IEEE Geoscience and Remote Sensing Magazine - December 2016 - 16
solved simultaneously with a surface reconstruction problem, one potential approach for a solution to the nontrivial
matching problem for data acquired from different viewing
angles or by sensors with different viewing geometries is to
combine the matching and the 3-D modeling steps in a joint
estimation procedure. Relevant approaches have until now
mainly come from the field of computer vision, e.g., for solving the multiview stereo problem within an optimization
framework [29], [131]. It must be mentioned, however, that,
in these examples, the alignment of the measurements is already solved because the camera positions are known.
matcHinG oF conVentionaL remote
sensinG oBserVations and otHer data
Another major challenge in the field of matching and coregistration is the joint exploitation of classical remote sensing
data (e.g., images, range measurements, depth maps, and
point clouds) and data from other domains, such as texts,
point-wise observations, or vector data. The coregistration
of point-wise and extensive observations is relatively easy to
achieve if the data are provided in geocoded form (e.g., [167]
and [183]). Far more challenging examples are the fusion of
text and image data, which has recently been demonstrated
for the detection of events based on the analysis of Twitter
messages [2]. In this case, the matching of geospatial information with the semantic content of the social media data
is certainly the main problem, whereas coregistration can be
achieved by the exploitation of geolocation information provided by the social media services [134].
In any case, these preliminary examples from other disciplines must be transferred and adapted to the remote sensing context to enable a maximally flexible alignment of the
different data types to be expected. Without this alignment
and the proper correlation of measurements and the object
of interest, any subsequent data fusion request will fail. There
will be cases where a 100% alignment might not be possible,
e.g., if small-scale nadir-view (e.g., containing only the roofs
of some buildings) and oblique-view (containing only the
buildings' facades) imagery are fused. Such a situation might
be interesting in the sense of complementary integration (see
the "Fusion by Estimation" section); but, depending on the
application, it might be reasonable to exclude the nonmatchable observations from further processing and instead focus
on other retrievable parameters (e.g., the roof or ground parts
visible in both images).
AN EXCURSION INTO ESTIMATION THEORY:
MODELING THE ACTUAL FUSION STEP
Although most data acquired during space-borne Earth-observation missions or well-planned airborne flight campaigns
will always be well documented and contain sufficient metadata, most of the potentially available crowd-sourced data
(e.g., GPS tracks or smartphone images) will not provide any
additional information. It will therefore be necessary to create sophisticated fusion approaches that go beyond classical
Bayesian estimation and can incorporate fuzzy, imprecise, or
16
incomplete data without losing the ability to deliver statistically optimal estimates including stochastically sound quality and reliability measures. Khaleghi et al. [71] provided an
extensive review of different fusion approaches in a broad,
general sense. They extended the well-known probabilistic
formulation of data fusion problems by evidential belief reasoning, fuzzy reasoning, possibilistic fusion, and rough or
random set-based fusion. While classical probabilistic fusion
relies on probability distribution functions and Bayesian
estimation, ranging from least-squares estimation via Kalman filter to particle filter and Markov chain Monte Carlo
algorithms, evidential belief reasoning is mainly based on
the Dempster-Shafer theory, which introduces the notion of
assigning beliefs and plausibilities rather than probability distributions to measurement hypotheses [34], [125]. In combination with suitable rules for the fusion step, this can be
considered a generalization of Bayesian theory dealing with
probability mass functions. An exemplary remote sensing application of the Dempster-Shafer theory has been presented
for the fusion of high-resolution optical and SAR imagery for
updating building databases [107].
Fuzzy set theory, then, is another example of a theoretical reasoning scheme for imperfect data and introduces the
notion of partial set membership that enables imprecise reasoning [174]. In contrast to probability and evidence theories,
fuzzy set theory is well suited to model the fuzzy membership
of an object in an ill-defined class, so it is a powerful theory
to represent vague data. In the remote sensing context, it has
already been applied for the fusion of displacement measurements derived from both amplitude image correlation and
differential SAR interferometry [171].
Fuzzy theory can also be integrated with probabilistic and
Dempster-Shafer-based fusion algorithms in a complementary manner. Possibilistic fusion is based on fuzzy set theory
but was designed to represent incomplete data [38]. In that
sense, it is similar to the Dempster-Shafer theory but uses a
different quantification approach.
Finally, rough set theory is a framework to model imprecise data, ignoring uncertainty at different granularity levels
[104], whereas random set theory models target states and
measurements as random sets of finite size instead of conventional vectors [85]. Priors and likelihood functions that
are capable of modeling a wide range of different phenomena are constructed.
While most of the mentioned estimation frameworks are
aiming at the attribute estimation step, another possibility,
which is particularly interesting in the context of identity
estimation, is the utilization of machine-learning methods
(see the "Integration of Machine Learning to the Data Fusion World" section) such as random forests [18] or neural networks [12] for bootstrap aggregating, which provides
improvements for unstable procedures and some variance
reduction and furthermore helps to avoid overfitting [17].
One example from the remote sensing context suggested
learning relevant features to improve multisensor classification results [148].
ieee Geoscience and remote sensing magazine
DECember 2016
Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - December 2016
IEEE Geoscience and Remote Sensing Magazine - December 2016 - Cover1
IEEE Geoscience and Remote Sensing Magazine - December 2016 - Cover2
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 1
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 2
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 3
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 4
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 5
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 6
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 7
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 8
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 9
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 10
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 11
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 12
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 13
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 14
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 15
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 16
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 17
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 18
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 19
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 20
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 21
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 22
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 23
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 24
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 25
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 26
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 27
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 28
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 29
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 30
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 31
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 32
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 33
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 34
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 35
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 36
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 37
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 38
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 39
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 40
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 41
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 42
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 43
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 44
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 45
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 46
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 47
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 48
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 49
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 50
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 51
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 52
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 53
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 54
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 55
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 56
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 57
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 58
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 59
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 60
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 61
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 62
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 63
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 64
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 65
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 66
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 67
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 68
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 69
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 70
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 71
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 72
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 73
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 74
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 75
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 76
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 77
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 78
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 79
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 80
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 81
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 82
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 83
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 84
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 85
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 86
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 87
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 88
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 89
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 90
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 91
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 92
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 93
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 94
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 95
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 96
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 97
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 98
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 99
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 100
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 101
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 102
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 103
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 104
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 105
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 106
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 107
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 108
IEEE Geoscience and Remote Sensing Magazine - December 2016 - Cover3
IEEE Geoscience and Remote Sensing Magazine - December 2016 - 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