An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction
The problems of the neural network-based nonuniformity correction algorithm for infrared focal plane arrays mainly concern slow convergence speed and ghosting artifacts. In general, the more stringent the inhibition of ghosting, the slower the convergence speed. The factors that affect these two pro...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/1/211 |
| _version_ | 1797999253098856448 |
|---|---|
| author | Yiyang Li Weiqi Jin Jin Zhu Xu Zhang Shuo Li |
| author_facet | Yiyang Li Weiqi Jin Jin Zhu Xu Zhang Shuo Li |
| author_sort | Yiyang Li |
| collection | DOAJ |
| description | The problems of the neural network-based nonuniformity correction algorithm for infrared focal plane arrays mainly concern slow convergence speed and ghosting artifacts. In general, the more stringent the inhibition of ghosting, the slower the convergence speed. The factors that affect these two problems are the estimated desired image and the learning rate. In this paper, we propose a learning rate rule that combines adaptive threshold edge detection and a temporal gate. Through the noise estimation algorithm, the adaptive spatial threshold is related to the residual nonuniformity noise in the corrected image. The proposed learning rate is used to effectively and stably suppress ghosting artifacts without slowing down the convergence speed. The performance of the proposed technique was thoroughly studied with infrared image sequences with both simulated nonuniformity and real nonuniformity. The results show that the deghosting performance of the proposed method is superior to that of other neural network-based nonuniformity correction algorithms and that the convergence speed is equivalent to the tested deghosting methods. |
| first_indexed | 2024-04-11T11:00:36Z |
| format | Article |
| id | doaj.art-3044726b6b494bc6a2acbd3e2f84339f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T11:00:36Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3044726b6b494bc6a2acbd3e2f84339f2022-12-22T04:28:36ZengMDPI AGSensors1424-82202018-01-0118121110.3390/s18010211s18010211An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity CorrectionYiyang Li0Weiqi Jin1Jin Zhu2Xu Zhang3Shuo Li4School of Optoelectronics, Beijing Institute of Technology, Key Laboratory of Photo-electronic Imaging Technology and System, Ministry of Education of China, Beijing 100081, ChinaSchool of Optoelectronics, Beijing Institute of Technology, Key Laboratory of Photo-electronic Imaging Technology and System, Ministry of Education of China, Beijing 100081, ChinaSchool of Optoelectronics, Beijing Institute of Technology, Key Laboratory of Photo-electronic Imaging Technology and System, Ministry of Education of China, Beijing 100081, ChinaSchool of Optoelectronics, Beijing Institute of Technology, Key Laboratory of Photo-electronic Imaging Technology and System, Ministry of Education of China, Beijing 100081, ChinaSchool of Optoelectronics, Beijing Institute of Technology, Key Laboratory of Photo-electronic Imaging Technology and System, Ministry of Education of China, Beijing 100081, ChinaThe problems of the neural network-based nonuniformity correction algorithm for infrared focal plane arrays mainly concern slow convergence speed and ghosting artifacts. In general, the more stringent the inhibition of ghosting, the slower the convergence speed. The factors that affect these two problems are the estimated desired image and the learning rate. In this paper, we propose a learning rate rule that combines adaptive threshold edge detection and a temporal gate. Through the noise estimation algorithm, the adaptive spatial threshold is related to the residual nonuniformity noise in the corrected image. The proposed learning rate is used to effectively and stably suppress ghosting artifacts without slowing down the convergence speed. The performance of the proposed technique was thoroughly studied with infrared image sequences with both simulated nonuniformity and real nonuniformity. The results show that the deghosting performance of the proposed method is superior to that of other neural network-based nonuniformity correction algorithms and that the convergence speed is equivalent to the tested deghosting methods.http://www.mdpi.com/1424-8220/18/1/211fixed pattern noisenonuniformity correctionnoise estimationneural network |
| spellingShingle | Yiyang Li Weiqi Jin Jin Zhu Xu Zhang Shuo Li An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction Sensors fixed pattern noise nonuniformity correction noise estimation neural network |
| title | An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction |
| title_full | An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction |
| title_fullStr | An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction |
| title_full_unstemmed | An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction |
| title_short | An Adaptive Deghosting Method in Neural Network-Based Infrared Detectors Nonuniformity Correction |
| title_sort | adaptive deghosting method in neural network based infrared detectors nonuniformity correction |
| topic | fixed pattern noise nonuniformity correction noise estimation neural network |
| url | http://www.mdpi.com/1424-8220/18/1/211 |
| work_keys_str_mv | AT yiyangli anadaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT weiqijin anadaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT jinzhu anadaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT xuzhang anadaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT shuoli anadaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT yiyangli adaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT weiqijin adaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT jinzhu adaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT xuzhang adaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection AT shuoli adaptivedeghostingmethodinneuralnetworkbasedinfrareddetectorsnonuniformitycorrection |