Taner ÜSTÜNTAŞ, Oğuz MÜFTÜOĞLU, Zekai ŞEN

Dijital fotogrametride yapısal görüntü eşleştirme

Görüntü eşleştirme algoritmaları bugüne kadar istatiksel yaklaşımla problemi çözmeye çalışmıştır. Burada yeni bir yaklaşım denenmiş ve uzman sistem tanımlaması yapılmıştır. Bu çalışmada bulanık mantık tabanlı görüntü eşleştirme algoritması önerilmiştir. Yapılan çalışma bulanık mantığın fotogrametrik amaçlı bir uygulamasıdır. Resim ve üzerindeki modeli tanımlayan kontrol noktalarını eşleştirmek için bulanık bir algoritmayla birlikte yazılım geliştirilmiştir. Bulanık mantık algoritması bulunacak hedefin topolojik ve geometrik özelliklerinin uygunluğunu belirlemektedir. Hedefin yaklaşık koordinatları civarında yazılım, tanımlanan hedefi aramakta ve en doğru işaretleme yapılacak yerin kararını vermektedir. Bu metot için resim yaklaşık yöneltme elemanları bilinmesi ve değerlendirilen görüntülerin örtüşmeli olması gerekir. Doğruluk, bilinmeyenlerin doğruluğuna bağlıdır.

Structural image matching in digital photogrammetry

The human vision system can be adapted easily to the insufficient data of the vision information. We can not describe that the size color and shape of an object correctly digital every time. We use fuzziness tools for describing the ambiguity. Fuzzy Logic Image processing has been used for describing this fuzziness of the results of the human brain. The location of the corner and location of the edge of the object have been recognized in gray values of pixels also classified of gray values of pixels. Answers of these questions have been considered, as fuzzy logic algorithm of image processing must have been used for in image processing algorithms. Image matching algorithms have been used for problem solving by statistical approaches. Herein, a new approach has been suggested and expert systems have been defined. In this study, image matching which is based on fuzzy logic algorithms is recommended. This is phologrammetric application based on fuzzy logic methodology. In order to solve the matching problem between an image patch and the model, a control point description is developed and a software is prepared based on fuzzy logic algorithm. This technique determines the corresponding topological and geometrical relations features of target. Software searches near the target and estimates the true pixel coordinates. This method requires some a-priori information like approximate orientation parameters and image overlap. Accuracy depends on the accuracy of apriori information.

PDF

___

Ackermann, R, (1983). High precision digital image correlation. In: Proceedings of 39th Photogrammetric Week. Institute of Photogrammetry, University of Stuttgart, 231-243.
Bezdek, J.C., (1981). Pattern recognition with fuzzy objective function algorithms, Plenum, New York.
Braess, M., (1997). Strukturbasierte Merkmalszuordnung in kurzen stereoskopischen Videosequenzen. Ph.D. dissertation, Technical University Aachen, Publication of the Geodetic Institute, No. 54, 119.
Greenfeld, J.S., Schulte-Hinsken, S., Schulte- Hinsken, S., Müler, W., (1991). A strategy for automated stereo model orientation using a feature- based matching procedure, Proceedings of the 1991 ASPRS Annual convention, 131-140.
Haralick, R.M., Shapiro, L.G., (1993). Computer and robot vision, II, Addison-Wesley, New York.
Karmakar Gour C., Dooley Laurence S., (2002). A generic fuzzy rule based image segmentation algorithm, Pattern Recognition Letters, 23, 1215 – 1227.
Kundu P., Chaudhuri B.B., (1993). Fuzzy geometric feature-based texture classification, Pattern Recognition Letters, 14, 825-832.
Lemmens, M., (1988), A survey on stereo matching techniques, International Archives of Photogrammetry and Remote Sensing, 27, B3, 11-23.
Looney Carl G., (2000). Fuzzy and rule-based image convolution, Math. and Computers in Simulation, 51, 209-219.
Li, M., (1988). High precision relative orientation using feature based techniques, International Archives of Photogrammetry and Remote Sensing 27, B3, 456-465.
Nakamura A., (1996), 'Continuous' functions on fuzzy digital pictures, Pattern Recognition Letters, 17, 557-563.
Pal S.K., King R.A., Hashim A.A., (1983). “Automatic gray level thresholding through index of fuzziness and entropy”, Pattern Recognition Letters, 1, 141-146.
Pal, S. K. ve Dutta Majumder, D., (1986). Fuzzy mathematical approach to pattern recognition. New York: John Wiley & Sons.
Pal S.K., Rosenfeld A., (1988). Image enhancement and thresholding by optimization of fuzzy compactness, Pattern Recognition Letters, 7, 77-86.
Russo F., Ramponi G., (1995). A fuzzy operator for the enhancement of blurred and noisy images, IEEE Transactions on Image Processing, 4, 8, 1169–1174.
Schenk, T., (1997). Towards automatic aerial triangulation, ISPRS Journal of Photogrammetry and Remote Sensing, 52, 3, 110-121.
Şen, Z., (2001), Bulanık mantık ve modelleme ilkeleri, Bilge Kültür Sanat Basımevi, 172 sayfa.
Tang, L., Heipke, C., (1993). An approach for automatic relative orientation. In: Gruen, A., Kahmen,H. (Eds.), Optical 3D Measurement Techniques II. Wichmann-Verlag, Karlsruhe, 347-354.
Tizhoosh, H., Michaelis, B., (1998). Improvement of image quality based on subjective evaluation and Fuzzy aggregation techniques. In EUFIT’98, Aachen, Germany, 2, 1325–1329.
Vadiee, N. (1993). Fuzzy rule-based expert systems – I Fuzzy logic and control: software and hardware applications, Prentice Hall, 51-85.
Vosselman. G., Haala, N., (1992). Erkennung topographischer Paβpunkte durch relationale Zuordnung. Z. Photogramm. Fernerkd. 6, 170-176.
Wang, Y., (1994). Strukturzuordnung zur automatischen Oberflächenrekonstruktion. Ph. D. dissertation, Wissenschaftliche Arbeiten der Fachrichtung Verfahren zur automatischen gegenseitigen Orientierung der digitalen Bilder. Z. Photogramm. Fernerkd., 3, 122-130.
Zadeh, L. A., (1975). The concept of a linguistic variable and its applications to approximate reasoning, Information Science, 8:199–249.
Zadeh, L.A., (1965). Fuzzy sets, Information and Control, 8, 338-353.