SavedAdd your journal

Journals / Havacılık ve Uzay Teknolojileri Dergisi / 2017 / Cilt: 10 - Sayı: 1

SEGMENTATION BASED CLOUD AND CLOUD SHADOW DETECTION IN SATELLITE IMAGERY

UYDU GÖRÜNTÜLERİNDE BÖLÜTLEME TABANLI BULUT VE GÖLGE BELİRLEME

Kaan KALKAN
Derya MAKTAV
Pages
45–54
Publication Date
2022-10-18
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Results are tested with different satellite imageries from different areas to test transferability and compared with other state-ofart methods in the literature.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:One of the main source of noises in remote sensingsatellite imageryis regional clouds and shadows of these cloudscaused by atmospheric conditions.
📊
Key Findings & Data:In many studies, these clouds and shadows are masked with multi-temporal imagery taken from the same area to decrease effects of misclassification and deficiency in different image processing techniques,such as change detection and NDVI (Normalized Difference Vegetation Index).
💡
Conclusion & Impact:Results are tested with different satellite imageries from different areas to test transferability and compared with other state-ofart methods in the literature.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

One of the main source of noises in remote sensingsatellite imageryis regional clouds and shadows of these cloudscaused by atmospheric conditions. In many studies, these clouds and shadows are masked with multi-temporal imagery taken from the same area to decrease effects of misclassification and deficiency in different image processing techniques,such as change detection and NDVI (Normalized Difference Vegetation Index). This problem is surpassed in many studies by mosaicking with different images obtained from different acquisition dates of the same region. The main step of all studies that cover cloud cloning or cloud detection is the detection of clouds from a satellite image. In this study, clouds and shadow patches are classified by using a spectral feature based rule set created after segmentation process of Landsat 8 image. Not only spectral characteristics but also structural parameters like pattern, area and dimension are used to detect clouds and shadows. Ruleset of classification is developed within a transferable approach to reach a scene independent method. Results are tested with different satellite imageries from different areas to test transferability and compared with other state-ofart methods in the literature.

Özet

Uzaktan algılamauydu görüntülerinde atmosfer etkilerinden kaynaklı olarak ortaya çıkan bölgesel bulutlar ve bu bulutların gölgeleri, yapılan çalışmalarda problem oluşturan temel gürültü kaynaklarından biridir. Değişiklik analizi, Normalize Edilmiş Fark Bitki Örtüsü İndeksi (NDVI:Normalized Difference Vegetation Index) hesaplama gibi önemlidijital işlemlerdebulut ve gölge bölgeleri, genel olarak yanıltıcı sonuçlar veren bölgeler olduğundan çoğu zaman maskelenerek işlemler gerçekleştirilmektedir. Bu problem,birçok çalışmada,aynı bölgeden elde edilmişçok zamanlı uydu görüntüleri ile mozaikleme yapılarak aşılmaktadır. Tüm bulut belirleme, gölge belirleme ve klonlama yöntemlerinin ortak adımı, görüntüdeki bulut ve gölge bölgelerinin belirlenmesi işlemidir. Bu çalışmada Landsat 8 görüntüleri kullanılarak, bulut ve gölge bölgeleri, görüntü bölütlemesinin ardından spektral özellik tabanlı bir kural dizisi oluşturularak belirlenmiştir. Bulut ve gölge belirlemede, görüntülerin spektral özelliklerinin yanı sıra, doku ve alan gibi yapısal özellikleri de kullanılmıştır. Oluşturulan kuraldizisi,birçok bölgede çalışması amaçlanarak transfer edilebilir bir yapıda oluşturulmuş,test görüntülerinde transfer edilebilirliği test edilmiş ve literatürdeki diğer yöntemlere olan üstünlükleri ve eksiklikleri gösterilmiştir.

🔖

Cite This Article

KALKAN, K., MAKTAV, D. (2022). SEGMENTATION BASED CLOUD AND CLOUD SHADOW DETECTION IN SATELLITE IMAGERY. Havacılık ve Uzay Teknolojileri Dergisi, Cilt: 10 - Sayı: 1, 45–54. https://ajindex.com/articles/535227

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (11)

  1. Gao, Bo-cai. (1996). “NDWI—A Normalized Difference Water Index for Remote Sensing of Vegetation Liquid Water from Space.”Remote Sensing of Environment 58 (3): 257–66.
  2. Hall, D.K., & Riggs, G. A. (2011). “Normalized-Difference Snow Index (NDSI)”. Encyclopedia of Snow, Ice and Glaciers (pp. 779–780).
  3. Vedaldi, A., & Fulkerson, B. (2010). “Vlfeat: an open and portable library of computer vision algorithms”. Proceedings of the international conference on Multimedia-MM ’10 (p. 1469). New York, New York, USA: ACM Press.
  4. Lloyd, S. (1982). “Least squares quantization in PCM”. IEEE Transactions on InformationTheory, 28(2), 129–137.
  5. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012). “SLIC superpixels compared to state-of-the-art superpixel methods”.IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2281.
  6. USGS. (2015). “Landsat 8 (L8) Data Users Handbook”. Earth Resources Observation and Science (EROS) Center, 8(June), 97. Simpson, J. J., Jin, Z., & Stitt, J. R. (2000). “Cloud shadow detection under arbitrary viewing and illumination conditions”. IEEE Transactions on Geoscience and Remote Sensing, 38(2 II), 972–976.
  7. Simpson, J. J., & Stitt, J. R. (1998). “A procedure for the detection and removal of cloud shadow from AVHRR data over land”. IEEE Transactions on Geoscience and Remote Sensing,36(3), 880–897.
  8. Berendes, T., Sengupta, S. K., Welch, R. M., Wielicki, B. a., & Navar, M. (1992). “Cumulus cloud base height estimation from high spatial resolution Landsat data: a Hough transform approach”. IEEE Transactions on Geoscience and Remote Sensing,30(3), 430–443. Le Hégarat-Mascle, S., & André, C. (2009).”Use of Markov Random Fields for automatic cloud/shadow detection on high resolution optical images”. ISPRS Journal of Photogrammetry and Remote Sensing,64(4), 351–366.
  9. Hutchison, K. D., Mahoney, R. L., Vermote, E. F., Kopp, T. J., Jackson, J. M., Sei, A., & Iisager, B. D. (2009). “A geometry-based approach to identifying cloud shadows in the VIIRS cloud mask algorithm for NPOESS”. Journal of Atmospheric and Oceanic Technology, 26(7), 1388–1397.
  10. Gao, B. C., Yang, P., Han, W., Li, R. R., & Wiscombe, W. J. (2002).“An algorithm using visible and 1.38-??m channels to retrieve cirrus cloud reflectances from aircraft and satellite data”. IEEE Transactions on Geoscience and Remote Sensing, 40(8), 1659–1668.
  11. Gao, B.-C., Kaufman, Y. J., Han, W., & Wiscombe, W. J. (1998). “Corection of thin cirrus path radiances in the 0.4–1.0 μ