Advertisement

3D Research

, 9:51 | Cite as

A Self-Supervised Learning Method for Shadow Detection in Remote Sensing Imagery

  • Shoulin Yin
  • Jie Liu
  • Hang Li
3DR Express
  • 47 Downloads
Part of the following topical collections:
  1. Object detection and Recognition

Abstract

Recent research progress in shadow detection has leveraged the development of remote sensing and computer vision. Since shadows of buildings, trees, bridges in one image can provide useful information about the scene to help people understand the shape, feature or estimate their locations and orientations of original objects, especially for damaged objects. In this study, a novel shadow detection algorithm for remote sensing imagery, called self-supervised learning method is proposed. The aim of this work is to generate shadow ratio threshold automatically without human interaction. To alleviate the traditional drawbacks of shadow detection, we fully combine supervised and unsupervised shadow detection method to suggest a self-supervised learning method, which supports us a strongly clue with establishing the relation of shadow and its original object. Subsequently, we benefit from gray-scale histogram to extract shadow segments, then shadow outlines are obtained. Finally, we assess the shadow detection performance of the proposed approach by comparing our results with the state-of-the-art methods. The results reveal the applicability and precision of the proposed self-supervised learning shadow detection technique.

Keywords

Shadow detection Remote sensing Self-supervised learning Unsupervised information Gray-scale histogram 

References

  1. 1.
    Hu, F., Xia, G. S., Hu, J., et al. (2015). Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sensing, 7(11), 14680–14707.CrossRefGoogle Scholar
  2. 2.
    Wu, H., Cheng, Z., Shi, W., et al. (2014). An object-based image analysis for building seismic vulnerability assessment using high-resolution remote sensing imagery. Natural Hazards, 71(1), 151–174.CrossRefGoogle Scholar
  3. 3.
    Celie, B. M., Boone, J., Dumortier, J., et al., (2016). Possible influences on the interpretation of functional domain (FD) near-infrared spectroscopy (NIRS): An explorative study. Applied Spectroscopy, 70(2), 363.CrossRefGoogle Scholar
  4. 4.
    Gao, J., Li, J., & Li, Y. (2015). Approximate event detection over multi-modal sensing data. Journal of Combinatorial Optimization, 32(4), 1–15.MathSciNetGoogle Scholar
  5. 5.
    Gao, J., Li, J., Cai, Z., et al. (2015). Composite event coverage in wireless sensor networks with heterogeneous sensors. In Computer communications (pp. 217–225). IEEE.Google Scholar
  6. 6.
    Li, P., Chen, Z., Yang, L. T., et al. (2017). Deep convolutional computation model for feature learning on big data in internet of things. IEEE Transactions on Industrial Informatics, 14(2), 790–798.CrossRefGoogle Scholar
  7. 7.
    Huang, G., Song, S., Gupta, J. N. D., et al. (2017). Semi-supervised and unsupervised extreme learning machines. IEEE Transactions on Cybernetics, 44(12), 2405–2417.CrossRefGoogle Scholar
  8. 8.
    Thiagarajan, J. J., Ramamurthy, K. N., & Spanias, A. (2014). Multiple kernel sparse representations for supervised and unsupervised learning. IEEE Transactions on Image Processing, 23(7), 2905–2915.MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Volkovs, M. N., & Zemel, R. S. (2014). New learning methods for supervised and unsupervised preference aggregation. The Journal of Machine Learning Research, 15(1), 1135–1176.MathSciNetzbMATHGoogle Scholar
  10. 10.
    Le, H., Vicente, T. F. Y., Nguyen, V., et al. (2018). A+D net: Training a shadow detector with adversarial shadow attenuation. http://cn.arxiv.org/pdf/1712.01361.
  11. 11.
    Tian, J., Qi, X., Qu, L., et al. (2016). New spectrum ratio properties and features for shadow detection. Pattern Recognition, 51(C):, 85–96.CrossRefGoogle Scholar
  12. 12.
    Zhang, Q., Yang, L. T., Chen, Z., et al. (2017). PPHOPCM: Privacy-preserving high-order possibilistic c-Means algorithm for big data clustering with cloud computing. IEEE Transactions on Big Data.  https://doi.org/10.1109/TBDATA.2017.2701816.CrossRefGoogle Scholar
  13. 13.
    Zhang, Q., Yang, L. T., Chen, Z., et al. (2018). A survey on deep learning for big data. Information Fusion, 42, 146–157.CrossRefGoogle Scholar
  14. 14.
    Jia, K., Li, Q., Wei, X., et al. (2015). Multi-temporal remote sensing data applied in automatic land cover update using iterative training sample selection and Markov Random Field model. Geocarto International, 30(8), 1–12.CrossRefGoogle Scholar
  15. 15.
    Liu, Y., & Li, X. (2014). Domain adaptation for land use classification: A spatio-temporal knowledge reusing method. ISPRS Journal of Photogrammetry and Remote Sensing, 98, 133–144.CrossRefGoogle Scholar
  16. 16.
    Tahmoresnezhad, J., & Hashemi, S. (2016). Visual domain adaptation via transfer feature learning. Knowledge and Information Systems, 50, 1–21.Google Scholar
  17. 17.
    Zhang, L., Zuo, W., & Zhang, D. (2016). LSDT: Latent sparse domain transfer learning for visual adaptation. IEEE Transactions on Image Processing, 25(3), 1177–1191.MathSciNetCrossRefGoogle Scholar
  18. 18.
    Zhang, L., & Zhang, D. (2016). Robust visual knowledge transfer via extreme learning machine based domain adaptation. IEEE Transactions on Image Processing, 25(10), 4959–4973.MathSciNetCrossRefGoogle Scholar
  19. 19.
    Long, M., Wang, J., Ding, G., et al. (2014). Transfer joint matching for unsupervised domain adaptation. In Computer vision and pattern recognition (pp. 1410–1417). IEEE.Google Scholar
  20. 20.
    Cote, M., & Saeedi, P. (2013). Automatic rooftop extraction in nadir aerial imagery of suburban regions using corners and variational level set evolution. IEEE Transactions on Geoscience and Remote Sensing, 51(1), 313–328.CrossRefGoogle Scholar
  21. 21.
    Ok, A. O., Senaras, C., & Yuksel, B. (2013). Automated detection of arbitrarily shaped buildings in complex environments from monocular VHR optical satellite imagery. IEEE Transactions on Geoscience and Remote Sensing, 51(3), 1701–1717.CrossRefGoogle Scholar
  22. 22.
    Xia, H., Song, S., & He, L. (2016). A modified Gaussian mixture background model via spatiotemporal distribution with shadow detection. Signal, Image and Video Processing, 10(2), 343–350.CrossRefGoogle Scholar
  23. 23.
    Movia, A., Beinat, A., & Crosilla, F. (2016). Shadow detection and removal in RGB VHR images for land use unsupervised classification. ISPRS Journal of Photogrammetry and Remote Sensing, 119, 485–495.CrossRefGoogle Scholar
  24. 24.
    Ghimire, D., & Lee, J. (2016). Online sequential extreme learning machine-based co-training for dynamic moving cast shadow detection. Multimedia Tools and Applications, 75(18), 11181–11197.CrossRefGoogle Scholar
  25. 25.
    Wang, B., Zhu, W., Zhao, Y., et al. (2015). Moving cast shadow detection using joint color and texture features with neighboring information. Revised selected papers of the Psivt 2015 workshops on image and video technology (pp. 15–25). Springer, New York.CrossRefGoogle Scholar
  26. 26.
    Martelbrisson, N., & Zaccarin, A. (2005). Moving cast shadow detection from a Gaussian mixture shadow model (Vol. 2, pp. 643–648).Google Scholar
  27. 27.
    Tian, Y. M., & Wang, X. T. (2010). A fast convergent Gaussian mixture model in moving object detection with shadow elimination. In International conference on E-Product E-Service and E-Entertainment (pp. 1–4). IEEE.Google Scholar
  28. 28.
    Amato, A., Huerta, I., Mozerov, M. G., et al. (2014). Moving cast shadows detection methods for video surveillance applications. In V. K. Asari (Ed.), Wide area surveillance. Augmented vision and reality (Vol. 6, pp. 23–47). Berlin: Springer.CrossRefGoogle Scholar
  29. 29.
    Martel-Brisson, N., & Zaccarin, A. (2007). Learning and removing cast shadows through a multidistribution approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(7), 1133–46.CrossRefGoogle Scholar
  30. 30.
    Nia, M. S., Wang, Z. D., Gader, P. D., et al. (2015). Impact of atmospheric correction and image filtering on hyperspectral classification of tree species using support vector machine. Journal of Applied Remote Sensing, 9(1), 095990.CrossRefGoogle Scholar
  31. 31.
    Sabnis, M. K., & Shukla, M. K. (2016). Model-based approach for shadow detection of static images. In A. Chakrabarti, N. Sharma, & V. E. Balas (Eds.), Advances in computing applications. Singapore: Springer.Google Scholar
  32. 32.
    Wang, Q., Yan, L., Yuan, Q., et al. (2017). An automatic shadow detection method for VHR remote sensing orthoimagery. Remote Sensing, 9(5), 469.CrossRefGoogle Scholar
  33. 33.
    Sun, J., Tian, J., Du, Y., et al. (2009). Retinex theory-based shadow detection and removal in single outdoor image. Industrial Robot, 36(3), 263–269.CrossRefGoogle Scholar
  34. 34.
    Finlayson, G. D., Hordley, S. D., & Drew, M. S. (2002). Removing shadows from images. In Computer vision ECCV (pp. 823–836).CrossRefGoogle Scholar
  35. 35.
    Makarau, A., Richter, R., Muller, R., et al. (2011). Adaptive shadow detection using a blackbody radiator model. IEEE Transactions on Geoscience and Remote Sensing, 49(6), 2049–2059.CrossRefGoogle Scholar
  36. 36.
    Jung, C., Kim, W., & Kim, C. (2011). Detecting shadows from a single image. Optics Letters, 36(22), 4428.CrossRefGoogle Scholar
  37. 37.
    Khan, S., Bennamoun, M., Sohel, F., et al. (2016). Automatic shadow detection and removal from a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(3), 431–446.CrossRefGoogle Scholar
  38. 38.
    Safari, L., Amaro, P., Fritzche, S., et al. (2012). Relativistic total cross section and angular distribution for Rayleigh scattering by atomic hydrogen. Physics, 85(4), 1354–1362.Google Scholar
  39. 39.
    Finlayson, G. D., & Hordley, S. D. (2001). Color constancy at a pixel. Journal of the Optical Society of America a Optics Image Science and Vision, 18(2), 253.CrossRefGoogle Scholar
  40. 40.
    Onyango, C. M., & Marchant, J. A. (2002). Spectral invariance under daylight illumination changes. Journal of the Optical Society of America a Optics Image Science and Vision, 19(5), 840.CrossRefGoogle Scholar
  41. 41.
    Besbes, O., & Benazza-Benyahia, A. (2016). A novel video-based smoke detection method based on color invariants. In IEEE international conference on acoustics, speech and signal processing (pp. 1911–1915). IEEE.Google Scholar
  42. 42.
    Kviatkovsky, I., Adam, A., & Rivlin, E. (2013). Color invariants for person reidentification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1622–34.CrossRefGoogle Scholar
  43. 43.
    Teke, M., Baeski, E., Ok, A., et al. (2011). Multi-spectral false color shadow detection. In Photogrammetric image analysis (pp. 109–119). Berlin: Springer.CrossRefGoogle Scholar
  44. 44.
    Sirmacek, B., & Unsalan, C. (2009). Damaged building detection in aerial images using shadow information. In International conference on recent advances in space technologies (pp. 249–252). IEEE.Google Scholar
  45. 45.
    Ghimire, D., & Lee, J. (2016). Online sequential extreme learning machine-based co-training for dynamic moving cast shadow detection. Multimedia Tools and Applications, 75(18), 11181–11197.CrossRefGoogle Scholar
  46. 46.
    Senaras, C., & Vural, F. T. Y. (2016). A self-supervised decision fusion framework for building detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(5), 1780–1791.CrossRefGoogle Scholar
  47. 47.
    Khan, S. H., Bennamoun, M., & Sohel, F. (2016). Automatic shadow detection and removal from a single image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(3), 431–446.CrossRefGoogle Scholar
  48. 48.
    Blakey, T., Melesse, A., & Hall, M. (2015). Supervised classification of benthic reflectance in shallow subtropical waters using a generalized pixel-based classifier across a time series. Remote Sensing, 7(5), 5098–5116.CrossRefGoogle Scholar

Copyright information

© 3D Research Center, Kwangwoon University and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Software CollegeShenyang Normal UniversityShenyangChina

Personalised recommendations