Professional Documents
Culture Documents
Change Detection and Image Time Series Analysis 1 Unsupervised Methods 1St Edition Abdourrahmane M Atto Full Chapter PDF
Change Detection and Image Time Series Analysis 1 Unsupervised Methods 1St Edition Abdourrahmane M Atto Full Chapter PDF
https://ebookmass.com/product/methods-and-techniques-for-fire-
detection-signal-image-and-video-processing-perspectives-1st-
edition-cetin/
https://ebookmass.com/product/interrupted-time-series-analysis-
david-mcdowall/
https://ebookmass.com/product/applied-economic-forecasting-using-
time-series-methods-ghysels/
https://ebookmass.com/product/time-series-analysis-in-seismology-
practical-applications-1st-edition-alejandro-ramirez-rojas/
Time Villains Series, Book 1 Victor Piñeiro
https://ebookmass.com/product/time-villains-series-book-1-victor-
pineiro/
https://ebookmass.com/product/demanding-energy-space-time-and-
change-1st-edition-allison-hui/
https://ebookmass.com/product/machine-vision-inspection-systems-
vol-1-image-processing-concepts-malarvel-m-ed/
https://ebookmass.com/product/deep-learning-for-medical-image-
analysis-1st-edition-s-kevin-zhou/
https://ebookmass.com/product/applied-time-series-analysis-a-
practical-guide-to-modeling-and-forecasting-terence-c-mills/
Change Detection and Image Time Series Analysis 1
SCIENCES
Image, Field Director – Laure Blanc-Feraud
Remote Sensing Imagery, Subject Heads –
Emmanuel Trouvé and Avik Bhattacharya
Coordinated by
Abdourrahmane M. Atto
Francesca Bovolo
Lorenzo Bruzzone
First published 2021 in Great Britain and the United States by ISTE Ltd and John Wiley & Sons, Inc.
Apart from any fair dealing for the purposes of research or private study, or criticism or review, as
permitted under the Copyright, Designs and Patents Act 1988, this publication may only be reproduced,
stored or transmitted, in any form or by any means, with the prior permission in writing of the publishers,
or in the case of reprographic reproduction in accordance with the terms and licenses issued by the
CLA. Enquiries concerning reproduction outside these terms should be sent to the publishers at the
undermentioned address:
www.iste.co.uk www.wiley.com
ERC code:
PE1 Mathematics
PE1_18 Scientific computing and data processing
PE10 Earth System Science
PE10_3 Climatology and climate change
PE10_4 Terrestrial ecology, land cover change
PE10_14 Earth observations from space/remote sensing
Contents
Preface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi
Abdourrahmane M. ATTO, Francesca B OVOLO and Lorenzo B RUZZONE
List of Notations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xv
1.6. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
1.7. Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
1.8. References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
3.4.6. Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 91
3.4.7. Results of change detectors on the UAVSAR dataset . . . . . . . . . 91
3.5. Change detection based on structured covariances . . . . . . . . . . . . 94
3.5.1. Low-rank Gaussian change detector . . . . . . . . . . . . . . . . . . 96
3.5.2. Low-rank compound Gaussian change detector . . . . . . . . . . . . 97
3.5.3. Results of low-rank change detectors on the UAVSAR dataset . . . 100
3.6. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 102
3.7. References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103
Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 277
RSI has become a broad multidisciplinary domain attracting scientists across the
diverse fields of science and engineering. The aim of the books proposed in this RSI
series is to present the state-of-the-art and available scientific knowledge about the
primary sources of images acquired by optical and radar sensors. The books cover
the processing methods developed by the signal and image processing community to
extract useful information for end-users for an extensive range of EO applications in
natural resources.
In this project, each RSI book focuses on general topics such as change
detection, surface displacement measurement, target detection, model inversion and
data assimilation. This first book of the RSI series is dedicated to Change Detection
and Image Time Series Analysis. It presents methods developed to detect changes
and analyze their temporal evolutions using optical and/or synthetic aperture radar
(SAR) images in diverse settings (e.g. image pairs, image time series). According
to the numerous works and applications in this domain, this book is divided into
two volumes, dedicated to unsupervised and supervised approaches, respectively.
Unsupervised methods require little to no expert-based information to resolve a
problem, whereas the contrary holds true, especially for methods that are supervised
in the sense of providing a wide amount of labeled training data to the method, before
testing this method.
difference image and derives from scratch a multiclass model for it in the context
of change vector analysis.
This book covers both methodological and application topics. From the
methodological viewpoint, contributions are provided with respect to feature
extraction and a large number of evaluation metrics for change detection, classification
and forecasting issues. Analysis has been performed in both bitemporal images and
time series, illustrating both unsupervised and supervised methods and considering
both binary- and multiclass outputs. Several applications are mentioned in the
chapters, including agriculture, urban areas and cryosphere analysis, among others.
This book provides a deep insight into the evolution of change detection and time
series analysis in the state-of-the-art, as well as an overview of the most recent
developments.
July 2021
List of Notations
I “ pIk pp, qqqk,p,q Image Time Series: time index k and pixel position
pp, qq
I “ p´Ikc pp, qqqk,p,q,c
¯
Vector Image Time Series: band/spectral index c
pu,vq
I “ Ik pp, q q Matrix Image Time Series: (polarimetric indices pu, v q)
k,p,q,u,v
N, Z, R, C Sets of Natural Numbers, Integers, Real and Complex
Numbers
μ, μ Means of Random Variables and Random Vectors
C, Σ Physical and Statistical Variance–Covariance Matrices
pdf Probability Density Function
1.1. Introduction
In recent years, many CD methods have been developed for multispectral images,
most of which focus on improving the automation, accuracy and applicability of CD
(Leichtle et al. 2017; Liu et al. 2017a, 2019b; Wang et al. 2018; Saha et al. 2019;
Wei et al. 2019). In general, according to the automation degree, they can be grouped
into three main categories: supervised, semi-supervised and unsupervised methods.
Usually, supervised CD approaches have better performance with higher accuracy by
taking advantage of certain robust supervised classifiers (Wang et al. 2018). However,
their implementation relies on the availability of ground reference data, which is
often difficult to collect in most practical cases. Semi-supervised CD approaches start
from limited training samples or partial prior knowledge learned from the single-time
image, where the active learning or transfer learning algorithm can usually be applied
to increase the sample representation (Liu et al. 2017b, 2019a; Zhang et al. 2018; Tong
et al. 2020). In contrast, unsupervised approaches have higher automation without
relying on the availability of ground reference data or prior knowledge (Liu et al.
2017a, 2019b; Saha et al. 2019). Therefore, the analysis in the unsupervised CD
case is mainly data-driven and is actually more challenging than the other two tasks.
Unsupervised Change Detection in Multitemporal Remote Sensing Images 3
However, from a practical application point of view, it is definitely more attractive due
to its simplicity and high automation.
The rest of this chapter is organized as follows. Section 1.2 points out the
key concepts and challenges in unsupervised CD, and especially reviews the
current development of spectral–spatial unsupervised CD techniques. Section 1.3
describes the two proposed unsupervised multiclass CD approaches in detail. Dataset
description and experimental setup are provided in section 1.4. Experimental results
and discussions are present in section 1.5. Finally, section 1.6 draws the conclusion of
this chapter.
• … • … • … • ….
Figure 1.1. The main technical components of an unsupervised CD process
Unsupervised Change Detection in Multitemporal Remote Sensing Images 5
Change index construction: the change index represents the temporal variations
extracted from multitemporal image features. It can be constructed based on different
operators and algorithms, such as univariate image differencing (Bruzzone and Prieto
2000a), change vector analysis (CVA) (Bovolo and Bruzzone 2007b), ratioing (Bazi
et al. 2005), distance or similarity measures (Du et al. 2012), etc. Transformation
approaches such as iterative reweighted multivariate alteration detection (IR-MAD)
(Nielsen 2007), principal components analysis (PCA) and its kernel version (Nielsen
and Canty 2008; Celik 2009), independent component analysis (ICA) (Liu et al.
2012), are also designed to transform the change information from the original
data space into a projected feature space. However, a careful selection of specific
components representing user-interested changes is required. This is often very
difficult in an unsupervised CD case without prior knowledge about the considered
study area and dataset, which may limit the automation degree of the CD application.
For a summary of the related methods for constructing different types of change index,
readers can refer to the paper by Bovolo and Bruzzone (2015).
For a multiclass CD case, the unsupervised task becomes more complex since
several sub-problems should be solved simultaneously, including the binary change
and no-change separation, the number of multiclass change estimation and the
multiclass change discrimination (Liu et al. 2019c). In particular, among many
solutions, we recall the classical multiple CD technique – change vector analysis
(CVA) (Malila 1980). It was designed to analyze possible multiple changes in pairs
of bitemporal image bands. A theoretical definition was given to the original CVA
approach in the polar domain to provide a more clear mathematical explanation to
CVA (Bovolo and Bruzzone 2007b). However, it still has a limitation, i.e. only a part
of all possible changes can be detected since only two selected bands are considered
in each implementation. If more spectral channels are considered, it becomes
very difficult to simultaneously model and visualize multidimensional changes. To
break this constraint, a compressed change vector analysis (C2 VA) approach was
proposed, which successfully extended the original CVA to a two-dimensional (2D)
representation of the multi-band problem (Bovolo et al. 2012). Other works in the
literature developed different variations of CVA. For example, a modified CVA
was developed to determine the magnitude threshold and direction by combining
single-date image classification results (Chen et al. 2003). An improved thresholding
approach on change magnitude was designed to optimize the binary separation on
each specific change class (Bovolo and Bruzzone 2011). A hierarchical version of
C2 VA with an adaptive and sequential projection of spectral change vectors (SCVs)
at each level of the hierarchy was proposed to detect multiple changes in bitemporal
hyperspectral images (Liu et al. 2015). In this chapter, we also explore the potential
capability of C2 VA and extend it from the spectral–spatial point of view.
Note that such a reference map is only used for accuracy evaluation, which is not
considered as training data as in the supervised case. In addition, the computational
time cost is also another important indicator that reflects the automation and efficiency
of unsupervised methods.
Accordingly, the following problems should be further analyzed: (1) how spatial
neighboring pixels have an impact on unsupervised change representation and
detection; (2) how to effectively model structural and geometric information of
change targets to enhance change representation; (3) how to integrate multiscale and
multidimensional change descriptions to increase change separability; (4) how to
adaptively find a suitable segmentation scale in the unsupervised OBCD approach.
In this chapter, we investigate these issues and develop new spectral–spatial CD
approaches in multitemporal multispectral images.
Unsupervised Change Detection in Multitemporal Remote Sensing Images 9
»¨ g ˛fi
fB
ÿ
B
` ˘ f ÿ ` ˘2 ÿ
B
θ “ arccos –˝ XD r {e
b b b
XD prb q2 ‚fl [1.2]
b 1“ b 1 “ “
b 1
b
where XD is the b-th (b=1,...,B) component of the differencing (SCVs) image XD ,
which was calculated on the co-registered images X1 and X2 , and B is the number
of image bands (i.e. the dimensionality of SCVs). rb is the b-th component of an
“ ?
adaptive ? ‰ r. In the standard C2 VA, r is2 defined as a unit constant vector
reference vector
r “ 1{ B, ..., 1{ B (Bovolo et al. 2012). In S CVA, it is improved as the first
eigenvector of the covariance matrix A of XD (Liu et al. 2015):
” ı
A “ cov pXD q “ E pXD ´ E rXD sq pXD ´ E rXD sqT [1.3]
A¨V“V¨W [1.4]
V “ rv1 , v2 , v3 , ..., vB s). The reference vector r is defined as the first eigenvector
v1 corresponding to the largest eigenvalue λ1 , i.e. r “ v1 . Note that this results in
an improved change representation by projecting the SCVs into a reference direction
that maximizes the variance of the measurement, while preserving the discriminative
information of different changes.
where ρmax is the maximum value of ρ. A semicircle scattergram (see Figure 1.2) is
used for visualizing multiple changes in D. Regions of the semicircle SCn (which
represents the unchanged pixels) and the semiannulus SAc (which represents the
changed pixels) are mathematically defined as:
and detect all possible changes (both strong and subtle changes) in hyperspectral
images due to complex change representations in the high dimensionality of
hyperspectral images. However, fewer levels may be obtained when only a few
spectral bands are considered, as in the multispectral case.
“ ‰
i
CR pf q “ Rε δi pf q [1.9]
where i is the radius of the SE. Here, δ i p¨q and εi p¨q are the dilation and erosion
operations, respectively. Rδ and Rε are the geodesic reconstruction by dilation and
erosion, respectively. In particular, the components of MP, i.e. OR and CR , are able
to suppress brighter and darker regions, respectively, that are smaller than the moving
SE, while preserving the geometrical characteristics of a region larger than the SE
(Dalla Mura et al. 2010). Small isolated objects are merged into a surrounding local
background while the main structure is kept. Due to the fact that different image
objects usually have different sizes, multiscale representation allows us to explore
different hypothetical spatial domains by using a range of SE sizes, in order to obtain
the best response for different structures (Mura et al. 2008).
12
X
2
Change Detection and Image Time Series Analysis 1
For the B-dimensional SCVs XD , at a given scale i, its OR and CR are also
B-dimensional:
` ˘ ` ˘ ` ˘(
i
OR pXD q “ ORi X1D , . . . , ORi XbD , . . . , ORi XBD [1.10]
` ˘ ` ˘ ` ˘(
i
CR pXD q “ CRi X1D , . . . , CRi XbD , . . . , CRi XBD [1.11]
b P r1, B s, i P r1, N s
defined as:
“ ‰
i
OCR pXD q “ ORi pXD q , CRi pXD q [1.12]
SCVs Y′ CD Map
X1
Instead of using thresholding to segment the binary and multiple classes in the
variables ρ and θ, the simple but effective clustering, i.e. k-means, is used for
generating the final CD map, which does not rely on any specific data distribution.
This is due to the fact that changed and unchanged pixels in ρ and multiclass changes
in θ do not always follow a Gaussian mixture distribution (Zanetti et al. 2015). Thus,
for the binary CD step (i.e. separating two classes), the number of clusters kρ is equal
to 2, and for the multiclass CD step, the number kθ is defined as the number of changes
observed in the 2D polar scattergram.
memory efficient, and only requires the storage of the distance from each pixel to
its nearest cluster center. Most importantly, it can be smoothly integrated within
the proposed method, especially from the pixel to superpixel-level spectral change
representation and detection, which drives a proper algorithm utilization.
The general idea of the SLIC algorithm is to find small regional clusters by
considering their local homogeneity (Achanta et al. 2012). The key step is to calculate
the distance d that implements a measurement from the spectral–spatial point of view.
Let dcolor and dxy be the spectral and spatial distances between two given pixels α
and β, respectively, defined as:
b
dcolor “ pLα ´ Lβ q2 ` pAα ´ Aβ q2 ` pBα ´ Bβ q2 [1.14]
b
dxy “ pxα ´ xβ q2 ` pyα ´ yβ q2 [1.15]
Here, pL, A, B qT denotes the CIELAB color space values, with L being the color
lightness and A and B representing color values along red-green and blue-yellow
axes, respectively. px, y qT denotes the coordinates of a given pixel. A final weighted
distance measure dαβ can be defined as:
d ˆ ˙2
dα,β “ d2color ` m2
dxy
s
[1.16]
where s is the width of grids. It controls the size of created superpixels, i.e. the greater
the s,a
the larger the superpixels. A roughly equal-sized grid interval can be defined as
s “ pZ {N q, where Z is the total number of pixels and N is the desired number
1
of superpixels. In reality, the real number of generated superpixels (defined as N )
might be slightly different from N . The parameter m controls the relative importance
between the color similarity and the spatial proximity. The greater the m, the greater
the emphasis on spatial proximity and the compactness of a generated superpixel. A
regular m value can be defined within the range of [1, 40]. For more details, readers
can refer to the paper by Achanta et al. (2012).
In order to enhance the spectral variations due to the limited bands in multispectral
images, principal component analysis (PCA) is applied to the original SCVs. This
strengthens the change representation and extends the feature space. The first three
principal components (i.e. PCs) are used in the SLIC algorithm to generate the
segments (i.e. superpixels) with the identified boundaries. Then original SCVs are
stacked with the PCs to create an enhanced feature set (denoted as SCVs-PC). Note
that normalization is conducted on SCVs-PC bands to make data dynamic range
consistent. Finally, a mean operation is applied on each segment in the SCVs-PC
Unsupervised Change Detection in Multitemporal Remote Sensing Images 17
bands, where the mean vector is used to replace the original SCVs-PC vectors, in
order to achieve the enhanced spectral change representation at the superpixel level.
Note that, by doing this, the change information is concentrated with spectral–spatial
coherence and the computational cost is largely reduced when compared with the
original pixel-wise processing.
where n denotes the gray level and p “ ppk qk“1,2,...,n contains the histogram counts
1
of the first three bands of Y . It is worth noting that with the increasing N, GE values
are expected to increase continuously and approach the value of the original image.
The logarithmic function is then used to fit the GE results to estimate the threshold
for the optimal segmentation scale. A detailed description of this step is provided in
Table 1.1.
Step 1: Initialize N , which is approximated as the smaller one in the rows and columns of
the input image, and the segmentation scale interval is set approximately equal to (row +
column)/20.
Step 2: Calculate the GE value of each segmented image under different searching scales.
Step 3: Fit the logarithmic function on the obtained GE results and calculate the gradient.
Step 4: Estimate the optimal segmentation scale by analyzing the gradient of GE values,
where the convergence threshold TGE is defined approximately equal to 100/(row +
column) based on the input image.
The first dataset is a pair of QuickBird images acquired over an urban area in
Xuzhou city, Jiangsu province (China) in September 2004 (X1 ) and May 2005 (X2 ),
respectively. The Gram–Schmidt (G-S) pan-sharpening algorithm was applied to fuse
the multispectral (2.4 m) and panchromatic images (0.6 m), in order to generate
the final fused dataset (0.6 m) with four spectral bands (i.e. red, green, blue and
near infrared). Images were radiometrically corrected and co-registered (with residual
misregistration of about 0.3 pixels), and the final region with a size of 760ˆ370 pixels
was extracted for the CD experiment. A total of six change classes are presented in
this scenario. Detailed class transitions are: 1) soil to built-up area (C1); 2) soil to roof
(face to the sun) (C2); 3) soil to roof (back to the sun) (C3); 4) built-up area to soil
(C4); 5) shadow to soil (C5); 6) trees to soil (C6). The false color composite images
X1 and X2 are shown in Figure 1.6 (a) and (b), respectively, and Figure 1.6 (c) presents
the change reference map made by careful image interpretation.
Figure 1.5. Illustration of the decision-level fusion-based binary CD step.
For a color version of this figure, see www.iste.co.uk/atto/change1.zip
Unsupervised Change Detection in Multitemporal Remote Sensing Images
19
20
Figure 1.7. False color composite of QuickBird images of the Indonesia tsunami dataset acquired in: (a) April 2004 (before
tsunami), (b) January 2005 (after tsunami); (c) and (d) are two subsets selected from the whole scene in the qualitative
experimental analysis. (e) Change reference samples. For a color version of this figure, see www.iste.co.uk/atto/change1.zip
Unsupervised Change Detection in Multitemporal Remote Sensing Images
21
22 Change Detection and Image Time Series Analysis 1
The optimal segmentation scale was estimated by analyzing the GE values (see
Figure 1.9(a)) and its logarithmic fitting results (see Figure 1.9(b)). The TGE was
calculated and defined as 1 ˆ 10´4 , then the final segmentation optimal scale was
obtained as 1,160.
From the detailed quantitative and qualitative analyses based on the obtained CD
accuracy and error indices (see Table 1.2) and the obtained CD maps (see Figure 1.10),
it can be observed that the proposed M2 C2 VA and SPC2 VA approaches resulted in
higher performance than the reference methods, with respect to the higher OA and
Kappa values and smaller detection errors (see Table 1.2). In particular, SPC2 VA
achieved the highest accuracy (i.e. OA = 92.74% and Kappa = 0.7464), outperforming
the other methods. Improvement can also be observed from the obtained change maps
by comparing them with the reference map; the identified change targets are more
accurate in the two proposed approaches (i.e. Figure 1.10(c) and (d)) than those in the
two reference methods (i.e. Figure 1.10(a) and (b)). In two reference methods, S2 CVA
showed better performance than IR-MAD. As for the computational cost, the proposed
SPC2 VA approach exhibited efficient performance, which consumed less time than the
proposed M2 C2 VA and IR-MAD, and similar or slightly more time than S2 CVA (i.e.
8.91 s vs. 7.12 s), but yielding a significantly higher OA value (i.e. 92.74% vs. 87.74%).
segmentation scale was estimated as 35,140 according to Figure 1.12. Note that the
CD experiment and the quantitative analysis were carried out on the whole image
scene.
(a) (b)
(c) (d)
Figure 1.10. Comparison of the multiclass CD maps obtained by: (a) IR-MAD;
(b) S2 CVA; (c) proposed M2 C2 VA ([u, v ] = [1, 6]); (d) proposed SPC2 VA with
N = 1,160 and m = 30 (Xuzhou dataset). For a color version of this figure, see
www.iste.co.uk/atto/change1.zip
(a) (b)
Figure 1.12. Determination of the optimal segmentation scale in the Indonesia tsunami dataset.
(a) GE values of different segmented scales; (b) logarithmic fitting results based on (a).
For a color version of this figure, see www.iste.co.uk/atto/change1.zip
Unsupervised Change Detection in Multitemporal Remote Sensing Images 27
From the CD maps shown at the global scale (first row) and the local scale (second
and third rows) in Figure 1.13 and the CD accuracies in Table 1.3, we can see that
the proposed approach SPC2 VA obtained the highest accuracy (i.e. OA: 93.69% and
Kappa: 0.8244) among all of the considered methods. The proposed M2 C2 VA also
showed good results and outperformed the two reference methods. Smaller detection
errors were found (i.e. 361,842 and 517,007 pixels in the two proposed approaches
against 908,649 and 806,039 pixels in the two reference methods), especially the
CE values. The detected change targets are more homogeneous and regular with
respect to their shapes and spatial distributions (see Figure 1.13(c) and (d)). This
demonstrates that the proposed spectral–spatial approaches are able to deal with
CD for large-scale data and offer a high detection performance, i.e. enhancing the
change targets and suppressing the no-change class. For two pixel-wise reference
methods, S2 CVA performed better than IR-MAD, as in the IR-MAD results, change
and no-change pixels are highly mixed in their spectral representation, leading to a
relatively poor detection accuracy. This is due to the complexity of the CD task in the
high spatial resolution multispectral images, and the pixel-wise correlation analysis
may fail to properly model the change targets solely based on spectral information.
From the point of view of the computational cost, the two proposed methods resulted
in a higher time cost than the two reference methods, but still at an acceptable level.
Therefore, from the careful qualitative analysis on both the global and local scales of
the obtained CD maps and the quantitative accuracy analysis, the effectiveness of the
proposed approaches in addressing a large complex multi-CD problem is validated.
28 Change Detection and Image Time Series Analysis 1
1.6. Conclusion
1.7. Acknowledgements
This work was supported by the Natural Science Foundation of China under Grant
42071324, 41601354, and by the Shanghai Rising-Star Program (21QA1409100).
1.8. References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S. (2012). Slic
superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on
Pattern Analysis and Machine Intelligence, 34(11), 2274–2282.
Ban, Y. and Yousif, O. (2016). Change Detection Techniques: A Review. Springer
International Publishing, Cham.
Bazi, Y., Bruzzone, L., Melgani, F. (2005). An unsupervised approach based on the
generalized Gaussian model to automatic change detection in multitemporal SAR
images. IEEE Transactions on Geoscience and Remote Sensing, 43(4), 874–887.
Benediktsson, J.A., Palmason, J.A., Sveinsson, J.R. (2005). Classification of
hyperspectral data from urban areas based on extended morphological profiles.
IEEE Transactions on Geoscience and Remote Sensing, 43(3), 480–491.
Bouziani, M., Goïta, K., He, D.-C. (2010). Automatic change detection of buildings
in urban environment from very high spatial resolution images using existing
geodatabase and prior knowledge. ISPRS Journal of Photogrammetry and Remote
Sensing, 65(1), 143–153 [Online]. Available at: http://www.sciencedirect.com/
science/article/pii/S092427160900121X.
Bovolo, F. (2009). A multilevel parcel-based approach to change detection in very
high resolution multitemporal images. IEEE Geoscience and Remote Sensing
Letters, 6(1), 33–37.
Bovolo, F. and Bruzzone, L. (2007a). A split-based approach to unsupervised change
detection in large-size multitemporal images: Application to tsunami-damage
assessment. IEEE Transactions on Geoscience and Remote Sensing, 45(6),
1658–1670.
Bovolo, F. and Bruzzone, L. (2007b). A theoretical framework for unsupervised
change detection based on change vector analysis in the polar domain. IEEE
Transactions on Geoscience and Remote Sensing, 45(1), 218–236.
30 Change Detection and Image Time Series Analysis 1
Du, P., Liu, S., Gamba, P., Tan, K., Xia, J. (2012). Fusion of difference images for
change detection over urban areas. IEEE Journal of Selected Topics in Applied
Earth Observations and Remote Sensing, 5(4), 1076–1086.
Du, P., Liu, S., Xia, J., Zhao, Y. (2013). Information fusion techniques for
change detection from multi-temporal remote sensing images. Information Fusion,
14(1), 19–27 [Online]. Available at: http://www.sciencedirect.com/science/article/
pii/S1566253512000565.
Falco, N., Mura, M.D., Bovolo, F., Benediktsson, J.A., Bruzzone, L. (2013).
Change detection in VHR images based on morphological attribute profiles. IEEE
Geoscience and Remote Sensing Letters, 10(3), 636–640.
Ghosh, A., Mishra, N.S., Ghosh, S. (2011). Fuzzy clustering algorithms for
unsupervised change detection in remote sensing images. Information Sciences,
181(4), 699–715 [Online]. Available at: http://www.sciencedirect.com/science/
article/pii/S0020025510005153.
Han, P., Gong, J., Li, Z. (2008). A new approach for choice of optimal spatial scale
in image classification based on entropy. Wuhan Daxue Xuebao (Xinxi Kexue Ban)/
Geomatics and Information Science of Wuhan University, 033(7), 676–679.
Han, Y., Javed, A., Jung, S., Liu, S. (2020). Object-based change detection of
very high resolution images by fusing pixel-based change detection results using
weighted Dempster–Shafer theory. Remote Sensing, 12(6) [Online]. Available at:
https://www.mdpi.com/2072-4292/12/6/983.
Huang, X., Zhang, L., Zhu, T. (2014). Building change detection from multitemporal
high-resolution remotely sensed images based on a morphological building index.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote
Sensing, 7(1), 105–115.
Hussain, M., Chen, D., Cheng, A., Wei, H., Stanley, D. (2013). Change detection
from remotely sensed images: From pixel-based to object-based approaches. ISPRS
Journal of Photogrammetry and Remote Sensing, 80, 91–106 [Online]. Available at:
http://www.sciencedirect.com/science/article/pii/S0924271613000804.
Kaszta, A., Van De Kerchove, R., Ramoelo, A., Cho, M.A., Madonsela, S., Mathieu, R.,
Wolff, E. (2016). Seasonal separation of African savanna components using
WorldView-2 imagery: A comparison of pixel- and object-based approaches and
selected classification algorithms. Remote Sensing, 8(9) [Online]. Available at:
https://www.mdpi.com/2072-4292/8/9/763.
Keshava, N. (2004). Distance metrics and band selection in hyperspectral processing
with applications to material identification and spectral libraries. IEEE Transactions
on Geoscience and Remote Sensing, 42(7), 1552–1565.
32 Change Detection and Image Time Series Analysis 1
Khan, S.H., He, X., Porikli, F., Bennamoun, M. (2017). Forest change detection
in incomplete satellite images with deep neural networks. IEEE Transactions on
Geoscience and Remote Sensing, 55(9), 5407–5423.
Leichtle, T., Geiß, C., Wurm, M., Lakes, T., Taubenböck, H. (2017). Unsupervised
change detection in VHR remote sensing imagery – An object-based clustering
approach in a dynamic urban environment. International Journal of Applied
Earth Observation and Geoinformation, 54, 15–27 [Online]. Available at:
http://www.sciencedirect.com/science/article/pii/S0303243416301490.
Li, H., Celik, T., Longbotham, N., Emery, W.J. (2015). Gabor feature based
unsupervised change detection of multitemporal SAR images based on two-level
clustering. IEEE Geoscience and Remote Sensing Letters, 12(12), 2458–2462.
Liu, S. and Du, P. (2010). Object-oriented change detection from multi-temporal
remotely sensed images. Geographic Object-Based Image Analysis, number
XXXVIII-4/C7.
Liu, S., Bruzzone, L., Bovolo, F., Du, P. (2012). Unsupervised hierarchical
spectral analysis for change detection in hyperspectral images. 4th Workshop
on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing
(WHISPERS), pp. 1–4.
Liu, S., Bruzzone, L., Bovolo, F., Zanetti, M., Du, P. (2015). Sequential spectral
change vector analysis for iteratively discovering and detecting multiple changes
in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing,
53(8), 4363–4378.
Liu, S., Du, Q., Tong, X., Samat, A., Bruzzone, L., Bovolo, F. (2017a). Multiscale
morphological compressed change vector analysis for unsupervised multiple
change detection. IEEE Journal of Selected Topics in Applied Earth Observations
and Remote Sensing, 10(9), 4124–4137.
Liu, S., Tong, X., Bruzzone, L., Du, P. (2017b). A novel semisupervised framework for
multiple change detection in hyperspectral images. IEEE International Geoscience
and Remote Sensing Symposium (IGARSS), 173–176.
Liu, J., Chen, K., Xu, G., Li, H., Yan, M., Diao, W., Sun, X. (2019a). Semi-supervised
change detection based on graphs with generative adversarial networks. IEEE
International Geoscience and Remote Sensing Symposium (IGARSS), 74–77.
Liu, S., Du, Q., Tong, X., Samat, A., Bruzzone, L. (2019b). Unsupervised
change detection in multispectral remote sensing images via spectral-spatial band
expansion. IEEE Journal of Selected Topics in Applied Earth Observations and
Remote Sensing, 12(9), 3578–3587.
Another random document with
no related content on Scribd:
these do more harm than good, and spoil young people for ordinary
life. Whatever may be said concerning the dull hotch-potch turned
out “in bulk” by the American film industry, nobody can deny that an
element of romance has been brought into the lives of countless
poor people by Edison’s and Berliner’s great invention.
As regards wireless broadcasting, it is too early to speak of its
permanent effects. It has come upon us like an avalanche. For the
first time, it has enlisted youth in the highest electrical problems. It
has paved the way for the general diffusion of scientific knowledge
while ostensibly popularizing the art of music. In any case, it is a
complete answer to Ben Akiba and his saying about there being
nothing new.
Mr. J. B. S. Haldane[2] believes that the centre of scientific interest
now lies in biology, and that physiology will eventually invade and
destroy mathematical physics. It is quite possible that the advance of
what physicists sometimes playfully call the “inexact” sciences may
cast those of physics and chemistry entirely in the shade, but
although biology has made some difference to human life in the last
generation, its effects cannot remotely compare with those of
physical and chemical discoveries. The mere increase of speed in
transport, due to the internal-combustion engine, has caused a
speeding-up of the whole nervous system and a brightening of the
intelligence of all but an insignificant fraction of the population. When
the choice lies between the Quick and the Dead, even the most
sluggish temperament will put on a spurt, and this continued
sprinting across the motor traffic has produced a more agile
generation. If such a profound difference can be made in twenty
years, what will be the effect of even 200 years of continually
accelerated progress?
[2] Dædalus, pp. 10 and 16.
The continual acceleration of the rate of progress must not be lost
sight of in forecasting the future. It happens to coincide with a similar
increase in the consumption of accumulated fuels, like coal and oil,
and might be expected to slow down when those supplies of
preserved sunlight come to an end. But by that time other
accumulations will no doubt have been discovered and utilized.
Unless the Russian blight extends over Europe and America, we
may confidently look forward to a long era of steadily accelerated
progress. What form that progress will take is notoriously difficult to
forecast. The main difficulty arises from the fact that the most
promising discoveries sometimes turn out to be impracticable, or at
least of quite secondary importance. Nobody prophesied the great
development of the motor car, nor of that gigantic child of the old
Zoetrope or “Wheel of Life” which we call the Picture Theatre. A
genius like H. G. Wells could indeed write a marvellously accurate
forecast of flying achievements, but in one of his books he makes a
great deal of the Brennan mono-rail, which, after a sensational
beginning, failed to reach maturity, probably owing to the temporary
failure of that much-maligned but quite essential fertilizer of
inventions, capital. Other inventions, such as the speaking film, bear
within themselves certain weaknesses which may prevent them from
attaining great popularity.
But previous failures to peep into the future effectively shall not
deter the author from another attempt to pierce the veil hiding our
fate. He will proceed by “extrapolating” the curves representing
progress made hitherto, but will always allow for unexpected new
departures in what are already known to be possible directions.