Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition
Edge‐preserving filters have been applied to Multi‐Scale Decomposition (MSD) for fusion of infrared and visible images. Traditional edge‐preserving MSDs may hardly make satisfied structural separation from details to cause fusion performance degradation. To suppress this challenge, the authors propo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-02-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5027 |
| _version_ | 1797684847793143808 |
|---|---|
| author | Changda Xing Zhisheng Wang Fanliang Meng Chong Dong |
| author_facet | Changda Xing Zhisheng Wang Fanliang Meng Chong Dong |
| author_sort | Changda Xing |
| collection | DOAJ |
| description | Edge‐preserving filters have been applied to Multi‐Scale Decomposition (MSD) for fusion of infrared and visible images. Traditional edge‐preserving MSDs may hardly make satisfied structural separation from details to cause fusion performance degradation. To suppress this challenge, the authors propose a novel fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition (MSD‐Iteration). This method consists of three steps. First, source images are decomposed by the Gaussian smoothness and joint bilateral filtering iteration. The implementation includes the fine‐scale detail removal with Gaussian filtering, edge and structure extraction with joint bilateral filtering iteration, and detail obtaining at multi‐scales. The decomposition has edge‐preserving and scale‐aware properties to improve detail acquisition. Second, rules are designed to conduct the layer combination. For the rule of base layers, saliency maps are constructed by Laplacian and Gaussian low‐pass filters to calculate initial weight maps. A guided filter is further applied to determine final weight maps for the combination. Meanwhile, they use the regional average energy weighting to obtain decision maps at multi‐scales by constructing intensity deviation to combine detail layers. Third, they implement the reconstruction with the combined layers. Sufficient experiments are presented to evaluate MSD‐Iteration, and experimental results validate the superiority of the authors’ method. |
| first_indexed | 2024-03-12T00:35:38Z |
| format | Article |
| id | doaj.art-f66caf8c04e2448b9b3bc736fe817cf3 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:35:38Z |
| publishDate | 2019-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-f66caf8c04e2448b9b3bc736fe817cf32023-09-15T09:51:44ZengWileyIET Computer Vision1751-96321751-96402019-02-01131445210.1049/iet-cvi.2018.5027Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decompositionChangda Xing0Zhisheng Wang1Fanliang Meng2Chong Dong3College of Automation Engineering, Nanjing University of Aeronautics and AstronauticsNanjingPeople's Republic of ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and AstronauticsNanjingPeople's Republic of ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and AstronauticsNanjingPeople's Republic of ChinaCollege of Automation Engineering, Nanjing University of Aeronautics and AstronauticsNanjingPeople's Republic of ChinaEdge‐preserving filters have been applied to Multi‐Scale Decomposition (MSD) for fusion of infrared and visible images. Traditional edge‐preserving MSDs may hardly make satisfied structural separation from details to cause fusion performance degradation. To suppress this challenge, the authors propose a novel fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition (MSD‐Iteration). This method consists of three steps. First, source images are decomposed by the Gaussian smoothness and joint bilateral filtering iteration. The implementation includes the fine‐scale detail removal with Gaussian filtering, edge and structure extraction with joint bilateral filtering iteration, and detail obtaining at multi‐scales. The decomposition has edge‐preserving and scale‐aware properties to improve detail acquisition. Second, rules are designed to conduct the layer combination. For the rule of base layers, saliency maps are constructed by Laplacian and Gaussian low‐pass filters to calculate initial weight maps. A guided filter is further applied to determine final weight maps for the combination. Meanwhile, they use the regional average energy weighting to obtain decision maps at multi‐scales by constructing intensity deviation to combine detail layers. Third, they implement the reconstruction with the combined layers. Sufficient experiments are presented to evaluate MSD‐Iteration, and experimental results validate the superiority of the authors’ method.https://doi.org/10.1049/iet-cvi.2018.5027infrared imagesvisible imagesGaussian smoothnessjoint bilateral filtering iteration decompositionedge-preserving filtersMultiScale Decomposition |
| spellingShingle | Changda Xing Zhisheng Wang Fanliang Meng Chong Dong Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition IET Computer Vision infrared images visible images Gaussian smoothness joint bilateral filtering iteration decomposition edge-preserving filters MultiScale Decomposition |
| title | Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition |
| title_full | Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition |
| title_fullStr | Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition |
| title_full_unstemmed | Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition |
| title_short | Fusion of infrared and visible images with Gaussian smoothness and joint bilateral filtering iteration decomposition |
| title_sort | fusion of infrared and visible images with gaussian smoothness and joint bilateral filtering iteration decomposition |
| topic | infrared images visible images Gaussian smoothness joint bilateral filtering iteration decomposition edge-preserving filters MultiScale Decomposition |
| url | https://doi.org/10.1049/iet-cvi.2018.5027 |
| work_keys_str_mv | AT changdaxing fusionofinfraredandvisibleimageswithgaussiansmoothnessandjointbilateralfilteringiterationdecomposition AT zhishengwang fusionofinfraredandvisibleimageswithgaussiansmoothnessandjointbilateralfilteringiterationdecomposition AT fanliangmeng fusionofinfraredandvisibleimageswithgaussiansmoothnessandjointbilateralfilteringiterationdecomposition AT chongdong fusionofinfraredandvisibleimageswithgaussiansmoothnessandjointbilateralfilteringiterationdecomposition |