Image defogging algorithm combining SLIC super-pixel segmentation and transmission optimization

Abstract

When images are captured under hazy conditions, light is attenuated and deflected by particle scattering, resulting in reduced brightness and color distortion, which affects the imaging quality of the visual system. This paper proposes a defogging method that combines super-pixel segmentation and transmission optimization. First, the complexity of the haze image was calculated using color entropy to adaptively determine the number of super-pixel blocks. The simple linear iterative clustering (SLIC) super-pixel segmentation method was used to obtain super-pixel blocks with the same features. And the super-pixel block with the highest score was selected as a candidate block to accurately estimate the atmospheric light value. Then, the transmission was estimated using the multiscale dark channel prior and the non-local haze-lines prior, and then the initial transmission after fusion was obtained by wavelet transform. In addition, a guided filter based on unsharp masking was introduced to further improve the transmission estimation accuracy. Finally, an atmospheric scattering model was used to invert the haze-free image. We have conducted a large number of quantitative and qualitative experiments on three datasets, and the results show that the proposed algorithm can achieve a better de-fogging effect, especially in the sky region, where the image restoration effect is more prominent.

Keywords

super-pixel blocks / atmospheric light value / multiscale dark channel prior / non-local haze-lines prior / transmission fusion / unsharpened masking

Acknowledgement

I would like to express my gratitude to the reviewers and editors.

Declaration of conflicting interests

The authors have no conflict of interests related to this publication.

References

[1] GOYAL B, DOGRA A, LEPCHA D C, et al. Recent advances in image dehazing: Formal analysis to automated approaches. Information Fusion, 2024, 104: 102151.

[2] WANG C, ZHANG Q, ZHANG H. A novel image visibility detection algorithm based on improved nonlocal fog line prior. Journal of Sensing Technology, 2022, 35(3): 342-348.

[3] NING B, YANG M. Real time video defogging algorithm based on multi-scale guided filtering. Journal of North University of China (Natural Science Edition), 2024, 45(4): 439-447.

[4] JIN T H, TAO Y Y, LI Z Y. Improved algorithm for dark channel a priori defogging based on super-pixel image segmentation. Electronics Letters, 2023, 51(1): 146-159.

[5] FU, Q Q, JING, C L, PEI, Y L, et al. Research on detail enhancement algorithm for underwater images based on unsharpened mask-guided filtering. Journal of Oceanography, 2020, 42(7): 130-138.

[6] MOHAN S, SIMON P. Underwater image enhancement based on histogram manipulation and multiscale fusion. Procedia Computer Science, 2020, 171: 941-950.

[7] DUTTA M K, SARKAR R K. Application of Retinex and histogram equalisation techniques for the restoration of faded and distorted artworks: a comparative analysis. Optik, 2023, 272: 170201.

[8] GAMINI S, KUMAR S S. Homomorphic filtering for the image enhancement based on fractional-order derivative and genetic algorithm. Computers and Electrical Engineering, 2023, 106: 108566.

[9] BABU G H, ODUGU V K, VENKATRAM N, et al. Development and performance evaluation of enhanced image dehazing method using deep learning networks. Journal of Visual Communication and Image Representation, 2023, 97: 103976.

[10] MUNIRAJ M, DHANDAPANI V. Underwater image enhancement by combining color constancy and dehazing based on depth estimation. Neurocomputing, 2021, 460: 211-230.

[11] ZHANG J L, YANG Y. End-to-end defogging algorithm based on fog layer feature extraction and augmentation network. Journal of Measurement Science and Instrumentation, 2023, 14(1): 45-54.

[12] BALLA P K, KUMAR A, PANDEY R. A 4-channelled hazy image input generation and deep learning-based single image dehazing. Journal of Visual Communication and Image Representation, 2024, 100: 104099.

[13] WANG X G, TIAN J W, YU Y L, et al. A modified atmospheric scattering model and degradation image clarification algorithm for haze environments. Optics Communications, 2024, 560: 130489.

[14] FAN H W, ZHANG C, CAO X G, et al. A method for dust fog removal and enhancement of low illumination environmental images based on segmentation fusion of dark and bright channels. Journal of Coal, 2024, 49(4): 2167-2178.

[15] XIE Y, JIA H Z, WANG T H, et al. A review of image defogging algorithms. Computer and Digital Engineering, 2022, 50(12): 2765-2774.

[16] HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior//2009 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2009, Miami, FL, USA. New York: IEEE, 2009: 1956-1963.

[17] EHSAN S M, IMRAN M, ULLAH A, et al. A single image dehazing technique using the dual transmission maps strategy and gradient-domain guided image filtering. IEEE Access, 2021, 9: 89055-89063.

[18] HUA Z, DING Y J, LI J J. Image dehazing using near-infrared information based on dark channel prior. Procedia Computer Science, 2021, 187: 18-23.

[19] ZHONG H J, LIAO Y P. Image defogging algorithm based on improved dark channel and adaptive tolerance. Chinese Journal of Liquid Crystals and Displays, 2022, 37(11): 1488-1497.

[20] DWIVEDI P, CHAKRABORTY S. Single image dehazing using extended local dark channel prior. Image and Vision Computing, 2023, 136: 104747.

[21] BERMAN D, TREIBITZ T, AVIDAN S. Non-local image dehazing//2016 IEEE Conference on Computer Vision and Pattern Recognition, June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE, 2016: 1674-1682.

[22] NIE X L, ZHANG C S, QIAN J B. Haze-lines optimized image defogging algorithm based on non-local prior. Journal of Optoelectronic.Laser, 2023, 34(2): 140-146.

[23] JIN K, LI G, ZHOU L, et al. Image dehazing using non-local haze-lines and multi-exposure fusion. Journal of Visual Communication and Image Representation, 2024, 101: 104145.

[24] HUANG W, WEI Y. Single image dehazing via color balancing and quad-decomposition atmospheric light estimation. Optik, 2023, 275: 170573.

[25] YADAV S K, SARAWADEKAR K. Robust multi-scale weighting-based edge-smoothing filter for single image dehazing. Pattern Recognition, 2024, 149: 110137.

[26] DI S H, LIAO M, ZHAO Y Q, et al. Image superpixel segmentation based on hierarchical multi-level LI-SLIC. Optics & Laser Technology, 2021, 135: 106703.

[27] LIANG H L, WANG Z Q, CUI P. Adaptive SLIC super-pixel segmentation algorithm based on Pearson’s correlation coefficient. Software Engineering, 2024, 27(3): 30-35.

[28] KARIM S, TONG G, LI J Y, et al. Current advances and future perspectives of image fusion: a comprehensive review. Information Fusion, 2023, 90: 185-217.

[29] LI B Y, REN W Q, FU D P, et al. Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 2019, 28(1): 492-505.

[30] SAHU G, SEAL A, KREJCAR O, et al. Single image dehazing using a new color channel. Journal of Visual Communication and Image Representation, 2021, 74: 103008.

[31] KUMARI A, SAHOO S K. A new fast and efficient dehazing and defogging algorithm for single remote sensing images. Signal Processing, 2024, 215: 109289.