Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS
Image intensifiers are used internationally as advanced military night-vision devices. They have better imaging performance in low-light-level conditions than CMOS/CCD. The intensified CMOS (ICMOS) was developed to satisfy the digital demand of image intensifiers. In order to make the ICMOS capable...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/11/3891 |
| _version_ | 1797531346624577536 |
|---|---|
| author | Zhenghao Han Li Li Weiqi Jin Xia Wang Gangcheng Jiao Xuan Liu Hailin Wang |
| author_facet | Zhenghao Han Li Li Weiqi Jin Xia Wang Gangcheng Jiao Xuan Liu Hailin Wang |
| author_sort | Zhenghao Han |
| collection | DOAJ |
| description | Image intensifiers are used internationally as advanced military night-vision devices. They have better imaging performance in low-light-level conditions than CMOS/CCD. The intensified CMOS (ICMOS) was developed to satisfy the digital demand of image intensifiers. In order to make the ICMOS capable of color imaging in low-light-level conditions, a liquid-crystal tunable filter based color imaging ICMOS was developed. Due to the time-division color imaging scheme, motion artifacts may be introduced when a moving target is in the scene. To solve this problem, a deformable kernel prediction neural network (DKPNN) is proposed for joint denoising and motion artifact removal, and a data generation method which generates images with color-channel motion artifacts is also proposed to train the DKPNN. The results show that, compared with other denoising methods, the proposed DKPNN performed better both on generated noisy data and on real noisy data. Therefore, the proposed DKPNN is more suitable for color ICMOS denoising and motion artifact removal. A new exploration was made for low-light-level color imaging schemes. |
| first_indexed | 2024-03-10T10:42:28Z |
| format | Article |
| id | doaj.art-eb147743ad7a4464a484a572a937323b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:42:28Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-eb147743ad7a4464a484a572a937323b2023-11-21T22:52:21ZengMDPI AGSensors1424-82202021-06-012111389110.3390/s21113891Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOSZhenghao Han0Li Li1Weiqi Jin2Xia Wang3Gangcheng Jiao4Xuan Liu5Hailin Wang6Key Laboratory of Photo-Electronic Imaging Technology and Systems, School of Optics and Photonics, Ministry of Education of China, Beijing Institute of Technology, Beijing 100081, ChinaKey Laboratory of Photo-Electronic Imaging Technology and Systems, School of Optics and Photonics, Ministry of Education of China, Beijing Institute of Technology, Beijing 100081, ChinaKey Laboratory of Photo-Electronic Imaging Technology and Systems, School of Optics and Photonics, Ministry of Education of China, Beijing Institute of Technology, Beijing 100081, ChinaKey Laboratory of Photo-Electronic Imaging Technology and Systems, School of Optics and Photonics, Ministry of Education of China, Beijing Institute of Technology, Beijing 100081, ChinaScience and Technology on Low-Light-Level Night Vision Laboratory, Xi’an 710065, ChinaKey Laboratory of Photo-Electronic Imaging Technology and Systems, School of Optics and Photonics, Ministry of Education of China, Beijing Institute of Technology, Beijing 100081, ChinaKey Laboratory of Photo-Electronic Imaging Technology and Systems, School of Optics and Photonics, Ministry of Education of China, Beijing Institute of Technology, Beijing 100081, ChinaImage intensifiers are used internationally as advanced military night-vision devices. They have better imaging performance in low-light-level conditions than CMOS/CCD. The intensified CMOS (ICMOS) was developed to satisfy the digital demand of image intensifiers. In order to make the ICMOS capable of color imaging in low-light-level conditions, a liquid-crystal tunable filter based color imaging ICMOS was developed. Due to the time-division color imaging scheme, motion artifacts may be introduced when a moving target is in the scene. To solve this problem, a deformable kernel prediction neural network (DKPNN) is proposed for joint denoising and motion artifact removal, and a data generation method which generates images with color-channel motion artifacts is also proposed to train the DKPNN. The results show that, compared with other denoising methods, the proposed DKPNN performed better both on generated noisy data and on real noisy data. Therefore, the proposed DKPNN is more suitable for color ICMOS denoising and motion artifact removal. A new exploration was made for low-light-level color imaging schemes.https://www.mdpi.com/1424-8220/21/11/3891color-intensified CMOSliquid-crystal tunable filterimage denoisingmotion artifactsconvolutional neural network |
| spellingShingle | Zhenghao Han Li Li Weiqi Jin Xia Wang Gangcheng Jiao Xuan Liu Hailin Wang Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS Sensors color-intensified CMOS liquid-crystal tunable filter image denoising motion artifacts convolutional neural network |
| title | Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS |
| title_full | Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS |
| title_fullStr | Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS |
| title_full_unstemmed | Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS |
| title_short | Denoising and Motion Artifact Removal Using Deformable Kernel Prediction Neural Network for Color-Intensified CMOS |
| title_sort | denoising and motion artifact removal using deformable kernel prediction neural network for color intensified cmos |
| topic | color-intensified CMOS liquid-crystal tunable filter image denoising motion artifacts convolutional neural network |
| url | https://www.mdpi.com/1424-8220/21/11/3891 |
| work_keys_str_mv | AT zhenghaohan denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos AT lili denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos AT weiqijin denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos AT xiawang denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos AT gangchengjiao denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos AT xuanliu denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos AT hailinwang denoisingandmotionartifactremovalusingdeformablekernelpredictionneuralnetworkforcolorintensifiedcmos |