图像重建是图像处理领域中的重要组成部分，为提升图像重建质量，提出基于虚拟现实技术的低质量船舶三维图像重建方法。针对外部环境与采集设备等因素导致图像质量低的问题，采用虚拟现实技术的形态学滤波技术预处理初始船舶图像，通过膨胀、腐蚀与开启、闭合运算实现船舶图像增强处理；利用指数权重系数描述船舶图像特征；通过虚拟现实设备获取船舶三维图像最小识别距离，在船舶图像特征基础上，确定理论图像投影值与实际投影值间的偏差，利用偏差值校准船舶图像重建像素值，实现高精度船舶三维图像重建。实验结果显示，该方法增强后图像峰值信噪比提升14%以上，重建后图像结构相似性达到95%以上，清晰度显著提升。
Image reconstruction is an important component in the field of image processing. To improve the quality of image reconstruction, a low-quality ship 3D image reconstruction method based on virtual reality technology is studied. In response to the problem of low image quality caused by external environment and collection equipment, the morphological filtering technology of virtual reality technology is used to preprocess the initial ship image. The ship image enhancement processing is achieved through dilation, corrosion, opening, and closing operations; Using exponential weight coefficients to describe ship image features; Obtain the minimum recognition distance of ship 3D images through virtual reality devices, determine the deviation between the theoretical image projection value and the actual projection value based on ship image features, and use the deviation value to calibrate the pixel values of ship image reconstruction to achieve high-precision ship 3D image reconstruction. The experimental results show that the method enhances the peak signal-to-noise ratio of the image by more than 14%, and the structural similarity of the reconstructed image reaches more than 95%, significantly improving the clarity.
2023,45(20): 206-209 收稿日期：2023-4-14
DOI：10.3404/j.issn.1672-7649.2023.20.040
分类号：TP393
基金项目：河南省本科高校研究性教学改革研究与实践项目（2022SYJXLX097）；河南省职业教育教学改革研究与实践项目；河南工程学院博士培育基金项目（D2022036）
作者简介：周雷(1984-),男,博士,副教授,研究方向为海洋文化遗产保护及环境设计
参考文献：
[1] 许少秋, 余扬帆, 郭俊林, 等. 基于大场景三维点云的集装箱船关键绑扎特征识别与重建[J]. 船舶工程, 2022, 44(6): 127-133.
XU Shao-qiu, YU Yang-fan, GUO Jun-lin, et al. Identification and reconstruction of Key lashing features of container ships based on large scene 3D point cloud[J]. Ship Engineering, 2022, 44(6): 127-133.
[2] 毕军涛. 基于虚拟现实技术的3D图像重建方法[J]. 信息记录材料, 2022, 23(4): 133-135.
BI Jun-tao. 3D image reconstruction method based on virtual reality technology[J]. Information Recording Materials, 2022, 23(4): 133-135
[3] 石磊, 马丽茵. 基于稀疏度自适应的视觉图像三维清晰重构[J]. [J]. 计算机仿真, 2021, 38(3): 139-142.
SHI Lei, MA Li-yan. Three-dimensional clear reconstruction of visual images based on adaptive sparsity[J]. Computer Simulation, 2021, 38(3): 139-142.
[4] 姚程, 马彩文. 基于平面补丁的自适应八叉树三维图像重建[J]. [J]. 光学精密工程, 2022, 30(9): 1113-1122.
YAO Cheng, MA Cai-wen. Adaptive octree 3D image reconstruction based on plane patch[J]. Optics and Precision Engineering, 2022, 30(9): 1113-1122.
[5] 杨晓, 任鸿翔, 廉静静, 等. VR交互式三维虚拟船舶建模与仿真[J]. 中国航海, 2022, 45(1): 37-49.
YANG Xiao, REN Hong-xiang, LIAN Jing-jing, et al. 3D virtual ship construction and simulation through vr interactive technology[J]. Navigation of China, 2022, 45(1): 37-49.
[6] 王震, 盖孟, 许恒硕. 基于虚拟现实技术的三维场景图像表面重建算法[J]. 吉林大学学报(工学版), 2022, 52(7): 1620-1625.
WANG Zhen, GAI Meng, XU Heng-shuo. A surface reconstruction algorithm for 3D scene images based on virtual reality technology[J]. Journal of Jilin University (Engineering Edition), 2022, 52(7): 1620-1625.
[7] 时光志, 周毅, 李萌, 等. 基于虚拟现实技术的LNG船舶仿真系统[J]. 船海工程, 2021, 50(3): 25-28+33.
SHI Guang-zhi, ZHOU Yi, LI Meng, et al. LNG ship navigation simulation system based on virtual reality technology[J]. Ship & Ocean Engineering, 2021, 50(3): 25-28+33.
