| Citation: |
SUN Hongyu, LI Jun, YUAN Bo, ZHOU Yuchao. Deep Learning-Based Polarization Image Fusion Method[J]. Infrared Technology , 2025, 47(2): 193-200.
|
To improve image quality in complex and dim environments, a network that leverages both the global information and textural details of polarized images through a strategy of multi-scale feature extraction and dual fusion, known as the Scale Feature Extraction and Dual Fusion Strategy Network (SFE-DFS-Nest), is proposed. The proposed network fuses polarized intensity images with polarization degree images. Initially, an encoder is constructed to extract multi-scale features from source images. Then, shallow features are fused using a lightweight Transformer, while deep features are integrated through a residual network. Finally, a decoder is built to reconstruct the fused features. Compared with existing image fusion networks, this network employs distinct fusion strategies for features at different scales. The experimental results show that images from dark and complex environments exhibited improved subjective visual comfort after fusion through this network. Furthermore, the fused images obtained using the proposed method outperformed those obtained using the compared methods in terms of objective evaluation metrics.
| [1] |
CHEN W, YAN L, CHANDRASEKAR V. Optical polarization remote sensing[J]. International Journal of Remote Sensing, 2020, 41(3): 4849-4852.
|
| [2] |
闫德利, 申冲, 王晨光, 等. 强度图像和偏振度图像融合网络的设计[J]. 光学精密工程, 2023, 31(8): 1256-1266.
YAN Deli, SHEN Chong, WANG Chenguang, et al. Design of a fusion network for intensity and polarization degree images[J]. Optical Precision Engineering, 2023, 31(8): 1256-1266.
|
| [3] |
孟建雯. 基于深度学习偏振图像融合的金属工业件检测[D]. 咸阳: 西北农林科技大学, 2023.
MENG Jianwen. Detection of Metal Industrial Parts Based on Deep Learning Polarization Image Fusion[D]. Xianyang: Northwest A&F University, 2023.
|
| [4] |
梁开阳. 基于多尺度变换和稀疏表示的遥感图像融合算法研究[D]. 银川: 北方民族大学, 2020.
LIANG Kaiyang. Research on Remote Sensing Image Fusion Algorithm Based on Multi-scale Transformations and Sparse Representation[D]. Yinchuan: Northern University for Nationalities, 2020.
|
| [5] |
李蕾, 郭天太, 潘孙强, 等. 基于Laplacian算法的水下偏振图像复原[J]. 电子技术应用, 2019, 45(9): 85-88.
LI Lei, GUO Tiantai, PAN Sunqiang, et al. Underwater polarization image restoration based on the Laplacian algorithm[J]. Electronic Technology Application, 2019, 45(9): 85-88.
|
| [6] |
MA J Y, YU W, LIANG P W, et al. Fusion-GAN: a generative adversarial network for infrared and visible image fusion [J]. Information Fusion, 2019, 48(8): 11-26.
|
| [7] |
李辉. 基于表示学习的图像融合算法研究与应用[D]. 无锡: 江南大学, 2022.
LI Hui. Research and Application of Image Fusion Algorithms Based on Representation Learning[D]. Wuxi: Jiangnan University, 2022.
|
| [8] |
ZHANG J C, SHAO J B, CHEN J L, et al. PF-NET: an unsupervised deep network for polarization image fusion[J]. Optics Letters, 2020, 45(6): 1507-1510. DOI: 10.1364/OL.384189
|
| [9] |
Lowe D G. Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision of IEEE, 1999, 36(2): 1150-1157.
|
| [10] |
赵鹏翔. 基于偏振信息的多孔径水下成像技术研究[D]. 太原: 中北大学, 2021.
ZHAO Pengxiang. Research on Multi-Aperture Underwater Imaging Technology Based on Polarization Information[D]. Taiyuan: North University of China, 2021.
|
| [11] |
WEI Y, HAN P, LIU F, et al. Enhancement of underwater vision by fully exploiting the polarization information from the Stokes vector[J]. Optics Express, 2021, 29(14): 22275-22287. DOI: 10.1364/OE.433072
|
| [12] |
吕义付, 张乾, 徐艳. 基于BEDU-Net算法的皮肤病灶分割研究[J]. 智能计算机与应用, 2023, 13(8): 73-79, 87.
LYU Yifu, ZHANG Qian, XU Yan. Research on skin Lesion segmentation based on BEDU-Net algorithm[J]. Intelligent Computer and Applications, 2023, 13(8): 73-79, 87.
|
| [13] |
牛睿智, 潘斐扬, 刘志亮. 基于YOLO的鱼道过鱼粗粒度目标检测算法[J]. 长江信息通信, 2023, 36(12): 45-51.
NIU Ruizhi, PAN Feiyang, LIU Zhiqiang. Fishway coarse-grained target detection algorithm based on YOLO[J]. Yangtze Information and Communication, 2023, 36(12): 45-51.
|
| [14] |
张翔. 基于深度学习的人脸表情识别研究[D]. 兰州: 西北师范大学, 2023.
ZHANG Xiang. Research on Facial Expression Recognition Based on Deep Learning[D]. Lanzhou: Northwest Normal University, 2023.
|
| [15] |
陈霞晖. 基于生成式对抗网络的人脸年龄合成算法的研究[D]. 南京: 南京理工大学, 2023.
CHEN Xiahui. Research on Facial Age Synthesis Algorithm Based on Generative Adversarial Networks[D]. Nanjing: Nanjing University of Science and Technology, 2023.
|
| [16] |
杨彪, 江朝晖, 陈铎, 等. 基于客观参数的图像质量评估[J]. 计算机仿真, 2009, 26(5): 232-235.
YANG Biao, JIANG Zhaohui, CHEN Duo, et al. Image quality assessment based on objective parameters[J]. Computer Simulation, 2009, 26(5): 232-235.
|
| [17] |
黄丹丹. 基于深度学习的中文分词和关键词抽取模型研究[D]. 北京: 北京邮电大学, 2019.
HUANG Dandan. Research on Chinese Word Segmentation and Keyword Extraction Models Based on Deep Learning[D]. Beijing: Beijing University of Posts and Telecommunications, 2019.
|
| [18] |
陈中琴. 基于RDN-LTE与改进DINO的布匹瑕疵检测技术研究[D]. 上海: 东华大学, 2023.
CHEN Zhongqin. Research on Fabric Defect Detection Technology Based on RDN-LTE and Improved DINO[D]. Shanghai: Donghua University, 2023.
|
| [19] |
姜兆祯, 韩裕生, 任帅军, 等. 基于改进PCNN模型的偏振图像融合算法[J]. 舰船电子工程, 2021, 41(3): 33-36, 175.
JIANG Zhaozhen, HAN Yusheng, REN Shuaiyun, et al. Polarization image fusion algorithm based on improved PCNN model[J]. Shipborne Electronic Engineering, 2021, 41(3): 33-36, 175.
|
| [1] | CHEN Chaoyang, JIANG Yuanyuan. Infrared and Visible Image Fusion Based on Deep Image Decomposition[J]. Infrared Technology , 2024, 46(12): 1362-1370. |
| [2] | FENG Rui, YUAN Hongwu, ZHOU Yuye, WANG Feng. Fusion Method for Polarization Direction Image Based on Double-branch Antagonism Network[J]. Infrared Technology , 2024, 46(3): 288-294. |
| [3] | DUAN Jin, ZHANG Hao, SONG Jingyuan, LIU Ju. Review of Polarization Image Fusion Based on Deep Learning[J]. Infrared Technology , 2024, 46(2): 119-128. |
| [4] | GAO Yi, YU Jinqiang, ZHANG Xiaodong, DUAN Jin. Underwater Evidence Detection Method Based on Polarization Fusion Image[J]. Infrared Technology , 2023, 45(9): 962-968. |
| [5] | CAO Yutong, HUAN Kewei, XUE Chao, HAN Fengdi, LI Xiangyang, CHEN Xiao. Infrared and Visible Image Fusion Based on CNN with NSCT[J]. Infrared Technology , 2023, 45(4): 378-385. |
| [6] | CHEN Jinni, CHEN Yuyang, LI Yunhong, BAI Xiaohua. Fusion of Infrared Intensity and Polarized Images Based on Structure and Decomposition[J]. Infrared Technology , 2023, 45(3): 257-265. |
| [7] | HU Xuekai, LUO Peng, LI Tiecheng, CAI Yuru, MA Na, ZHOU Xueqing. Multi-scale Image Fusion Based on Adaptive Weighting[J]. Infrared Technology , 2022, 44(4): 404-409. |
| [8] | QU Haicheng, WANG Yuping, GAO Jiankang, ZHAO Siqi. Mode Adaptive Infrared and Visible Image Fusion[J]. Infrared Technology , 2022, 44(3): 268-276. |
| [9] | LUO Di, WANG Congqing, ZHOU Yongjun. A Visible and Infrared Image Fusion Method based on Generative Adversarial Networks and Attention Mechanism[J]. Infrared Technology , 2021, 43(6): 566-574. |
| [10] | SHEN Xuechen, LIU Jun, GAO Ming. Polarizing Image Fusion Algorithm Based on Wavelet-Contourlet Transform[J]. Infrared Technology , 2020, 42(2): 182-189. |
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: