OPEN STREET MAP (OSM) İÇİN DERİN ÖĞRENME ALGORİTMALARI KULLANARAK YARI OTOMATİK VERİ ZENGİNLEŞTİRME

Abstract

Plansız kentleşme bölgeleri hakkında sürekli veri elde etmek, bu bölgelerde gelecekte yapılacak çalışmalar için kesin planlar geliştirmek açısından büyük önem taşımaktadır. Analiz için bir çarpık kentleşme alanı seçilmiş ve çok yüksek çözünürlüklü insansız hava aracı (İHA) görüntüleri kullanılarak yol çıkarımı yapılmıştır. Bu bağlamda, çok yüksek çözünürlüklü İHA görüntüsünden yol çıkarımı amacıyla ArcGIS Pro yazılımı tarafından yayınlanan derin öğrenme paketine entegre edilmiş nesne tespit aracı kullanılarak Sat2Graph derin öğrenme modeli kullanılmıştır. Yüksek çözünürlüklü İHA görüntüleri, Sat2Graph derin öğrenme modelinin uygulanmasıyla elde edilen sonuçlarla birlikte fotogrametri yöntemi kullanılarak analize tabi tutulmuştur. Elde edilen yol çıkarımı OpenStreetMap (OSM) üzerinde veri iyileştirme amacıyla kullanılmıştır. Bu, gönüllüler tarafından gerçekleştirilen veri güncellemelerinin hızlı ve hassas bir şekilde uygulanmasını kolaylaştıracaktır. Geri çağırma, F1 puanı, kesinlik oranı/belirsizlik doğruluğu, ortalama üretici doğruluğu ve ürünlerin birleşimi üzerindeki kesişimin algoritma ile otomatik olarak çıkarıldığı ve sırasıyla 0,816, 0,827, 0,838, 0,792 ve 0,597 olarak belirlendiği belirtilmelidir.

Keywords

• CBS
• OpenStreetMap
• Derin öğrenme
• Veri zenginleştirme
• Fotogrametri

SEMI-AUTOMATIC DATA ENRICHMENT FOR OPEN STREET MAP (OSM) USING DEEP LEARNING ALGORITHMS

Abstract

It is crucial to obtain continuous data on unplanned urbanization regions in order to develop precise plans for future studies in these regions. An unplanned urbanization area was selected for analysis, and road extraction was performed using very high-resolution unmanned aerial vehicle (UAV) images. In this regard, the Sat2Graph deep learning model was employed, utilizing the object detection tool integrated within the deep learning package published by ArcGIS Pro software, for the purpose of road extraction from a very high-resolution UAV image. The high-resolution UAV images were subjected to analysis using the photogrammetry method, with the results obtained through the application of the Sat2Graph deep learning model. The resulting road extraction was employed for the purpose of data enhancement on OpenStreetMap (OSM). This will facilitate the expeditious and precise implementation of data updates conducted by volunteers. It should be noted that the recall, F1 score, precision ratio/uncertainty accuracy, average producer accuracy, and intersection over union of products were automatically extracted with the algorithm and determined to be 0.816, 0.827, 0.838, 0.792, and 0.597, respectively.

Keywords

• GIS
• OpenStreetMap
• Deep learning
• Data enrichment
• Photogrammetry

References

1. Biçici, S., & Zeybek, M. (2021). Effectiveness of Training Sample and Features for Random Forest on Road Extraction from Unmanned Aerial Vehicle-Based Point Cloud. Transportation Research Record, 2675(12), 401–418.
2. Hamal, S. N. G. (2022). Accuracy of digital maps produced from UAV images in rural areas. Advanced UAV, 2(1), 29-34.
3. Yiğit, A. Y., & Uysal, M. (2021). Yüksek Çözünürlüklü İnsansız Hava Aracı (İHA) Görüntülerinden Karayolların Tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 10(3), 1040-1054.
4. Yiğit, A. Y., & Uysal, M. (2020). Automatic road detection from orthophoto images. Mersin Photogrammetry Journal, 2(1), 10-17.
5. https://www.openstreetmap.org (Date of Access: 30/10/2023)
6. Girres, J. F., & Touya, G. (2010). Quality assessment of the French OpenStreetMap dataset. Transactions in GIS, 14(4), 435-459.
7. Şenol, H. İ., Yiğit, A. Y., Kaya, Y. & Ulvi, A. (2021). İHA ve yersel fotogrametrik veri füzyonu ile kültürel mirasın 3 boyutlu (3B) modelleme uygulaması: Kanlıdivane Örneği. Türkiye Fotogrametri Dergisi, 3(1), 29-36.
8. Yiğit, A. Y., Kaya, Y., & Şenol, H. İ. (2022). Monitoring the change of Turkey’s tourism city Antalya’s Konyaaltı shoreline with multi-source satellite and meteorological data. Applied Geomatics, 14(2), 223-236.

9. Şenol, H. İ., Kaya, Y., Yiğit, A. Y., & Yakar, M. (2023). Extraction and geospatial analysis of the Hersek Lagoon shoreline with Sentinel-2 satellite data. Survey Review, 1-16.
10. Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., & Alamri, A. (2020). Deep learning approaches applied to remote sensing datasets for road extraction: A state-of-the-art review. Remote Sensing, 12(9), 1444.
11. Xu, Y., Xie, Z., Feng, Y., & Chen, Z. (2018). Road extraction from high-resolution remote sensing imagery using deep learning. Remote Sensing, 10(9), 1461.
12. Abdollahi, A., Pradhan, B., & Alamri, A. (2022). SC-RoadDeepNet: A New Shape and Connectivity-Preserving Road Extraction Deep Learning-Based Network from Remote Sensing Data. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-15.
13. Shivappriya, S. N., M.J.P. Priyadarsini, A. Stateczny, C. Puttamadappa and B. D. Parameshachari. (2021). Cascade object detection and remote sensing object detection method based on trainable activation function. Remote Sensing 13(2):200.
14. de Arruda, M.D.S., L. P. Osco, P. R. Acosta, D. N. Gonçalves, J. M. Junior, A. P. M. Ramos and W. N. Gonçalves. (2022). Counting and locating high-density objects using convolutional neural network. Expert Systems with Applications 195:116555.
15. Sun, X., P. Wang, C. Wang, Y. Liu and K. Fu. (2021). PBNet: Part-based convolutional neural network for complex composite object detection in remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing 173:50–65.
16. Ming, Q., L. Miao, Z. Zhou and Y. Dong. (2021). CFC-Net: A critical feature capturing network for arbitrary-oriented object detection in remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing 60:1–14.
17. Gao, G., Q. Liu and Y. Wang. (2021). Counting from sky: A large-scale data set for remote sensing object counting and a benchmark method. IEEE Transactions on Geoscience and Remote Sensing 59(5):3642–3655.
18. Cheng, G., C. Lang, M. Wu, X. Xie, X. Yao and J. and Han. (2021). Feature enhancement network for object detection in optical remote sensing images. Journal of Remote Sensing 2021:9805389.
19. Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., & Alamri, A. (2020). Deep learning approaches applied to remote sensing datasets for road extraction: A state-of-the-art review. Remote Sensing, 12(9), 1444.
20. Zhu, Q., Zhang, Y., Wang, L., Zhong, Y., Guan, Q., Lu, X., Zhang, L., & Li, D. (2021). A global context-aware and batch-independent network for road extraction from VHR satellite imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 175, 353-365.
21. Li, J., Meng, Y., Dorjee, D., Wei, X., Zhang, Z., & Zhang, W. (2021). Automatic road extraction from remote sensing imagery using ensemble learning and postprocessing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 10535-10547.
22. Lian, R., & Huang, L. (2020). DeepWindow: Sliding window based on deep learning for road extraction from remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 1905-1916.
23. Senaratne, H., Mobasheri, A., Ali, A. L., Capineri, C., & Haklay, M. (2017). A review of volunteered geographic information quality assessment methods. International Journal of Geographical Information Science, 31(1), 139-167.
24. Neis, P. (2015). Measuring the reliability of wheelchair user route planning based on volunteered geographic information. Transactions in GIS, 19(2), 188-201.
25. Mobasheri, A., Sun, Y., Loos, L., & Ali, A. L. (2017). Are crowdsourced datasets suitable for specialized routing services? Case study of OpenStreetMap for routing of people with limited mobility. Sustainability, 9(6), 997.
26. Qin, H., Rice, R. M., Fuhrmann, S., Rice, M. T., Curtin, K. M., & Ong, E. (2016). Geocrowdsourcing and accessibility for dynamic environments. GeoJournal, 81(5), 699-716.
27. Mobasheri, A., Huang, H., Degrossi, L. C., & Zipf, A. (2018). Enrichment of OpenStreetMap data completeness with sidewalk geometries using data mining techniques. Sensors, 18(2), 509.
28. Mobasheri, A. (2017). A rule-based spatial reasoning approach for OpenStreetMap data quality enrichment; case study of routing and navigation. Sensors, 17(11), 2498.
29. Zhao, W., Bo, Y., Chen, J., Tiede, D., Blaschke, T., & Emery, W. J. (2019). Exploring semantic elements for urban scene recognition: Deep integration of high-resolution imagery and OpenStreetMap (OSM). ISPRS Journal of Photogrammetry and Remote Sensing, 151, 237-250.
30. Ulvi, A., Yakar, M., Yiğit, A. Y., & Kaya, Y. (2020). İHA ve yersel fotogrametrik teknikler kullanarak Aksaray Kızıl Kilise’nin 3 Boyutlu nokta bulutu ve modelinin üretilmesi. Geomatik Dergisi, 5(1), 22-30.
31. Yiğit, A. Y., & Ulvi, A. (2020). İHA fotogrametrisi tekniği kullanarak 3B model oluşturma: Yakutiye Medresesi Örneği. Türkiye Fotogrametri Dergisi, 2(2), 46-54.
32. He, S., Bastani, F., Jagwani, S., Alizadeh, M., Balakrishnan, H., Chawla, S., & Sadeghi, M. A. (2020). Sat2graph: Road graph extraction through graph-tensor encoding. In European Conference on Computer Vision (pp. 51-67). Springer, Cham.
33. https://www.arcgis.com/home/item.html?id=b3696a0118b340c6befb96932f67b29f (Date of Access: 30/10/2023).
34. Memduhoglu, A., & Basaraner, M. (2024). Semantic enrichment of building functions through geospatial data integration and ontological inference. Environment and Planning B: Urban Analytics and City Science, 51(4), 923-938.
35. Arsanjani, J. J., Barron, C., Bakillah, M., & Helbich, M. (2013, May). Assessing the quality of OpenStreetMap contributors together with their contributions. In Proceedings of the AGILE (pp. 14-17).