|
|
基于深度学习的图像去雾研究综述
|
Abstract:
恶劣天气环境下拍摄的图像会受到雾或霾的影响，从而导致图像饱和度过低模糊、以及颜色灰白等负面效果，这不仅会使图像中的重要信息丢失，还会对后续计算机视觉任务(如目标检测、图像分割、人员再识别)的研究造成负面影响。为了解决上述问题，文章首先对图像去雾的发展历程进行分析和梳理，接下来重点论述了深度学习在图像去雾领域的研究进展，主要包含有监督去雾、无监督去雾和半监督去雾技术，并对各自的代表性算法进行深入对比分析。最后，介绍了图像去雾领域主流的数据集和评估指标。
Images captured in harsh weather environments are often affected by fog or haze, which can lead to negative effects such as low saturation, blurring, and grayish-white colors. This not only results in the loss of important information in the image, but also has a negative impact on subsequent computer vision tasks such as object detection, image segmentation, and personnel re-identification. This article first provides a comprehensive analysis and sorting of image defogging and then reviews the research progress of deep learning in the field of image defogging, mainly including supervised defogging, unsupervised defogging, and semi-supervised defogging. We compared and analyzed representative algorithms among these methods. Finally, the commonly used datasets and evaluation metrics for image defogging were introduced.
| [1] | Sujeesh Kumar, J., Shiny, B. and Sugathan, P. (2021) Review Paper on Image Dehazing Techniques. International Journal of Engineering Research & Technology, 10, 7-9. |
| [2] | Joseph, J.E. and Gopakumar, G. (2021) A Comprehensive Review on Image Dehazing. International Journal of Engineering Research and Technology, 9, 1074-1077. |
| [3] | Parihar, A.S., Gupta, Y.K., Singodia, Y., Singh, V. and Singh, K. (2020) A Comparative Study of Image Dehazing Algorithms. 2020 5th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, 10-12 June 2020, 766-771. https://doi.org/10.1109/icces48766.2020.9138037 |
| [4] | Mahatma, H. (2021) Review on Single Image Dehazing Techniques. International Journal for Research in Applied Science and Engineering Technology, 9, 64-68. https://doi.org/10.22214/ijraset.2021.33168 |
| [5] | Ju, M., Ding, C., Zhang, D. and Guo, Y.J. (2018) Gamma-Correction-Based Visibility Restoration for Single Hazy Images. IEEE Signal Processing Letters, 25, 1084-1088. https://doi.org/10.1109/lsp.2018.2839580 |
| [6] | 吴成茂. 直方图均衡化的数学模型研究[J]. 电子学报, 2013, 41(3): 598-602. |
| [7] | 陈国强, 徐丽, 于雷, 等. 中国人工智能产品的设计评价现状与发展趋势研究综述[J]. 包装工程, 2023, 44(12): 16-28, 117. |
| [8] | Yugander, P., Tejaswini, C.H., Meenakshi, J., kumar, K.S., Varma, B.V.N.S. and Jagannath, M. (2020) MR Image Enhancement Using Adaptive Weighted Mean Filtering and Homomorphic Filtering. Procedia Computer Science, 167, 677-685. https://doi.org/10.1016/j.procs.2020.03.334 |
| [9] | Jobson, D.J. (2004) Retinex Processing for Automatic Image Enhancement. Journal of Electronic Imaging, 13, 100-110. https://doi.org/10.1117/1.1636183 |
| [10] | Li, C., Liu, J., Liu, A., Wu, Q. and Bi, L. (2019) Global and Adaptive Contrast Enhancement for Low Illumination Gray Images. IEEE Access, 7, 163395-163411. https://doi.org/10.1109/access.2019.2952545 |
| [11] | Stark, J.A. (2000) Adaptive Image Contrast Enhancement Using Generalizations of Histogram Equalization. IEEE Transactions on Image Processing, 9, 889-896. https://doi.org/10.1109/83.841534 |
| [12] | Stimper, V., Bauer, S., Ernstorfer, R., Scholkopf, B. and Xian, R.P. (2019) Multidimensional Contrast Limited Adaptive Histogram Equalization. IEEE Access, 7, 165437-165447. https://doi.org/10.1109/access.2019.2952899 |
| [13] | Adhikari, S. and Panday, S.P. (2019) Image Enhancement Using Successive Mean Quantization Transform and Homomorphic Filtering. 2019 Artificial Intelligence for Transforming Business and Society (AITB), Kathmandu, 5 November 2019, 1-5. https://doi.org/10.1109/aitb48515.2019.8947437 |
| [14] | Land, E.H. (1977) The Retinex Theory of Color Vision. Scientific American, 237, 108-128. https://doi.org/10.1038/scientificamerican1277-108 |
| [15] | Choi, D.H., Jang, I.H., Kim, M.H. and Kim, N.C. (2008) Color Image Enhancement Using Single-Scale Retinex Based on an Improved Image Formation Model. 2008 16th European Signal Processing Conference, 25-29 August 2008, Lausanne, 1-5. |
| [16] | Jobson, D.J., Rahman, Z. and Woodell, G.A. (1997) A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes. IEEE Transactions on Image Processing, 6, 965-976. https://doi.org/10.1109/83.597272 |
| [17] | He, K.M., Sun, J. and Tang, X.O. (2009) Single Image Haze Removal Using Dark Channel Prior. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, 20-25 June 2009, 1956-1963. https://doi.org/10.1109/cvpr.2009.5206515 |
| [18] | Liu, C., Zhao, J., Shen, Y., Zhou, Y., Wang, X. and Ouyang, Y. (2016) Texture Filtering Based Physically Plausible Image Dehazing. The Visual Computer, 32, 911-920. https://doi.org/10.1007/s00371-016-1259-3 |
| [19] | Ju, M., Ding, C., Guo, Y.J. and Zhang, D. (2020) IDGCP: Image Dehazing Based on Gamma Correction Prior. IEEE Transactions on Image Processing, 29, 3104-3118. https://doi.org/10.1109/tip.2019.2957852 |
| [20] | Berman, D., Treibitz, T. and Avidan, S. (2020) Single Image Dehazing Using Haze-Lines. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 720-734. https://doi.org/10.1109/tpami.2018.2882478 |
| [21] | 张然. 基于分数阶偏微分方程的雾天图像增强算法[D]: [硕士学位论文]. 西安: 西安理工大学, 2018. |
| [22] | Cai, B., Xu, X., Jia, K., Qing, C. and Tao, D. (2016) Dehazenet: An End-to-End System for Single Image Haze Removal. IEEE Transactions on Image Processing, 25, 5187-5198. https://doi.org/10.1109/tip.2016.2598681 |
| [23] | Liu, X., Ma, Y., Shi, Z. and Chen, J. (2019) GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 7313-7322. https://doi.org/10.1109/iccv.2019.00741 |
| [24] | Zheng, Z., Ren, W., Cao, X., Hu, X., Wang, T., Song, F., et al. (2021). Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 16180-16189. https://doi.org/10.1109/cvpr46437.2021.01592 |
| [25] | Engin, D., Genc, A. and Ekenel, H.K. (2018) Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, 18-22 June 2018, 938 https://doi.org/10.1109/cvprw.2018.00127 |
| [26] | Golts, A., Freedman, D. and Elad, M. (2020) Unsupervised Single Image Dehazing Using Dark Channel Prior Loss. IEEE Transactions on Image Processing, 29, 2692-2701. https://doi.org/10.1109/tip.2019.2952032 |
| [27] | Yang, Y., Wang, C., Liu, R., Zhang, L., Guo, X. and Tao, D. (2022) Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 18-24 June 2022, 2027-2036. https://doi.org/10.1109/cvpr52688.2022.00208 |
| [28] | Chen, Z., Wang, Y., Yang, Y. and Liu, D. (2021) PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 7176-7185. https://doi.org/10.1109/cvpr46437.2021.00710 |
| [29] | Li, L., Dong, Y., Ren, W., Pan, J., Gao, C., Sang, N., et al. (2020) Semi-Supervised Image Dehazing. IEEE Transactions on Image Processing, 29, 2766-2779. https://doi.org/10.1109/tip.2019.2952690 |
| [30] | Li, B., Peng, X., Wang, Z., Xu, J. and Feng, D. (2017) AOD-Net: All-in-One Dehazing Network. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 4780-4788. https://doi.org/10.1109/iccv.2017.511 |
| [31] | Li, L., Dong, Y., Ren, W., Pan, J., Gao, C., Sang, N., et al. (2020) Semi-Supervised Image Dehazing. IEEE Transactions on Image Processing, 29, 2766-2779. https://doi.org/10.1109/tip.2019.2952690 |
| [32] | Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., et al. (2019) Benchmarking Single-Image Dehazing and Beyond. IEEE Transactions on Image Processing, 28, 492-505. https://doi.org/10.1109/tip.2018.2867951 |
| [33] | Ancuti, C., Ancuti, C.O. and De Vleeschouwer, C. (2016) D-HAZY: A Dataset to Evaluate Quantitatively Dehazing Algorithms. 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, 25-28 September 2016, 2226-2230. https://doi.org/10.1109/icip.2016.7532754 |
| [34] | Ancuti, C., Ancuti, C.O., Timofte, R., De Vleeschouwer, C. (2018) I-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Indoor Images. In: Blanc-Talon, J., Helbert, D., Philips, W., Popescu, D. and Scheunders, P., Eds., Advanced Concepts for Intelligent Vision Systems, ACIVS 2018, Springer, 620-631. https://doi.org/10.1007/978-3-030-01449-0_52 |
| [35] | Ancuti, C.O., Ancuti, C., Timofte, R. and De Vleeschouwer, C. (2018) O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, 18-22 June 2018, 867-8678. https://doi.org/10.1109/cvprw.2018.00119 |
| [36] | Ancuti, C.O., Ancuti, C. and Timofte, R. (2020) NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, 14-19 June 2020, 1798-1805. https://doi.org/10.1109/cvprw50498.2020.00230 |
| [37] | Liu, W., Hou, X., Duan, J. and Qiu, G. (2020) End-to-End Single Image Fog Removal Using Enhanced Cycle Consistent Adversarial Networks. IEEE Transactions on Image Processing, 29, 7819-7833. https://doi.org/10.1109/tip.2020.3007844 |
| [38] | Zhao, S., Zhang, L., Huang, S., Shen, Y. and Zhao, S. (2020) Dehazing Evaluation: Real-World Benchmark Datasets, Criteria, and Baselines. IEEE Transactions on Image Processing, 29, 6947-6962. https://doi.org/10.1109/tip.2020.2995264 |
