-
摘要:
雾天情况下获得的图像通常会出现对比度低、色彩丢失及噪声等问题,传统的去雾方法主要着眼于解决对比度低、色彩损失等问题,而没有考虑空气中灰尘颗粒散射隐藏的噪声光,导致去雾结果中易出现大量的噪声。针对该问题,提出了一种基于改进大气散射模型的单幅图像去雾方法。结合雾霾天气的特点,通过增加空气中介质散射的噪声光对传统雾天成像的大气散射模型进行改进;针对暗通道先验计算透射率不准确的问题,根据改进的模型构建一种透射率精细化的求取方法;结合全变分模型保边抑噪的思想,构造一种新的目标函数,迭代求解获得去雾图像。实验结果和对比分析表明:所提方法能有效去除图像中的雾,减少去雾结果中的噪声,同时也能保留图像中丰富的纹理信息。
Abstract:Images obtained in foggy conditions often suffer from low contrast, color loss, and noise. At present, many traditional dehazing methods mainly focus on solving problems such as low contrast and color loss, but do not consider the hidden noise light scattered by dust particles in the air, resulting in a large amount of noise in the dehazing results. This work provides an image dehazing algorithm based on an enhanced atmospheric scattering model to address the mentioned problems. Firstly, according to the characteristics of haze, the traditional atmospheric scattering model of hazy imaging is improved by adding the noise light reflected by the medium in the air. Then, in order to address the transmission calculation inaccuracy problem for the dark channel prior, a refined calculation method of transmission is constructed according to the improved model. Finally, combined with the idea of edge preservation and noise suppression of the total variation model, a new objective function is constructed and solved iteratively to obtain the final defogging image. A large number of experimental results and comparative analyses show that the proposed method can effectively remove the haze in the image, reduce the noise in the dehazing results, and retain the rich texture information in the image.
-
表 1 不同方法在HSTS数据集上的SSIM、PSNR、CIEDE2000值对比
Table 1. Comparison of SSIM, PSNR and CIEDE2000 values of different methods on HSTS dataset
表 2 不同方法在SOTS室外数据集上的SSIM、PSNR、CIEDE2000值对比
Table 2. Comparison of SSIM, PSNR and CIEDE2000 values of different methods on SOTS outdoor dataset
表 3 不同方法在SOTS室内数据集上的SSIM、PSNR、CIEDE2000值对比
Table 3. Comparison of SSIM, PSNR and CIEDE2000 values of different methods on SOTS indoor dataset
表 4 SOTS室外数据集上的消融实验
Table 4. Ablation experiments on SOTS outdoor dataset
方法 改进透射率求取 新的目标函数 SSIM PSNR CIEDE2000 基准 × × 0.753 7 14.65 13.90 方法1 √ × 0.868 5 19.38 8.29 方法2 × √ 0.813 3 15.76 11.59 本文方法 √ √ 0.873 0 19.39 8.26 注:黑体数据表示最优结果。 -
[1] ZHANG J, TAO D C. FAMED-Net: A fast and accurate multi-scale end-to-end dehazing network[J]. IEEE Transactions on Image Processing, 2019, 29: 72-84. [2] SALAZAR-COLORES S, CABAL-YEPEZ E, RAMOS-ARRE-GUIN J M, et al. A fast image dehazing algorithm using morphological reconstruction[J]. IEEE Transactions on Image Processing, 2019, 28(5): 2357-2366. doi: 10.1109/TIP.2018.2885490 [3] GALDRAN A. Image dehazing by artificial multiple-exposure image fusion[J]. Signal Processing, 2018, 149: 135-147. doi: 10.1016/j.sigpro.2018.03.008 [4] HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(12): 2341-2353. [5] LU Z W, LONG B Y, YANG S Q. Saturation based iterative approach for single image dehazing[J]. IEEE Signal Processing Letters, 2020, 27: 665-669. doi: 10.1109/LSP.2020.2985570 [6] YANG Y, WANG Z W. Haze removal: Push DCP at the edge[J]. IEEE Signal Processing Letters, 2020, 27: 1405-1409. doi: 10.1109/LSP.2020.3013741 [7] MENG G F, WANG Y, DUAN J Y, et al. Efficient image dehazing with boundary constraint and contextual regularization[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2013: 617-624. [8] BERMAN D, AVIDAN S. Non-local image dehazing[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2016: 1674-1682. [9] LIU X H, MA Y R, SHI Z H, et al. GridDehazeNet: Attention-based multi-scale network for image dehazing[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE Press, 2019: 7314-7323. [10] CHEN D D, HE M M, FAN Q N, et al. Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE Press, 2019: 1375-1383. [11] HONG M, XIE Y, LI C H, et al. Distilling image dehazing with heterogeneous task imitation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2020: 3462-3471. [12] DONG H, PAN J S, XIANG L, et al. Multi-scale boosted dehazing network with dense feature fusion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2020: 2157-2167. [13] HUANG S Y, LI H X, YANG Y, et al. An end-to-end dehazing network with transitional convolution layer[J]. Multidimensional Systems and Signal Processing, 2020, 31(4): 1603-1623. doi: 10.1007/s11045-020-00723-2 [14] YANG H H, YANG C H H, TSAI Y C J. Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazing[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE Press, 2020: 2628-2632. [15] DONG Y, LIU Y H, ZHANG H, et al. FD-GAN: Generative adversarial networks with fusion-discriminator for single image dehazing[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020, 34(7): 10729-10736. [16] WU H, QU Y, LIN S, et al. Contrastive learning for compact single image dehazing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2021: 10551-10560. [17] SHAO Y, LI L, REN W, et al. Domain adaptation for image dehazing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2020: 2808-2817. [18] WU Q B, ZHANG J G, REN W Q, et al. Accurate transmission estimation for removing haze and noise from a single image[J]. IEEE Transactions on Image Processing, 2019, 29: 2583-2597. [19] NAYAR S K, NARASIMHAN S G. Vision in bad weather[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 1999, 2: 820-827. [20] GASTAL E S L, OLIVEIRA M M. Domain transform for edge-aware image and video processing[M]. New York: ACM, 2011: 1-12. [21] CHOI L K, YOU J, BOVIK A C. Referenceless prediction of perceptual fog density and perceptual image defogging[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3888-3901. doi: 10.1109/TIP.2015.2456502 [22] RUDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms[J]. Physica D: Nonlinear Phenomena, 1992, 60(1-4): 259-268. doi: 10.1016/0167-2789(92)90242-F [23] CHEN Q, MONTESINOS P, SUN Q S, et al. Adaptive total variation denoising based on difference curvature[J]. Image and Vision Computing, 2010, 28(3): 298-306. doi: 10.1016/j.imavis.2009.04.012 [24] SHIN J, KIM M, PAIK J, et al. Radiance-reflectance combined optimization and structure-guided l0-norm for single image dehazing[J]. IEEE Transactions on Multimedia, 2019, 22(1): 30-44. [25] LI B Y, REN W Q, FU D P, et al. Benchmarking single-image dehazing and beyond[J]. IEEE Transactions on Image Processing, 2018, 28(1): 492-505.