本文开展基于总布置图二维图片的船舶舱室特征点识别和舱室自动搜索的技术和方法研究。应用图像处理技术中的Harris角点识别和Canny边缘处理技术实现了对舱室特征点的自动识别、定位和分类。本文提出优先右转搜索算法，实现了根据舱室特征点对规则形状舱室的自动识别；提出不规则形状舱室特征点处理算法，实现了对不规则形状舱室的自动识别。基于得到的舱室信息数据，可自动生成二维舱室图，并实现舱室的三维数字化建模。
The technology and method of cabin feature point recognition and cabin automatic search based on the two-dimensional picture of the cabin in the general arrangement of the ship were carried out. Harris corner recognition and Canny edge processing technology in image processing technology are used to realize the automatic identification, positioning and classification of cabin feature points.A preferential right-turn search algorithm was proposed, which realized the automatic recognition of the regular-shaped cabin according to the feature points of the cabin. A feature point processing algorithm for irregularly shaped cabins was proposed, which realized the automatic recognition of irregularly shaped cabins. Based on the obtained cabin information data, the two-dimensional cabin diagram can be automatically generated, and the three-dimensional digital modeling of the cabin can be realized.
2025,47(20): 165-169 收稿日期：2024-11-1
DOI：10.3404/j.issn.1672-7649.2025.20.025
分类号：U695；U169
作者简介：杨明瑶(2000-),女,硕士研究生,研究方向为船舶数字化设计技术
参考文献：
[1] 刘寅东. 高等船舶设计原理[M]. 大连: 大连海事大学出版社, 2021.
[2] SUN C, HSIAO C W, SUN M, et al. HorizonNet: learning room layout with 1D representation and panostretch data augmentation [C]//Proceedings of 2019 IEEE/ CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, US, 2019.
[3] YANG S T, WANG F E, PENG C H, et al. DuLa-Net: a dual projection network for estimating room layouts from a single RGB panorama[C]//Proceedings of 2019 IEEE/ CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, US, 2019.
[4] ZOU C, COLBURM A, SHAN Q, et al . Layoutnet: reconstructing the 3d room layout from a single rgb image[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, US, 2018.
[5] ZHANG W D, ZHANG W, ZHANG Y D. Geo Layout: geometry driven room layout estimation based on depth maps of planes[C]// Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2020.
[6] CHENY X, WANG C X. Two-stage Floor Plan Recognition with a Network Employing Attention Mechanism[C]//2024 IEEE 14th International Conference on Electronics Information and Emergency Communication (ICEIEC). Beijing, China, 2024.
[7] ZHAO Y F, DENG X Y, LAI H H. Reconstructing BIM from 2D structural drawings for existing buildings[J]. Automation in Construction, 2021, 128.
[8] H JANG, K YU et al. , Indoor reconstruction from floorplan images with a deep learning approach [J]. International Journal of Geo-Information, 2020, 9(2): 65.
[9] 翟凌宇. 室内场景的房间空间分割与三维重建方法研究[D]. 西安: 西安理工大学, 2024.
[10] 姜志刚. 基于全景图的房间布局重建算法研究[D]. 上海: 华东师范大学, 2022.
[11] 张宏鑫, 方雨桐, 刘木水, 等. 复杂建筑平面图纸的空间布局融合对偶识别方法[J]. 武汉大学学报(信息科学版), 2021, 46(9): 1354-1361.
[12] LIU C, WU J J, KOHLI P, et al. Raster-to-vector: revisiting floorplan transformation[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy, 2017.
[13] 王晓琦, 赵旸, 张键, 等. 基于深度学习的船体三维模型自动生成方法[J]. 兵工学报, 2022, 43(S2): 115-119.
[14] 王赛赛, 周阿维. 基于Canny-Harris角点检测的光学元件表面疵病检测[J]. 机械与电子, 2024, 42(8): 26-33.
