IEEE Geoscience and Remote Sensing Magazine - December 2020 - 104

The answer to these questions is clearly yes, as can be seen
from examples, studies, and projects. This prompts another
question: How one can benefit from crowdsourcing? The
answers may be found in connection with the challenging
problems posed by emerging research areas, such as data analytics and big data. Therefore, the use of this method with
remote sensing will make significant contributions.
◗◗ Perhaps one of the most important contributions of
crowdsourcing is its potential to solve the tagged data
problem in remote sensing. Thus, the greatest role of
crowdsourcing in scientific studies and applications
is that it can support the rapid, cost-effective, and reliable acquisition of large amounts of data in different
formats. One of the most important uses for data obtained by crowdsourcing is in the field of artificial intelligence. Even though the problem of tagged data in
classical machine-learning methods is largely solved by
the significant effect of crowdsourcing approaches, there
are still very few tagged data in the field of remote sensing. For this reason, artificial intelligence cannot cope
with the complete analysis of satellite imagery. However, this deficiency seems to be quickly resolved by the
emergence of platforms such as OSM, Geo-Wiki, SM,
and new software. By solving this problem, great success
will be achieved in the classification of satellite images
with significant accuracy. By having a sufficient amount
of tagged data, it will be possible to improving the accuracy of image classification and thus quickly classify
data for much wider areas. Understanding the distribution and dynamics of land cover is crucial for a better
understanding of the Earth's chemical and biological
processes, including soil fertility; diversity of plant and
animal species; and biological, chemical, and hydrological cycles. Assessing and monitoring the distribution
and dynamics of forests, shrubs, pastures, crops, rural
areas, urban areas, and water resources on our planet
are important priorities in global environmental change
studies and daily planning and management. The most
important source of LULC information is remotely
sensed data. The further introduction of crowdsourcing

◗◗

FIGURE 6. The distribution of studies by year.

2018

2017

2016

Year

104

◗◗

4
2015

2014

2013

2012

2011

2010

10
5

2019

2009

Number of Studies

for examining, processing, and editing these data can
produce faster and more accurate results.
Another important contribution is the generation of ancillary data that can be integrated into images obtained
by remote sensing thanks to the use of sensor technologies. An example of this is the concept of indoor perception, sometimes called indoor geography, which is
another trend of recent developments in mobile technology [51]. Remotely sensed images intrinsically can
provide a planar view of the Earth's surface, including
human structures as well as natural features. Although
lidar technology complements classical 2D images with
a depth-added dimension, it still does not provide insight into the interiors of buildings. In this sense, indoor
perception may be a future trend in indoor positioning
and mapping. Thus, sensor fusion will be able to generate data that consider the indoor locations [51].
It will also be possible to install smaller and more capable remote sensing sensors in smart devices in the
future. For example, the use of a hyperspectral camera
in a smartphone can be a significant breakthrough in
the field of food quality thanks to an algorithm that can
process information from this sensor. You will be able
to get a lot of information about an apple (e.g., type of
apple, whether it is fresh or not, and other characteristics) with a picture taken with a smartphone incorporating a hyperspectral camera. In this way, consumers will
be able to choose better products. It will be possible to
perform various analyses by gathering the data collected
by many people on a server.
In addition, the integration of mobile technology with
geospatial data via real-time remote sensing supports
the development of decision-support tools for various
environmental applications and for disaster alert and
emergency monitoring and management systems. Specific examples include applications related to forest fire
risk and damage assessment, large-scale drought monitoring, irrigation and water drainage systems, flood risk
and damage assessments, earthquakes, tsunamis, and
the development of public health nursing infrastructures. Sensors and scanners are integrated into mobile
devices for continuous health care and prevention of
disease outbreaks. Air quality indices are monitored in
real time regionally and presented as applications for
mobile phones.
Today, a wide variety of geospatial analyses can be performed with the data obtained from SM platforms. In
the future, SM data will be further integrated with remotely sensed data, and geospatial and sociological
analysis carried out using the fusion of image and SM
platforms will be of greater importance.
When remote sensing is used for more real-time (or
near-real-time) applications, then the scope of activities
and applications can vary considerably, and the door is
opened to new possibilities and new realities for using
spatial information. This transition will be made possible

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE

DECEMBER 2020

IEEE Geoscience and Remote Sensing Magazine - December 2020

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - December 2020