Research Article
BibTex RIS Cite

Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi

Year 2022, Volume: 7 Issue: 3, 197 - 208, 15.12.2022
https://doi.org/10.29128/geomatik.947334

Abstract

Şekil analizi, bilgisayar görüsü, coğrafi bilgi bilimi, kartografya, uzaktan algılama, kent morfolojisi, arazi yönetimi ve ekoloji gibi çeşitli alanlarda mekansal olguları/nesneleri karakterize etmek ve mekansal örüntüleri ortaya çıkartmak için kullanılır. Bu bağlamda, şekil göstergeleri, genel olarak mekansal detayların geometrilerinin ve/veya onlardan türetilen yardımcı geometrilerin metrik özellikleri yardımıyla karmaşıklık ve benzerlik gibi şekilsel karakteristikleri niceliksel olarak ifade ederler. Bununla birlikte, şekil göstergeleri mekansal detayların farklı şekilsel özelliklerini ölçmektedir. Bu nedenle, bir detayı şekilsel olarak karakterize ederken tek bir şekil göstergesinin kullanımı her zaman yeterli olmaz. Ayrıca, bu amaçla uygun sınıflandırma yöntemlerinin kullanılması da önemlidir. Bu çalışmada, dairesellik, dışbükeylik ve dikdörtgensellik şekil göstergeleri ile rastgele orman ve gradyan artırma topluluk öğrenme sınıflandırma algoritmaları birlikte kullanılarak 300 adet bina detayı şekilsel karmaşıklık düzeylerine göre basit, orta ve karmaşık olarak sınıflandırılmıştır. Görsel algıya dayalı olarak etiketlenen veri setiyle karşılaştırıldığında rastgele orman algoritması %93.33 genel doğruluk ( = 0.900) üretirken, gradyan artırma algoritması ise %92.33 genel doğruluk (󠆻 = 0.885) üretmiştir. Bu bulgular, bina detaylarının şekilsel karmaşıklık düzeylerinin, çeşitli şekil göstergeleri ve yaygın kullanılan topluluk öğrenmesi sınıflandırma algoritmaları aracılığıyla oldukça yüksek bir doğrulukla sınıflandırılabileceğini göstermiştir.

References

  • Ai T, Cheng X, Liu P & Yang M (2013). A shape analysis and template matching of building features by the fourier transform method. Computers, Environment and Urban Systems, 41, 219–233.
  • Akar Ö & Görmüş E T (2019). Göktürk-2 ve Hyperion EO-1 Uydu Görüntülerinden Rastgele Orman Sınıflandırıcısı ve Destek Vektör Makineleri ile Arazi Kullanım Haritalarının Üretilmesi. Geomatik, 4(1), 68-81.
  • Aktaş M (2012). Shape Descriptors. Doktora Tezi, Exeter Üniversitesi, Bilgisayar Bilimleri Bölümü, İngiltere.
  • Angel S, Parent J & Civco L (2010). Ten compactness properties of circles: measuring shape in geography. The Canadian Geographer / Le Géographe canadien, 54(4), 441–461.
  • Arkin E, Chew L P, Huttenlocher D P, Kedem K & Mitchell J S B (1991). An efficiently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3), 209–216.
  • Basaraner M & Cetinkaya S (2017). Performance of shape indices and classification schemes for characterising perceptual shape complexity of building footprints in GIS. International Journal of Geographical Information Science, 31(10), 1952–1977.
  • Basaraner M (2020). Geometric and semantic quality assessments of building features in OpenStreetMap for some areas of Istanbul. Polish Cartographical Review, 52(3), 94–107.
  • Başaraner M (2005). Nesne Yönelimli Coğrafi Bilgi Sistemi Ortamında Orta Ölçekli Topografik Haritalar İçin Bina ve Yerleşim Alanlarının Otomatik Genelleştirilmesi. Doktora Tezi, Yıldız Teknik Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul.
  • Bonaccorso G (2020). Mastering Machine Learning Algorithms, 2nd edn. Packt Publishing. Birmingham, 798 s.
  • Breiman L (2001). Random forests. Machine Learning, 45(1), 5–32.
  • Burghardt D & Steiniger S (2005). Usage of principal component analysis in the process of automated generalisation. Proceedings of 22nd International Cartographic Conference, La Coruna, Spain.
  • Burkov A (2019). The Hundred-Page Machine Learning Book. Andriy B., 159 s.
  • Burkov A (2020). Machine Learning Engineering. True Positive Inc., Quebec City, 310 s.
  • Congalton R G & Green K (2019). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, 3rd edn. CRC Press, Boca Raton, FL, 328 s.
  • Çetinkaya S (2014). Kartografik Genelleştirmede Bina Dizilimlerinin Karakterizasyonu ve Yorumlanmasına İlişkin Yeni Yaklaşımlar. Doktora Tezi, Yıldız Teknik Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul.
  • Da Costa F & Cesar R (2009). Shape Classification and Analysis: Theory and Practice, 2nd edn. CRC Press, Boca Raton, FL, 685 s.
  • Demetriou D, See L & Stillwell J (2013). A parcel shape index for use in land consolidation planning. Transactions in GIS 17(6), 861–882.
  • Euler T (2014). Who wants my product? Affinity-based marketing. M. Hofmann ve R. Klinkenberg (ed.) Data Mining Use Cases and Business Analytics Applications. Chapman & Hall/CRC Press, Boca Raton, FL, 77-96.
  • Fleischmann M, Romice O & Porta S (2020). Measuring urban form: Overcoming terminological inconsistencies for a quantitative and comprehensive morphologic analysis of cities. Environment and Planning B: Urban Analytics and City Science. DOI: 10.1177/2399808320910444
  • Frenkel A & Ashkenazi M (2008). Measuring urban sprawl: how can we deal with it? Environment and Planning B: Planning and Design, 35(1), 56–79.
  • Friedman J H (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29, 1189-1232.
  • Görmüş E T & Akar Ö (2019). Headwall Hyperspec VNIR kamerası ile elde edilen hiperspektral hava fotografı için boyut indirgeme yöntemlerinin performanslarının analizi. Geomatik, 4(3), 201-214.
  • Grabler F, Agrawala M, Sumner W & Pauly M (2008). Automatic generation of tourist maps. ACM Transactions on Graphics 27(3), 1–11.
  • Han J, Micheline K & Jian P (2012). Data Mining: Concepts and Techniques. 3nd edn. Morgan Kaufmann, Cambridge, MA, 744 s.
  • Huang H, Kieler B & Sester M (2013). Urban building usage labeling by geometric and context analyses of the footprint data. Proceedings of 26th International Cartographic Conference, 25–30 August, Dresden, Germany.
  • Kotu V & Deshpande B (2019). Data Science: Concepts and Practice, 2nd ed. Morgan Kaufmann Publishers, Cambridge, M A,. 568 s.
  • Li W, Goodchild F & Church R (2013). An efficient measure of compactness for two-dimensional shapes and its application in regionalization problems. International Journal of Geographical Information Science, 27(6), 1227–1250.
  • Medda F, Nijkamp P & Rietveld P (1998). Recognition and classification of urban shapes. Geographical Analysis, 30(3), 304-314.
  • Oksanen T (2013). Shape-describing indices for agricultural field plots and their relationship to operational efficiency. Computers and Electronics in Agriculture, 98, 252-259.
  • Oshiro T M, Perez P S & Baranauskas J A (2012). How many trees in a Random Forest? P. Perner (ed.) Machine Learning and Data Mining in Pattern Recognition- MLDM 2012. Lecture Notes in Computer Science, vol. 7376. Springer, Berlin, Heidelberg, 154-168.
  • Rosin P L (2000). Measuring shape: ellipticity, rectangularity, and triangularity. Proceedings 15th International Conference on Pattern Recognition (ICPR-2000), Vol. 1, 952-955.
  • Ruas A & Holzapfel F (2003). Automatic characterisation of building alignments by means of expert knowledge. Proceedings of 21st International Cartographic Conference, Durban, South Africa, 1604-1615.
  • Shi W (2010). Principles of Modeling Uncertainties in Spatial Data and Spatial Analyses. CRC Press, Boca Raton, FL, 454 s.
  • Tattar P N (2018). Hands-On Ensemble Learning with R. Packt Publishing, Birmingham, 376 s.
  • Toussaint G (1983). Solving geometric problems with the “Rotating Calipers”. Proceedings of IEEE MELECON’83, A10.02/1–4.
  • URL-1: https://www.analyticsvidhya.com/blog/2016/02/complete-guide-parameter-tuning-gradient-boosting-gbm-python/ Erişim Tarihi: 05.04.2021.
  • Üstüner M, Abdikan S, Bilgin G & Şanlı F B (2020). Hafif gradyan artırma makineleri ile tarımsal ürünlerin sınıflandırılması. Türk Uzaktan Algılama ve CBS Dergisi, 1(2), 97-105.
  • Vohra R & Tiwari K C (2020). Spatial shape feature descriptors in classification of engineered objects using high spatial resolution remote sensing data. Evolving Systems, 11(4), 647–660.
  • Vukicevic M, Jovanovic Z, Delibašić B & Suknovic M (2013). Recommender system for selection of the right study program for higher education students. M. Hofmann ve R. Klinkenberg (ed.) Data Mining Use Cases and Business Analytics Applications. Chapman & Hall/CRC Press, Boca Raton, FL, 145-156.
  • Wade C (2020). Hands-On Gradient Boosting with XGBoost and scikit-learn: Perform accessible machine learning and extreme gradient boosting with Python. Packt Publishing, Birmingham, 310 s.
  • Wentz A (1997). Shape analysis in GIS. Proceedings of Auto-Carto 13, 204–213.
  • Witten I H (2017). Data Mining: Practical Machine Learning Tools and Techniques. 4nd edn. Morgan Kaufmann, San Francisco, CA, 654 s.
  • Xu Y, Xie Z, Chen Z & Wu L (2017). Shape similarity measurement model for holed polygons based on position graphs and Fourier descriptors. International Journal of Geographical Information Science, 31(2), 253-279.
  • Yan X, Ai T, Yang M & Yin H (2019). A graph convolutional neural network for classification of building patterns using spatial vector data. ISPRS Journal of Photogrammetry and Remote Sensing, 150, 259-273.
  • Yang X (2019). Introduction to Algorithms for Data Mining and Machine Learning. Academic Press, Cambridge, MA, 188 s.
  • Zeybek M (2020). El-tipi LiDAR nokta bulutundan tek ağaç gövdesinin otomatik çıkarımında istatistiksel sınıflandırma algoritmalarının performans analizi. Artvin Çoruh Üniversitesi Orman Fakültesi Dergisi, 21 (2), 200-213.
  • Zeybek M (2021). Classification of UAV point clouds by random forest machine learning algorithm. Turkish Journal of Engineering, 5(2),48-57.
  • Zhao Z & Stough R R (2005). Measuring similarity among various shapes based on geometrical matching. Geographical Analysis, 37(4), 410–422.
  • Zhong Y, Lin A, He L, Zhou Z & Yuan M (2020). Spatiotemporal dynamics and driving forces of urban land-use expansion: a case study of the Yangtze River Economic Belt, China. Remote Sensing, 12(2), 287.
  • Zhou X, Chen Z, Zhang X & Tinghua A (2018). Change detection for building footprints with different levels of detail using combined shape and pattern analysis. ISPRS International Journal of Geo-Information, 7(10), 406–430.
Year 2022, Volume: 7 Issue: 3, 197 - 208, 15.12.2022
https://doi.org/10.29128/geomatik.947334

Abstract

References

  • Ai T, Cheng X, Liu P & Yang M (2013). A shape analysis and template matching of building features by the fourier transform method. Computers, Environment and Urban Systems, 41, 219–233.
  • Akar Ö & Görmüş E T (2019). Göktürk-2 ve Hyperion EO-1 Uydu Görüntülerinden Rastgele Orman Sınıflandırıcısı ve Destek Vektör Makineleri ile Arazi Kullanım Haritalarının Üretilmesi. Geomatik, 4(1), 68-81.
  • Aktaş M (2012). Shape Descriptors. Doktora Tezi, Exeter Üniversitesi, Bilgisayar Bilimleri Bölümü, İngiltere.
  • Angel S, Parent J & Civco L (2010). Ten compactness properties of circles: measuring shape in geography. The Canadian Geographer / Le Géographe canadien, 54(4), 441–461.
  • Arkin E, Chew L P, Huttenlocher D P, Kedem K & Mitchell J S B (1991). An efficiently computable metric for comparing polygonal shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(3), 209–216.
  • Basaraner M & Cetinkaya S (2017). Performance of shape indices and classification schemes for characterising perceptual shape complexity of building footprints in GIS. International Journal of Geographical Information Science, 31(10), 1952–1977.
  • Basaraner M (2020). Geometric and semantic quality assessments of building features in OpenStreetMap for some areas of Istanbul. Polish Cartographical Review, 52(3), 94–107.
  • Başaraner M (2005). Nesne Yönelimli Coğrafi Bilgi Sistemi Ortamında Orta Ölçekli Topografik Haritalar İçin Bina ve Yerleşim Alanlarının Otomatik Genelleştirilmesi. Doktora Tezi, Yıldız Teknik Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul.
  • Bonaccorso G (2020). Mastering Machine Learning Algorithms, 2nd edn. Packt Publishing. Birmingham, 798 s.
  • Breiman L (2001). Random forests. Machine Learning, 45(1), 5–32.
  • Burghardt D & Steiniger S (2005). Usage of principal component analysis in the process of automated generalisation. Proceedings of 22nd International Cartographic Conference, La Coruna, Spain.
  • Burkov A (2019). The Hundred-Page Machine Learning Book. Andriy B., 159 s.
  • Burkov A (2020). Machine Learning Engineering. True Positive Inc., Quebec City, 310 s.
  • Congalton R G & Green K (2019). Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, 3rd edn. CRC Press, Boca Raton, FL, 328 s.
  • Çetinkaya S (2014). Kartografik Genelleştirmede Bina Dizilimlerinin Karakterizasyonu ve Yorumlanmasına İlişkin Yeni Yaklaşımlar. Doktora Tezi, Yıldız Teknik Üniversitesi, Fen Bilimleri Enstitüsü, İstanbul.
  • Da Costa F & Cesar R (2009). Shape Classification and Analysis: Theory and Practice, 2nd edn. CRC Press, Boca Raton, FL, 685 s.
  • Demetriou D, See L & Stillwell J (2013). A parcel shape index for use in land consolidation planning. Transactions in GIS 17(6), 861–882.
  • Euler T (2014). Who wants my product? Affinity-based marketing. M. Hofmann ve R. Klinkenberg (ed.) Data Mining Use Cases and Business Analytics Applications. Chapman & Hall/CRC Press, Boca Raton, FL, 77-96.
  • Fleischmann M, Romice O & Porta S (2020). Measuring urban form: Overcoming terminological inconsistencies for a quantitative and comprehensive morphologic analysis of cities. Environment and Planning B: Urban Analytics and City Science. DOI: 10.1177/2399808320910444
  • Frenkel A & Ashkenazi M (2008). Measuring urban sprawl: how can we deal with it? Environment and Planning B: Planning and Design, 35(1), 56–79.
  • Friedman J H (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29, 1189-1232.
  • Görmüş E T & Akar Ö (2019). Headwall Hyperspec VNIR kamerası ile elde edilen hiperspektral hava fotografı için boyut indirgeme yöntemlerinin performanslarının analizi. Geomatik, 4(3), 201-214.
  • Grabler F, Agrawala M, Sumner W & Pauly M (2008). Automatic generation of tourist maps. ACM Transactions on Graphics 27(3), 1–11.
  • Han J, Micheline K & Jian P (2012). Data Mining: Concepts and Techniques. 3nd edn. Morgan Kaufmann, Cambridge, MA, 744 s.
  • Huang H, Kieler B & Sester M (2013). Urban building usage labeling by geometric and context analyses of the footprint data. Proceedings of 26th International Cartographic Conference, 25–30 August, Dresden, Germany.
  • Kotu V & Deshpande B (2019). Data Science: Concepts and Practice, 2nd ed. Morgan Kaufmann Publishers, Cambridge, M A,. 568 s.
  • Li W, Goodchild F & Church R (2013). An efficient measure of compactness for two-dimensional shapes and its application in regionalization problems. International Journal of Geographical Information Science, 27(6), 1227–1250.
  • Medda F, Nijkamp P & Rietveld P (1998). Recognition and classification of urban shapes. Geographical Analysis, 30(3), 304-314.
  • Oksanen T (2013). Shape-describing indices for agricultural field plots and their relationship to operational efficiency. Computers and Electronics in Agriculture, 98, 252-259.
  • Oshiro T M, Perez P S & Baranauskas J A (2012). How many trees in a Random Forest? P. Perner (ed.) Machine Learning and Data Mining in Pattern Recognition- MLDM 2012. Lecture Notes in Computer Science, vol. 7376. Springer, Berlin, Heidelberg, 154-168.
  • Rosin P L (2000). Measuring shape: ellipticity, rectangularity, and triangularity. Proceedings 15th International Conference on Pattern Recognition (ICPR-2000), Vol. 1, 952-955.
  • Ruas A & Holzapfel F (2003). Automatic characterisation of building alignments by means of expert knowledge. Proceedings of 21st International Cartographic Conference, Durban, South Africa, 1604-1615.
  • Shi W (2010). Principles of Modeling Uncertainties in Spatial Data and Spatial Analyses. CRC Press, Boca Raton, FL, 454 s.
  • Tattar P N (2018). Hands-On Ensemble Learning with R. Packt Publishing, Birmingham, 376 s.
  • Toussaint G (1983). Solving geometric problems with the “Rotating Calipers”. Proceedings of IEEE MELECON’83, A10.02/1–4.
  • URL-1: https://www.analyticsvidhya.com/blog/2016/02/complete-guide-parameter-tuning-gradient-boosting-gbm-python/ Erişim Tarihi: 05.04.2021.
  • Üstüner M, Abdikan S, Bilgin G & Şanlı F B (2020). Hafif gradyan artırma makineleri ile tarımsal ürünlerin sınıflandırılması. Türk Uzaktan Algılama ve CBS Dergisi, 1(2), 97-105.
  • Vohra R & Tiwari K C (2020). Spatial shape feature descriptors in classification of engineered objects using high spatial resolution remote sensing data. Evolving Systems, 11(4), 647–660.
  • Vukicevic M, Jovanovic Z, Delibašić B & Suknovic M (2013). Recommender system for selection of the right study program for higher education students. M. Hofmann ve R. Klinkenberg (ed.) Data Mining Use Cases and Business Analytics Applications. Chapman & Hall/CRC Press, Boca Raton, FL, 145-156.
  • Wade C (2020). Hands-On Gradient Boosting with XGBoost and scikit-learn: Perform accessible machine learning and extreme gradient boosting with Python. Packt Publishing, Birmingham, 310 s.
  • Wentz A (1997). Shape analysis in GIS. Proceedings of Auto-Carto 13, 204–213.
  • Witten I H (2017). Data Mining: Practical Machine Learning Tools and Techniques. 4nd edn. Morgan Kaufmann, San Francisco, CA, 654 s.
  • Xu Y, Xie Z, Chen Z & Wu L (2017). Shape similarity measurement model for holed polygons based on position graphs and Fourier descriptors. International Journal of Geographical Information Science, 31(2), 253-279.
  • Yan X, Ai T, Yang M & Yin H (2019). A graph convolutional neural network for classification of building patterns using spatial vector data. ISPRS Journal of Photogrammetry and Remote Sensing, 150, 259-273.
  • Yang X (2019). Introduction to Algorithms for Data Mining and Machine Learning. Academic Press, Cambridge, MA, 188 s.
  • Zeybek M (2020). El-tipi LiDAR nokta bulutundan tek ağaç gövdesinin otomatik çıkarımında istatistiksel sınıflandırma algoritmalarının performans analizi. Artvin Çoruh Üniversitesi Orman Fakültesi Dergisi, 21 (2), 200-213.
  • Zeybek M (2021). Classification of UAV point clouds by random forest machine learning algorithm. Turkish Journal of Engineering, 5(2),48-57.
  • Zhao Z & Stough R R (2005). Measuring similarity among various shapes based on geometrical matching. Geographical Analysis, 37(4), 410–422.
  • Zhong Y, Lin A, He L, Zhou Z & Yuan M (2020). Spatiotemporal dynamics and driving forces of urban land-use expansion: a case study of the Yangtze River Economic Belt, China. Remote Sensing, 12(2), 287.
  • Zhou X, Chen Z, Zhang X & Tinghua A (2018). Change detection for building footprints with different levels of detail using combined shape and pattern analysis. ISPRS International Journal of Geo-Information, 7(10), 406–430.
There are 50 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Makaleler
Authors

Hüseyin Safa Duman 0000-0001-6413-0873

Melih Başaraner 0000-0002-4619-7801

Publication Date December 15, 2022
Published in Issue Year 2022 Volume: 7 Issue: 3

Cite

APA Duman, H. S., & Başaraner, M. (2022). Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi. Geomatik, 7(3), 197-208. https://doi.org/10.29128/geomatik.947334
AMA Duman HS, Başaraner M. Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi. Geomatik. December 2022;7(3):197-208. doi:10.29128/geomatik.947334
Chicago Duman, Hüseyin Safa, and Melih Başaraner. “Şekil göstergeleri Ve Topluluk öğrenmesi sınıflandırma Algoritmaları Ile Bina detaylarının şekil karmaşıklık Analizi”. Geomatik 7, no. 3 (December 2022): 197-208. https://doi.org/10.29128/geomatik.947334.
EndNote Duman HS, Başaraner M (December 1, 2022) Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi. Geomatik 7 3 197–208.
IEEE H. S. Duman and M. Başaraner, “Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi”, Geomatik, vol. 7, no. 3, pp. 197–208, 2022, doi: 10.29128/geomatik.947334.
ISNAD Duman, Hüseyin Safa - Başaraner, Melih. “Şekil göstergeleri Ve Topluluk öğrenmesi sınıflandırma Algoritmaları Ile Bina detaylarının şekil karmaşıklık Analizi”. Geomatik 7/3 (December 2022), 197-208. https://doi.org/10.29128/geomatik.947334.
JAMA Duman HS, Başaraner M. Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi. Geomatik. 2022;7:197–208.
MLA Duman, Hüseyin Safa and Melih Başaraner. “Şekil göstergeleri Ve Topluluk öğrenmesi sınıflandırma Algoritmaları Ile Bina detaylarının şekil karmaşıklık Analizi”. Geomatik, vol. 7, no. 3, 2022, pp. 197-08, doi:10.29128/geomatik.947334.
Vancouver Duman HS, Başaraner M. Şekil göstergeleri ve topluluk öğrenmesi sınıflandırma algoritmaları ile bina detaylarının şekil karmaşıklık analizi. Geomatik. 2022;7(3):197-208.