ارزیابی آثار موجک پایه و تعداد سطوح تجزیه جهت تخمین نقشۀ تغییرات، با استفاده از الگوریتم موجک

نوع مقاله : علمی - پژوهشی

نویسندگان

1 کارشناس ارشد سنجش از دور و GIS، دانشگاه تربیت مدرس

2 دانشیار گروه مهندسی GIS، دانشگاه خواجه نصیرالدین طوسی

3 استاد دانشکدۀ مهندسی برق و کامپیوتر، دانشگاه تربیت مدرس

چکیده

روش‌های بارزسازی تغییرات ابزاری قدرتمند در نمایش تغییرات در سطح زمین به‌شمار می‌آیند. برای افزایش دقت نقشۀ تغییرات تهیه‌شده می‌شود از تکنیک‌های چند‌مقیاسی که هم‌زمان مشاهدات را در مقیاس‌های بزرگ و کوچک انجام می‌دهند، استفاده کرد. در این تکنیک‌ها، افزون‌بر اطلاعات طیفی، اطلاعات مکانی موجود در تصویر نیز در پردازش دخالت داده می‌شود. یکی از این تکنیک‌ها، تکنیک چندمقیاسی موجک است. تکنیک موجک در بسیاری از زمینه‌های پردازش تصویر کاربرد دارد. در تحقیق حاضر، توانایی تکینک موجک در بارزسازی تغییرات با استفاده از تصاویر ماهواره‌ای TM ارزیابی شده است. پارامترهای مورد نیاز برای تبدیل موجک تعداد سطوح تجزیه و موجک پایه‌اند. بنابراین، آثار موجک‌های پایۀ bior3/7 و db4 و سطوح تجزیۀ s=1 تا s=6 در نقشۀ تغییرات نهایی ارزیابی شده است. همۀ نتایج با استفاده از روش‌های بررسی دقت، شامل ضریب کاپا و دقت کلی، بیان شده‌اند. نتایج تأثیر نوع موجک پایۀ انتخاب‌شده و سطوح تجزیه را در نقشۀ تغییرات نهایی نشان می‌دهد. نقشۀ تغییرات محاسبه‌شده با استفاده از موجک پایۀ bior3/7 دقت کلی بالاتر و آمارۀ کاپای بهتری را درمقایسه با موجک پایۀ db4 نشان می‌دهد. به‌طوری‌که برای باند 3 با موجک پای، bior3/7 دقت کلی 51/90 و آمارۀ کاپا 79/0 و برای همین باند با موجک پایۀdb4 ، به‌ترتیب، برابر 80/89 و 79/0 است. پارامتر بعدی که در اینجا بررسی شده، تأثیر سطوح تجزیه در دقت نقشۀ بارزسازی تغییرات است. در هر دو، موجک پایه تا سطح تجزیۀ 3 روند صعودی دارد و سپس، سیر نزولی پیدا می‌کند. به‌طوری‌که بیشتر دقت کلی و آمارۀ کاپا مربوط به سطح تجزیۀ 3 در هر دو موجک پایه است. همچنین در این تحقیق بین تکنیک موجک و سه تکنیک تفاضل، نسبت و طبقه‌بندی نظارت‌شده مقایسه‌ای انجام شده است. بررسی نشان می‌دهد که تکنیک موجک نتایج بهتری دارد.

کلیدواژه‌ها

عنوان مقاله [English]

Impact Assessment Of Mother Wavelet And Number Of Wavelet Decomposition To Estimate Of Change Map By Wavelet Algorithm

نویسندگان [English]

  • R Hosseini 1
  • A Alimohammadi 2
  • M.H Ghasemian 3
1 M.Sc of Remote Sensing and GIS, Tarbiat Modares University, Tehran
2 Associate Prof. of GIS Engineering, K.N. Toosi University of Technology
3 Prof. of Electrical & Computer Engineering Faculty, Tarbiat Modares University
چکیده [English]

Change detection methods are powerful tools to present the changes on the Earth’ surface. The multi-scale approaches which proceed the observations at coarser and finer scales, can be applied to maximize the accuracy of the change maps. The multi-scale approach, based on discrete wavelet, has been applied in this research. In addition to the spectral information, the contextual or local information- available in the image are set in the processing. The wavelet technique is exploited in many processing fields of images. The ability of the wavelet technique has been applied for the change-detection, based on the satellite images in this study. The necessary parameters for the wavelet modification are the quantity decomposition levels and kind of mother wavelet. Thus The effect of the mother wavelet boir3/7 and db4 and the levels of  decomposition s=1 to s=6 on the final change detection map have been assessed . All the results have been stated on the basis of the detection accuracy kappa coefficient and overall accuracy. The results reveal the influences of the mother wavelet and levels of decomposition on the final change detection map. The Change detection map, using t bior3/7mother wavelet, reveals higher overall accuracy and better kappa coefficient in proportion to bd4 mother wavelet. It is 0/7966 and 89/8013 for band 3 of Mother wavelet bior3/7 and 9/8013 & 0/7966 for mother wavelet db4. The next parameter being investigated here is related to the analysis surfaces influence on the precision of the change detection map. It increases to the level 3 of analysis and then decrease down. Eventually, most of the overall precision and kappa coefficient is related to the analysis level 3 of both mother wavelet. A comparison has been also conducted between the wavelet technique and the three methods image differencing , image ratio and supervised classification. The final review reveals the priority of the wavelet technique, as it presents better results.

کلیدواژه‌ها [English]

  • Wavelet algorithm
  • Mother wavelet
  • Number of decomposition
  • kappa coefficient

مراجع

  1. جعفری، ح.، حمزه، م.، نصیری، ح.، رفیعی، ی.، 1390، توسعۀ مدل مفهومی مبتنی بر الگوریتم Decision Tree و داده‌کاوی به‌منظور آشکارسازی تغییرات پوشش اراضی با استفاده از تصاویر سنجندۀ TM و داده‌های کمکی (مطالعۀ موردی: بخش مرکزی شهرستان بویراحمد)، فصلنامۀ علوم محیطی، دورۀ هشتم، شمارۀ 3 (پیاپی 31)، صص. 19-1.
  2. Adithyan, M., Pandi, R.A., Ramesh, A., Venkatesen, J. & Tech, M., 2016, Dual Ratio Operator and Wavelet Fusion Based Supervised Change Detection in SAR Image, International Journal of Engineering Science and Computing,Vol. 6, No. 4, PP. 3260-3263.
  3. Alagu Raja, R.A., Anand, V., Senthil Lumar, A., Maithani, S. & Abhai Kumar, V., 2013, Wavelet Based Post Classification Change Detection Technique for Urban Growth Monitoring, Springer Journal of the Indian Society of Remote Sensing ,Vol. 41, No. 1, PP. 35–43
  4. Ajadi, A.O., Franz, J., Meyer, F.G., Peter, W. & Webley, P.W.,2016, Change Detection in Synthetic Aperture Radar Images Using a Multiscale-Driven Approach, Remote Sensing, Vol. 8, No. 6,PP. 1-27.
  5. Bouhlel, N., Ginolhac, G., Jolibois, E & Atto, A.,2015, Multivariate Statistical Modeling for Multi-Temporal SAR Change Detection Using Wavelet Transforms, Analysis of Multitemporal Remote Sensing Images (Multi-Temp), 8th International Workshop.
  6. Bruzzone, L. & Prieto, D.F., 2000, Automatic Analysis of the Difference Image for Unsupervised Change Detection, IEEE Trans. Geosci. RemoteSensing, Vol. 38, No. 3, pp. 1171–1182.
  7. Zare Baghbidi, M., Jamshidi, K., Naghsh Nilchi, A.R. & Homayouni, S., 2011, Improvement of Anomaly Detection Algorithms in Hyperspectral Image Using Discrete Wavelet Transform, Signal and Image Processing, Vol. 2, No. 4, PP. 13-25.
  8. Carvalho, O.A., Guimaraes, R.F., Gomes, R.A.T., deCarvalho, A.P.F. & daSilva, N.C., 2006, Normalization of Multi-Temporal Images Using a New Change Detection Method Based on the Spectral Classifier ,Geoscience and Remote Sensing Symposium, IGARSS, IEEE International Conference, PP.771 – 774.
  9. Carvalho, L.M.T., Acerbi, F.W., Scolforo, J.R., de Mello, J.M. & de Oliveira, A.D., 2007, Wavechange: A Procedure for Change Detection Based on Wavelet Product Spaces, Analysis of Multi-temporal Remote Sensing Images, PP. 1-5 .
  10. Celik, T., 2009, Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and K-Means Clustering, Geoscience and Remote Sensing Letters, IEEE ,Vol. 6, Issue 4, PP. 772 – 776.
  11. Dai, X. & Khorram, S.,1998, The Effects of Image Misregistration on the Accuracy of Remotely Sensed Change Detection, IEEE Trans. Geosci. Remote Sensing, Vol. 36, No. 5, PP. 1566–1577.
  12. Peijun Du, P., Sicong Liu, S., Xia, J. & Zhao, Y., 2013, Information Fusion Techniques for Change Detection from Multi-Temporal Remote Sensing Images, Information Fusion, Vol. 14, No. 1, PP. 19–27.
  13. Elvidge, Y. & Lunetta, R.S, 1999, Survey of Multi-Spectral Methods for Land-Cover Change Detection Analysis in Remote Sensing Change Detection, Enviromenal Monitoring Methods and Applications, edited by R.S. Lunetta and C.D. Elvidge, london, UK: Taylor & Francis, PP. 21-39.
  14. Epinat, V., Stein, A. , Jong, S. & Bournal, J., 2001, A Wavelet Characterization of High-Resolution NDVI Patterns for Precision Agriculture, International Journal of Applied Earth Observation and Geoinformation, Vol. 3, No. 2, PP. 121–132.
  15. Cohen, J.,1960, A Coefficient of Agreement for Nominal Scale, Educ. Psychol Measure, Vol. 20, PP. 37‐46.
  16. Galford, G.L., Mustard, .J.F, Melillo, J., Gendrin, A., Cerri, C. & Cerri, C.E.P.C., 2008, Wavelet Analysis of MODIS Time Series to Detect Expansion and Intensification of Row-Crop Agriculture in Brazil, Remote Sensing of Environment, Vol. 112 , PP. 576–587.
  17. He, Z., Wei, Zh., Feng, H. & Wang, L.,2013, The Application of Wavelet Transform and the Adaptive Threshold Segmentation in Image Change Detection, Advanced Materials Research, Vol. 709, PP. 547-550.
  18. Hussain, M., Chen, D.,Cheng, A. & Wei, H.,2013, Change Detection from Remotely Sensed Images: From Pixel-Based to Object-Based Approaches, Photogrammetry and Remote Sensing, Vol. 80, PP. 91-106.
  19. Jensen, J.R., 1996, Introductory Digital Image Processing: Remote Sensing Preperspective, second edition, NewJersey, USA: Prentice Hall, PP. 257-278.
  20. Jia, L., Wu, Y., An, L., Song, W., Li, M. & Zhang, P., 2016, Remote-Sensing Image Change Detection with Fusion of Multiple Wavelet Kernels, Applied Earth Observations and Remote Sensing, Vol. 99, PP. 1-14.
  21. Khare, M., Srivastava, R.K. & Khare, A., 2014, Single Change Detection-Based Moving Object Segmentation by Using Daubechies Complex Wavelet Transform, IET Image Processing, Vol. 8, No. 6, PP. 334 - 344.
  22. Kingsbury, N., 2000, A Dual-Tree Complex Wavelet Transform with Improved Orthogonality and Symmetry Properties, in Proc. IEEE Int. Conf. Image Process., PP. 375–378.
  23. Krejcie, R.V. & Morgan, D.W.,1970, Determining Sample Size for Research Activities, Educational and Psychological Measurement, Vol. 30, PP. 607-610.
  24. Li, ZH. & Liu, G.,2008, A Novel Scene Change Detection Algorithm Based on the 3d Wavelet Transform, IEEE, 15th International Conference, PP. 1536- 1539.
  25. Li,Y., Davis, C.H., 2008, Unsupervised Change Detection in High Resolution Satellite Imagery from Fusion of Spectral and Spatial Information, Geoscience and Remote Sensing Symposium, IEEE International, II-109 - II-112.
  26. 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, Vol. 12, No. 12, PP. 2458 – 2462.
  27. Lu, D., Mausel, P., Brondizio, E. & Moran, E., 2004, Change Detection Techniques, International Journal of Remote Sensing, Vol. 25, No. 12, PP. 2365-2407.
  28. Lowell, K.,2001, An Area-Base Accuracy Assessment Methodology for Digital Change Detection Maps, International Journal of remote Sensing, Vol. 22, Issue 17, PP. 3571-3596.
  29. Mallat, S.G,1998, A Theory for Multi-Resolution Signal Decomposition; The Wavelet Representation, IEEE Transations On Pattern Analysis and Machine Intelligence, Vol. 2, No. 7, PP. 674-693.
  30. Mercier, G. & Inglad, J.,2008, Change Detection with Misregistration Errors, Geoscience and Remote Sensing Symposium, IEEE International 3, PP. 154-157.
  31. Moosavi, V., Talebi, A., Mokhtari, M.H., Fallah Shamsi, S.R. & Yaghoub Niazi, Y.,2015, A Wavelet-Artificial Intelligence Fusion Approach (WAIFA) for Blending Landsat and MODIS Surface Temperature, Remote Sensing of Environment, Vol. 169, PP. 243–254.
  32. Moser, G., Melgani, F., Serpico, B.S. & Caruso, A.,2003, Partially Supervised Detection of Changes from Remote Sensing Images, IEEE Geoscience and Remote Sensing Symposium, PP. 299-301.
  33. Moser, G., 2011, Multiscale Unsupervised Change Detection on Optical Images by Markov Random Fields and Wavelets, IEEE Geoscience and Remote Sensing letters, Vol. 8, No. 4, PP. 725-729.
  34. Pooja, H.M. & Dhanushree, M.C., 2012, Change Detection in Synthetic Aperture Radar Image based Image Fusion And Fuzzy Clustering, International, Journal of Engineering Science and Computing, PP. 201-206.
  35. Campos, A.N. & Bella, C.M.D., 2012, Multi-Temporal Analysis of Remotely Sensed Information Using Wavelets, Earth & Environmental Sciences, Vol. 4, No. 4, PP. 383-391.
  36. Richards, J.A. & Jia, X, 2006, Remote Sensing Digital Image Analysis: An Introduction, Springer-Verlag, Berlin.
  37. Singh A.,1986, Tropical Forest Monitoring Using Digital Landsat Data in Northeastern India, Remote Sensing and Tropical Land Management, edited by M.J. Eden and J.T. Parry (London: John Wiley & Sons), PP.237-254.
  38. Si-Nong, Q., Ying, C., Bo-Li, X. & Gang-Yao, K,2016, Employing Multi-scale Fusion for SAR Image Change Detection, Signal Processing, Vol. 32, No. 4, PP. 430-437.
  39. Tarantino, C., Adamo, M., Lucas, R. & Blonda, P.,2016, Detection of Changes in Semi-Natural Grasslands by Cross Correlation Analysis with WorldView-2 Images and New Landsat 8 Data, Remote Sensing of Environment, Vol. 175, PP. 65-72.
  40. Tong, T & He, G.,2005, A Comparison of Wavelet and Fourier Analysis for Image Change Detection , Geoscience and Remote Sensing Symposium.
  41. Van Oort, P.A.J.,2007, Interpreting the Change Detection Error Matrix, Remote Sensing of Environment, Vol. 108, No. 1, PP. 1–8.
  42. Zhang, J., Wang, X., Chen, T. & Zhang, Y., 2005, Change Detection for the Urban Area Based on Multiple Sensor Information Fusion, Geoscience and Remote Sensing Symposium IEEE, Vol. 1, PP. 226-228.
  43. Zhao, K.,Valle, D., Popescu, S., Zhang, X. & Mallick, B.,2013, Hyperspectral Remote Sensing of Plant Biochemistry Using Bayesian Model Averaging with Variable and Band Selection, Geoscience and Remote Sensing Symposium IEEE, Vol. 132, PP. 102-119.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار