The linear array push-broom optical satellite sensors are prone to vignetting and striping noise due to optical stitching and uneven sensor response, particularly under high dynamic range and low brightness conditions, where nonlinear effects become more pronounced. To address this issue, this paper proposes a relative radiometric calibration method based on an end-to-end multi-scale residual network. First, a high-quality sample set is constructed for training by selecting samples using a piecewise linear correction. Then, a multi-scale residual network is built, combining multi-scale feature extraction modules and skip connections to extract and integrate the features of vignetting and striping noise, and subsequently remove them from the original image. Experiments using GF1B multispectral images demonstrate that the proposed method effectively removes inter-frame vignetting and intra-frame striping. The striping coefficient decreases by 26.31% and 21.04% compared to traditional linear and piecewise linear methods, while the relative standard deviation decreases by 66.53% and 52.32%, respectively. Compared to statistical methods and deep learning denoising models, the proposed method maintains high accuracy and shows good generalization performance on GF1C and GF1D images.
[1] Dinguirard M, Slater P N.Calibration of space-multispectral imaging sensors A review[J]. Remote Sensing of Environment, 1999, 68(3): 194-205. DOI:10.1016/S0034-4257(98)00111-4.
[2] Li L T, Zhang G, Jiang Y H, et al.An improved on-orbit relative radiometric calibration method for agile high-resolution optical remote-sensing satellites with sensor geometric distortion[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5606715. DOI:10.1109/TGRS.2021.3078815.
[3] 段依妮, 张立福, 晏磊, 等. 遥感影像相对辐射校正方法及适用性研究[J]. 遥感学报, 2014, 18(3): 597-617. DOI:10.11834/jrs.20143204.
[4] Wang J, Gu X, Ming T, et al.Classification and gradation rule for remote sensing satellite data products[J]. National Remote Sensing Bulletin, 2013, 17(3): 566-577. DOI:10.11834/jrs.20131364.
[5] 刘扬, 方俊永, 刘学, 等. 基于滤光片转轮式多光谱相机的辐射校正[J]. 中国科学院大学学报(中英文), 2024, 41(5): 636-643. DOI:10.7523/j.ucas.2022.083.
[6] 师英蕊, 姜洋, 李立涛, 等. 光学卫星常态化相对辐射定标方法研究[J]. 地球信息科学学报, 2020, 22(12): 2410-2424. DOI:10.12082/dqxxkx.2020.190536.
[7] 宋瑞. 基于相对辐射定标的高光谱成像去条带噪声方法研究[D]. 南京: 南京林业大学, 2022. DOI:10.27242/d.cnki.gnjlu.2022.000051.
[8] 郭建宁, 于晋, 曾湧, 等. CBERS-01/02卫星CCD图像相对辐射校正研究[J]. 中国科学E辑:信息科学, 2005, 35(S1): 11-25. DOI:10.3969/j.issn.1674-7259.2005.z1.002.
[9] Ratliff B M, Hayat M M, Hardie R C.An algebraic algorithm for nonuniformity correction in focal-plane arrays[J]. Journal of the Optical Society of America. A, Optics, Image Science, and Vision, 2002, 19(9): 1737-1747. DOI:10.1364/jossa.19.001737.
[10] Li Z, Wei J, Huang X, et al.Laboratory radiometric calibration technique of an imaging system with pixel-level adaptive gain[J]. Sensors, 2023, 23(4): 2083. DOI:10.3390/s23042083.
[11] 王灵丽, 武红宇, 白杨, 等. 基于可展开式太阳漫反射板的星上相对辐射定标[J]. 遥感学报, 2021, 25(10): 2067-2075. DOI:10.11834/jrs. 20210064.
[12] Begeman C. Helder D, Leigh L, et al.Relative radiometric correction of pushbroom satellites using the yaw maneuver[J]. Remote Sensing, 2022, 14(12): 2820. DOI:10.3390/rs14122820.
[13] Chen R, Wang M, Pi Y D, et al.An improved side-slither relative radiometric calibration method for WFV satellite: taking HY1D CZI as an example[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 10893-10913. DOI:10.1109/JSTARS.2024.3402812.
[14] 陈儒, 韩静雨, 王密, 等. 海洋一号D卫星海岸带成像仪偏航90°相对辐射定标[J]. 遥感学报, 2023, 27(1): 43-54. DOI:10.11834/jrs.20221611.
[15] 杨赞伟. 基于CMOS传感器的高光谱遥感图像非均匀性校正技术研究 [D]. 长春:中国科学院大学(中国科学院长春光学精密机械与物理研究所), 2020. DOI:10.27522/d.cnki.gkcgs.2020.000101.
[16] Bian J, Hu Z Y, Wang Q Y, et al.Nonlinear response correction based on fully connected neural network[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 7000605. DOI:10.1109/LGRS.2024.3367175.
[17] 王玲, 胡秀清, 郑照军, 等. 联合南北极冰雪目标的FY-3A/MERSI辐射定标跟踪监测[J]. 光学学报, 2018, 38(2): 0212003. DOI:10.3788/AOS201838.0212003.
[18] 李海超, 满益云. 基于非均匀同区域线性CCD成像的卫星姿态调整与非线性定标方法[J]. 红外与激光工程, 2015, 44(4): 1370. DOI:10.3969/j.issn.1007-2276.2015.04.045.
[19] Kim N, Han S S, Jeong C S.ADOM: ADMM-based optimization model for stripe noise removal in remote sensing image[J]. IEEE Access, 2023, 11: 106587-10606. DOI:10.1109/ACCESS.2023.3319268.
[20] 张兵. 遥感大数据时代与智能信息提取[J]. 武汉大学学报(信息科学版), 2018, 43(12): 1861-1871. DOI:10.13203/j.whugis20180172.
[21] 刘李, 高海亮, 潘志强, 等. 基于深度学习的在轨辐射定标方法研究[J]. 航天返回与遥感, 2017, 38(2): 64-71. DOI:10.3969/j.issn.1009-8518.2017.02.009.
[22] Guan J T, Lai R, Xiong A.Wavelet deep neural network for stripe noise removal[J]. IEEE Access, 2019, 7: 44544-445554. DOI:10.1109/ACCESS.2019.2908720.
[23] Xiao P F, Guo Y C, Zhuang P X.Removing stripe noise from infrared cloud images via deep convolutional networks[J]. IEEE Photonics Journal, 2018, 10(4): 7801114. DOI:10.1109/JPHOT.2018.2854303.
[24] Yu X, Fan J F, Zhang M Z, et al.Relative radiation correction based on CycleGAN for visual perception improvement in high-resolution remote sensing images[J]. IEEE Access, 2021, 9: 106627-106640. DOI:10.1109/ACCESS.2021.3101110.
[25] Adegun A A, Viriri S, Tapamo J R.Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis[J]. Journal of Big Data, 2023, 10(1): 93. DOI:10.1186/s40537-023-00772-x.
[26] He K M, Zhang X Y, Ren S Q, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:770-778. DOI:10.1109/CVPR.2016.90.
[27] Shi W Z, Caballero J, Huszár F, et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 1874-1883. DOI:10.1109/CVPR.2016.207.
[28] 敖为赳, 陈文志, 童英良. GF-1B、C、D星数据质量在轨测试评价研究[J]. 浙江国土资源, 2019(2): 46-49. DOI:10.16724/j.cnki.cn33-1290/p.2019.02.026.
