Abstract
In order to solve the problem of detail-preserving and ghost-elimination in multi-exposure image fusion, this paper uses an improved Butterworth low-pass filter curve to determine the absolute exposure weight of each pixel in the input image, calculates the relative exposure weight based on the reference image according to the gradient direction information of the pixel, and proposes a moving-object correction method to detect and eliminate the pixels which change suddenly in the exposure sequence. Experimental results show that this algorithm can successfully generate fusion results with good performance, and can retain most of the details and texture information of the sequence while removing ghosts. In addition to the traditional image processing field, the algorithm can also be applied to mobile robot intelligent inspection and defect detection and other engineering fields which rely on image processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zheng, C., Li, Z., Yang, Y., Wu, S.: Single image brightening via multi-scale exposure fusion with hybrid learning. IEEE Trans. Circuits Syst. Video Technol. 31(4), 1425–1435 (2021)
Vanmali, A.V., Deshmukh, S.S., Gadre, V.M.: Low complexity detail preserving multi-exposure image fusion for images with balanced exposure. In: Proceedings of 2013 National Conference on Communications, New Delhi, India, 5–17 February 2013, pp. 1–5. IEEE (2013)
Zhang, W., Cham, W.K.: Gradient-directed composition of multi-exposure images. In: Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, California, USA, 13–18 June 2010, pp. 530–536. IEEE (2010)
Vanmali, A.V., Kelkar, S.G., Gadre, V.M.: Multi-exposure image fusion for dynamic scenes without ghost effect. In: Proceedings of 2015 Twenty First National Conference on Communications, Mumbai, India, 27 February–1 March 2015, pp. 1–6. IEEE (2015)
Li, Z., Wei, Z., Wen, C., et al.: Detail-enhanced multi-scale exposure fusion. IEEE Trans. Image Process. 26(3), 1243–1252 (2017)
Gallo, O., Gelfand, N., Chen, W., et al.: Artifact-free high dynamic range imaging. In: Proceedings of 2009 IEEE International Conference on Computational Photography, New York, San Francisco, CA, USA, 16–17 April 2009, pp. 1–7. IEEE (2009)
Qu, Z., Huang, X., Liu, L.: An improved algorithm of multi-exposure image fusion by detail enhancement. Multimedia Syst. 27(1), 33–44 (2020). https://doi.org/10.1007/s00530-020-00691-4
Yan, Q., Wang, B., Li, P., et al.: Ghost removal via channel attention in exposure fusion. Comput. Vis. Image Underst. 201, 103079 (2020)
Ma, K., Duanmu, Z., Zhu, H., et al.: Deep guided learning for fast multi-exposure image fusion. IEEE Trans. Image Process. 29, 2808–2819 (2020)
Hayat, N., Imran, M.: Ghost-free multi exposure image fusion technique using dense SIFT descriptor and guided filter. J. Vis. Commun. Image Represent. 62, 295–308 (2019)
Hayat, N., Imran, M.: Detailed and enhanced multi-exposure image fusion using recursive filter. Multimedia Tools Appl. 79(33–34), 25067–25088 (2020). https://doi.org/10.1007/s11042-020-09190-0
Acknowledgements
This work is supported by science and technology project of China Southern Power Grid Corporation (080007kk52180005).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liang, G., He, J., Luo, L., Liu, J., Xiong, G. (2022). An Efficient Anti-ghost Multiple Exposure Fusion with Detail Preserving. In: Li, X. (eds) Advances in Intelligent Automation and Soft Computing. IASC 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 80. Springer, Cham. https://doi.org/10.1007/978-3-030-81007-8_84
Download citation
DOI: https://doi.org/10.1007/978-3-030-81007-8_84
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81006-1
Online ISBN: 978-3-030-81007-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)