为提升舰船三维重构结果的细节丰富度，在双目视觉支持下提出红外遥感舰船图像三维重构设计方法。通过像素坐标系与世界坐标系的转换，融合可见光图像与红外遥感图像的点云信息。从可见光图像与红外遥感图像融合结果中提取舰船目标的质心、质心区域灰度以及舰船区域面积的特征点。利用半全局匹配算法，匹配提取特征点。依据匹配结果采用三角化曲面算法实现舰船图像三维重构。实验结果表明，该方法重构获取的舰船图像，细节丰富，未出现空洞或细节丢失情况。
To enhance the detail richness of ship 3D reconstruction results, a design method for infrared remote sensing ship image 3D reconstruction is proposed with the support of binocular vision. By converting the pixel coordinate system to the world coordinate system, the point cloud information of visible light images and infrared remote sensing images is fused. Extract the centroid, centroid region grayscale, and ship area feature points of ship targets from the fusion results of visible light images and infrared remote sensing images. Utilize semi global matching algorithm to extract feature points for matching. Based on the matching results, the triangulation surface algorithm is used to achieve three-dimensional reconstruction of ship images. The experimental results show that the reconstructed ship image obtained by this method has rich details and no voids or loss of details.
2023,45(22): 202-205 收稿日期：2023-9-14
DOI：10.3404/j.issn.1672-7649.2023.22.039
分类号：TP391
基金项目：郑州市社会科学调研课题(ZSLX20210678)
作者简介：赵金(1988-),男,硕士,讲师,研究方向为计算机图像、视觉传达及美术学
参考文献：
[1] 裘莉娅, 陈玮琳, 李范鸣, 等. 复杂背景下基于LBP纹理特征的运动目标快速检测算法[J]. 红外与毫米波学报, 2022, 41(3): 639-651.
QIU Li-ya, CHEN Wei-lin, LI Fan-ming, et al. Fast moving target detection algorithm based on LBP texture feature in complex background[J]. Journal of Infrared and Millimeter Waves, 2022, 41(3): 639-651.
[2] 胡利平, 闫华, 钟卫军, 等. 舰船目标三维散射中心建模及SAR快速仿真方法[J]. 西安电子科技大学学报, 2021, 48(2): 72-83.
HU Li-ping, YAN Hua, ZHONG Wei-jun, et al. Three-dimensional scattering center modeling and a fast SAR simulation method for ship targets[J]. Journal of Xidian University(Natural Science), 2021, 48(2): 72-83.
[3] 刘哲军. 视觉传达约束下三维图像虚拟重建[J]. 哈尔滨工程大学学报, 2022, 43(4): 536-540.
LIU Zhe-jun. Virtual reconstruction of 3D images under visual communication constraints[J]. Journal of Harbin Engineering University, 2022, 43(4): 536-540.
[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 Hui-ying, WANG Chun-ping, 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] 庄苏锋, 屠大维, 张旭, 等. 水下双目立体视觉对应点匹配与三维重建方法研究[J]. 仪器仪表学报, 2022, 43(5): 147-154.
ZHUANG Su-feng, TU Da-wei, ZHANG Xu, et al. Research on corresponding point matching and 3D reconstruction of underwater binocular stereo vision[J]. Chinese Journal of Scientific Instrument, 2022, 43(5): 147-154.
[6] 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]. 计算机仿真, 2021, 38(3): 139-142.
SHI Lei, MA Li-yin. Three-dimensional clear reconstruction of visual images based on adaptive sparsity[J]. Computer Simulation, 2021, 38(3): 139-142.
[7] 成艳, 于雪莲, 钱惟贤, 等. 红外遥感图像舰船尾迹提取及检测[J]. 红外与激光工程, 2022, 51(2): 32-39.
CHENG Yan, YU Xue-lian, QIAN Wei-xian, et al. Ship wake extraction and detection from infrared remote sensing images[J]. Infrared and Laser Engineering, 2022, 51(2): 32-39.
[8] 刘万军, 高健康, 曲海成, 等. 多尺度特征增强的遥感图像舰船目标检测[J]. 自然资源遥感, 2021, 33(3): 97-106.
LIU Wan-jun, GAO Jian-kang, QU Hai-cheng, et al. Ship detection based on multi-scale feature enhancement of remote sensing images[J]. Remote Sensing for Natural Resources, 2021, 33(3): 97-106.
