为可靠完成图像退化处理，提升图像视觉质量，提出基于视觉传达的舰船遥感图像复原方法。该方法采用多项式校正方法获取控制点舰船图像坐标和坐标变换结果，依据变换关系校正舰船遥感图像的几何畸变；通过傅里叶变换方法变换校正后图像，将其变换至频率域内，在该域中分析舰船遥感图像退化过程后，采用超复数频域变换模型实现舰船遥感图像复原，获取复原后图像结果。测试结果表明：能够有效完成图像几何畸变校正，校正后图像对应坐标位置精准性显著提升；空间频率结果均在0.92以上；复原后图像的颜色、目标和背景的对比度等均显著提升，满足人眼视觉标准。
In order to reliably complete image degradation processing and improve image visual quality, a ship remote sensing image restoration method based on visual communication is proposed. This method uses polynomial correction method to obtain the coordinates and coordinate transformation results of the control point ship image, and corrects the geometric distortion of the ship remote sensing image based on the transformation relationship; The corrected image is transformed into frequency domain by Fourier transform method. After analyzing the degradation process of ship remote sensing image in this domain, the hypercomplex number frequency domain transform model is used to restore the ship remote sensing image and obtain the restored image results. The test results show that it can effectively correct the geometric distortion of the image, and the accuracy of the corresponding coordinate position of the corrected image is significantly improved. The spatial frequency results are all above 0.92, the color, target, and background contrast of the restored image have significantly improved, meeting human visual standards.
2023,45(17): 174-177 收稿日期：2023-03-09
DOI：10.3404/j.issn.1672-7649.2023.17.035
分类号：TP751
作者简介：邓智渊(1987-),女,硕士,讲师,研究方向为视觉传达
参考文献：
[1] 冯蕊涛, 杜清运, 罗恒, 等. 基于光流校正的复杂地形区多时相遥感影像配准[J]. 遥感学报, 2021, 25(2): 630-640.FENG Ruitao, DU Qingyun, LUO Heng, et al. A registration algorithm based on optical flow modification for multi-temporal remote sensing images covering the complex-terrain region[J]. Journal of Remote Sensing, 2021, 25(2): 630-640.
[2] 刘纪伟, 王晓东, 李云辉. 基于矩阵复原和暗通道理论的单色遥感图像去雾算法[J]. 液晶与显示, 2023, 38(2): 225-235.LIU Jiwei, WANG Xiaodong, LI Yun-hui. Dehazing algorithm of monochromatic remote sensing image based on matrix restoration and dark channel theory[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(2): 225-235.
[3] 王琪瑶, 胡琸悦, 李潇雁, 等. 基于局部最大和最小强度先验的遥感图像盲去模糊[J]. 激光与光电子学进展, 2023, 60(4): 429-436.WANG Qiyao, HU Zhuoyue, LI Xiaoyan, et al. Blind deblurring of remote sensing images based on local maximum and minimum intensity priors[J]. Laser & Optoelectronics Progress, 2023, 60(4): 429-436.
[4] 岳荣刚, 王世涛, 王虎妹, 等. 基于惯性参考基准的像移测量与图像复原[J]. 航天返回与遥感, 2021, 42(1): 125-134.YUE Ronggang, WANG Shitao, WANG Humei, et al. Image motion measurement and image restoration based on the inertial reference[J]. Spacecraft Recovery & Remote Sensing, 2021, 42(1): 125-134.
[5] 黄国兴, 刘艺鹏, 彭宏, 等. 洛伦兹拟合点扩展函数的遥感图像复原方法[J]. 光学学报, 2021, 41(16): 224-236.HUANG Guoxing, LIU Yipeng, PENG Hong, et al. Remote sensing image restoration method based on lorentz fitting point spread function[J]. Acta Optica Sinica, 2021, 41(16): 224-236.
[6] 张华卫, 贾文娟, 张金龙, 等. 基于二次约束与雾气分布的图像复原算法[J]. 激光与光电子学进展, 2021, 58(22): 450-459.ZHANG Huawei, JIA Wenjuan, ZHANG Jinlong, et al. Image restoration algorithm based on quadratic constraint and haze distribution[J]. Laser & Optoelectronics Progress, 2021, 58(22): 450-459.
[7] 顾勇翔, 蓝鑫, 伏博毅, 等. 基于几何适应与全局感知的遥感图像目标检测算法[J]. 计算机应用, 2023, 43(3): 916-922.Gu Yongxiang, Lan Xin, Fu Boyi, et al. Object detection algorithm for remote sensing images based on geometric adaptation and global perception[J]. Journal of Computer Applications, 2023, 43(3): 916-922.
