Advertisement

An Object-Based Shadow Detection Method for Building Delineation in High-Resolution Satellite Images

  • Deepa SharmaEmail author
  • Jyoti Singhai
Original Article
  • 48 Downloads

Abstract

In satellite image analysis, detection of shadow plays a critical role in the precise object detection applications. The size and intensity of shadow vary with solar illumination angle and miscellaneous building attributes, which may lead to their misclassification. Hence, there is a need for an accurate and robust shadow detection method. In this paper, an object-based shadow detection method is proposed to extract building shadows and subsequently used to delineate buildings from high-resolution satellite images. In the presented method, a shadow mask is generated at pixel level using a fused ratio map of a visible and a false colour image in HSI colour space. Then, the building shadow map is delineated by an automatic thresholding process on an object level. The results of a qualitative and quantitative analysis reveal the effectiveness and stability of the proposed approach for shadow detection and building delineation in high-resolution satellite images. These satellite images are taken at a different solar illumination angle and for different building attributes. Experimental results show that the proposed method achieves average improvement in F score by 21%, IOU (Intersection over Union) by 16%, and accuracy by 9% as compared to some of the state-of-the-art shadow detection methods.

Keywords

Shadow detection Building detection Satellite images Near-infrared Object based Fused ratio mask 

Zusammenfassung

Objektbasiertes Schattenerkennungsverfahren zur Detektion von Bauwerken in hochauflösenden Satellitenbildern. In der Satellitenbildanalyse spielt die Erkennung von Schatten eine entscheidende Rolle für die präzise Objekterkennung. Die Größe und Intensität des Schattens variiert je nach Sonnenstand und Bauwerkseigenschaften, was zu einer Fehlklassifizierung führen kann. Daher ist eine genaue und robuste Schattenerkennungsmethode erforderlich. In diesem Beitrag wird ein objektbasiertes Schattenerkennungsverfahren zur Extraktion von Bauwerksschatten vorgeschlagen und anschließend zur Beschreibung von Bauwerken aus hochauflösenden Satellitenbildern verwendet. Bei dem vorgestellten Verfahren wird eine Bauwerksschattenkarte auf Pixelebene auf der Basis des Verhältnisses eines sichtbaren zu einem Falschfarbenbild im HSIFarbraum erzeugt. Anschließend werden aus der Bauwerksschattenkarte durch einen automatischen Schwellenwertprozess die Objekte extrahiert. Die Ergebnisse einer qualitativen und quantitativen Analyse zeigen die Wirksamkeit und Stabilität des vorgeschlagenen Ansatzes zur Schattendetektion und Bauwerksabgrenzung in hochauflösenden Satellitenbildern. Die Satellitenbilder wurden bei unterschiedlichen Sonnenständen und für unterschiedliche Bauwerksattribute aufgenommen. Die Untersuchungen zeigen, dass die vorgeschlagene Methode eine durchschnittliche Verbesserung des F-Tests um 21%, des IOU (Intersection over Union) um 16% und der Genauigkeit um 9% im Vergleich zu einigen der modernsten Schattenerkennungsmethoden erreicht.

Notes

Acknowledgements

The authors would like to thank’s Dr. Ali Ozgun Ok and Dr. M. Volpi for providing the dataset. Also to the Editor and the reviewers for their valuable feedback and comments on the manuscript that improved it remarkably.

References

  1. Adeline K, Chen M, Briottet X, Pang S, Paparoditis N (2013) Shadow detection in very high spatial resolution aerial images: a comparative study. ISPRS J Photogramm Remote Sens 80:21–38.  https://doi.org/10.1016/j.isprsjprs.2013.02.003 CrossRefGoogle Scholar
  2. Arevalo V, Gonzalez J, Ambrosio G (2008) Shadow detection in colour high-resolution satellite images. Int J Remote Sens 29(7):1945–1963.  https://doi.org/10.1080/01431160701395302 CrossRefGoogle Scholar
  3. Ashton EA, Wemett BD, Leathers RA, Downes TV (2008) A novel method for illumination suppression in hyperspectral images. In: Algorithms and technologies for multispectral, hyperspectral, and ultraspectral imagery XIV, vol 6966. SPIE, Orlando, Florida, United States.  https://doi.org/10.1117/12.777153 CrossRefGoogle Scholar
  4. Aytekin O, Erener A, Ulusoy I, Duzgun HSB (2012) Unsupervised building detection in complex urban environments from multispectral satellite imagery. Int J Remote Sens 33(7):2152–2177.  https://doi.org/10.1080/01431161.2011.606852 CrossRefGoogle Scholar
  5. Aytekin O, Ulusoy I, Abacioglu EZ, Gokcay E (2009) Building detection in high resolution remotely sensed images based on morphological operators. In: 4th international conference on recent advances in space technologies, 2009. RAST ’09, pp 376–379.  https://doi.org/10.1109/RAST.2009.5158228
  6. Aytekin O, Ulusoy I, Erener A, Duzgun HSB (2009) Automatic and unsupervised building extraction in complex urban environments from multi spectral satellite imagery. In: 2009 4th international conference on recent advances in space technologies, pp 287–291.  https://doi.org/10.1109/RAST.2009.5158214
  7. Chaudhuri D, Kushwaha NK, Samal A, Agarwal RC (2016) Automatic building detection from high-resolution satellite images based on morphology and internal gray variance. IEEE J Sel Top Appl Earth Obs Remote Sens 9(5):1767–1779.  https://doi.org/10.1109/JSTARS.2015.2425655 CrossRefGoogle Scholar
  8. Chung K, Lin Y, Huang Y (2009) Efficient shadow detection of color aerial images based on successive thresholding scheme. IEEE Trans Geosci Remote Sens 47(2):671–682.  https://doi.org/10.1109/TGRS.2008.2004629 CrossRefGoogle Scholar
  9. Dare PM (2005) Shadow analysis in high-resolution satellite imagery of urban areas. Photogramm Eng Remote Sens 71(2):169–177.  https://doi.org/10.14358/PERS.71.2.169 CrossRefGoogle Scholar
  10. Ghaffarian S, Ghaffarian S (2014) Automatic building detection based on purposive fastica (pfica) algorithm using monocular high resolution google earth images. ISPRS J Photogramm Remote Sens 97:152–159.  https://doi.org/10.1016/j.isprsjprs.2014.08.017 CrossRefGoogle Scholar
  11. Huang X, Yuan W, Li J, Zhang L (2017) A new building extraction postprocessing framework for high-spatial-resolution remote-sensing imagery. IEEE J Sel Top Appl Earth Obs Remote Sens 10:654–668.  https://doi.org/10.1109/JSTARS.2016.2587324 CrossRefGoogle Scholar
  12. Huang J, Xie W, Tang L (2004) Detection of and compensation for shadows in urban aerial images. In: 5th world congress on intelligent control and automation. IEEE, Hangzhou, China.  https://doi.org/10.1109/WCICA.2004.1343090 Google Scholar
  13. Levine MD, Bhattacharyya J (2005) Removing shadows. Pattern Recognit Lett 26(3):251–265.  https://doi.org/10.1016/j.patrec.2004.10.021 CrossRefGoogle Scholar
  14. Li E, Femiani J, Xu S, Zhang X, Wonka P (2015) Robust rooftop extraction from visible band images using higher order CRF. IEEE Trans Geosci Remote Sens 53(8):4483–4495.  https://doi.org/10.1109/TGRS.2015.2400462 CrossRefGoogle Scholar
  15. Li E, Xu S, Meng W, Zhang X (2017) Building extraction from remotely sensed images by integrating saliency cue. IEEE J Sel Top Appl Earth Obs Remote Sens 10(3):906–919.  https://doi.org/10.1109/JSTARS.2016.2603184 CrossRefGoogle Scholar
  16. Liasis G, Stavrou S (2016) Satellite images analysis for shadow detection and building height estimation. ISPRS J Photogramm Remote Sens 119:437–450.  https://doi.org/10.1016/j.isprsjprs.2016.07.006 CrossRefGoogle Scholar
  17. Luo H, Wang L, Shao Z, Li D (2015) Development of a multi-scale object-based shadow detection method for high spatial resolution image. Remote Sens Lett 6(1):59–68.  https://doi.org/10.1080/2150704X.2014.1001079 CrossRefGoogle Scholar
  18. Makarau A, Richter R, Muller R, Reinartz P (2011) Adaptive shadow detection using a blackbody radiator model. IEEE Trans Geosci Remote Sens 49(6):2049–2059.  https://doi.org/10.1109/TGRS.2010.2096515 CrossRefGoogle Scholar
  19. Manno-Kovacs A, Ok AO (2015) Building detection from monocular vhr images by integrated urban area knowledge. IEEE Geosci Remote Sens Lett 12(10):2140–2144.  https://doi.org/10.1109/LGRS.2015.2452962 CrossRefGoogle Scholar
  20. Movia A, Beinat A, Crosilla F (2016) Shadow detection and removal in rgb vhr images for land use unsupervised classification. ISPRS J Photogram Remote Sens 119:485–495.  https://doi.org/10.1016/j.isprsjprs.2016.05.004 CrossRefGoogle Scholar
  21. Nagao M, Matsuyama T, Ikeda Y (1979) Region extraction and shape analysis in aerial photographs. Comput Graph Image Process 10(3):195–223.  https://doi.org/10.1016/0146-664X(79),90001-7 CrossRefGoogle Scholar
  22. Ngo TT, Mazet V, Collet C, de Fraipont P (2017) Shape-based building detection in visible band images using shadow information. IEEE J Sel Top Appl Earth Obs Remote Sens 10(3):920–932.  https://doi.org/10.1109/JSTARS.2016.2598856 CrossRefGoogle Scholar
  23. Ok AO (2013) Automated detection of buildings from single VHR multispectral images using shadow information and graph cuts. ISPRS J Photogramm Remote Sens 86:21–40.  https://doi.org/10.1016/j.isprsjprs.2013.09.004 CrossRefGoogle Scholar
  24. Ok AO, Senaras C, Yuksel B (2013) Automated detection of arbitrarily shaped buildings in complex environments from monocular vhr optical satellite imagery. IEEE Trans Geosci Remote Sens 51(3):1701–1717.  https://doi.org/10.1109/TGRS.2012.2207123 CrossRefGoogle Scholar
  25. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66.  https://doi.org/10.1109/TSMC.1979.4310076 CrossRefGoogle Scholar
  26. Polidorio AM, Flores FC, Imai NN, Tommaselli AMG, Franco C (2003) Automatic shadow segmentation in aerial color images. In: 16th brazilian symposium on computer graphics and image processing (SIBGRAPI 2003), pp 270–277.  https://doi.org/10.1109/SIBGRA.2003.1241019
  27. Richter R, Muller A (2005) De-shadowing of satellite/airborne imagery. Int J Remote Sens 26(15):3137–3148.  https://doi.org/10.1080/01431160500114664 CrossRefGoogle Scholar
  28. Rother C, Kolmogorov V, Blake A (2004) “grabcut”: Interactive foreground extraction using iterated graph cuts. ACM Trans Graph 23(3):309–314.  https://doi.org/10.1145/1015706.1015720 CrossRefGoogle Scholar
  29. Senaras C, Vural FTY (2016) A self-supervised decision fusion framework for building detection. IEEE J Sel Top Appl Earth Obs Remote Sens 9(5):1780–1791.  https://doi.org/10.1109/JSTARS.2015.2463118 CrossRefGoogle Scholar
  30. Senaras C, Ozay M, Vural FTY (2013) Building detection with decision fusion. IEEE J Sel Top Appl Earth Obs Remote Sens 6(3):1295–1304.  https://doi.org/10.1109/JSTARS.2013.2249498 CrossRefGoogle Scholar
  31. Shi W, Mao Z (2016) Building extraction from panchromatic high-resolution remotely sensed imagery based on potential histogram and neighborhood total variation. Earth Sci Inform 9(4):497–509.  https://doi.org/10.1007/s12145-016-0262-6 CrossRefGoogle Scholar
  32. Silva GF, Carneiro GB, Doth R, Amaral LA, de Azevedo DF (2018) Near real-time shadow detection and removal in aerial motion imagery application. ISPRS J Photogramm Remote Sens 140:104–121.  https://doi.org/10.1016/j.isprsjprs.2017.11.005 CrossRefGoogle Scholar
  33. Tatar N, Saadatseresht M, Arefi H, Hadavand A (2018) A robust object-based shadow detection method for cloud-free high resolution satellite images over urban areas and water bodies. Adv Space Res 61(11):2787–2800.  https://doi.org/10.1016/j.asr.2018.03.011 CrossRefGoogle Scholar
  34. Teke M, Başeski E, Ok AO, Yüksel B, Şenaras c (2011) Multi-spectral false color shadow detection. In: Proceedings of the 2011 ISPRS conference on photogrammetric image analysis, PIA’11, Springer, Berlin, pp 109–119.  https://doi.org/10.1007/978-3-642-24393-6-10
  35. Tolt G, Shimoni M, Ahlberg J (2011) A shadow detection method for remote sensing images using vhr hyperspectral and lidar data. In: 2011 IEEE international geoscience and remote sensing symposium, pp 4423–4426.  https://doi.org/10.1109/IGARSS.2011.6050213
  36. Tsai VJD (2006) A comparative study on shadow compensation of color aerial images in invariant color models. IEEE Trans Geosci Remote Sens 44(6):1661–1671.  https://doi.org/10.1109/TGRS.2006.869980 CrossRefGoogle Scholar
  37. Tucker CJ (1979) Red and photographic infrared linear combinations for monitoring vegetation. Remote Sens Environ 8(2):127–150.  https://doi.org/10.1016/0034-4257(79)90013-0 CrossRefGoogle Scholar
  38. Volpi M, Ferrari V (2015) Semantic segmentation of urban scenes by learning local class interactions. In: 2015 IEEE conference on computer vision and pattern recognition workshops (CVPRW), pp 1–9.  https://doi.org/10.1109/CVPRW.2015.7301377
  39. Yang HL, Yuan J, Lunga D, Laverdiere M, Rose A, Bhaduri B (2018) Building extraction at scale using convolutional neural network: mapping of the united states. IEEE J Sel Top Appl Earth Obs Remote Sens.  https://doi.org/10.1109/JSTARS.2018.2835377 Google Scholar
  40. Zhou K, Gorte B (2017) Shadow detection from vhr aerial images in urban area by using 3 d city models and a decision fusion approach. In: The international archives of the photogrammetry, remote sensing and spatial information sciences, pp 579–586.  https://doi.org/10.5194/isprs-archives-XLII-2-W7-579-2017
  41. Zhu J, Samuel KGG, Masood SZ, Tappen MF (2010) Learning to recognize shadows in monochromatic natural images. In: 2010 IEEE Computer Society conference on computer vision and pattern recognition, pp 223–230.  https://doi.org/10.1109/CVPR.2010.5540209

Copyright information

© Deutsche Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation (DGPF) e.V. 2019

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringMaulana Azad National Institute of TechnologyBhopalIndia

Personalised recommendations