Multi-Feature Fusion ECANet-Based Adaptive Dehazing Algorithm for Aerial Images
DOI:
https://doi.org/10.54097/9epdb545Keywords:
Image Dehazing, Feature Extraction, Multi-feature Fusion, ECANet, GammaAbstract
Aiming at the problems of blurred details, insufficient utilization of multi-scale features, brightness shift and color distortion in aerial hazy images, this paper proposes a multi-feature fusion attention-based adaptive dehazing network (MFFAMA-Net), which is composed of three cascaded modules, feature extraction, multi-feature fusion attention and adaptive brightness correction. The feature extraction module preserves shallow edge and texture details, and adopts three-branch parallel multi-scale convolutions to enlarge the receptive field level by level while keeping the number of channels constant, with skip connections linking the shallow and deep information. In the multi-feature fusion attention module, global max pooling (GMP) is introduced in parallel into the channel attention of ECA-Net without dimensionality reduction, and is combined with global average pooling (GAP) to form a dual-path encoding, so as to realize channel recalibration and adaptive fusion of shallow and deep features. The adaptive brightness correction module predicts pixel-wise and channel-wise Gamma parameters through the network to adaptively correct the brightness and color of the restored result. The network is optimized in an end-to-end manner with a multi-constraint joint loss function composed of a pixel-level reconstruction loss, a perceptual loss and a color consistency loss. Experimental results show that on the RESIDE dataset the proposed method outperforms the mainstream dehazing methods in objective metrics such as PSNR and SSIM, and the information entropy also indicates that the restored images contain richer details. Validation on the real aerial hazy images selected from HazyDet shows that the proposed method still maintains a good visual restoration effect in real scenes and has favorable practical applicability. In addition, the inference time of the proposed method for a single image is 0.216 s, which can meet the requirement of fast image dehazing.
Downloads
References
[1] Pandey, P., Gupta, R., & Goel, N. (2025). Comprehensive review of single image defogging techniques: enhancement, prior, and learning based approaches. Artificial Intelligence Review, 58(4), 116. https://doi.org/10.1007/s10462-024-110 34-4. DOI: https://doi.org/10.1007/s10462-024-11034-4
[2] He, K., Sun, J., & Tang, X. (2011). Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), 2341–2353. DOI: https://doi.org/10.1109/TPAMI.2010.168
[3] He, K., Sun, J., & Tang, X. (2013). Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(6), 1397–1409. DOI: https://doi.org/10.1109/TPAMI.2012.213
[4] Berman, D., Treibitz, T., & Avidan, S. (2016). Non-local image dehazing. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. DOI: https://doi.org/10.1109/CVPR.2016.185
[5] Soni, B., & Mathur, P. (2020). An improved image dehazing technique using CLAHE and guided filter. In 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 902–907). IEEE. DOI: https://doi.org/10.1109/SPIN48934.2020.9071296
[6] Stark, J. A. (2000). Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on Image Processing, 9(5), 889–896. DOI: https://doi.org/10.1109/83.841534
[7] Kim, J. Y., Kim, L. S., & Hwang, S. H. (2001). An advanced contrast enhancement using partially overlapped sub-block histogram equalization. IEEE Transactions on Circuits and Systems for Video Technology, 11(4), 475–484. DOI: https://doi.org/10.1109/76.915354
[8] Liu, X., Liu, C., Lan, H., et al. (2020). Dehaze enhancement algorithm based on retinex theory for aerial images combined with dark channel. Open Access Library Journal, 7(4), 1–12. DOI: https://doi.org/10.4236/oalib.1106280
[9] Shi, Z. (2026). Uav path planning and obstacle avoidance based on deep learning and reinforcement learning. Frontiers in Computing and Intelligent Systems, 16(1), 178–184. https:// doi. org/10.54097/7g9fac16. DOI: https://doi.org/10.54097/7g9fac16
[10] Ren, W., Liu, S., Zhang, H., et al. (2016). Single image dehazing via multi-scale convolutional neural networks. In European Conference on Computer Vision. DOI: https://doi.org/10.1007/978-3-319-46475-6_10
[11] Cai, B., Xu, X., Jia, K., et al. (2016). DehazeNet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 25(11), 5187–5198. DOI: https://doi.org/10.1109/TIP.2016.2598681
[12] Li, B., Peng, X., Wang, Z., et al. (2017). Aod-net: All-in-one dehazing network. In Proceedings of the IEEE International Conference on Computer Vision (pp. 4770–4778). DOI: https://doi.org/10.1109/ICCV.2017.511
[13] Jiang, J. S., Huang, J. M., Yu, Y., et al. (2026). Traffic image defogging method under hazy environments based on frequency domain fusion and attention mechanism. Transportation Research Record, 2680(7), 104–116. https:// doi. org/ 10.1177/03611981251387597. DOI: https://doi.org/10.1177/03611981251387597
[14] Qin, X., Wang, Z., Bai, Y., et al. (2020). FFA-Net: Feature fusion attention network for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, 34(7), 11908–11915. https://doi.org/10.1609/aaai.v34i07.6865. DOI: https://doi.org/10.1609/aaai.v34i07.6865
[15] Wang, Q., Wu, B., Zhu, P., et al. (2020). ECA-Net: Efficient channel attention for deep convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 11534–11542). DOI: https://doi.org/10.1109/CVPR42600.2020.01155
[16] Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 7132–7141). DOI: https://doi.org/10.1109/CVPR.2018.00745
[17] Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3–19). DOI: https://doi.org/10.1007/978-3-030-01234-2_1
[18] Xu, S., Chen, Q., Peng, L., et al. (2026). Towards fast and effective low-light image enhancement via adaptive Gamma correction and detail refinement. Journal of Visual Communication and Image Representation, 116, 104724. https: // doi.org/10.1016/j.jvcir.2026.104724. DOI: https://doi.org/10.1016/j.jvcir.2026.104724
[19] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556.
[20] Li, B., Ren, W., Fu, D., et al. (2018). Benchmarking single-image dehazing and beyond. IEEE Transactions on Image Processing, 28(1), 492–505. DOI: https://doi.org/10.1109/TIP.2018.2867951
[21] Feng, C., Chen, Z., Li, X., et al. (2024). HazyDet: Open-source benchmark for drone-view object detection with depth-cues in hazy scenes. https://doi.org/10.1109/TGRS.2026.3701819. DOI: https://doi.org/10.1109/TGRS.2026.3701819
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
