{"title":"基于正则化约束的高斯曲面拟合非均匀校正算法","authors":"Ruzhou Li, Yu Shi, Zhigao Huang","doi":"10.1109/AICIT55386.2022.9930169","DOIUrl":null,"url":null,"abstract":"Due to the limitation of hardware, infrared optical systems often have thermal radiation noise effects on the acquired images. Although the effect of thermal radiation on image quality can be reduced with proper optical design, it is expensive and cannot completely eliminate the effect of thermal radiation. To solve this problem, for the purpose of improving the image quality after imaging, we propose a novel image non-uniformity correction method. The optical head cover of the imaging system is usually semi-circular, and the thermal radiation effect conforms to the Gaussian distribution. Therefore, this paper firstly preprocesses the degraded image, including Gaussian surface fitting and image layering, and then introduces the preprocessing results into In the correction model, frame wave regularization constraints are imposed on the potential clear images, and the Gaussian surface fitting regularization term is introduced into the thermal radiation correction model, and the clear images and thermal radiation effect maps are estimated by Split Bregman iterative optimization. The experimental results show that our proposed method can perform the non-uniform correction caused by thermal radiation noise well.","PeriodicalId":231070,"journal":{"name":"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)","volume":"298 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Nonuniform Correction Algorithm Based on Regularization Constraints of Gaussian Surface Fitting\",\"authors\":\"Ruzhou Li, Yu Shi, Zhigao Huang\",\"doi\":\"10.1109/AICIT55386.2022.9930169\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Due to the limitation of hardware, infrared optical systems often have thermal radiation noise effects on the acquired images. Although the effect of thermal radiation on image quality can be reduced with proper optical design, it is expensive and cannot completely eliminate the effect of thermal radiation. To solve this problem, for the purpose of improving the image quality after imaging, we propose a novel image non-uniformity correction method. The optical head cover of the imaging system is usually semi-circular, and the thermal radiation effect conforms to the Gaussian distribution. Therefore, this paper firstly preprocesses the degraded image, including Gaussian surface fitting and image layering, and then introduces the preprocessing results into In the correction model, frame wave regularization constraints are imposed on the potential clear images, and the Gaussian surface fitting regularization term is introduced into the thermal radiation correction model, and the clear images and thermal radiation effect maps are estimated by Split Bregman iterative optimization. The experimental results show that our proposed method can perform the non-uniform correction caused by thermal radiation noise well.\",\"PeriodicalId\":231070,\"journal\":{\"name\":\"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)\",\"volume\":\"298 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AICIT55386.2022.9930169\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Artificial Intelligence and Computer Information Technology (AICIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AICIT55386.2022.9930169","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Nonuniform Correction Algorithm Based on Regularization Constraints of Gaussian Surface Fitting
Due to the limitation of hardware, infrared optical systems often have thermal radiation noise effects on the acquired images. Although the effect of thermal radiation on image quality can be reduced with proper optical design, it is expensive and cannot completely eliminate the effect of thermal radiation. To solve this problem, for the purpose of improving the image quality after imaging, we propose a novel image non-uniformity correction method. The optical head cover of the imaging system is usually semi-circular, and the thermal radiation effect conforms to the Gaussian distribution. Therefore, this paper firstly preprocesses the degraded image, including Gaussian surface fitting and image layering, and then introduces the preprocessing results into In the correction model, frame wave regularization constraints are imposed on the potential clear images, and the Gaussian surface fitting regularization term is introduced into the thermal radiation correction model, and the clear images and thermal radiation effect maps are estimated by Split Bregman iterative optimization. The experimental results show that our proposed method can perform the non-uniform correction caused by thermal radiation noise well.