Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework
The measurement accuracy and reliability of thermography is largely limited by a relatively low spatial-resolution of infrared (IR) cameras in comparison to digital cameras. Using a high-end IR camera to achieve high spatial-resolution can be costly or sometimes infeasible due to the high sample rat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7471 |
| _version_ | 1797508516775198720 |
|---|---|
| author | Shuozhi Wang Jianqiang Mei Lichao Yang Yifan Zhao |
| author_facet | Shuozhi Wang Jianqiang Mei Lichao Yang Yifan Zhao |
| author_sort | Shuozhi Wang |
| collection | DOAJ |
| description | The measurement accuracy and reliability of thermography is largely limited by a relatively low spatial-resolution of infrared (IR) cameras in comparison to digital cameras. Using a high-end IR camera to achieve high spatial-resolution can be costly or sometimes infeasible due to the high sample rate required. Therefore, there is a strong demand to improve the quality of IR images, particularly on edges, without upgrading the hardware in the context of surveillance and industrial inspection systems. This paper proposes a novel Conditional Generative Adversarial Networks (CGAN)-based framework to enhance IR edges by learning high-frequency features from corresponding visual images. A dual-discriminator, focusing on edge and content/background, is introduced to guide the cross imaging modality learning procedure of the U-Net generator in high and low frequencies respectively. Results demonstrate that the proposed framework can effectively enhance barely visible edges in IR images without introducing artefacts, meanwhile the content information is well preserved. Different from most similar studies, this method only requires IR images for testing, which will increase the applicability of some scenarios where only one imaging modality is available, such as active thermography. |
| first_indexed | 2024-03-10T05:05:03Z |
| format | Article |
| id | doaj.art-7b02ecd9a61a4b4a9a3b12daa3483b8f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:05:03Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7b02ecd9a61a4b4a9a3b12daa3483b8f2023-11-23T01:23:51ZengMDPI AGSensors1424-82202021-11-012122747110.3390/s21227471Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) FrameworkShuozhi Wang0Jianqiang Mei1Lichao Yang2Yifan Zhao3School of Aerospace, Transport and Manufacturing, Cranfield University, Bedford MK43 0AL, UKSchool of Electronic Engineering, Tianjin University of Technology and Education, Tianjin 300222, ChinaSchool of Aerospace, Transport and Manufacturing, Cranfield University, Bedford MK43 0AL, UKSchool of Aerospace, Transport and Manufacturing, Cranfield University, Bedford MK43 0AL, UKThe measurement accuracy and reliability of thermography is largely limited by a relatively low spatial-resolution of infrared (IR) cameras in comparison to digital cameras. Using a high-end IR camera to achieve high spatial-resolution can be costly or sometimes infeasible due to the high sample rate required. Therefore, there is a strong demand to improve the quality of IR images, particularly on edges, without upgrading the hardware in the context of surveillance and industrial inspection systems. This paper proposes a novel Conditional Generative Adversarial Networks (CGAN)-based framework to enhance IR edges by learning high-frequency features from corresponding visual images. A dual-discriminator, focusing on edge and content/background, is introduced to guide the cross imaging modality learning procedure of the U-Net generator in high and low frequencies respectively. Results demonstrate that the proposed framework can effectively enhance barely visible edges in IR images without introducing artefacts, meanwhile the content information is well preserved. Different from most similar studies, this method only requires IR images for testing, which will increase the applicability of some scenarios where only one imaging modality is available, such as active thermography.https://www.mdpi.com/1424-8220/21/22/7471image enhancementedge detectiondeep learningthermography |
| spellingShingle | Shuozhi Wang Jianqiang Mei Lichao Yang Yifan Zhao Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework Sensors image enhancement edge detection deep learning thermography |
| title | Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework |
| title_full | Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework |
| title_fullStr | Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework |
| title_full_unstemmed | Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework |
| title_short | Infer Thermal Information from Visual Information: A Cross Imaging Modality Edge Learning (CIMEL) Framework |
| title_sort | infer thermal information from visual information a cross imaging modality edge learning cimel framework |
| topic | image enhancement edge detection deep learning thermography |
| url | https://www.mdpi.com/1424-8220/21/22/7471 |
| work_keys_str_mv | AT shuozhiwang inferthermalinformationfromvisualinformationacrossimagingmodalityedgelearningcimelframework AT jianqiangmei inferthermalinformationfromvisualinformationacrossimagingmodalityedgelearningcimelframework AT lichaoyang inferthermalinformationfromvisualinformationacrossimagingmodalityedgelearningcimelframework AT yifanzhao inferthermalinformationfromvisualinformationacrossimagingmodalityedgelearningcimelframework |