霧霾除了危害人體健康外，同時也造成能見度降低，使自駕系統中影像視覺相關演算法性能降低，若無法正確偵測周遭物體，將有可能造成危險。因此，為避免交通事故發生，在輸入這些演算法前需要做影像去霾是極為關鍵的。早期研究主要以事先統計的經驗來解決此問題，但隨著電腦硬體製程技術提升，近年研究採用的方式則是使用深度學習(Deep Learning)來達到更佳的影像去霾品質。本文是基於深度學習應用於影像復原的概念來設計適合用於單一影像去霾(Single Image Dehazing)的網路模塊。由於生成對抗網路(Generative Adversarial Network, GAN)所需的訓練時間較長，且不易達成好的影像去霾效果，因此，本文採監督式學習(Supervised Learning)解決此問題，將不同的網路模塊導入U-Net架構，在其編碼器(Encoder)與解碼器(Decoder)中加入類感受模塊(Inception-Like Block)、空間金字塔池化模塊(Spatial Pyramid Pooling, SPP)與關注閘(Attention Gate, AG)。另外，在輸入影像去霾模型中除了透過影像正規化(Image Normalization)作預處理外，亦擴展輸入的色彩空間，保留不同色彩空間的優勢，提高模型最終輸出的去霾品質。最後以現有室內外測試資料集與其他網路模型進行影像去霾品質比較，並同時考慮模型可訓練的參數量，達成輕巧且即時的影像去霾模型。

In recent decades, haze has become an environmental issue owing to its effects on human health. It also reduces visibility and degrades the performance of computer vision algorithms in autonomous driving applications, which may jeopardize car driving safety. Therefore, it is extremely important to instantly remove the haze effect on an image. The purpose of this study is to leverage useful modules to achieve lightweight and real-time image dehazing model. Based on the U-Net architecture, this study integrates four modules including image pre-processing block, inception-like blocks, spatial pyramid pooling blocks, and attention gates. The original attention gate was revised to fit the field of image dehazing and consider different color spaces to retain the advantages of each color space. Furthermore, using ablation study and quantitative evaluation, the advantages of using these modules were illustrated. Through existing indoor and outdoor test datasets, the proposed method shows outstanding dehazing quality and efficient execution time compared to other state-of-the-art methods. This study demonstrates that the proposed model can improve dehazing quality, keep the model lightweight, and obtain pleasing dehazing result. A comparison to existing methods using RESIDE SOTS dataset revealed that the proposed model improves SSIM and PSNR metrics by about 5-10% at least.

1. F. Cozman and E. Krotkov, "Depth from scattering," in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997, pp. 801-806.
2. O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Cham, 2015: Springer International Publishing, pp. 234-241.
3. A. Mehra, P. Narang, and M. Mandal, "TheiaNet: Towards fast and inexpensive CNN design choices for image dehazing," Journal of Visual Communication and Image Representation, vol. 77, p. 103137, 2021/05/01/ 2021.
4. K. He, J. Sun, and X. Tang, "Single Image Haze Removal Using Dark Channel Prior," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341-2353, 2011.
5. Q. Zhu, J. Mai, and L. Shao, "A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior," IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 3522-3533, 2015.
6. A. Mehra, M. Mandal, P. Narang, and V. Chamola, "ReViewNet: A Fast and Resource Optimized Network for Enabling Safe Autonomous Driving in Hazy Weather Conditions," IEEE Transactions on Intelligent Transportation Systems, vol. PP, pp. 1-11, 08/14 2020.
7. J. Gui et al., "A Comprehensive Survey on Image Dehazing Based on Deep Learning," arXiv preprint arXiv:2106.03323, 2021.
8. R. T. Tan, "Visibility in bad weather from a single image," in 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1-8.
9. D. Berman, T. Treibitz, and S. Avidan, "Non-local Image Dehazing," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1674-1682.
10. M. Ju, C. Ding, W. Ren, Y. Yang, D. Zhang, and Y. J. Guo, "IDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model," IEEE Transactions on Image Processing, vol. 30, pp. 2180-2192, 2021.
11. G. Yang and A. N. Evans, "Improved single image dehazing methods for resource-constrained platforms," Journal of Real-Time Image Processing, vol. 18, no. 6, pp. 2511-2525, 2021/12/01 2021.
12. D. Engin, A. Genç, and H. Kemal Ekenel, "Cycle-dehaze: Enhanced cyclegan for single image dehazing," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, pp. 825-833.
13. J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2223-2232.
14. Y. Qu, Y. Chen, J. Huang, and Y. Xie, "Enhanced Pix2pix Dehazing Network," in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8152-8160.
15. A. Mehta, H. Sinha, P. Narang, and M. Mandal, "HIDeGan: A Hyperspectral-guided Image Dehazing GAN," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, pp. 846-856.
16. M. Mirza and S. Osindero, "Conditional generative adversarial nets," arXiv preprint arXiv:1411.1784, 2014.
17. B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, "Dehazenet: An end-to-end system for single image haze removal," IEEE Transactions on Image Processing, vol. 25, no. 11, pp. 5187-5198, 2016.
18. B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng, "AOD-Net: All-in-One Dehazing Network," in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4780-4788.
19. J. Zhang and D. Tao, "FAMED-Net: A fast and accurate multi-scale end-to-end dehazing network," IEEE Transactions on Image Processing, vol. 29, pp. 72-84, 2019.
20. X. Qin, Z. Wang, Y. Bai, X. Xie, and H. Jia, "FFA-Net: Feature fusion attention network for single image dehazing," in Proceedings of the AAAI Conference on Artificial Intelligence, 2020, vol. 34, no. 07, pp. 11908-11915.
21. Z. Liu, B. Xiao, M. Alrabeiah, K. Wang, and J. Chen, "Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network," IEEE Signal Processing Letters, vol. 26, no. 6, pp. 833-837, 2019.
22. W. Ren et al., "Gated fusion network for single image dehazing," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3253-3261.
23. Y. Wan and Q. Chen, "Joint image dehazing and contrast enhancement using the HSV color space," in 2015 Visual Communications and Image Processing (VCIP), 2015, pp. 1-4.
24. Z. Tufail, K. Khurshid, A. Salman, I. F. Nizami, K. Khurshid, and B. Jeon, "Improved Dark Channel Prior for Image Defogging Using RGB and YCbCr Color Space," IEEE Access, vol. 6, pp. 32576-32587, 2018.
25. Y. Liu and G. Zhao, "Pad-net: A perception-aided single image dehazing network," arXiv preprint arXiv:1805.03146, 2018.
26. H. Zhang, V. Sindagi, and V. M. Patel, "Multi-scale Single Image Dehazing Using Perceptual Pyramid Deep Network," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018, pp. 1015-101509.
27. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
28. B. Li et al., "RESIDE: A Benchmark for Single Image Dehazing," 12/12 2017.
29. K. He, X. Zhang, S. Ren, and J. Sun, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 9, pp. 1904-1916, 2015.
30. N. Ibtehaz and M. S. Rahman, "MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation," Neural Networks, vol. 121, pp. 74-87, 2020.
31. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818-2826.
32. O. Oktay et al., "Attention u-net: Learning where to look for the pancreas," arXiv preprint arXiv:1804.03999, 2018.
33. A. Lou, S. Guan, and M. H. Loew, "DC-UNet: rethinking the U-Net architecture with dual channel efficient CNN for medical image segmentation," in Medical Imaging 2021: Image Processing, 2021, vol. 11596: International Society for Optics and Photonics, p. 115962T.
34. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
35. S. Zhao, L. Zhang, S. Huang, Y. Shen, and S. Zhao, "Dehazing Evaluation: Real-World Benchmark Datasets, Criteria, and Baselines," IEEE Transactions on Image Processing, vol. 29, pp. 6947-6962, 2020.
36. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "Yolov4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.