This paper presents a change detection approach for sarimags based on contourlet image fusion and fuzzy clustering .In this novel method difference image is generated from log ratio and mean ratio images by image fusion technique. For an optimal difference image, it should restrain the unchanged area information and enhance the changed areas information. The quality of difference image depends on image fusion technique. In the present work, we have proposed a new edge preserving image fusion method based on contourlet transform. Contourlet transform represent salient features of images such as edges, curves and contours in better way. To process the difference image is to discriminate changed regions from unchanged regions using fuzzy clustering algorithms. We have verified the goodness of the proposed fusion algorithm by well-known image fusion measures, entropy and also calculate the percentage correct classification. On the basis of experimental results it was found that performance of proposed fusion method is better than wavelet transform.
Keywords |
Contourlet, image fusion, fuzzy clustering, synthetic aperture radar images, change detection. |
INTRODUCTION |
Change detection is a technique that identifying changes by analysing images obtained from the same geographical
area at different times [1]. The changes detecting in the regions of same area at different periods is of great interest.
This pro-cess have many applications in different fields .The main applications include medical diagnosis [2]-[3],
remote sensing [4]-[5] [6], video surveillance [7]-[8]. One of the major data sources for remote sensing applications is
synthetic aperture radar images [9]. The importance of SAR images in variety applications is because SAR sensors is
adaptable to all weather conditions. The main disadvantage is presence of multiplicative speckle noise. Change
detection may be done by supervised or in unsupervised manner. In supervised technique, a set of training patterns are
required.it is little difficult. But in the case of unsupervised manner, there is no need of training data.so unsupervised
technique is better than unsupervised techniques. [4]. |
In this literature, three main steps are adopted to perform unsupervised change detection,1) Pre-processing of image,
2) Comparison of image and 3)Image analysis for change detection. The main purpose of step 1 include reduction of
noise, geometric and radiometric corrections and coregistration. In the second step that is after preprocessing, two sar
images are taken as input and compared pixel by pixel to produce difference image. For producing difference image,
ratio operator and subtraction operator are most popular techniques. In the case of rationing technique, two
preprocessed images are taken as input and applying pixel by pixel ratio operator to it, thereby changes are obtained. In
the case of differencing technique, pixel by pixel subtraction is done between the 2 pre-processed images. Generally in
sar images instead of differencing operator, ratio operator is typically used. Because differencing operator is affected by
calibration errors [10]. |
After performing above steps change detection is done on the difference image. For this, purpose context sensitive or
context insensitive methods [11] are adopted. They are of many kinds. Among them, histogramthresholding is one
method. In that method the threshold value may be detected by automatic techniques or manual trial and error
methods .There are many thresholding techniques to determine the threshold like expectation maximization
algorithm[12],otsu, Kittler and Illingworth minimum error thresholding algorithm (K&I). An optimal synthetic aperture radar image change detection is achieved by the accuracy of the classification method and quality of the
difference image. In order to achieve these two qualities, we propose this change detection method. The main two steps
are: 1) By fusing a mean-ratio image and a log-ratio image, difference image is produced and 2) to identify the change
are-as in the difference image, by using fuzzy clustering technique. This paper is composed of four sections. Section 2
involves proposed approach and our motivation will be enhanced. Section 3 defines the proposed method. In section 4
includes experimental results and conclusion. |
MOTIVATION |
Consider two mulititemporalsar images x1 and x2 as input that is taken from same geographical area at different
times. The main aim is to produce difference image that consists of change information, then image analysis for change
detection. According to the fig. 1, the proposed change detection method involves mainly two steps 1) generate the
difference image using contourlet fusion and 2) to identify the changed areas in fused image by fuzzy clustering. |
Because of the multiplicative nature of noise, the ratio images are represented in a logarithmic [13] or a mean scale
[14]. These two methods have good results for the change detection in SAR images. But it have some disadvantages. In
the case of log ratio image, it is not able to reflect the information of changed regions completely. For the rmd
technique, the unchanged regions of mean-ratio image are quite rough, and clarity of the image is less. For producing
optimal difference image, it should restrain the unchanged areas information and should improve the information of
changed regions. To solve this problem, an image fusion technique is introduced to generate the difference image.
According to the literature[15],we can conclude that generating the difference image by fusing log ratio image and
mean ratio image contain better information than individual difference image. Among the fusion methods pixel level
image fusion is widely used [16]. Discrete wavelet transform is mostly used for pixel level image fusion.it is a
multiscale transform technique. But it have lack of shift invariance property and directional selectivity. One of the
important property that require for change detection is shift invariance property. The image fusion based on dwt does
not preserve the fine edges and curves. And also clarity of the image is less.so we introduce image fusion by contourlet
fusion. The detailed description of this method will be presented in section 3. The main purpose to analyse the
difference image is to determine the changed regions and unchanged regions. Expectation maximization and K&I
algorithms are mainly used to identify the changed regions. These algorithms are carried out by applying a thresholding
procedure to the histogram of the image. In addition to that, these methods requires accurate estimation of threshold
values. If the estimation is not correct, we cannot correctly detect the changed and unchanged regions. So in this
literature, fuzzy c means clustering algorithm is proposed to analyse the difference image.it is an unsupervised
technique. |
PROPOSED METHODOLOGY |
In this section we describe the proposed change detection method, which consists of two steps; 1) Generate the
difference image using contourlet fusion, and 2) Detecting changed regions using fuzzy c means clustering. |
I. Generate the difference image based on contourlet fusion |
Image fusion is a process of fusing two or more images into a single fused image, thereby relevant information in
images are combined. So this single fused image will be more informative than any of the input imges [17]. The
majority of fusion techniques are based on wavelet transformation. But, the DWT image fusion is resulting with shift
variant and additive noise in fused image.it does not pre-serve edges of the image.so information loss is more. Thereby
clarity of the fused image is reduced. These issues can be re-solved using contourlet transform. The main properties of
contourlet Transform [17] is, multiresolution, localization, directionality anisotropy and local brightness, etc. it also
provide smoothness in a fused difference image .This tech-nique is realized by double iterated filter bank.it uses
laplacian pyramid and directional filter bank. There are mainly two steps for implementation of this transform. That is
trans-formation and decomposition. |
The two source images used for fusion are obtained from the mean-ratio operator and the log-ratio operator,
respectively, which are given by [18]. |
![equation](https://www.rroij.com/articles-images/IJAREEIE-322-e001.gif) |
Where X1 and X2 are multitemporal SAR images & m1 and m2 represent local mean values of multitemporal SAR
images.
Fig 2 shown above represent the block diagram of the contourlet based image fusion. Here image X1 and X2 denotes
the input source images respectively. F is the final fused image. The image fusion scheme based on contourlet
transform can be described as follows. Mainly there are two stages, transformation stage and decomposition stage [17]. |
A. Transformation method |
In the transformation stage, for the decomposition of sub-bands double filter bank is used it is composed of laplacian
pyramid and directional filter bank.so it is also called pyramidal directional filter bank. For capturing the edge point,
Laplacian pyramid filter is used. Directional Filter Bank is used to link the point discontinuities in the image [19]. |
In this method each input image undergone subband decomposition. That is in low frequency and bandpass highfrequency subbands [19]. In the case of low frequency subband, the same process is repeated upto specified contourlet
decomposition level. Above block diagram fig. 3 shows the laplacian pyramid decomposition. Here the input
image is fed to a low pass analysis filter (H) and then down sampled to lowpassSubband. Then this image is up
sampled and applied to a synthesis filter (G). Finally subtracting the output of the synthesis filter and input image we
get highpasssubbands [17]. The laplacian pyramid also allows high frequency bandpass image s into further
decomposition. That is this bandpass images are passed through the directional filterbank. It captures directional
information accurately. So in this transformation stage, it decomposes the image into directional subbands at multiscale. |
B. Decomposition Method |
In this stage, decomposed subbands of transformation stage are fused by fusion rules. There are separate fusion rules
for lowpass and highpass band. The coefficients in the lowpasssubband a represents the profile features of the source
image. For this measurement local area energy contourlet domain is used. Then the selection and averaging modes are
used to compute the final coefficients [19]. |
The local energy E(x,y) is calculated by [17] |
![equation](https://www.rroij.com/articles-images/IJAREEIE-322-e002.gif) |
ANALYSIS OF FUSED IMAGE USING FUZZY CLUSTERING |
Clustering means partioning a data set into a reasonable number of disjoint groups where each group containing
similar samples [20].In this partitions, patterns are similar within the clusters and different between the clusters. In
fuzzy clustering the samples are assigned not only to one cluster in fuzzy clustering the samples are assigned not only
to one cluster, but belongs to different clusters. That is samples with certain degree of belonging to all clusters. Among
the fuzzy clustering methods, the FCM algorithm [21] is one of the most popular methods since it can retain more
information from the original image and has robust characterise-tics for ambiguities.Here clustering is done to
discriminate changed regions from unchanged regions. For improving the performance of image clustering, we use
improved version of fuzzy clustering technique. That is fuzzy local information c means clustering algorithm. Here we
introduce, a novel fuzzy factor into the object function of FLICM.The peculiarity of fuzzy local information c means
algorithm is the main use of local similarity measure, which is aimed at ensuring the image detail preservation and
noise insensitiveness. This fuzzy factor is [18], |
![equation](https://www.rroij.com/articles-images/IJAREEIE-322-e003.gif) |
FLICM algorithum [18] [22] is described as follows: |
Step1) Initialize the number of the cluster prototypes, fuzzi-fication parameter m and the stopping condition ɛ. |
Step 2) Initialize randomly the fuzzy partition matrix. |
Step 3) Then set the loop counter b=0. |
Step 4) Compute the cluster prototypes. |
Step 5) Also Calculate the fuzzy partition matrix. |
Step 6) max {U (b) - U (b+ 1)} < ɛ then stop; otherwise, set |
b=b+1, and go to step 4. |
EXPERIMENTAL STUDY |
By presenting numerical results on five data sets we will show the performance of the proposed method. That is by
this quantative analysis we will prove the effectiveness of proposed change detection method. Here only images of
two dataset is shown. In this analysis ,the first data set contain a ection of two SAR images of Dubai obtained in the
years of 2000 and 2010 respectively shown in Fig. 4(a) and 4(b). The available ground truth (reference image) is shown
in Fig. 4(d). The Fig. 4(c) shows the proposed contourlet fused image. The second data set is a section of two SAR
images over the area of Istanbul. That is multitemporal images relating to Istanbul used in the experiments. In fig 5(a)
Image acquired in 1975 and 5 (b) Image acquired in 2011. In fig 5(c) fused image is shown. The available ground truth
is shown in Fig. 5(d). The experiments have been carried out for obtaining better fused image. That is here analyzing
the effectiveness of the contourlet fusion strategy to generate the difference image. And, we compared the change
detection performance of our algorithm with other two methods, including the DWT and the mean ratio operation. We
presented a comparative analysis for the suitability of the proposed approach for the fused difference image. .For
quantative analysis of change detection, we calculate the Percentage Correct Classification [23] which is given by [18]. |
PCC= (TP+ TN)/ (TP+ FP+ TN+ FN) |
Here, TP is the number of pixels that are detected as the changed area .TN is the number of pixels that are detected as
the unchanged area. The false negatives (FN) are the changed pixels that an undetected.False positive (FP) is the
unchanged pixels wrongly classified as changed. In this experiment, we analyzed the effectiveness of contourlet im-age
fusion technique to generate the difference image. As shown in Table I, the change detection results of the fused
difference image were compared with the ones generate from mean-ratio operator anddwt by Istanbul and Dubai. And
the proposed fusion method resulted in highest PCC value than other methods. The quality of the difference image
depend on the image fusion technique. So we have also verified the goodness of proposed image fusion algorithm by
well-known image fusion measure. That is entropy it helps better in assessing the information of images. Entropy can
effectively reflect the amount of information in certain image. The larger value indicates, the better fusion result is
obtained. |
![equation](https://www.rroij.com/articles-images/IJAREEIE-322-e004.gif) |
CONCLUSION |
In this project, we have presented a change detection on sar images based on contourlet fusion. In order to restrain
the unchanged areas and enhance the changed areas, fusion approach is used for producing the difference image.
Among the fusion methods, the limitations of wavelet transforms is capturing the geometry of image edges. In the
present work, we have proposed a new edge preserving image fusion method based on contourlet transform for
producing difference image. That is we pursue contourlet transform that can capture the intrinsic geometrical structure
that is key in visual information. .We will show that, this method can provide fused image with better visual quality.
In addition to that difference image produced in this method is better represented than that of dwt fused difference
image. The obtained fusion image can preserve much information of edges and textures of SAR images. The
experiment results also show that the proposed contourlet fusion strategy can integrate the advantages of the log ratio
operator and the mean-ratio operator and gain a better performance. The performance analysis also show that the pcc
value of this method is better than that of previous method. In this project, the changes in images are found by Fuzzy
clustering algorithms. In future, we can increase the efficiency of fuzzy clustering by combining with another
algorithms. |
Tables at a glance |
|
Figures at a glance |
![Click Here Figure](https://www.rroij.com/articles-images/IJAREEIE-322-g001.gif) |
![Click Here Figure](https://www.rroij.com/articles-images/IJAREEIE-322-g002.gif) |
![Click Here Figure](https://www.rroij.com/articles-images/IJAREEIE-322-g003.gif) |
![Click Here Figure](https://www.rroij.com/articles-images/IJAREEIE-322-g004.gif) |
![Click Here Figure](https://www.rroij.com/articles-images/IJAREEIE-322-g005.gif) |
Figure 1 |
Figure 2 |
Figure 3 |
Figure 4 |
Figure 5 |
|
References |
- R. J. Radke, S. Andra, O. Al-Kofahi, and B. Roysam, “Image change detection algorithms: A systematic survey,” IEEE Trans. Image Process., vol. 14, no. 3, pp. 294–307, Mar. 2005.
- M. Bosc, F. Heitz, J. P. Armspach, I. Namer, D. Gounot, and L. Rumbach, “Au-tomatic change detection in multimodal serial MRI: Application to multiple sclero-sis lesion evolution,” Neuroimage, vol. 20, no. 2, pp. 643–656, Oct. 2003.
- D. Rey, G. Subsol, H. Delingette, and N. Ayache, “Automatic detection and seg-mentation of evolving processes in 3-D medical images: Application to multiple sclerosis,” Med. Image Anal., vol. 6, no. 2, pp. 163–179, Jun. 2002.
- Y. Bazi, L. Bruzzone, and F. Melgani, “An unsupervised approach based on the generalizedGaussianmodel to automatic change detection in multitemporal SAR images,” IEEE Trans. Geosci. Remote Sens., vol. 43, no. 4, pp. 874–887, Apr. 2005.
- F. Bovolo and L. Bruzzone, “A detail-preserving scale-driven approach to change detection in multitemporal SAR images,” IEEE Trans. Geosci. Remote Sens., vol. 43, no. 12, pp. 2963–2972, Dec. 2005.
- A. A. Nielsen, “The regularized iteratively reweighted MAD method for change detection in multi- and hyperspectral data,” IEEE Trans. Image Process., vol. 16, no. 2, pp. 463–478, Feb. 2007.
- D. M. Tsai and S. C. Lai, “Independent component analysis-based background subtraction for indoor surveillance,” IEEE Trans. Image Process., vol. 18, no. 1, pp. 158–167, Jan. 2009.
- S. S. Ho and H. Wechsler, “A martingale framework for detecting changes in data streams by testing exchangeability,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 12, pp. 2113–2127, Dec.2010.
- F. Chatelain, J.-Y. Tourneret, and J. Inglada, “Change detection in multisensor SAR images using bivariate Gamma distributions,” IEEE Trans. Image Process. vol. 17, no. 3, pp. 249–258, Mar. 2008.
- A. Singh, “Digital change detection techniques using remotely sensed data,” Int. J. Remote Sens., vol. 10, no. 6, pp. 989–1003, 1989.
- S. Marchesi, F. Bovolo, and L. Bruzzone, “A context-sensitive technique robust to registration noise for change detection in VHR multispectral images,” IEEE Trans. Image Process., vol. 19, no. 7, pp. 1877–1889, Jul. 2010. [12] M. Sezgin and B. Sankur, “A survey over image thresholding techniques and quantitative performance evaluation,” J. Electron. Imag, vol. 13, no. 1, pp. 146–165, Jan. 2004.
- M. Sezgin and B. Sankur, “A survey over image thresholding techniques and quantitative performance evaluation,” J. Electron. Imag, vol.
13, no. 1, pp. 146–165, Jan. 2004.
- F. Bujor, E. Trouvé, L. Valet, J. M. Nicolas, and J. P. Rudant, “Application of log-cumulants to the detection of spatiotemporal
discontinuities in multitemporal SAR images,” IEEE Trans. Geosci. Remote Sens., vol. 42, no. 10, pp. 2073–2084, Oct. 2004.
- J. Inglada and G. Mercier, “A new statistical similarity measure for change detec-tion in multitemporal SAR images and its extension to
multiscale change analy-sis,” IEEE Trans. Geosci. Remote Sens., vol. 45, no. 5, pp. 1432–1445, May 2007.
- E. J. M. Rignot and J. J. Van Zyl, “Change detection techniques for ERS-1 SAR data,” IEEE Trans. Geosci. Remote Sens., vol. 31, no. 4,
pp. 896–906, Jul. 1993.
- S. S. Ho and H. Wechsler, “A martingale framework for detecting changes in data streams by testing exchangeability,” IEEE Trans.
Pattern Anal. Mach. Intell., vol. 32, no. 12, pp. 2113–2127, Dec. 2010.
- S Rajkumar, S Kavitha, “Redundancy Discrete Wavelet Transform and Contour-let Transform for Multimodality Medical Image Fusion
with Quantitative Analy-sis”, Third International Conference on Emerging Trends in Engineering and Tech-nology, pp. 134-139.
- Maoguo Gong, Zhiqiang Zhou, “Change Detection in Synthetic Aperture Radar Images based on Image Fusion and Fuzzy Clustering,”
IEEE Trans. Image Pro-cess, vol. 21, no. 4, pp. 2141–2151, Apr. 2012.
- L.Yang, B.L.Guo, W.Ni, “Multimodality Medical Image Fusion Based on Mul-tiscale Geometric Analysis of Contourlet Transform”,
Elsevier Science Publishers, vol. 72, pp. 203-211, December 2008.
- M. Ahmed, S. Yamany, N. Mohamed, A. Farag, and T. Moriarty, “A modified fuzzy C-means algorithm for bias field estimation and
segmentation of MRI da-ta,” IEEE Trans. Med. Imag., vol. 21, no. 3, pp. 193–199, Mar. 2002.
- J. C. Bezdek, Pattern Recognition with Fuzzy Objective Function. New York: Ple-num, 1981.
- W. Cai, S. Chen, and D. Zhang, “Fast and robust fuzzy C-means clustering algo-rithms incorporating local information for image
segmentation,” Pattern Recognit., vol. 40, no. 3, pp. 825–838, Mar. 2007.
- P. L. Rosin and E. Ioannidis, “Evaluation of global image thresholding for change detection,” Pattern Recognit. Lett., vol. 24, no. 14, pp.2345
|