A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data
Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior information about changed and unchanged pixels. The...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2014-09-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-7/15/2014/isprsarchives-XL-7-15-2014.pdf |
| _version_ | 1818570822912049152 |
|---|---|
| author | U. H. Atasever P. Civicioglu E. Besdok C. Ozkan |
| author_facet | U. H. Atasever P. Civicioglu E. Besdok C. Ozkan |
| author_sort | U. H. Atasever |
| collection | DOAJ |
| description | Change detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change
detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior
information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion
and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and
absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these
difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener
filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two
groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA,
FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are
used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness
of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change
detection of optical remote sensing data. |
| first_indexed | 2024-12-14T13:46:56Z |
| format | Article |
| id | doaj.art-141a73ad34064a60bbbfd3c478e22242 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-14T13:46:56Z |
| publishDate | 2014-09-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-141a73ad34064a60bbbfd3c478e222422022-12-21T22:59:17ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342014-09-01XL-7151810.5194/isprsarchives-XL-7-15-2014A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing DataU. H. Atasever0P. Civicioglu1E. Besdok2C. Ozkan3Department of Geomatic Engineering, Erciyes University, Kayseri, TurkeyCollege of Aviation, Dept. of Aircraft Electrics and Electronics, Erciyes University, Kayseri, TurkeyDepartment of Geomatic Engineering, Erciyes University, Kayseri, TurkeyDepartment of Geomatic Engineering, Erciyes University, Kayseri, TurkeyChange detection is one of the most important subjects of remote sensing discipline. In this paper, a new unsupervised change detection approach is proposed for multi-temporal remotely sensed optic imagery. This approach does not require any prior information about changed and unchanged pixels. The approach is based on Discrete Wavelet Transform (DWT) based image fusion and Backtracking Search Optimization Algorithm (BSA). In the first step of the approach, absolute-valued difference image and absolute-valued log-ratio image is calculated from co-registered and radiometrically corrected multi-temporal images. Then, these difference images are fused using DWT. The fused image is filtered by median filter for edge information preservation and by wiener filter for image smoothing. Then, a min-max normalization is applied to the filtered data. The normalized data is clustered into two groups with BSA as changed and unchanged pixels by minimizing an objective function, unlike classical methods using CVA, PCA, FCM or K-means techniques. To show effectiveness of proposed approach, two remote sensing data sets, Sardinia and Mexico, are used. False Alarm, Missed Alarm, Total Alarm and Total Error Rate are selected as performance criteria to evaluate the effectiveness of new approach using ground truth images. Experimental results show that proposed approach is effective for unsupervised change detection of optical remote sensing data.http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-7/15/2014/isprsarchives-XL-7-15-2014.pdf |
| spellingShingle | U. H. Atasever P. Civicioglu E. Besdok C. Ozkan A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data |
| title_full | A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data |
| title_fullStr | A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data |
| title_full_unstemmed | A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data |
| title_short | A New Unsupervised Change Detection Approach Based On DWT Image Fusion And Backtracking Search Optimization Algorithm For Optical Remote Sensing Data |
| title_sort | new unsupervised change detection approach based on dwt image fusion and backtracking search optimization algorithm for optical remote sensing data |
| url | http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-7/15/2014/isprsarchives-XL-7-15-2014.pdf |
| work_keys_str_mv | AT uhatasever anewunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT pcivicioglu anewunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT ebesdok anewunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT cozkan anewunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT uhatasever newunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT pcivicioglu newunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT ebesdok newunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata AT cozkan newunsupervisedchangedetectionapproachbasedondwtimagefusionandbacktrackingsearchoptimizationalgorithmforopticalremotesensingdata |