Abstract
This paper presents a GPU based parallel implementation for the non-uniform illumination image restoration method, which uses a retinex based algorithm to decompose the original image into brightness and reflectance components, and adjusts the brightness value through an adaptive gamma correction and nonparametric mapping to achieve the restoration. Specifically, we parallelize the improved retinex algorithm on GPU to extract the brightness value of each pixel. After that, the probability of different brightness range is counted through each block to the entire image to reduce the competition of memory access. Finally, we use two different parallel reduce methods to calculate the probability density and cumulative density of brightness value and generate the mapping curve. The experiment conducted on three different GPUs and two CPUs with different resolution images shows that our method can process a 1024 × 2048 image in 1.024 ms on RTX2080Ti, indicates a great potential for real-time application.
Similar content being viewed by others
References
Lee, S., et al.: A review on dark channel prior based image dehazing algorithms. Eurasip J. Image Video Process. 1, 4 (2016)
Berman, D., Treibitz, T., Avidan, S.: Non-local image dehazing. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
Kumar, A., et al.: Tchebichef moment based restoration of Gaussian blurred images. Appl. Opt. 55(32), 9006 (2016)
Stoker, D.S., et al.: Restoration and recognition of distant, blurry irises. Appl. Opt. 52(9), 1864–1875 (2013)
Ma, L., et al.: Region-confined restoration method for motion-blurred star image of the star sensor under dynamic conditions. Appl. Opt. 55(17), 4621 (2016)
Solachidis, V., Maiorana, E., Campisi, P.: HDR image multi-bit watermarking using bilateral-filtering-based masking. In: Proceedings of SPIE (2013)
Kim, K., Bae, J., Kim, J.: Natural HDR image tone mapping based on retinex. IEEE Trans. Consum. Electron. 57(4), 1807–1814 (2012)
Khan, I.R., et al.: HDR image tone mapping using histogram adjustment adapted to human visual system. In: International Conference on Information (2009)
Fang, C., Liao, Z., Yu, Y.: Piecewise flat embedding for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 99, 1 (2018)
Jie, T., et al.: A textured object recognition pipeline for color and depth image data. IEEE Int. Conf. Robot. Autom. 2012, 3467–3474 (2012)
Kong, Q.J., et al.: Efficient traffic state estimation for large-scale urban road networks. IEEE Trans. Intell. Transp. Syst. 14(1), 398–407 (2013)
Wu, X., et al.: Separable convolution template (SCT) background prediction accelerated by CUDA for infrared small target detection. Infrared Phys. Technol. 60, 300–305 (2013)
Yang, X., et al.: Implementing real-time RCF-Retinex image enhancement method using CUDA. J. Real Time Image Process. 16(1), 115–125 (2019)
Haythem, B., et al.: Fast generalized fourier descriptor for object recognition of image using CUDA. In: Computer Applications & Research IEEE (2014)
Yuan, Y., et al.: A fast single-image super-resolution method implemented with CUDA. J. Real Time Image Process. 16(1), 81–97 (2019)
Jalloul, M., Baydoun, M., Al-Alaoui, M.A.: Gauss-Newton image registration with CUDA. In: IEEE International Conference on Electronics IEEE (2012)
Haweel, R.T., El-Kilani, W.S., Ramadan, H.H.: Fast approximate DCT with GPU implementation for image compression. J. Vis. Commun. Image Represent. 40, 357–365 (2016)
Lamas-Rodríguez, J., et al.: GPU-accelerated level-set segmentation. J. Real Time Image Process. 12(1), 15–29 (2016)
Shin, Yonghun, Jeong, Soowoong, Lee, Sangkeun: Efficient naturalness restoration for non-uniform illumination images. IET Image Proc. 9(8), 662–671 (2015)
Reza, Ali M.: Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement. J. VLSI Signal Process. Syst. Signal Image Video Technol. 38(1), 35–44 (2004)
Park, J.S., Cho, N.I.: Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images. arXiv:1708.00636
Sheet, D., Garud, H., Suveer, A., Mahadevappa, M., Chatterjee, J.: Brightness preserving dynamic fuzzy histogram equalization. IEEE Trans. Consum. Electron. 56(4), 2475–2480 (2010)
Funding
National Science Foundation of China (61675160, 61705173, 51801142); Natural Science Foundation of Shaanxi Province (2018JQ5022, 2018JQ6004); Fundamental Research Funds for the Central University (JB180502, JBX170513); China Scholarship Council (201806960036) and 111 Project (B17035).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cheng, K., Yu, Y., Zhou, H. et al. GPU fast restoration of non-uniform illumination images. J Real-Time Image Proc 18, 75–83 (2021). https://doi.org/10.1007/s11554-020-00950-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-020-00950-7