IEEE Geoscience and Remote Sensing Magazine - December 2021 - 69

Land Cover and Land Use
Buildings
Vegetation
Crops
Feature
Extraction
Textural Features
Deep Features
Object-Based Features
Angular Features
Lakes and Wetlands
Ecosystem Services
Impervious Surfaces
(a)
Algebra
Change
Detection
Transforms
Machine Learning
End-to-End Architectures
(b)
FIGURE 1. An outline of this review, including (a) applications, (b) methods, and (c) future directions.
BACKGROUND
Change detection is a vibrant area of research with wideranging
applicability, including damage assessment, land
management, and environment monitoring. Due to the
revisit property of Earth observation sensors, multitemporal
remote sensing images at a large geographical scale
can be acquired easily and conveniently. Due to their extensive
availability, optical images become the main data
sources for change detection [1]. Since these satellite sensors
are able to acquire images with meter and submeter
spatial resolutions, ground objects in fine spatial detail can
be investigated [2]. Subtle change detection using these
VHR images has drawn great interest in both the academic
and industrial communities. However, multitemporal VHR
images exhibit unique properties, such as limited spectral
information, intrinsic spectral variability, spatial displacement,
and information loss, that limit the usefulness of
traditional change detection methods. Therefore, a great
number of studies have been carried out on VHR change
detection, and a series of new research topics has emerged
along with advances in remote sensing technology and data
computing methods. In this regard, a timely overview of
VHR change detection is required to summarize the new
techniques and applications.
Although a number of reviews about change detection
using remote sensing data [3]-[10] exist in the literature,
the publications discuss general change detection methods
and do not focus on high-spatial-resolution images.
Only a few available works involve VHR images, e.g., the
reviews in [6] and [7]. However, those two works concern
object-based change detection methods for VHR data, neglecting
other aspects, e.g., recent technological advances
in deep learning and multiview and 3D change detection.
Moreover, specific applications of VHR change detection
have rarely been summarized and discussed in the currently
available literature. Therefore, a comprehensive review
of change detection from VHR remote sensing images,
including methods, applications, and future directions, is
presented (Figure 1).
DECEMBER 2021 IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
ISSUES RELATED TO VHR IMAGES
AND THEIR CHANGE DETECTION
With the ongoing development of remote sensing imaging
techniques, an increasing number of VHR sensors are
available, and many new sensors are being planned and
launched [11]. New platforms, such as unmanned aerial
vehicles (UAVs) and remotely piloted aircraft systems, have
grown in popularity [12] and are now providing a large
amount of VHR remote sensing data. As seen in Table 1,
the imaging capabilities of VHR platforms and sensors
TABLE 1. THE MAIN PARAMETERS OF SOME VHR SENSORS.
SENSOR
IKONOS
QuickBird
SPOT-5
OrbView-3
Cartosat-2
SPATIAL
RESOLUTION
(M)
1
0.61
2.5
1
0.8
WorldView-1 0.5
GeoEye-1
0.41
WorldView-2 0.46
KOMPSAT-3 0.7
2.1
2
2
Ziyuan-3
SPOT-6/7
Gaofen-1
Gaofen-2
Planet Labs
Deimos-2
DMC-3
0.8
3
1
WorldView-3 0.31
1
WorldView-4 0.31
NUMBER
OF BANDS
Four
Four
Four
Four
One
One
Four
Four
Four
Four
Four
Four
Four
Four
Four
16
Four
Four
REVISIT
TIME (DAYS)
LAUNCH
YEAR
One to three 1991
1.5-2.5
26
Three
Four
1.7
Fewer than
three
1.1
Three
Four to five
One
Fewer than
four
Four
One or two
One or two
Fewer than
one
One
Fewer than
one
2001
2002
2003
2007
2007
2008
2009
2012
2012
2012/2014
2013
2014
2014
2014
2014
2015
2016
SPOT: Satellite Pour l'Observation de la Terre; KOMPSAT: Korean Multipurpose Satellite;
DMC: Disaster Monitoring Constellation.
69
Frequency
Scale
Detailed
Semantic
Change Tracking
Global Change Detection
Hyperspectral Change Detection
Urban Functional Zone Changes
(c)
IEEE Geoscience and Remote Sensing Magazine - December 2021

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - December 2021
