CHANGE DETECTION TECHNIQUES - A SUR V EY

International Journal on Computational Sciences & Applications (IJCSA) Vol.5, No.2,April 2015
DOI:10.5121/ijcsa.2015.5205 45
CHANGE DETECTION TECHNIQUES - A
SURVEY
R.Naveena Devi1
, Dr.G.Wiselin Jiji2
PG Scholar, Dr.Sivanthi Aditanar College of Engineering,Tiruchendur,India1
Dr.Sivanthi Aditanar College of Engineering, Tiruchendur,India2
ABSTRACT
The data obtained from remote sensing satellites furnish information about the land at varying resolutions
and has been widely used for change detection studies. There exist a huge number of change detection
methodologies and techniques with the continual emergence of new ones. This paper provides a review of
pixel based and object-based change detection techniques in conjunction with the comparison of their
merits and limitations. The advent of very-high-resolution remotely sensed images, exponentially increased
image data volume and multiple sensors demand the potential use of data mining techniques in tandem
with object-based methods for change detection.
KEYWORDS
Change detection, pixel-based, object-based, spatial data mining and hybrid change detection.
1.INTRODUCTION
Change detection is defined as the process of identifying differences in the state of an object or
phenomenon by observing it at different times (Singh, 1989). The general goal of change
detection in remote sensing includes identifying the geographical location, recognizing and
quantifying the type of changes and finally assessing the accuracy results (Macleod and
Congalon, 1998; Coppin et al., 2004; Im and Jensen, 2005 ;). Remote sensing data is used for
change detection because the changes in the object of interest modifies the spectral behavior (like
reflectance value or local texture) which can be differentiated from changes caused by other
factors (e.g. illumination and viewing angles, atmospheric conditions and soil moistures) (Jensen,
1983; Singh, 1989; Green et al., 1994;Deer, 1995;). The elements that affect change detection
using remote sensing data includes spatial, spectral, thematic and temporal constraints,
atmospheric conditions, radiometric resolution and soil moisture conditions (Jensen, 2005).
Change information obtained may be either in the form of simple binary change (i.e. change vs.
no change as in the case of image differencing, image rationing etc) or detailed from-to change as
in the case of using post-classification comparison (Im et al., 2007).

46
The considerations to be followed before using remote sensing data for change detection includes
(i) Usage of data from same sensor, radiometric and spatial resolutions and near-anniversary
acquisition dates to remove the effects of seasons, sun angle and phonological difference (Song
and Woodcock, 2003). (ii) Precise geometric registration between multi-temporal images to avoid
false change areas being detected due to image displacement. (iii) Performing radiometric
corrections to rectify errors caused by the variation in sensor characteristics, atmospheric
condition, solar angle, and sensor view angle (Chen et al., 2005; Du et al., 2002). (iv) Data
collection - data collected ahead of time fail to cover slower change process whereas data
collected in a delayed manner leads to excessive omission errors which significantly impact the
completeness of change detection (Lunetta et al., 2004). (v) Choice of change detection technique
which is influenced by spatial resolution and the size of the study area.
In this paper change detection methodologies is categorized based on the unit of image analysis.
First being the traditional/classical pixel-based, where an image pixel is the fundamental unit of
analysis. Second is the object-based method, in which image objects are first created and then
subjected to further analysis. In any approach the pre-processing stage handles radiometric,
atmospheric, and topographic corrections, geometrical rectification and image registration.
Higher registration accuracy is inevitable when using data from different sensors and at different
resolutions whereas registration accuracy can be avoided when object-based change detection is
employed where ‘‘buffer detection’’ algorithms can be applied to compare the extracted features
(Deren et al., 2003).
2.PIXEL-BASED CHANGE DETECTION TECHNIQUES
The spectral characteristics of an image pixel are exploited to detect and measure changes without
taking into considering the spatial context. Different pixel-based methods are explained in depth
by various researchers (Coppin et al., 2004; Deer, 1995; Ilsever and Ünsalan, 2012; Lu et al.,
2004; Singh, 1989).A brief summarization of these techniques is as follows.
2.1.Image Differencing
Image differencing is performed by subtracting the DN (digital number) value of one date for a
given band from the DN value of the same pixel for the same band of another date which results
in a new image. Mathematically, image differencing is given by
Id(x,y) = I1(x,y) - I2(x,y)
Where I1 and I2 are images from time t1 and t2 and (x,y) are coordinates and Id is the difference
image. A series of threshold values based on standard deviations from the mean can be used on
the new image to determine the changed from unchanged pixels. An accuracy assessment on the
no-change from change pixels was performed to determine the threshold value with the highest
accuracy. Pixels with change in radiance are distributed in the tails of the distribution curve
(Singh, 1989) whereas pixels with no change are distributed around the mean (Lu et al., 2005. As
changes seem to occur in both directions, the analyst have to decide the order of the image to
subtracted (Gao, 2009).

47
2.2.Image Rationing
Change results are expressed as a ratio between two co-registered images and unchanged areas
theoretically have 1 as its value.
Ir=I1(x,y)/I2(x,y)
The advantage of this method is that it handles calibration (including sun angle, shadow and
topography impact) errors efficiently (Rignot and van Zyl, 1993)
2.3.Image Regression
In this method one image (subject) is assumed to be a linear function of the other image
(reference) and the subject image is adjusted to match the radiometric conditions of the reference
image. When using least-squares regression analysis gains and offsets are identified by
radiometrically normalizing the subject image to match the reference image (Lunetta, 1999). And
the change denoted by Id can be obtained by subtracting regressed image from the ﬁrst-date
image.
Id1(x,y)=aId(x,y)+b
Id(x,y)=Id(x,y)-Id1(x,y)
As this method accounts for differences in the mean and variance between different date pixel
values, it reduces the adverse effects by sun angles and atmospheric conditions (Singh, 1989)
2.4.Vegetation Index Differencing
This technique uses data transformation that is related to green biomass. The Normalized
Difference Vegetation Index (NDVI) is calculated by NDVI = (NIR- RED)/ (NIR + RED) where
NIR is the near-infrared band response for a given pixel and RED is the red band response. After
computing the vegetation index for two date’s standard pixel based approaches (e.g. differencing
or rationing) are applied to determine the change (Nelson 1983, Singh 1986). Other vegetation
indices developed include (a) Ratio Vegetation Index (RVI) (b) orthogonal indices, including
Perpendicular Vegetation Index (PVI) and Difference Vegetation Index (DVI), and (c) Soil
Adjusted Vegetation Index (SAVI) and modiﬁed soil adjusted vegetation index (MSAVI) (Chen
et al., 1999).
RVI=n/r
NDVI=(n-r)/nr
TVI=(((n-r)/(n+r))+0.5)1/2
SAVI=((n-r)/(n+r+L))(1+L)
MSVI=(2n+1-((2n+1)2
-8(n-r))1/2
)/2
Where n is near infrared band, r is the red band and L indicates the same bound between NDVI
and SAVI. This method is that it reduces the impacts of illumination and topographic effects but
the output is subjected to random or coherence noise.

48
2.5.Change Vector Analysis
This method analyzes simultaneously multiple image bands to detect the change. The pixel values
are considered to be the vectors of spectral values and change vector can be computed by
subtracting vectors for all pixels at different dates (Malila, 1980). Type of change can be
determined from the direction of change vector while the length corresponds to the magnitude of
change. This method can be used when change of interest and their spectral manifestation are not
well-known; change of interest is known or has high spectral variability and when changes in
both land cover type and condition may be of interest (Johnson and Kasischke, 1998). The
drawback in using this method is that it requires the acquisition of remotely sensed data from
same phonological period (Chen et al., 2003) and furthermore the land cover change trajectories
are difficult to identify.
2.6.Principal Component Analysis
This method reduces data redundancy by transforming multivariate data to a new set of
components (Lillesand et al., 2008) with the assumption that areas of change are not highly
correlated. Covariance or correlation matrix is used to transfer data to an uncorrelated set. Then
sort the resulting matrices consisting of eigen vectors in descending order. Most of the data
variation is expressed by the first principal component. The next largest amount of variation is
defined by the succeeding principal component and this is orthogonal/independent to the principal
component that precedes it. Merged approach and separate rotation are two principal component
analysis based change detection approaches generally used. In separate rotation the principal
components are first acquired and then change detection techniques such as image rationing or
image differencing are applied. In the merged approach bi-temporal images are first merged into
one set and then the principal component is applied. To analyze the change types the eigen
structure of the data is to examined and the combined images should be subjected to visual
inspection (Coppin and Bauer, 1996). Since this method is scene dependent it is quiet
complicated to interpret and label for different dates. Moreover it just reports the changed areas
and does not give information about the type of change.
2.7.Kauth-Thomas Transformation (KT)/Tasseled Cap Transformation
This method involves fixed linear transformation (i.e., orthogonalization) of a multi-date and
multiband dataset. Here the structure of the spectral data is analyzed which is given as the
function of a particular characteristic of scene classes. Change is measured based on the
brightness, greenness and wetness values (Lu et al., 2004). This method is scene-independent and
uses stable and calibrated transformation coefficients to make sure that the applications can be
made appropriate across time and between regions (Crist, 1985). The major advantage of this
method is that it allows developing baseline spectral information for long-term studies by
producing stable spectral components.

49
2.8.Post-classification
In the post-classification change-detection technique, each image is rectified and classified
separately using both supervised and unsupervised classification techniques and then compared to
generate a change matrix which is used to measure the changes. To facilitate one-to-one
comparison classes for both the images have to be identical. This method provides the complete
matrices of change reducing the impact of atmospheric, sensor and environmental effects and
issues related to the usage of multi-sensor images. The limitation is that the accuracy of the final
image depends entirely on the classification accuracy of individual image. When using supervised
classification methods accurate, complete and high-quality training datasets is inevitable to
produce accurate classification but acquiring such datasets especially for historical image
classification is time-consuming and difficult task. Eventually using unsupervised classification
encounter problems in selecting the number of clusters as this has great impact on the results
generated furthermore the identification and labeling of change trajectories is yet another issue to
be noted (Lu et al., 2004). Different sensors produce different resolution images and hence
classification applied to coarser resolution image misses out certain elements that make the
matching process to the elements in fine scale resolution image difficult.
2.9.Composite or Direct Multi-date Classification
To identify areas of change this method involves performing single analysis of a combined
dataset of the two dates where initially multi-temporal and rectified images are stacked and then
to reduce the number of spectral components to a fewer principal components the principal
component analysis is applied (Mas, 1999; Singh, 1989). Significant difference in statistics is
presented by the classes where change has occurred. Spectral contrast is enhanced by the minor
components and the changes can be represented (Collins and Woodcock, 1996).
2.10.Machine Learning
Artificial neural network algorithm learns from the training dataset and build networks between
input images and output nodes (i.e., changes). Changed map is obtained by applying the trained
network to the main dataset (Dai and Khorram, 1999; Gopal and Woodcock, 1996). Support
vector machine, a supervised non-parametric statistical learning technique implements structural
risk minimization for classification (Vapnik, 2000). The algorithm learns from training data and
finds threshold values (Bovolo et al., 2008) from the spectral features automatically for
classifying change from no-change. Decision tree, a non-parametric classification algorithm
builds a hierarchical structure in which test on a number of attribute values is represented by each
node, outcome of the test is represented by each branch and tree leaves represent classes or class
distribution (Han et al., 2011; Larose, 2005). The classification rules at the node are based on the
analysis of attribute values. Other machine learning algorithms used include genetic programming
(Makkeasorn et al., 2009), random forest (Smith, 2010) and Cellular automata (Yang et al.,
2008).

50
2.11.Texture analysis based
Structural arrangement of objects and their relationship to local neighborhoods are provided by
texture (Caridade et al., 2008). Comparing the textural values from images is used to measure
changes. Grey level co-occurrence matrix is one among the texture measuring algorithms is a
second order statistics that examine the spectral as well as spatial distribution of grey values. Here
initially the image is divided into smaller windows instead of per-pixel comparison then the
texture is computed and comparison is performed at window level (Sali and Wolfson, 1992). He
and Wang (1991) highlighted to use texture information only in conjunction with spectral data.
2.12.Multi-temporal Spectral Mixture Analysis
In multi-temporal spectral mixture analysis the multispectral image pixels is assumed to be
defined in terms of sub-pixel proportions of pure spectral components that is related to surface
constituents in a scene. Due to high spectral resolution it addresses the increased dimensionality.
In linear mixture model, each end-member is linearly combined with the end-member spectra that
are weighted by the percent ground cover (Versluis and Rogan, 2009). For accuracy in applying
this technique that is based on image or field-spectra measures in situ or in labs Solans Vila and
Barbosa (2010) argue to give importance in selecting the number and spectrum of the end-
members.
2.13.Fuzzy Change Detection
Fuzzy set is defined by a membership function and differs from probabilistic interpretation; here
the class with highest probability is taken to be the actual class and change is measured by
applying post-classification comparison (Fisher et al., 2006). This method is useful when
selecting a threshold value to distinguish change from no-change is difficult.
3.OBJECT-BASED CHANGE DETECTION
Object-based change detection is performed by separately segmenting objects defined by a
threshold from multi-temporal images and analyzing the changes based on the spectral
information like averaged band values of the object or by extracting various features (i.e.,
geometry and image-texture) from the original objects
3.1.Image-object Change Detection
Object-based change detection algorithms that focus on direct image-object comparisons are
grouped into image-object change detection. Change can be detected either by comparing the
geometrical properties (width, area and compactness) (Lefebvreet al., 2008;), or spectral
information (mean band values) (Hall and Hay, 2003), and/or extracted features (e.g. texture)
(Lefebvre et al., 2008;) of the image objects. The algorithm used by Miller et al. (2005) involved
two steps to detect the change of significant objects between a pair of grey-level images. Here
connectivity analysis is used to extract the objects from the master image and each of these

51
objects was searched for a corresponding object in the second image. A matching method to
identify the relationship between two object boundary pixels was used to detect the change. Since
the algorithm performed processing directly on the objects extracted pre-defined window was not
required and it produced better results even with noisy input images. To detect changes in very
high-resolution airborne or space-borne images at the sub-metre level Lefebvreet al. (2008)
preferred texture features and object contour to e effective. The major advantage is that since
objects are extracted using segmentation the algorithms are easy to implement and involves the
direct comparison of objects to detect the change.
3.2.Class-object Change Detection
In this approach the extracted object is assigned to a specific class and changes are detected by
comparing the independently classified objects from multi-temporal images. The classification
algorithms incorporate both texture and spectral information. The GIS layers or existing maps are
updated using this approach. Classification techniques used include decision-tree, maximum
likelihood, nearest neighbor (Im and Jensen, 2005), fuzzy (Durieux et al., 2008).
3.3.Multitemporal-object Change Detection
In this approach temporally sequential images are combined and segmented to produce spatially
corresponding change objects as image-objects from different dates generated through
segmentation vary geometrically despite having same geographic feature(s). The algorithm
proposed by Descléeet al. (2006) initially involved the segmentation of multi-date image-set and
computing its spectral features (i.e. standard deviation and mean) from each date for all image-
objects. Statistical analysis based on the chi-square test was used to detect change. Mahalanobis
distance calculation and thresholding method can also be integrated to detect change Bontempset
al. (2008). Nearest-neighbor supervised classification approach and reference data was used by
Concheddaet al. (2008) to quantify changes. Incremental segmentation procedure by Liet al.
(2009) for radar imagery first segmented the first-date image then treated the result as a thematic
layer and finally segmented the derived layer together with the second-date image. However the
effect of mixed-object spectral information (i.e., viewing angles, meteorological, atmospheric and
illumination) on change results is still under research.
4.HYBRID CHANGE DETECTION
Hybrid change detection uses two or more methods for detecting change and is categorized as: (a)
procedure-based (using different detection methods in different detection phases) (b) result-based
(using different CD methods and analyzing their results) (Jianyaa et al., 2008). Combination of
pixel- and object-based approaches was used by Niemeyer and Nussbaum (2006) where initially
statistical change detection and object extraction pinpointing change pixels and semantic model
of object features subsequently post-classified the changes. Region-merging segmentation was
applied on Landsat Thematic Mapper (TM) and Landsat Enhanced Thematic Matter (ETM) and
then fuzzy-logic model classification was performed before comparing them to compute the
change (Gamanya et al. (2009)). Yu et al. (2010) used support vector machine to perform an
object based classification and then compared land use vector data with these objects to detect
change.

52
5.SPATIAL DATA MINING IN CHANGE DETECTION
Due to rapid increase in very high resolution remote sensing data availability and sophisticated
algorithm’s computational power change detection is becoming more data driven. Data mining
technique is part of a knowledge discovery in database that is supposed to extract non-trivial,
implicit information using various algorithms and techniques and this leads to the construction of
a knowledge model (Larose, 2005). Geo-graphical or spatial data mining, a specialized area of
KDD has the fundamental objective to explore both spatial and non-spatial properties to discover
hidden knowledge. Using data mining Boulila et al.(2011) developed a predictive model for land
cover change detection in image time series. Petitjean et al. (2010) applied mining techniques to
35 images covering 20 years to understand the frequent sequential patterns by providing Near
Infra-Red (NIR), Red (R), Green (G) and NDVI values. Otukei and Blaschke (2010) applied a
decision tree data mining algorithm C4.5 on the principle components, tasselled cap bands, and
normalized vegetation index and texture features extracted from Landsat TM to determine
threshold value that enabled the selection of appropriate bands for classification. In the work
proposed by Vieira et al. (2012), the objects were extracted from an image using object-based
image analysis followed by the usage of J48 decision tree data mining algorithms (using WEKA)
to create two classes. Data mining based change detection seems to achieve higher accuracy than
post-classification comparison.

53
Technique and
Approaches
Issues
(Pixel-based)
Image differencing
Image rationing
Image regression
Vegetation index
differencing
Change vector analysis
Principal component
analysis
Kauth-Thomas
transformation
Post-classification
comparison
Direct multi-date
classification
Machine learning
Texture analysis based
Multi-temporal spectral
mixture
Fuzzy
• Over-detection or mis-detection due to the failure in choosing right threshold
value to differentiate change from no- change. Low threshold value excludes
areas of change; high threshold value includes areas of change.
• Selecting an appropriate threshold is generally ambiguous especially for
unsupervised algorithms when ground truth is not available to present prior
knowledge.
• A variety of automated threshold selection algorithms are proposed but
Rosin and Ioannidis (2003) emphasize that the performance of these
algorithms is scene-dependent.
• Pu et al. (2008) focused on setting different thresholds for positive and
negative changes to improve the accuracy of change detection but the
identification of optimum threshold(s) has to be performed using either a
trial-and-error manual method or automatic generation and testing (Im et al.,
2007; Lu et al., 2004). Here the drawback while using the former method is
that it labor intensive, uses only one image for analysis, test just a few
discrete threshold and time consuming.
• The results of pixel-based methods are limited when applied to very-high-
resolution (VHR) imagery as it has to face a number of challenges which
includes increased variability in reflectance for each class resulting in salt-
and-pepper effect, various acquisition characteristics (e.g. viewing geometry
of sensor, illumination angle and effects due to shadow), geo- referencing
accuracy (Wulder et al., 2008)
• The spatial characteristic, relationships and arrangements of the real-world
objects are not modeled which results in missing the vital clues about the
area under investigation (Johansen et al., 2010)
• Output is subjected to noise (i.e., jagged boundaries or holes in the
connected changed components and isolated changed pixels (Bontemps et
al., 2008)).
(Object-based)
Image-object
Class-object
Multi-temporal
• Searching the spatially corresponding objects that are of different sizes and
shapes in multi-temporal images is a critical procedure and errors in it lead
to incorrect change detection results.
• Selecting the appropriate change threshold is a challenge in image-object
change detection.
• Performance and accuracy of the classification algorithm and selection of
image segmentation technique which results in different object sizes based
on different segmentation parameters influence the performance of class-
object change detection approach.
• In multi-temporal-object change detection approach the defect in registration
and shadowing effect affect multi-temporal segmentation (Stow, 2010) and
use of a single segmentation for all the images fails to provide new/different
objects which may be created at different times because of change

54
6.CONCLUSION
Developing change detection methods in remote sensing is an ever-growing research agenda.
Change detection is a complicated process with no single optimal approach applicable to all
cases. The change detection applications are on bio-physical, environmental change detection,
land use/cover change, security related application but the domain to explore is still wider
(Kennedy et al., 2009). The technological advancements over the last few decades has allowed
the applications to exceed the traditional limits and endeavor new ventures which in turn fed back
to the remote sensing technologies for further developments (Blaschke et al., 2011). The launch
of new satellites represent challenges to develop effective and efficient change detection
methodologies and frameworks capable of searching through huge achieve of remote sensing data
with different spatial/ spectral/temporal resolutions and enable change analysis (Vieira et al.,
2012).
REFERENCES
1. Blaschke, T., Hay, G.J., Weng, Q., Resch, B., 2011. Collective sensing: integrating geospatial
technologies to understand urban systems—an overview. Remote Sensing 3, 1743–1776.
2. Bontemps, S., Bogaert, P., Titeux, N., Defourny, P., 2008. An object-based change detection method
accounting for temporal dependences in time series with medium to coarse spatial resolution. Remote
Sensing of Environment 112, 3181–319.
3. Boulila, W., Farah, I.R., Ettabaa, K.S., Solaiman, B., Ghézala, H.B., 2011. A data mining based
approach to predict spatiotemporal changes in satellite images. International Journal of Applied Earth
Observation and Geoinformation 13, 386–395.
4. Bovolo, F., Bruzzone, L., Marconcini, M., 2008. A novel approach to unsupervised change detection
based on a semisupervised SVM and a similarity measure. IEEE Transactions on Geoscience and
Remote Sensing 46, 2070–2082.
5. Caridade, C.M.R., Marçal, A.R.S., Mendonça, T., 2008. The use of texture for image classification of
black & white air photographs. International Journal of Remote Sensing 29, 593–607.
6. Chen, J., Gong, P., He, C., Pu, R., Shi, P., 2003. Land-use/land-cover change detection using improved
change-vector analysis. Photogrammetric Engineering & Remote Sensing 69, 369–379.
7. Chen, X., Vierling, L., Deering, D., 2005. A simple and effective radiometric correction method to
improve landscape change detection across sensors and across time. Remote Sensing of Environment
98, 63–79.
8. Chen, Z., Elvidge, C.D., Groeneveld, D.P., 1999. Vegetation change detection using high spectral
resolution vegetation indices. In: Lunetta, R.S., Elvidge, C.D. (Eds.), Remote Sensing Change
Detection: Environmental Monitoring Methods and Applications. Taylor & Francis, London, pp. 181–
190.
9. Collins, J.B., Woodcock, C.E., 1996. An assessment of several linear change detection techniques for
mapping forest mortality using multitemporal landsat TM data. Remote Sensing of Environment 56,
66–77.
10. Conchedda, G., Durieux, L., Mayaux, P., 2008. An object-based method for mapping and change
analysis in mangrove ecosystems. ISPRS Journal of Photogrammetry and Remote Sensing 63, 578–
589.

55
11. Congalton, R.G., Green, K., 2009. Assessing the Accuracy of Remotely Sensed Data: Principles and
Practices. CRC/Taylor & Francis Group, LLC, Boca Raton, London, New York
12. Coppin, P., Jonckheere, I., Nackaerts, K., Muys, B., Lambin, E., 2004. Review article digital change
detection methods in ecosystem monitoring: a review. International Journal of Remote Sensing 25,
1565–1596.
13. Coppin, P.R., Bauer, M.E., 1996. Digital change detection in forest ecosystems with remote sensing
imagery. Remote Sensing Reviews 13, 207–234.
14. Crist, E.P., 1985. A TM tasseled cap equivalent transformation for reflectance factor data. Remote
Sensing of Environment 17, 301–306.
15. Dai, X.L., Khorram, S., 1999. Remotely sensed change detection based on artificial neural networks.
PhotogrammetricEngineering&RemoteSensing65, 1187–1194.
16. Deer, P., 1995. Digital Change Detection Techniques in Remote Sensing. Technical Report, DSTO-
TR-0169. Department of Defence, Australia, p. 52.
17. Deren, L., Haigang, S., Ping, X., 2003. Automatic change detection of geo-spatial data from imagery.
Geo-Spatial Information Science 6, 1–7.
18. Desclée, B., Bogaert, P., Defourny, P., 2006. Forest change detection by statistical object-based
method. Remote Sensing of Environment 102, 1–11
19. Du, Y., Teillet, P.M., Cihlar, J., 2002. Radiometric normalization of multitemporal high-resolution
satellite images with quality control for land cover change detection. Remote Sensing of Environment
82, 123–134.
20. Durieux, L., Lagabrielle, E., Nelson, A., 2008. A method for monitoring building construction in urban
sprawl areas using object-based analysis of Spot 5 images and existing GIS data. ISPRS Journal of
Photogrammetry and Remote Sensing 63, 399–408.
21. Fisher, P., Arnot, C., Wadsworth, R., Wellens, J., 2006. Detecting change in vague interpretations of
landscapes. Ecological Informatics 1, 163–178.
22. Gamanya, R., De Maeyer, P., De Dapper, M., 2009. Object-oriented change detection for the city of
Harare, Zimbabwe. Expert Systems with Applications 36, 571– 588.
23. Gao, J., 2009. Digital Analysis of Remotely Sensed Imagery. McGraw-Hill, New York.
24. Gopal, S., Woodcock, C., 1996. Remote sensing of forest change using artificial neural networks.
IEEE Transactions on Geoscience and Remote Sensing 34, 398–404.
25. Green, K., Kempka, D., Lackey, L., 1994. Using remote sensing to detect and monitor land-cover and
land-use change. Photogrammetric Engineering & Remote Sensing 60, 331–337.
26. Hall, O., Hay, G.J., 2003. A multiscale object-specific approach to digital change detection.
International Journal of Applied Earth Observation and Geoinformation 4, 311–327.
27. Han, J., Kamber, M., Pei, J., 2011. Data Mining: Concepts and Techniques. Morgan Kaufmann,
Amsterdam..
28. He, D.-C., Wang, L., 1991. Texture features based on texture spectrum. Pattern Recognition 24, 391–
399.
29. Ilsever, M., Ünsalan, C., 2012. Two-Dimensional Change Detection Methods Remote Sensing
Applications. Springer, New York.
30. Im, J., Jensen, J.R., 2005. A change detection model based on neighborhood correlation image analysis
and decision tree classification. Remote Sensing of Environment 99, 326–340
31. Im, J., Rhee, J., Jensen, J.R., Hodgson, M.E., 2007. An automated binary change detection model using
a calibration approach. Remote Sensing of Environment 106, 89–105.

56
32. Jensen, J.R., 1983. Urban/Suburban Land Use Analysis, Manual of Remote Sensing. American Society
of Photogrammetry, Falls Church, Virginia, pp. 1571–1666.
33. Jianyaa, G., Haiganga, S., Guoruia, M., Qimingb, Z., 2008. A Review of Multi-Temporal Remote
Sensing Data Change Detection Algorithms, ISPRS Congress, Beijing, China, pp. 757–762.
34. Johansen, K., Arroyo, L.A., Phinn, S., Witte, C., 2010. Comparison of geo-object based and pixel-
based change detection of riparian environments using high spatial resolution multi-spectral imagery.
Photogrammetric Engineering & Remote Sensing 76, 123–136.
35. Johnson, R.D., Kasischke, E.S., 1998. Change vector analysis: a technique for the multispectral
monitoring of land cover and condition. International Journal of Remote Sensing 19, 411–426.
36. Kennedy, R.E., Townsend, P.A., Gross, J.E., Cohen, W.B., Bolstad, P., Wang, Y.Q., Adams, P., 2009.
Remote sensing change detection tools for natural resource managers: understanding concepts and
tradeoffs in the design of landscape monitoring projects. Remote Sensing of Environment 113, 1382–
1396.
37. Larose, D.T., 2005. Discovering Knowledge in Data: An Introduction to Data Mining. John Wiley &
Sons, New Jersey.
38. Lefebvre, A., Corpetti, T., Hubert-Moy, L., 2008. Object-oriented approach and texture analysis for
change detection in very high resolution images. In: Geoscience and Remote Sensing Symposium,
2008. IGARSS 2008. IEEE International, pp. IV-663–IV-666.
39. Lillesand, T.M., Kiefer, R.W., Chipman, J.W., 2008. Remote Sensing and Image Interpretation, sixth
ed. John Wiley & Sons, Hoboken, NJ.
40. Lu, D., Mausel, P., Brondízio, E., Moran, E., 2004. Change detection techniques. International Journal
of Remote Sensing 25, 2365–240.
41. Lunetta, R.S., 1999. Applications, project formulation, and analytical approach. In: Lunetta, R.S.,
Elvidge, C.D. (Eds.), Remote Sensing Change Detection: Environmental Monitoring Methods and
Applications. Taylor & Francis, London, pp. 1–19.
42. Lunetta, R.S., Johnson, D.M., Lyon, J.G., Crotwell, J., 2004. Impacts of imagery temporal frequency
on land-cover change detection monitoring. Remote Sensing of Environment 89, 444–454.
43. Makkeasorn, A., Chang, N.-B., Li, J., 2009. Seasonal change detection of riparian zones with remote
sensing images and genetic programming in a semi-arid watershed. Journal of Environmental
Management 90, 1069–1080.
44. Malila, W.A., 1980. Change vector analysis: an approach for detecting forest changes with Landsat. In:
6th Annual Symposium on Machine Processing of Remotely Sensed Data, Purdue University, West
Lafayette, Indiana, pp. 326–335
45. Mas, J.F., 1999. Monitoring land-cover changes: a comparison of change detection techniques.
International Journal of Remote Sensing 20, 139–152
46. Miller, O., Pikaz, A., Averbuch, A., 2005. Objects based change detection in a pair of gray-level
images. Pattern Recognition 38, 1976–1992.
47. Niemeyer, I., Nussbaum, S., 2006. In: Avenhaus, R., Kyriakopoulos, N., Richard, M., Stein, G. (Eds.),
Change Detection: The Potential for Nuclear Safeguards Verifying Treaty Compliance. Springer Berlin
Heidelberg, pp.335–348.
48. Otukei, J.R., Blaschke, T., 2010. Land cover change assessment using decision trees, support vector
machines and maximum likelihood classification algorithms. International Journal of Applied Earth
Observation and Geoinformation 12 (Suppl. 1), S27–S31.

57
49. Petitjean, F., Gançarski, P., Masseglia, F., Forestier, G., 2010. Analysing satelliteimage time series by
means of pattern mining. In: Fyfe, C., Tino, P., Charles, D., Garcia-Osorio, C., Yin, H. (Eds.),
Intelligent Data Engineering and Automated Learning – IDEAL 2010. Springer-Verlag, Paisley, UK,
pp. 45–52.
50. Pu, R., Gong, P., Tian, Y., Miao, X., Carruthers, R.I., Anderson, G.L., 2008. Using classification and
NDVI differencing methods for monitoring sparse vegetation coverage: a case study of saltcedar in
Nevada, USA. International Journal of Remote Sensing 29, 3987–4011.
51. Rignot, E.J.M., van Zyl, J.J., 1993. Change detection techniques for ERS-1 SAR data. IEEE
Transactions on Geoscience and Remote Sensing 31, 896–906.
52. Rosin, P.L., Ioannidis, E., 2003. Evaluation of global image thresholding for change detection. Pattern
Recognition Letters 24, 2345–2356.
53. Sali, E., Wolfson, H., 1992. Texture classification in aerial photographs and satellite data. International
Journal of Remote Sensing 13, 3395–3408.
54. Singh, A ., 1989, Digital change detection techniques using remotely-sensed data. International Journal
of Remote Sensing, 6, 989± 1003.
55. Smith, A., 2010. Image segmentation scale parameter optimization and land cover classification using
the Random Forest algorithm. Journal of Spatial Science 55, 69–79.
56. Solans Vila, J.P., Barbosa, P., 2010. Post-fire vegetation regrowth detection in the Deiva Marina region
(Liguria–Italy) using Landsat TM and ETM+ data. Ecological Modelling 221, 75–84.
57. Song, C., Woodcock, C.E., 2003. Monitoring forest succession with multitemporal Landsat
images:factors of uncertainty. IEEE Transactions on Geoscience and Remote Sensing 41, 2557–2567.
58. Stow, D., 2010. Geographic object-based image change analysis. In: Fischer, M.M.,Getis, A. (Eds.),
Handbook of Applied Spatial Analysis. Springer, Berlin Heidelberg, pp. 565–582
59. Vapnik, V.N., 2000. The Nature of Statistical Learning Theory, second ed. Springer, New York.
60. Versluis, A., Rogan, J., 2009. Mapping land-cover change in a Haitian watershed using a combined
spectral mixture analysis and classification tree procedure. Geocarto International 25, 85–103.
61. Vieira, M.A., Formaggio, A.R., Rennó, C.D., Atzberger, C., Aguiar, D.A., Mello, M.P., 2012. Object
based image analysis and data mining applied to a remotely sensed Landsat time-series to map
sugarcane over large areas. Remote Sensing of Environment 123, 53–562.
62. Wulder, M.A., Ortlepp, S.M., White, J.C., Coops, N.C., Coggins, S.B., 2008. Monitoring tree-level
insect population dynamics with multi-scale and multi-source remote sensing. Journal of Spatial
Science 53, 49–61.
63. Yang, Q., Li, X., Shi, X., 2008. Cellular automata for simulating land use changes based on support
vector machines. Computers & Geosciences 34, 592–602.
64. Yu, C., Shen, S., Huang, J., Yi, Y., 2010. An object-based change detection approach using high-
resolution remote sensing image and GIS data. In: 2010 International Conference on Image Analysis
and Signal Processing (IASP), pp. 565–569.

CHANGE DETECTION TECHNIQUES - A SUR V EY

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Viewers also liked

Viewers also liked (20)

Similar to CHANGE DETECTION TECHNIQUES - A SUR V EY

Similar to CHANGE DETECTION TECHNIQUES - A SUR V EY (20)

Recently uploaded

Recently uploaded (20)

CHANGE DETECTION TECHNIQUES - A SUR V EY