Skip to main content
SpringerLink
Log in

Near-infrared shadow detection based on HDR image

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

High dynamic range images have higher contrast, which can provide more dynamic range and image details to reflect the visual effects in the real environment better, while dark objects tend to have higher near-infrared reflectivity in the near-infrared spectrum. After studying these two tasks in depth, we propose a novel method for detecting shadows based on high dynamic range images and near-infrared information. The proposed method takes advantage of the characteristics of high dynamic range images for pre-processing before shadow detection. The low dynamic range images are firstly converted into high dynamic range images by increasing the dynamic range and contrast enhancement, and then proceeding to the next step of shadow detection. In this way, we can further perform shadow detection on the basis of establishing an accurate and clear shadow map. The key point of shadow detection is to distinguish between shadows and dark objects, which can be improved by the near-infrared information of images. In the process of shadow detection, high dynamic range image obtained in the previous step and the corresponding near-infrared image undergo some operations to obtain a determined shadow map, which includes the process of images’ multiplication and division. Finally, the shadow mask is obtained through adaptive thresholding. Quantitative comparison and qualitative analysis show that our method is superior to other shadow detection methods in accuracy and computational efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Awad M, Elliethy A, Aly HA (2019) Adaptive near-infrared and visible fusion for fast image enhancement[J]. IEEE Trans Comput Imaging 6:408–418

    Article  Google Scholar 

  2. Brown M, Susstrunk S (2011) Multi-spectral SIFT for scene category recognition[c] CVPR 2011. IEEE, pp 177–184

  3. Chen Z, Zhu L, Wan L (2020) A multi-task mean teacher for semi-supervised shadow detection[C]// Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, pp 5611–5620

  4. Dawar J, Raheja P, Vashisth U et al (2020) Color balanced histogram equalization for image Enhancement[C]// 2020 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). IEEE, pp 1–4

  5. Deng JY, Chiang JC (2017) Multi-exposure images coding for efficient high dynamic range image compression[C]// 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS). IEEE, pp 554–558

  6. Ding B, Long C, Zhang L et al (2019) Argan: Attentive recurrent generative adversarial network for shadow detection and removal[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 10213–10222

  7. Farou B, Rouabhia H, Seridi H et al (2017) Novel approach for detection and removal of moving cast shadows based on RGB, HSV and YUV color spaces[J]. Comput Inf 36(4):837–856

    MathSciNet  MATH  Google Scholar 

  8. Fang H, Wei Y, Luo H et al (2019) Detection of building shadow in remote sensing imagery of urban areas with fine spatial resolution based on saturation and near-infrared information[J]. IEEE J Sel Top Appl Earth Observ Remote Sens 12(8):2695–2706

    Article  Google Scholar 

  9. Huo Y, Yang F (2016) High-dynamic range image generation from single low-dynamic range image[J]. IET Image Process 10(3):198–205

    Article  Google Scholar 

  10. Hou L, Vicente TFY, Hoai M et al (2019) Large scale shadow annotation and detection using lazy annotation and stacked CNNs[j]. IEEE Trans Pattern Anal Mach Intell 43(4):1337–1351

    Article  Google Scholar 

  11. Hu X, Zhu L, Fu CW et al (2018) Direction-aware spatial context features for shadow detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7454–7462

  12. Ibarra-Arenado MJ, Tjahjadi T, Perez-Oria J (2020) Shadow detection in still road images using chrominance properties of shadows and spectral power distribution of the illumination[J]. Sensors 20(4):1012

    Article  Google Scholar 

  13. Jang H, Bang K, Jang J et al (2020) Dynamic range expansion using cumulative histogram learning for high dynamic range image generation[J]. IEEE Access 8:38554–38567

    Article  Google Scholar 

  14. Jin Y, Xu W, Hu Z et al (2864) GSCA-UNEt: towards automatic shadow detection in urban aerial imagery with global-spatial-context attention module[J]. Remote Sens 12(17):2020

    Google Scholar 

  15. Johnson AK, Jiji CV (2015) Single shot high dynamic range imaging using histogram separation and exposure fusion[C]// 2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image processing and graphics (NCVPRIPG). IEEE, pp 1–4

  16. Kandhway P, Bhandari AK (2019) An optimal adaptive thresholding based sub-histogram equalization for brightness preserving image contrast enhancement[J]. Multidimen Syst Signal Process 30(4):1859–1894

    Article  Google Scholar 

  17. Kinoshita Y, Kiya H (2019) Deep inverse tone mapping using LDR based learning for estimating HDR images with absolute Luminance[J]

  18. Khekade A, Bhoyar K (2015) Shadow detection based on RGB and YIQ color models in color aerial images[C]// 2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE). IEEE, pp 144–147

  19. Lee S, An GH, Kang SJ (2018) Deep recursive hdri: Inverse tone mapping using generative adversarial networks[C]// Proceedings of the European Conference on Computer Vision (ECCV), pp 596–611

  20. Lee S, An GH, Kang SJ (2018) Deep chain hdri: Reconstructing a high dynamic range image from a single low dynamic range image[J]. IEEE Access 6:49913–49924

    Article  Google Scholar 

  21. Li J, Feng X, Fan H (2020) Saliency-based image correction for colorblind patients[J]. Comput Vis Media 6(2):169–189

    Article  Google Scholar 

  22. Li R, Wang C, Liu S et al (2021) UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data[J]. arXiv:2102.01850

  23. Li J, Feng X, Hua Z (2021) Low-light image enhancement via progressive-recursive network[J]. IEEE Trans Circ Syst Video Technol 31 (11):4227–4240

    Article  Google Scholar 

  24. Liu X, Zhang Y, Bao F et al (2020) Kernel-blending connection approximated by a neural network for image classification[J]. Comput Vis Media 6 (4):467–476

    Article  Google Scholar 

  25. Luo J, Qiu S, Jiang Y et al (2020) A Contribution Algorithm from LDRI to HDRI[J]. Int J Pattern Recogn Artif Intell 34(07):2059025

  26. Majeed SH, Isa NAM (2020) Iterated adaptive entropy-clip limit histogram equalization for poor contrast images[J]. IEEE Access 8:144218–144245

    Article  Google Scholar 

  27. Macedo MCF, Nascimento VP, Souza A (2020) Real-time shadow detection using multi-channel binarization and noise removal[J]. J Real-Time Image Proc 17(3):479–492

    Article  Google Scholar 

  28. Marnerides D, Bashford-Rogers T, Hatchett J et al (2018) Expandnet: A deep convolutional neural network for high dynamic range expansion from low dynamic range content[C]. Comput Graph Forum 37(2):37–49

    Article  Google Scholar 

  29. Mertens T, Kautz J, Van Reeth F (2009) Exposure fusion: A simple and practical alternative to high dynamic range photography[C]// Computer graphics forum. Oxford, UK: Blackwell Publishing Ltd 28(1):161–171

    Google Scholar 

  30. Mostafa Y, Abdelhafiz A (2017) Accurate shadow detection from high-resolution satellite images[J]. IEEE Geosci Remote Sens Lett 14(4):494–498

    Article  Google Scholar 

  31. Mohajerani S, Saeedi P (2019) Shadow detection in single RGB images using a context preserver convolutional neural network trained by multiple adversarial examples[J]. IEEE Trans Image Process 28(8):4117–4129

    Article  Google Scholar 

  32. Ning S, Xu H, Song L et al (2018) Learning an inverse tone mapping network with a generative adversarial regularizer[C]// 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 1383–1387

  33. Nguyen V, Yago Vicente TF, Zhao M et al (2017) Shadow detection with conditional generative adversarial networks[C]// Proceedings of the IEEE International Conference on Computer Vision, pp 4510–4518

  34. Nur SA, Ibrahim MM, Ali NM et al (2016) Vehicle detection based on underneath vehicle shadow using edge features[C]// 2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE). IEEE, pp 407–412

  35. Perez-Pellitero E, Catley-Chandar S, Leonardis A et al (2021) NTIRE 2021 challenge on high dynamic range imaging: Dataset, methods and results[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 691–700

  36. Qiu S, Li X, Huang Y et al (2020) New algorithm of response curve for fitting HDR image[J]. Int J Pattern Recogn Artif Intell 34(01):2054001

  37. Raveendranath A, Johnson AK (2016) Single shot high dynamic range imaging using power law transformation and exposure fusion[C]// 2016 International Conference on Communication Systems and Networks (ComNet). IEEE, pp 120–126

  38. Rufenacht D, Fredembach C, Susstrunk S (2013) Automatic and accurate shadow detection using near-infrared information[J]. IEEE Trans Pattern Anal Mach Intell 36(8):1672–1678

    Article  Google Scholar 

  39. Sharif ASM, Naqvi RA, Biswas M et al (2021) A two-stage deep network for high dynamic range image reconstruction[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 550–559

  40. Shao Q, Xu C, Zhou Y et al (2020) Cast shadow detection based on the YCbcr color space and topological cuts[J]. J Supercomput 76(5):3308–3326

    Article  Google Scholar 

  41. Sharma D, Singhai J (2019) An object-based shadow detection method for building delineation in high-resolution satellite images[J]. PFG-J Photogramm Remote Sens Geoinform Sci 87(3):103–118

    Google Scholar 

  42. Sheet D, Garud H, Suveer A et al (2010) Brightness preserving dynamic fuzzy histogram equalization[J]. IEEE Trans Consum Electron 56(4):2475–2480

    Article  Google Scholar 

  43. Shor Y, Lischinski D (2008) The shadow meets the mask: Pyramid-based shadow removal[C]. Comput Graph Forum. Oxford, UK: Blackwell Publishing Ltd 27(2):577–586

    Article  Google Scholar 

  44. Tian J, Qi X, Qu L et al (2016) New spectrum ratio properties and features for shadow detection[J]. Pattern Recogn 51:85–96

    Article  Google Scholar 

  45. Wang Q, Yan P, Yuan Y et al (2013) Multi-spectral saliency detection[J]. Pattern Recogn Lett 34(1):34–41

    Article  MathSciNet  Google Scholar 

  46. Wang J, Li X, Yang J (2018) Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1788–1797

  47. Wang T, Hu X, Wang Q et al (2020) Instance shadow detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 1880–1889

  48. Xie WH, Zhao JY, Hu YM (2015) Moving shadow detection algorithm using multiple features[C]// 2015 International Conference on Computer Science and Applications (CSA). IEEE, pp 95–98

  49. Yahya AA, Tan J, Su B et al (2019) Image noise reduction based on adaptive thresholding and clustering[J]. Multimed Tools Appl 78(11):15545–15573

    Article  Google Scholar 

  50. Yarlagadda SK, Zhu F (2018) A reflectance based method for shadow detection and removal[C]// 2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI). IEEE, pp 9–12

  51. YLin YH, Hua KL, Lu HH et al (2019) An adaptive exposure fusion method using fuzzy logic and multivariate normal conditional random Fields[J]. Sensors 19(21):4743

    Article  Google Scholar 

  52. Zhang X, Wang H, Zhang Y et al (2021) Improved fuzzy clustering for image segmentation based on a low-rank prior[J]. Comput Vis Media 7 (4):513–528

    Article  Google Scholar 

  53. Zhang T, Li J, Fan H (2022) Progressive edge-sensing dynamic scene deblurring[J]. Comput Vis Media:1–14

  54. Zheng Q, Qiao X, Cao y et al (2019) Distraction-aware shadow detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5167–5176

  55. Zhu L, Deng Z, Hu X et al (2018) Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection[C]// Proceedings of the European Conference on Computer Vision (ECCV), pp 121–136

  56. Zhu Q (2020) On the performance of Matthews correlation coefficient (MCC) for imbalanced dataset[J]. Pattern Recogn Lett 136:71–80

    Article  Google Scholar 

Download references

Acknowledgments

This research was supported by the National Natural Science Foundation of China (61772319, 62002200, 62176140, 12001327), Shandong Natural Science Foundation of China (ZR2020QF012, ZR2021MF068).

Author information

Authors and Affiliations

  1. School of Information and Electronic Engineering, Shandong Technology and Business University, Yantai, 264005, China

    Wanwan Zhang

  2. School of Computer Science and Technology, Shandong Technology and Business University, Yantai, 264005, China

    Jinjiang Li

  3. Institute of Network Technology, ICT, Yantai, 264005, China

    Zhen Hua

Authors
  1. Wanwan Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinjiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhen Hua
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jinjiang Li.

Ethics declarations

Conflict of Interests

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, W., Li, J. & Hua, Z. Near-infrared shadow detection based on HDR image. Multimed Tools Appl 81, 38459–38483 (2022). https://doi.org/10.1007/s11042-022-12996-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12996-9

Keywords

Search

Navigation