Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing
Source abstract
Abstract
In recent decades, haze has become an environmental issue due 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 a lightweight and real-time image-dehazing model. Based on the U-Net architecture, this study integrates four modules, including an 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 an ablation study and a 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 an 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 results. A comparison to existing methods using the RESIDE SOTS dataset revealed that the proposed model improves the SSIM and PSNR metrics by at least 5–10%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Video Surveillance and Tracking Methods · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Aeronautics and Astronautics, National Cheng Kung University, Tainan 70101, Taiwan
Funding
Ministry of Science and Technology, Taiwan
References (30)
Show source-provided references
1. Gui, J., Cong, X., Cao, Y., Ren, W., Zhang, J., Zhang, J., and Tao, D. (2021). A Comprehensive Survey on Image Dehazing Based on Deep Learning. arXiv.10.24963/ijcai.2021/604 ↗
2. Cozman, F., and Krotkov, E. (1997, January 17–19). Depth from scattering. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA.
3. Tan, R.T. (2008, January 23–28). Visibility in bad weather from a single image. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587643 ↗
4. Single Image Haze Removal Using Dark Channel Prior10.1109/TPAMI.2010.168 ↗
5. A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior10.1109/TIP.2015.2446191 ↗
6. Berman, D., Treibitz, T., and Avidan, S. (2016, January 27–30). Non-local Image Dehazing. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.185 ↗
7. IDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model10.1109/TIP.2021.3050643 ↗
8. Improved single image dehazing methods for resource-constrained platforms10.1007/s11554-021-01143-6 ↗
9. Dehazenet: An end-to-end system for single image haze removal10.1109/TIP.2016.2598681 ↗
10. Li, B., Peng, X., Wang, Z., Xu, J., and Feng, D. (2017, January 22–29). AOD-Net: All-in-One Dehazing Network. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.511 ↗
11. FAMED-Net: A fast and accurate multi-scale end-to-end dehazing network10.1109/TIP.2019.2922837 ↗
12. Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2020, January 7–12). FFA-Net: Feature fusion attention network for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NJ, USA.10.1609/aaai.v34i07.6865 ↗
13. Single Image Dehazing with a Generic Model-Agnostic Convolutional Neural Network10.1109/LSP.2019.2910403 ↗
14. Engin, D., Genç, A., and Ekenel, H.K. (2018, January 18–22). Cycle-dehaze: Enhanced cyclegan for single image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA.10.1109/CVPRW.2018.00127 ↗
15. Zhu, J.-Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.244 ↗
16. Qu, Y., Chen, Y., Huang, J., and Xie, Y. (2019, January 15–20). Enhanced Pix2pix Dehazing Network. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00835 ↗
17. Mehta, A., Sinha, H., Narang, P., and Mandal, M. (2020, January 14–19). HIDeGan: A Hyperspectral-guided Image Dehazing GAN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00114 ↗
18. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
19. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Munich, Germany, 5–9 October 2015, Springer International Publishing.10.1007/978-3-319-24574-4_28 ↗
20. TheiaNet: Towards fast and inexpensive CNN design choices for image dehazing10.1016/j.jvcir.2021.103137 ↗
21. Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., and Yang, M.-H. (2018, January 18–23). Gated fusion network for single image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00343 ↗
22. Wan, Y., and Chen, Q. (2015, January 13–16). Joint image dehazing and contrast enhancement using the HSV color space. Proceedings of the 2015 Visual Communications and Image Processing (VCIP), Singapore.10.1109/VCIP.2015.7457892 ↗
23. Improved Dark Channel Prior for Image Defogging Using RGB and YCbCr Color Space10.1109/ACCESS.2018.2843261 ↗
24. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
25. MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation10.1016/j.neunet.2019.08.025 ↗
26. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
27. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.
28. ReViewNet: A Fast and Resource Optimized Network for Enabling Safe Autonomous Driving in Hazy Weather Conditions10.1109/TITS.2020.3013099 ↗
29. Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., and Wang, Z. (2017). RESIDE: A Benchmark for Single Image Dehazing. arXiv.
30. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.