Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism
Since light propagation in water bodies is subject to absorption and scattering effects, underwater images using only conventional intensity cameras will suffer from low brightness, blurred images, and loss of details. In this paper, a deep fusion network is applied to underwater polarization images...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/12/5594 |
| _version_ | 1827735647427756032 |
|---|---|
| author | Haoyuan Cheng Deqing Zhang Jinchi Zhu Hao Yu Jinkui Chu |
| author_facet | Haoyuan Cheng Deqing Zhang Jinchi Zhu Hao Yu Jinkui Chu |
| author_sort | Haoyuan Cheng |
| collection | DOAJ |
| description | Since light propagation in water bodies is subject to absorption and scattering effects, underwater images using only conventional intensity cameras will suffer from low brightness, blurred images, and loss of details. In this paper, a deep fusion network is applied to underwater polarization images; that is, the underwater polarization images are fused with intensity images using the deep learning method. To construct a training dataset, we establish an experimental setup to obtain underwater polarization images and perform appropriate transformations to expand the dataset. Next, an end-to-end learning framework based on unsupervised learning and guided by an attention mechanism is constructed for fusing polarization and light intensity images. The loss function and weight parameters are elaborated. The produced dataset is used to train the network under different loss weight parameters, and the fused images are evaluated based on different image evaluation metrics. The results show that the fused underwater images are more detailed. Compared with light intensity images, the information entropy and standard deviation of the proposed method increase by 24.48% and 139%. The image processing results are better than other fusion-based methods. In addition, the improved U-net network structure is used to extract features for image segmentation. The results show that the target segmentation based on the proposed method is feasible under turbid water. The proposed method does not require manual adjustment of weight parameters, has faster operation speed, and has strong robustness and self-adaptability, which is important for research in vision fields, such as ocean detection and underwater target recognition. |
| first_indexed | 2024-03-11T01:56:45Z |
| format | Article |
| id | doaj.art-2899e4e53a2541f2acdab69978c08000 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:56:45Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2899e4e53a2541f2acdab69978c080002023-11-18T12:33:19ZengMDPI AGSensors1424-82202023-06-012312559410.3390/s23125594Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention MechanismHaoyuan Cheng0Deqing Zhang1Jinchi Zhu2Hao Yu3Jinkui Chu4College of Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Engineering, Ocean University of China, Qingdao 266100, ChinaKey Laboratory for Micro/Nano Technology and System of Liaoning Province, Dalian University of Technology, Dalian 116024, ChinaKey Laboratory for Micro/Nano Technology and System of Liaoning Province, Dalian University of Technology, Dalian 116024, ChinaSince light propagation in water bodies is subject to absorption and scattering effects, underwater images using only conventional intensity cameras will suffer from low brightness, blurred images, and loss of details. In this paper, a deep fusion network is applied to underwater polarization images; that is, the underwater polarization images are fused with intensity images using the deep learning method. To construct a training dataset, we establish an experimental setup to obtain underwater polarization images and perform appropriate transformations to expand the dataset. Next, an end-to-end learning framework based on unsupervised learning and guided by an attention mechanism is constructed for fusing polarization and light intensity images. The loss function and weight parameters are elaborated. The produced dataset is used to train the network under different loss weight parameters, and the fused images are evaluated based on different image evaluation metrics. The results show that the fused underwater images are more detailed. Compared with light intensity images, the information entropy and standard deviation of the proposed method increase by 24.48% and 139%. The image processing results are better than other fusion-based methods. In addition, the improved U-net network structure is used to extract features for image segmentation. The results show that the target segmentation based on the proposed method is feasible under turbid water. The proposed method does not require manual adjustment of weight parameters, has faster operation speed, and has strong robustness and self-adaptability, which is important for research in vision fields, such as ocean detection and underwater target recognition.https://www.mdpi.com/1424-8220/23/12/5594underwater target detectionimage fusionunsupervised learningattention mechanismpolarization |
| spellingShingle | Haoyuan Cheng Deqing Zhang Jinchi Zhu Hao Yu Jinkui Chu Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism Sensors underwater target detection image fusion unsupervised learning attention mechanism polarization |
| title | Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism |
| title_full | Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism |
| title_fullStr | Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism |
| title_full_unstemmed | Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism |
| title_short | Underwater Target Detection Utilizing Polarization Image Fusion Algorithm Based on Unsupervised Learning and Attention Mechanism |
| title_sort | underwater target detection utilizing polarization image fusion algorithm based on unsupervised learning and attention mechanism |
| topic | underwater target detection image fusion unsupervised learning attention mechanism polarization |
| url | https://www.mdpi.com/1424-8220/23/12/5594 |
| work_keys_str_mv | AT haoyuancheng underwatertargetdetectionutilizingpolarizationimagefusionalgorithmbasedonunsupervisedlearningandattentionmechanism AT deqingzhang underwatertargetdetectionutilizingpolarizationimagefusionalgorithmbasedonunsupervisedlearningandattentionmechanism AT jinchizhu underwatertargetdetectionutilizingpolarizationimagefusionalgorithmbasedonunsupervisedlearningandattentionmechanism AT haoyu underwatertargetdetectionutilizingpolarizationimagefusionalgorithmbasedonunsupervisedlearningandattentionmechanism AT jinkuichu underwatertargetdetectionutilizingpolarizationimagefusionalgorithmbasedonunsupervisedlearningandattentionmechanism |