An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System
Imaging research on complex samples going through random scattering medias is a very difficult challenge in the field of computational optics. With the deep learning methods applying to the field of speckle correlation image reconstruction, many problems of imaging through strong scattering media an...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9031329/ |
| _version_ | 1818557991849295872 |
|---|---|
| author | Linli Xu Jing Han Tian Wang Lianfa Bai |
| author_facet | Linli Xu Jing Han Tian Wang Lianfa Bai |
| author_sort | Linli Xu |
| collection | DOAJ |
| description | Imaging research on complex samples going through random scattering medias is a very difficult challenge in the field of computational optics. With the deep learning methods applying to the field of speckle correlation image reconstruction, many problems of imaging through strong scattering media and small perturbations of the media which reduces the imaging performance have been resolved. However, due to the randomness of the scattering medium, large and complex samples are required to be trained, deep learning based methods alway occupy a lot of energy consumption on Graphic Processing Unit (GPU). Cyber-Physical-Social Systems (CPSS) integrating the cyber, physical, and social worlds is a key technology to provide proactive and personalized services for humans. This paper proposes an efficient CNN to do speckle image reconstruction based on cloud-edge computing for CPSS, which can achieve higher image resolution by less inputs.In this work, we design a self-back stacked Efficient Residual Factorized Network (SBS-ERFNet) to do image reconstruction through scattering medium. Different from the traditional ERFNets, our framework includes two stages of training, we use this model to study the speckle image from a low-to-high resolution manner. The experiments show that even if a small samples is input for training, the test results can reach a high resolution. |
| first_indexed | 2024-12-14T00:06:58Z |
| format | Article |
| id | doaj.art-59368cdbc91d42579d030fb42db0475c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T00:06:58Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-59368cdbc91d42579d030fb42db0475c2022-12-21T23:25:58ZengIEEEIEEE Access2169-35362020-01-018541545416310.1109/ACCESS.2020.29797869031329An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-SystemLinli Xu0Jing Han1https://orcid.org/0000-0002-1033-566XTian Wang2Lianfa Bai3https://orcid.org/0000-0002-6688-4529Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, ChinaKey Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaKey Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, ChinaImaging research on complex samples going through random scattering medias is a very difficult challenge in the field of computational optics. With the deep learning methods applying to the field of speckle correlation image reconstruction, many problems of imaging through strong scattering media and small perturbations of the media which reduces the imaging performance have been resolved. However, due to the randomness of the scattering medium, large and complex samples are required to be trained, deep learning based methods alway occupy a lot of energy consumption on Graphic Processing Unit (GPU). Cyber-Physical-Social Systems (CPSS) integrating the cyber, physical, and social worlds is a key technology to provide proactive and personalized services for humans. This paper proposes an efficient CNN to do speckle image reconstruction based on cloud-edge computing for CPSS, which can achieve higher image resolution by less inputs.In this work, we design a self-back stacked Efficient Residual Factorized Network (SBS-ERFNet) to do image reconstruction through scattering medium. Different from the traditional ERFNets, our framework includes two stages of training, we use this model to study the speckle image from a low-to-high resolution manner. The experiments show that even if a small samples is input for training, the test results can reach a high resolution.https://ieeexplore.ieee.org/document/9031329/Random scattering mediumcyber-physical-social systems (CPSS)cloud-edge computingself back stacked efficient residual factorized network (SBS-ERFNet)low-to-high resolution |
| spellingShingle | Linli Xu Jing Han Tian Wang Lianfa Bai An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System IEEE Access Random scattering medium cyber-physical-social systems (CPSS) cloud-edge computing self back stacked efficient residual factorized network (SBS-ERFNet) low-to-high resolution |
| title | An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System |
| title_full | An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System |
| title_fullStr | An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System |
| title_full_unstemmed | An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System |
| title_short | An Efficient CNN to Realize Speckle Correlation Imaging Based on Cloud-Edge for Cyber-Physical-Social-System |
| title_sort | efficient cnn to realize speckle correlation imaging based on cloud edge for cyber physical social system |
| topic | Random scattering medium cyber-physical-social systems (CPSS) cloud-edge computing self back stacked efficient residual factorized network (SBS-ERFNet) low-to-high resolution |
| url | https://ieeexplore.ieee.org/document/9031329/ |
| work_keys_str_mv | AT linlixu anefficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT jinghan anefficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT tianwang anefficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT lianfabai anefficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT linlixu efficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT jinghan efficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT tianwang efficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem AT lianfabai efficientcnntorealizespecklecorrelationimagingbasedoncloudedgeforcyberphysicalsocialsystem |