Infrared and Visible Image Fusion with Significant Target Enhancement
Existing fusion rules focus on retaining detailed information in the source image, but as the thermal radiation information in infrared images is mainly characterized by pixel intensity, these fusion rules are likely to result in reduced saliency of the target in the fused image. To address this pro...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/24/11/1633 |
| _version_ | 1827646663784660992 |
|---|---|
| author | Xing Huo Yinping Deng Kun Shao |
| author_facet | Xing Huo Yinping Deng Kun Shao |
| author_sort | Xing Huo |
| collection | DOAJ |
| description | Existing fusion rules focus on retaining detailed information in the source image, but as the thermal radiation information in infrared images is mainly characterized by pixel intensity, these fusion rules are likely to result in reduced saliency of the target in the fused image. To address this problem, we propose an infrared and visible image fusion model based on significant target enhancement, aiming to inject thermal targets from infrared images into visible images to enhance target saliency while retaining important details in visible images. First, the source image is decomposed with multi-level Gaussian curvature filtering to obtain background information with high spatial resolution. Second, the large-scale layers are fused using ResNet50 and maximizing weights based on the average operator to improve detail retention. Finally, the base layers are fused by incorporating a new salient target detection method. The subjective and objective experimental results on TNO and MSRS datasets demonstrate that our method achieves better results compared to other traditional and deep learning-based methods. |
| first_indexed | 2024-03-09T19:05:40Z |
| format | Article |
| id | doaj.art-9d650418038d476eadf5533dddcb2fd1 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T19:05:40Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-9d650418038d476eadf5533dddcb2fd12023-11-24T04:37:24ZengMDPI AGEntropy1099-43002022-11-012411163310.3390/e24111633Infrared and Visible Image Fusion with Significant Target EnhancementXing Huo0Yinping Deng1Kun Shao2School of Mathematics, Hefei University of Technology, Hefei 230009, ChinaSchool of Mathematics, Hefei University of Technology, Hefei 230009, ChinaSchool of Software, Hefei University of Technology, Hefei 230009, ChinaExisting fusion rules focus on retaining detailed information in the source image, but as the thermal radiation information in infrared images is mainly characterized by pixel intensity, these fusion rules are likely to result in reduced saliency of the target in the fused image. To address this problem, we propose an infrared and visible image fusion model based on significant target enhancement, aiming to inject thermal targets from infrared images into visible images to enhance target saliency while retaining important details in visible images. First, the source image is decomposed with multi-level Gaussian curvature filtering to obtain background information with high spatial resolution. Second, the large-scale layers are fused using ResNet50 and maximizing weights based on the average operator to improve detail retention. Finally, the base layers are fused by incorporating a new salient target detection method. The subjective and objective experimental results on TNO and MSRS datasets demonstrate that our method achieves better results compared to other traditional and deep learning-based methods.https://www.mdpi.com/1099-4300/24/11/1633image fusioninfrared imagevisible imagesignificant target enhancementmulti-level Gaussian curvature filteringResNet50 |
| spellingShingle | Xing Huo Yinping Deng Kun Shao Infrared and Visible Image Fusion with Significant Target Enhancement Entropy image fusion infrared image visible image significant target enhancement multi-level Gaussian curvature filtering ResNet50 |
| title | Infrared and Visible Image Fusion with Significant Target Enhancement |
| title_full | Infrared and Visible Image Fusion with Significant Target Enhancement |
| title_fullStr | Infrared and Visible Image Fusion with Significant Target Enhancement |
| title_full_unstemmed | Infrared and Visible Image Fusion with Significant Target Enhancement |
| title_short | Infrared and Visible Image Fusion with Significant Target Enhancement |
| title_sort | infrared and visible image fusion with significant target enhancement |
| topic | image fusion infrared image visible image significant target enhancement multi-level Gaussian curvature filtering ResNet50 |
| url | https://www.mdpi.com/1099-4300/24/11/1633 |
| work_keys_str_mv | AT xinghuo infraredandvisibleimagefusionwithsignificanttargetenhancement AT yinpingdeng infraredandvisibleimagefusionwithsignificanttargetenhancement AT kunshao infraredandvisibleimagefusionwithsignificanttargetenhancement |