiple computers simultaneously to solve one or more
problems that requires numerous data computing cycles. 2. Literature review
Grid technologies tend to provide efficient and desired
tools and datasets for remote sensing (2). There are several The grid infrastructure that is being developed by the
grid types used in satellite image processing, like the Space Research Institute (SRI) is presented by Kussul
computational grid, which is used for high-performance et al. (5). In this article, the grid infrastructure that is
computational image processing, and the data or instrument being developed is reviewed explicitly using resources that
grid, which is used for processing an extensive amount of are available. This grid focuses on quick responses from
data with high speed and precision. Furthermore, the service earth observation satellites to prevent disasters by taking
grid used for web services is required for remote sensing. precautions. Furthermore, they reviewed some applications

59
60 Rushikesh and Mane

Remote-sensed image processing using grids for earth

observation training study and observation is presented by
Daniala Zaharie et al. (7) in order to fulfill the need of
training in earth observation on grid platforms. The project
provides grid training platforms for earth observation and
the technologies used for training. The basic grid services,
their applications, and the results of image processing are
provided by the GiSHEO platform. The structure of the
GiSHEO platform is shown in Figure 4.
Sowmya D.R. et al. (8) have presented a comprehensive
survey of satellite image processing techniques for image
classification. This article aims to present a comprehensive
survey of advanced technologies used in satellite image
FIGURE 1 | Structure of computational grid (12).
processing. The image processing is classified into four
different categories, namely, pre-processing, enhancing,
transformation, and image classification. Pre-processing of
images includes correction of several kinds of distortions
present in the image. Image enhancement consists of visual
data interpretation. Transformation is used to identify image
data and features, and classification is characterized by the
grouping of pixels.
For environment and natural resource monitoring, there
is a platform called ‘Greenland Web-Based Platform’,
which uses grids for remote sensing. The development of
applications and comprehensive analysis are presented by
Filiz Bektas Balcik et al. (9). High-performance computation
FIGURE 2 | Structure of data or instrument grid (10). methods are required to perform earth monitoring; hence,
grid infrastructure is an essential platform to provide these
capabilities. This article aims to develop new applications in
remote sensing with an open Greenland web-based platform
using computational grids.
Andrei Eckstein et al. (10) have presented different case
studies and scenarios of satellite image processing using
grids that consist of remote processing of images, remote
parallel processing of images, and processing of images
using grids. By analyzing these scenarios, a prototype
is developed, designed, and tested for classification of
satellite images.

FIGURE 3 | Service grid for web services (9).

like monitoring earth’s climate change, real time weather

forecasting, and so on.
The Romanian collaborative project MedioGrid aims to
provide large and extensive grid services for satellite image
processing. The summary of this project is provided by
Dana Petcu et al. (6). This article presents a brief review of
MedioGrid for remote sensing with real-world applications.
The data are collected and compared with previous results in
order to improve precision. FIGURE 4 | Structure of GiSHEO platform (3).
10.54646/bijscit.2021.20 61

3. Satellite image processing using authority to give commands to be performed in GIMP. The
GNU program language that is used for image manipulation
grids is GIMP (11). The image is divided into several number of
parts tends to produce sub-images. Using the constellation of
We have considered two methods for satellite image
head nodes, the user selects the required cluster where the
processing that are commonly used for satellite image
operation is intended to be performed.
processing. We are going to look into these two
methods briefly before diving into another significant
method that is used for satellite image processing
using grid services. 3.3. Satellite image processing using grids

The user intends to apply special methods for processing

3.1. Remote satellite image processing images to extract required information from the images
that are being selected. A significant number of images are
A massive amount of data is available for various research being analyzed simultaneously, and if the CPU is taking
and academic uses. Extraction of particular information more than anticipated time to extract the required data from
from specific images using certain procedures is something the selected images, the user will apparently have the idea
a user intends to do. A user has been granted access to that the local tools available for processing satellite images
a workstation and a grid certificate issued by the virtual are not sufficient.
organization. The user should have technical knowledge of To support this method, the available technology must
the operations that needs to be performed as well as lower or acquire the components as follows: some essential facilities
upper intermediate knowledge of programming. The CPU’s and codes provided by the clients to operate grid services at
time increases for extraction of features simultaneously the node, which is operated by the user; the infrastructure
as the number of images increases. Instantaneously, the of grid must have middleware grid to execute the codes at
user would get an idea about the available resources and remote computation nodes. The structure mentioned here is
computation techniques that are not able to acquire the for the grids used for computation.
satellite images (10). The codes must be rewritten by the user in order to
The available technology must acquire the following perform various tasks which are split to speed up the
components to support this scenario. The codes provided computation for satellite image processing. The transfer of
by the clients and some essential facilities to operate intact images must be avoided because satellite images carry
grids are at the one end, where the user is; satellite enormous sizes (12). Hence, the splitting of images and
data and grid services for indexing are at the second tasks is preferable. The required number of tasks and images
node, which is the repository nodes; software for satellite should be elected on the basis of theoretical performance to
image and data processing is at the retrieval, storage, and obtain the anticipated response in time.
computation nodes. In the next point, we are going to present a case
A grid prototype for the GIMP tool was developed study of satellite image processing, which was part of the
using Globus Toolkit 4 to respond to this method for MedioGrid infrastructure.
image processing.

3.2. Remote parallel image processing 3.4. Case study

The protocols and essential requirements are the same The case study consists of the classification and
as those mentioned earlier in the previous method. implementation of a basic algorithm to classify forestation
Furthermore, neither of the nodes has the required capability and deforestation. The process of classification involves the
to perform the operation in the required time. translation of satellite images from pixel values to produce
The infrastructure used in this method is considerably meaningful images. A decision tree is the stack, which
modified using the available tools. The head node, which is consists of binary rules that are used to define particular
used for computation, is on the one side that manages the terms that are assigned to each pixel. The input here is in the
grid services. The constellation of head nodes is explicitly red and infrared bands. The classes of land that are being
visible on the virtual organization’s index. Additionally, the detected here, are open surface, forests, water sources, and
assumption that is made is that the processing of image rain clouds. Each specified class has a different color, as
replicas is available on every head node, which makes it depicted in Figure 5.
available for computation. It is assumed that the user possesses a code in sequential
A new grid prototype was built in order to respond to form that applies to the classification of decision trees
this method. The user has access to remote images and the on images that are being taken by satellite cameras. The
62 Rushikesh and Mane

TABLE 1 | Response time (s) for small image classification.

Split type Nodes no. Response time Image file size in bytes

1×1 1 5.66 5324604

2×2 4 2.23 1331018
3×3 9 1.63 591947
4×3 12 1.49 443758

Table 1 explicitly depicts the response time reduction by utilizing grid computation
technology for small image classification. The bands of smaller dimensions have a very
less response time. Similar procedures and operations can be used to build codes to
perform more intricate satellite image processing.

images. With the small satellite images, which have a

band size of approximately 64 megabytes, it is possible
to obtain an appropriate response time by performing a
few operations with the help of grid services in place of
a single computer. Meanwhile, for images with large sizes
carrying band size around 450 megabytes, it is difficult
to process on a single computer memory. A significant
number of operations must be considered to write the
composer and splitter.

4. Conclusion
Remote sensing and information and data processing are
intricate tasks, which require powerful and efficient tools.
The proposed prototype of grid technology is efficient in
providing desired tools for satellite image processing on
grid platforms. The code used for grid computing is the
property of user that splits into a number of operations
that are performed on grid platform. This is a very brief
overview of the framework of MedioGrid infrastructure,
which shows compatibility of the grids for high-speed
FIGURE 5 | Decision tree implementation applied to bands 3 (first)
satellite image processing.
and bands 4 that yields a color image with a specified meaning (1).

sequence code must have the following components for the References
computation:
1. Petcu D, Zaharie D, Neagul M, Panica S, Frincu M, Gorgan D, et al.
Remote sensed image processing on grids for training in earth observation.
1. A splitter with the ability to acquire two bands in order (2009). Available online at: https://www.intechopen.com/chapters/6674
to split them into several numbers of small images. (accessed January 13, 2023)
2. A classifier that acquires a couple of images from the 2. Geoid. GRID services for earth observation image data processing.
bands that produces small images. (2014). Available online at: https://agris.fao.org/agris-search/search.do?
3. Essentially, a composer accumulates sub-images with recordID=US201400184198 (accessed January 14, 2023).
defined colors (1). 3. Cao Q, Li G, Yao X, Jia T, Yu G, Zhang L, et al. GF-1 satellite imagery
data service and application based on open data cube. Appl Sci. (2022)
The primary sequence code that applies to small images is 12:7816.
called the classifier. 4. Igi Global. Using grid computing and satellite remote sensing
in evapotranspiration estimation. (2015). Available online at:
Meanwhile, the composer and splitter are situated at the https://www.igi-global.com/chapter/using-grid-computing-and-
user end, where the small images and classifiers are gathered satellite-remote-sensing-in-evapotranspiration-estimation/131529
for grid computation. (accessed January 19, 2023)
The case study was intended to detect the appropriate 5. Computer vsion modern approach. (n.d.).
number of sub-images using appropriate dimensions of 6. Gonzalez RC. Digital image processing basics. (2009).
10.54646/bijscit.2021.20 63

7. Christopher MB. Pattern recognition and machine learning. New York, 11. Petcu D, Gorgan D, Pop F, Tudor D, Zaharie D. Satellite image processing
NY: Springer (2006). on a grid-based platform. (2000).
8. Konecny G. Small satellites – a tool for earth observation? (2014). 12. Petcu D, Panica S, Eckstein A. Satellite image processing on
9. Kussul N, Shelestov A, Skakun S. Grid and sensor web technologies computational grids state-of-the-art in grid processing satellite images.
for environmental monitoring. Earth Sci Inform. (2009) 2:37–51. doi: (2007).
10.1007/s12145-009-0024-9 13. Sowmya DR. Remote sensing satellite image processing techniques for
10. Petcu D. A solution for satellite image processing on grids. image remote sensing satellite image processing techniques for image
(2014). classification: a comprehensive survey. (2020).