تفسیر شی‌مبنای تصاویر سنجش‌ازدوری با حد تفکیک بالا بر مبنای سیستم‌های دانش‌پایه

نوع مقاله : علمی - پژوهشی

نویسندگان

1 دانشجوی دکتری نقشه­ برداری گروه فتوگرامتری و سنجش از دور دانشکده مهندسی ژئودزی و ژئوماتیک

2 استاد گروه فتوگرامتری و سنجش از دور دانشکده مهندسی ژئودزی و ژئوماتیک، دانشگاه صنعتی خواجه نصیرالدین طوسی (عضو قطب علمی فناوری اطلاعات مکانی)

3 کارشناسی ارشد ژئودزی، دانشگاه آزاد اسلامی واحد شاهرود

چکیده

طبقه‌بندی پوشش اراضی در تصاویر سنجش‌ازدور، یکی از پرکاربردترین روش‌های استخراج اطلاعات مکانی است که می‌تواند با تولید کلاس‌های تصویری عوارض سطح زمین به‌منظور اتوماسیون و تسریع در جهت رفع نیازهای اساسی برای در اختیار داشتن اطلاعات مکانی بهنگام از منابع، با هدف مدیریت، ساماندهی و بهره‌برداری از محیط مفید واقع شود. به دلیل مشابهت رفتار پیکسل‌ها، طبقه‌بندی تصاویر هوایی در مناطق پیچیده و متراکم شهری، صرفاً با استفاده از اطلاعات طیفی و بافتی منجر به ناکارآمدی طبقه‌بندی می‌شود. به عبارتی در طبقه‌بندی رایج، عمدتا با استفاده از خصوصیات طیف و ویژگی‌های پیکسل‌های تصویر، به شناسایی عوارض و کلاس­ها پرداخته می‌شود. درصورتی‌که بتوان تطابق مکانی و مفهومی پیکسل­ها را نیز در نظر گرفت، به این ترتیب می­توان تمایز بیشتری بین کلاس­های تصویری قائل شد و فرآیند ماشینی را به تفسیر ذهنی و انسانی نزدیک کرده و بر کارایی سیستم افزود. تمرکز اصلی تحقیق حاضر، استفاده از مفاهیم سیستم­های خبره در طبقه­بندی، به‌منظور آنالیز شئ‏گرای تصاویر در سطوح مقیاس کلاسی است. به همین دلیل، با وارد نمودن قوانین دانش‌پایه به‌منظور کنترل هدفمند و قانونمندسازی روند توأمان قطعه­بندی و تفسیر تصویر، با در نظر گرفتن ویژگی­های هندسی کلاس­های هدف، بهبود دقت را منجر شود. برای بررسی کارایی تکنیک پیشنهادی، ارزیابی و مقایسه روش پیشنهادی با چند روش دیگر بر روی تصاویر ماهواره­ا‌ی IRS در منطقه شهری جزیره کیش صورت پذیرفته است. نتایج حاصل از این تحقیق، نشان می‌دهد ویژگی‌های هندسی و مفهومی می‌توانند به‌عنوان ­منبع اطلاعاتی مکمل، سبب بهبود نتایج طبقه­بندی در منطقه شهری با عوارض ناهمگون طیفی شوند. به‌طوریکه در بررسی مورد اشاره، صحت کلی و ضریب کاپا به ترتیب 8 درصد و 11/5 درصد افزایش پیدا کرده­اند.

کلیدواژه‌ها


عنوان مقاله [English]

Object based interpretation of high spatial remote sensing images based on knowledge-based systems

نویسندگان [English]

  • Abbas Kiani 1
  • Hamid Ebadi 2
  • Hekmat allah Khanlou 3
1 Geomatics Engineering Faculty, K.N.Toosi University of Technology
2 Professor in Geomatics Engineering Faculty, K.N.Toosi University of Technology
3 Department of Geomatics Engineering, Islamic Azad University, Shahrood, Iran
چکیده [English]

Land cover classification in remote sensing imagery is one of the most widely used spatial information extraction methods, which can facilitate generating object imagery classes of the ground surface in order to automate and accelerate meeting the basic needs of management, organization, and exploitation of the environment. Due to the similar behavior of pixels, remote-sensing image classification using merely the spectral and textural information would lead to inefficiency in the classification. In fact, in classification process, objects are commonly identified using spectral properties of image pixels. If the spatial and conceptual properties are also considered, it causes to a better distinction between image classes and closes the machine process to human interpretation and adds to the system's performance. The present research is mainly focused on the use of interactive segmentation and interpretation processes with respect to the geometry of the image classes. The accuracy of the results have improved by introducing the knowledge-based rules to control and regulate the interactive process, taking into account the geometric properties of target classes. To evaluate the efficiency of the proposed method, the results were evaluated and compared with some of the other methods on IRS satellite images in an urban area. The results showed that geometric and conceptual features as a complementary information source, improve classification results in the urban area with heterogeneous spectral effects. Overall, the proposed hybrid technique improved overall accuracy and Kappa coefficient by 8% and 11.5%, respectively.

کلیدواژه‌ها [English]

  • Classification
  • High spatial image
  • Knowledge based system
  • Object based interpretation
  1. Agarwal, P., 2005, Ontological considerations in GIScience, International journal of geographical information science, 19, 501-536
  2. Almendros-Jimenez, J.M., Domene, L. & Piedra-Fernandez, J.A., 2013, A framework for ocean satellite image classification based on ontologies, IEEE Journal of selected topics in applied earth observations and remote sensing, 6, 1048-1063
  3. Andres, S., Arvor, D. & Pierkot, C., 2012, Towards an ontological approach for classifying remote sensing images, in Signal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on (pp. 825-832): IEEE
  4. Arvor, D., Durieux, L., Andres, S. & Laporte, M.-A., 2013, Advances in geographic object-based image analysis with ontologies: A review of main contributions and limitations from a remote sensing perspective, ISPRS Journal of Photogrammetry and Remote Sensing, 82, 125-137
  5. Azizia, Z., Najafi, A. & Sohrabia, H., 2008, Forest Canopy Density Estimating Using Satellite Images, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 37, 1127-1130
  6. Belgiu, M. & Drǎguţ, L., 2014, Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high resolution imagery, ISPRS Journal of Photogrammetry and Remote Sensing, 96, 67-75
  7. Belgiu, M., Tomljenovic, I., Lampoltshammer, T.J., Blaschke, T. & Höfle, B., 2014, Ontology-based classification of building types detected from airborne laser scanning data, Remote Sensing, 6, 1347-1366
  8. Bhagat, V., 2014, Use of IRS P6 LISS-IV data for land suitability analysis for cashew plantation in hilly zone, Asian Journal of Geoinformatics, 14, 23-35
  9. Carletta, J., 1996, Assessing agreement on classification tasks: the kappa statistic, Computational linguistics, 22, 249-254
  10. Cohn, A.G. & Renz, J., 2008, Qualitative spatial representation and reasoning, Foundations of Artificial Intelligence, 3, 551-596
  11. Comaniciu, D. & Meer, P., 2002, Mean shift: A robust approach toward feature space analysis, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 24, 603-619
  12. Costa, H., Foody, G.M. & Boyd, D.S., 2017, Using mixed objects in the training of object-based image classifications, Remote Sensing of Environment, 190, 188-197
  13. Cui, P., Liu, S., & Zhu, W., 2018, General Knowledge Embedded Image Representation Learning, IEEE Transactions on Multimedia, 20, 198-207
  14. de Leeuw, J., Jia, H., Yang, L., Liu, X., Schmidt, K., & Skidmore, A., 2006, Comparing accuracy assessments to infer superiority of image classification methods, International Journal of Remote Sensing, 27, 223-232
  15. Dey, V., Zhang, Y. & Zhong, M., 2010, A review on image segmentation techniques with remote sensing perspective. na
  16. Di Sciascio, E., Donini, F.M. & Mongiello, M., 2002, Structured Knowledge Representation for Image Retrieval, J. Artif. Intell. Res.(JAIR), 16, 209-257
  17. Eric Maillot, N. & Thonnat, M., 2008, Ontology based complex object recognition, Image and Vision Computing, 26, 102-113
  18. Fonseca, F.T., Egenhofer, M.J., Agouris, P. & Câmara, G., 2002, Using ontologies for integrated geographic information systems, Transactions in GIS, 6, 231-257
  19. Foody, G.M., 2004, Thematic map comparison, Photogrammetric Engineering & Remote Sensing, 70, 627-633
  20. Forestier, G., Puissant, A., Wemmert, C. & Gançarski, P., 2012, Knowledge-based region labeling for remote sensing image interpretation, Computers, Environment and Urban Systems, 470-480
  21. Gruber, T.R., 1995, Toward principles for the design of ontologies used for knowledge sharing?, International journal of human-computer studies, 43, 907-928
  22. Guindon, B., 1997, Computer-based aerial image understanding: A review and assessment of its application to planimetric information extraction from very high resolution satellite images, Canadian journal of remote sensing, 23, 38-47
  23. Hay, G., Niemann, K. & McLean, G., 1996, An object-specific image-texture analysis of H-resolution forest imagery, Remote Sensing of Environment, 55, 108-122
  24. Hay, G.J., Castilla, G., Wulder, M.A. & Ruiz, J.R., 2005, An automated object-based approach for the multiscale image segmentation of forest scenes, International Journal of Applied Earth Observation and Geoinformation, 7, 339-359
  25. Herold, M., Liu, X. & Clarke, K.C., 2003, Spatial metrics and image texture for mapping urban land use, Photogrammetric Engineering & Remote Sensing, 69, 991-1001
  26. Jelokhani-Niaraki, M., Sadeghi-Niaraki, A. & Choi, S.-M., 2018, Semantic interoperability of GIS and MCDA tools for environmental assessment and decision making, Environmental Modelling & Software, 100, 104-122
  27. Khelifa, D. & Mimoun, M., 2012, Object-based image analysis and data mining for building ontology of informal urban settlements, In, Image and Signal Processing for Remote Sensing XVIII (p. 85371I): International Society for Optics and Photonics
  28. Kiani, A. & Sahebi, M.R., 2015, Edge detection based on the Shannon Entropy by piecewise thresholding on remote sensing images, IET Computer Vision, 9, 758-768
  29. Kim, M., Madden, M. & Warner, T., 2008, Estimation of optimal image object size for the segmentation of forest stands with multispectral IKONOS imagery. Object-based image analysis (pp. 291-307): Springer
  30. Luo, H., Li, L., Zhu, H., Kuai, X., Zhang, Z. & Liu, Y., 2016, Land cover extraction from high resolution zy-3 satellite imagery using ontology-based method, ISPRS International Journal of Geo-Information, 5, 31
  31. Lv, Z., Liu, T., Wan, Y., Benediktsson, J.A. & Zhang, X., 2018, Post-Processing Approach for Refining Raw Land Cover Change Detection of Very High-Resolution Remote Sensing Images, Remote Sensing, 10, 472
  32. Ma, L., Fu, T., Blaschke, T., Li, M., Tiede, D., Zhou, Z., Ma, X. & Chen, D., 2017, Evaluation of feature selection methods for object-based land cover mapping of unmanned aerial vehicle imagery using random forest and support vector machine classifiers, ISPRS International Journal of Geo-Information, 6, 51
  33. Maillot, N.E. & Thonnat, M., 2008, Ontology based complex object recognition, Image and Vision Computing, 26, 102-113
  34. Matsuyama, T., 1987, Knowledge-based aerial image understanding systems and expert systems for image processing, IEEE Transactions on Geoscience and Remote Sensing,, 25, 305-316
  35. Matsuyama, T. & Hwang, V., 1990, SIGMA: A knowledge-based aerial image understanding system, Perseus Publishing
  36. McKeown, D.M., et al., 1994, Research in the Automated Analysis of Remotely Sensed Imagery, DARPA Image Understanding Workshop, 99-132
  37. Meinel, G. & Neubert, M., 2004, A comparison of segmentation programs for high resolution remote sensing data, International Archives of Photogrammetry and Remote Sensing, 35, 1097-1105
  38. Powers, R.P., Hay, G.J. & Chen, G., 2012, How wetland type and area differ through scale: A GEOBIA case study in Alberta's Boreal Plains, Remote Sensing of Environment, 117, 135-145
  39. Rao, A.R. & Lohse, G.L., 1996, Towards a texture naming system: identifying relevant