针对虚拟多视点舰船图像生成时，图像背景容易出现局部缺失的问题，研究虚拟多视点舰船图像背景局部缺失修复方法。依据舰船的多视点图像及相应视差图，利用反向映射方法生成舰船虚拟视点图像，将消除伪影后的舰船虚拟视点图像，合成为虚拟多视点舰船图像。利用图切割方法，构建虚拟多视点舰船图像前景与背景标号对应的吉布斯能量方程，确定各像素点的标号，自动分割虚拟多视点舰船图像。利用快速行进算法，依据由外至内的次序，依次修复图像背景中的局部缺失点，实现虚拟多视点舰船图像背景的局部缺失修复。实验结果表明，该方法可有效修复虚拟多视点舰船图像背景中的局部缺失，修复后图像像素点的峰值信噪比高于25 dB。
Aiming at the problem of local missing background in virtual multi view ship image generation, a method for repairing local missing background in virtual multi view ship image is studied. Based on the multi view image and corresponding disparity map of the ship, a reverse mapping method is used to generate a virtual view image of the ship. After eliminating artifacts, the virtual view image of the ship is synthesized into a virtual multi view ship image. Using graph cutting method, construct Gibbs energy equations corresponding to foreground and background labels of virtual multi view ship images, determine the labels of each pixel, and automatically segment virtual multi view ship images. Using the fast marching algorithm, local missing points in the image background are sequentially repaired in order from outside to inside, achieving local missing repair of virtual multi view ship image background. The experimental results show that this method effectively repairs local missing points in the background of virtual multi view ship images, and the peak signal-to-noise ratio of the repaired image pixels is higher than 25 dB.
2024,46(3): 161-164 收稿日期：2023-09-06
DOI：10.3404/j.issn.1672-7649.2024.03.029
分类号：TP393
作者简介：赵善利(1982-),男,硕士,副教授,研究方向为动画及三维动画虚拟仿真
参考文献：
[1] 林鑫伟, 徐志京, 黄海. 复杂背景下的SAR图像多尺度舰船检测[J]. 中国航海, 2023, 46(2): 17-24+32.
LIN Xinwei, XU Zhijing, HUANG Hai. Multi-scale detection of ship target against complex background out of SAR image[J]. Navigation of China, 2023, 46(2): 17-24+32.
[2] 黎经元, 厉小润, 赵辽英. 融合空频域特征的光学遥感图像舰船目标检测[J]. 激光与光电子学进展, 2021, 58(4): 357-365.
LI Jingyuan, LI Xiaorun, ZHAO Liaoying. Ship target detection in optical remote sensing images based on spatial and frequency features[J]. Laser & Optoelectronics Progress, 2021, 58(4): 357-365.
[3] 崔宗勇, 王晓雅, 施君南, 等. 基于中心点回归的大场景SAR图像舰船检测方法[J]. 电波科学学报, 2022, 37(1): 153-161.
CUI Zongyong, WANG Xiaoya, SHI Junnan, et al. Ship detection in large scene SAR images based on target center point regression[J]. Chinese Journal of Radio Science, 2022, 37(1): 153-161.
[4] 王慧赢, 王春平, 付强, 等. 面向嵌入式平台的轻量级光学遥感图像舰船检测[J]. 光学学报, 2023, 43(12): 121-134.
WANG Huiying, WANG Chunping, FU Qiang, et al. Lightweight ship detection based on optical remote sensing images for embedded platform[J]. Acta Optica Sinica, 2023, 43(12): 121-134.
[5] 樊瑶,石英男,柏劲咸. 基于边缘与注意力跨层转移的图像修复模型[J]. 计算机工程, 2023, 49(6): 180-192.
FAN Yao, SHI Yingnan, BAI Jinxian. Image Restoration Model Based on Edge and Attention Cross layer Transfer[J]. Computer Engineering, 2023, 49(6): 180-192.
[6] 胡秋生,胡璋. 基于变分自编码器的非规则缺失图像修复仿真[J]. 计算机仿真, 2021, 38(12): 155-159.
HU Qiusheng, HU Zhang. Simulation of Irregular Missing Image Restoration Based on Variational Autoencoder[J]. Computer Simulation, 2021, 38(12): 155-159.
[7] 秦娟英. 应用均值滤波的舰船红外图像规整化复原算法[J]. 舰船科学技术, 2023, 45(13): 182-185.
QIN Juanying. The regularization and restoration algorithm of ship infrared image using mean filtering[J]. Ship Science and Technology, 2023, 45(13): 182-185.
[8] 刘康, 冼楚华, 李桂清. 多尺度特征融合的透明物体深度图像快速修复方法[J]. 计算机辅助设计与图形学学报, 2023, 35(2): 312-319.
LIU Kang, XIAN Chuhua, LI Guiqing. Fast repair method of transparent object depth image based on multi-scale fusion[J]. Journal of Computer-Aided Design & Computer Graphics, 2023, 35(2): 312-319.
[9] 李海军, 孔繁程, 魏嘉彧, 等. 基于直觉模糊集和CLAHE红外舰船图像增强算法[J]. 兵器装备工程学报, 2022, 43(11): 88-94.
LI Haijun, KONG Fancheng, WEI Jiayu, et al. Based on intuitionistic fuzzy set and CLAHE infrared ship image enhancement algorithm[J]. Journal of Ordnance Equipment Engineering, 2022, 43(11): 88-94.
