IEEE Geoscience and Remote Sensing Magazine - June 2016 - 11
properties in the two regions. In fact, the two classification
boundaries can be seen to provide different class labels on
the same test instance in the feature space, highlighted by a
star in Figure 1(c) and (d), across the two regions. This exemplifies the heterogeneity in the decision boundaries of the
target class across the two regions in space, making it difficult to learn a single classifier that can detect the burned
pixels in both regions.
With the presence of heterogeneity in the data across
space and time, it is important to learn different changedetection models for different regions and time steps, as
opposed to learning a single model that can capture the
characteristics of land-cover changes across all regions
and time steps. However, since representative training instances are only available in a limited number of regions
and time steps, the presence of heterogeneity has limited
the scope of existing land-cover change-detection methods to local or regional scales. The existing nonlinear
classification approaches that have attempted to handle
the diversity or multimodality within the data by making use of kernel-based methods include [10] and [14].
However, such methods are not able to handle the heterogeneity in the data in scenarios where different partitions (i.e., regions or times) of the data show different
characteristics and, therefore, require different models, as
highlighted in Figure 1.
RARITY OF LAND-COVER CHANGES
The majority of land-cover changes are rare events that occur
infrequently in comparison with other no-change events.
For example, land-cover changes such as forest fires and flash
floods only occur for short durations over small spatial regions. Hence, there is often a huge class imbalance between
land-cover change events of interest and no-change events,
which makes their detection and verification challenging.
A class imbalance can impact the performance of
change-detection algorithms in a number of ways. First,
the presence of a class imbalance between change and nochange events makes it difficult to obtain representative
training instances of the rare change class, which can result
in poor detection performance. Second, a class imbalance
can contaminate the performance of PCCD techniques
by the detection of a large number of spurious changes
as false alarms or inclusion errors because individual errors in classifications across time steps may lead to accumulation and propagation of these errors in the change
detection. For example, it can be shown that the accuracy
of detecting a land-cover transition across two time steps
is equal to the product of the land-cover classification accuracies at those two time steps, assuming that they are
independent [15], [16]. Third, since compound classification approaches require training instances for every transition among land-cover labels, they can suffer from poor
performance on rare land-cover transitions that are underrepresented in the training set. Finally, a class imbalance
also impacts the effectiveness of traditional evaluation
june 2016
ieee Geoscience and remote sensing magazine
schemes for land-cover change detection because commonly used evaluation metrics, such as accuracy and false
positive rate, can produce misleading results due to the
skewness among the classes. For example, even in the presence of a high true positive rate (TPR), a, and a low false
positive rate (FPR), b, of an approach for detecting change
events, the precision of correctly detecting change events in
the presence of a class imbalance of 1:s is equal to a /(a + bs)
[13], which can be significantly poor when the skew s is
large. To illustrate this, if we consider a class imbalance
of 1:100, which is commonly observed in the illustrative
application of detecting forest fire events, even a TPR of
0.99 and an FPR of 0.01 can result in a precision of 0.009,
which is quite low. The existing approaches for land-cover
change detection in the presence of a class imbalance have
explored the use of one-class classification techniques [17]
and techniques that use the unsupervised information of
rare changes for adapting the learning of a classifier [18].
THE USE OF MULTISCALE DATA
In a number of land-cover change-detection problems, observations of different physical quantities are available at varying
scales of resolution, both in
space and time. For example,
multispectral information of
commoNly used evaluathe earth's surface that is useful
tioN metrics, such as
in detecting the burned scars
accuracy aNd False posiof forest fire events is available
globally via Landsat data at
tive rate, caN produce
temporally coarse (i.e., every
misleadiNG results due
16 days) but spatially fine resoto the skeWNess amoNG
lutions (30 m) and via MODIS
the classes.
data at spatially coarse (250 m)
but temporally fine resolutions
(i.e., on a daily scale). It is important to note that the use of multiscale data for land-cover
change detection is important, as different data sets at varying
spatial and temporal resolutions capture the complementary
sources of information about a change phenomena. Hence,
the combined analysis using information from multiple scales
has the potential to provide a more comprehensive understanding of a land-cover change phenomena than any of the
individual data sets available at a single scale.
However, the multiscale nature of remote sensing data
presents challenges to the existing machine-learning algorithms that are primarily designed to operate with data sets
available at a single scale of observation. In the presence of
multiscale data, there is a lack of a clear one-to-one correspondence between the instances of different data sets that are
available at different scales. For example, the ground-truth information for land-cover change detection is often available at
a coarser resolution than the remote sensing observations due
to physical limitations of human annotation. In such scenarios, a single ground-truth label may correspond to multiple
instances of remote sensing features, which is not modeled by
traditional machine-learning formulations.
11
Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - June 2016
IEEE Geoscience and Remote Sensing Magazine - June 2016 - Cover1
IEEE Geoscience and Remote Sensing Magazine - June 2016 - Cover2
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 1
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 2
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 3
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 4
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 5
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 6
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 7
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 8
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 9
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 10
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 11
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 12
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 13
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 14
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 15
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 16
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 17
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 18
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 19
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 20
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 21
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 22
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 23
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 24
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 25
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 26
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 27
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 28
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 29
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 30
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 31
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 32
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 33
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 34
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 35
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 36
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 37
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 38
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 39
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 40
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 41
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 42
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 43
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 44
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 45
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 46
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 47
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 48
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 49
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 50
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 51
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 52
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 53
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 54
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 55
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 56
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 57
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 58
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 59
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 60
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 61
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 62
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 63
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 64
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 65
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 66
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 67
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 68
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 69
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 70
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 71
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 72
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 73
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 74
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 75
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 76
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 77
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 78
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 79
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 80
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 81
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 82
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 83
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 84
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 85
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 86
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 87
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 88
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 89
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 90
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 91
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 92
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 93
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 94
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 95
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 96
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 97
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 98
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 99
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 100
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 101
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 102
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 103
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 104
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 105
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 106
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 107
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 108
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 109
IEEE Geoscience and Remote Sensing Magazine - June 2016 - 110
IEEE Geoscience and Remote Sensing Magazine - June 2016 - Cover3
IEEE Geoscience and Remote Sensing Magazine - June 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