IEEE Geoscience and Remote Sensing Magazine - September 2019 - 71

undergo terrain correction before application. When
the slope is greater than 15°, images will lose effective
value. Most terrain correction algorithms are suitable
only for certain terrain data with a slope lower than 15°
[72]. However, optical RSIs combining SAR and lidar
data can overcome the problem caused by topographic
relief and land cover height differences. Fusion makes
full use of radiation information and geometric information to describe ground objects [73]. Fusion algorithms are described in the "Multisource Data Fusion
Models" section.
CHALLENGES WITH MULTISOURCE REMOTE
SENSING TECHNIQUES
Multisource RSI fusion focuses on reducing data redundancy or complementary multisource data in spectral and
spatiotemporal forms with richer information. Such fusion has been considered advantageous in leveraging the
respective data strengths and minimizing weaknesses to
improve classification and detection accuracy with spatial,
spectral, and temporal features [74], [75]. Data fusion
compensates for the deficiencies of single data sources, as
evidenced by previous studies [76]-[78]. The first problem
in multisource data fusion involves referencing data from
different geometrical, spatial, or spectral acquisitions, according to the requirements of UIS detection (accuracy
and scale), to decrease the impacts of imaging mechanisms
from different data sources and improve the complementary advantages [79], [80].
Multisource data fusion can be handled in terms of spectral, temporal, and spatial resolution and wavelength regions from different sensor images with multiple features [81].
Image fusion can increase the accuracy of image interpretation, reduce fuzziness, and improve classification. However,
the quality of multisource data fusion processing depends
largely on the reasonable selection of an image fusion model. Image fusion mainly uses spatial or spectral information
from RSIs. For spatial information, the statistical model, spatial model, and physical model are respectively employed
to describe the spatial distribution, geometric characteristics,
and physical characteristics of pixels. For spectral information, the spectral vector model, linear spectral mixture model, and various nonlinear spectral mixture models are used
to extract spectral features [82]. However, with these models,
effectively selecting an appropriate image model remains
difficult. The selection of fusion methods depends on the
chosen data fusion level, as described in the "Multisource
Data Fusion Models" section.
METHOD CLASSIFICATION
METHOD CLASSIFICATION
Different types of land cover have various geographic
spatial attributes, spatiotemporal characteristics, contexts, and geometric traits (e.g., shape, texture, and structure). These features are fundamental to the selection of
SEPTEMBER 2019

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE

RSIs in terms of application accuracy requirements [83],
[84]. However, all UIS detection, regardless of method,
involves transforming extracted features into identifiable
classified images to construct specific and quantitative
thematic UIS maps. The general processing scheme of UIS
detection includes data source selection, data preprocessing, feature extraction and classification, and thematic
mapping (Figure 7).
In the following sections, we survey major UIS detection methods and models that have emerged in the past decades. According to the characteristics of these techniques
and frameworks, we divide them into four categories: spectral mixing analysis (SMA), image classification methods,
Urban Index methods, and multisource data fusion models
(see Figure 8).
SPECTRAL MIXING ANALYSIS METHODS
Medium- to low-resolution images have many mixed pixels, derived from obvious spatial heterogeneity differences
in land cover and the limitation of low spatial resolution.
SMA was proposed to handle mixed-pixel UIS detection
[85]-[87]. Prior to UIS detection using SMA, water must be
excluded. The vegetation-impervious surface-soil (V-I-S)
theoretical model can be adopted to divide ground surface
cover into three types (vegetation, impervious surfaces,
and bare soils) based on biophysical composition [88]-
[90]. Appropriate endmember selection is a key issue in
successful SMA, namely, choosing the number and type
of endmembers and their corresponding spectral features
[91]. Various methods to determine the number and type of
endmembers in specific applied scenes have been described,
including the V-I-S model, linear unmixing for urban scenes
[92], [93], different endmember combinations using iterative
testing [94]-[96], and manual testing for different endmember sets [97]-[99]. The spectral features of endmembers are
mainly derived from RSIs [100] or simulated using radiative
transfer models [101]. Moreover, different analysis approaches for endmember location and extraction from RSIs have
been proposed [102], [103]. These concepts include the Pixel
Purity Index [104], n-dimensions fast autonomous spectral
endmember determination (i.e., N-FINDER) [105], and the
virtual endmember concept [106]. A thorough discussion
of endmember selection appears in a review of endmember
variability in SMA in [107].
The SMA model is divided into linear and nonlinear
models [108]. The linear SMA model is feasible for simple landscapes wherein same-category land objects have
the same spectral characteristics in the pixel. The nonlinear SMA model is suitable for processing multitype landscapes. Linear SMA is thus more popular than the nonlinear SMA model in estimating urban land cover because of
fewer nonlinear effects in UIS detection [109], [110]. However, linear SMA may encounter selection difficulties for
endmembers due to spectral variability and endmember
types. To overcome under- or overestimation in the linear SMA model, a normalized SMA (NSMA) method has
71



IEEE Geoscience and Remote Sensing Magazine - September 2019

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - September 2019

Contents
IEEE Geoscience and Remote Sensing Magazine - September 2019 - Cover1
IEEE Geoscience and Remote Sensing Magazine - September 2019 - Cover2
IEEE Geoscience and Remote Sensing Magazine - September 2019 - Contents
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 2
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 3
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 4
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 5
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 6
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 7
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 8
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 9
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 10
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 11
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 12
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 13
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 14
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 15
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 16
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 17
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 18
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 19
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 20
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 21
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 22
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 23
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 24
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 25
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 26
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 27
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 28
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 29
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 30
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 31
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 32
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 33
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 34
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 35
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 36
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 37
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 38
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 39
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 40
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 41
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 42
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 43
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 44
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 45
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 46
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 47
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 48
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 49
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 50
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 51
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 52
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 53
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 54
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 55
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 56
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 57
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 58
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 59
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 60
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 61
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 62
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 63
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 64
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 65
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 66
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 67
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 68
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 69
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 70
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 71
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 72
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 73
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 74
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 75
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 76
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 77
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 78
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 79
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 80
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 81
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 82
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 83
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 84
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 85
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 86
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 87
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 88
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 89
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 90
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 91
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 92
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 93
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 94
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 95
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 96
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 97
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 98
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 99
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 100
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 101
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 102
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 103
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 104
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 105
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 106
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 107
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 108
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 109
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 110
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 111
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 112
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 113
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 114
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 115
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 116
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 117
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 118
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 119
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 120
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 121
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 122
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 123
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 124
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 125
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 126
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 127
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 128
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 129
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 130
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 131
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 132
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 133
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 134
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 135
IEEE Geoscience and Remote Sensing Magazine - September 2019 - 136
IEEE Geoscience and Remote Sensing Magazine - September 2019 - Cover3
IEEE Geoscience and Remote Sensing Magazine - September 2019 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2023
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2022
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2021
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2020
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2019
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2018
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2017
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2016
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2015
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2014
https://www.nxtbook.com/nxtbooks/ieee/geoscience_december2013
https://www.nxtbook.com/nxtbooks/ieee/geoscience_september2013
https://www.nxtbook.com/nxtbooks/ieee/geoscience_june2013
https://www.nxtbook.com/nxtbooks/ieee/geoscience_march2013
https://www.nxtbookmedia.com