Classification of Hull Blocks of Ships Using CNN with Multi-View Image Set from 3D CAD Data

被引:2
|
作者
Chon, Haemyung [1 ]
Oh, Daekyun [2 ]
Noh, Jackyou [1 ]
机构
[1] Kunsan Natl Univ, Dept Naval Architecture & Ocean Engn, Gunsan 54150, South Korea
[2] Mokpo Natl Maritime Univ, Dept Naval Architecture & Ocean Engn, Mokpo 58628, South Korea
关键词
ship hull block; 3D CAD data; convolutional neural network; multi-view imageset; image classification; binarization;
D O I
10.3390/jmse11020333
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
In order to proceed with shipbuilding scheduling involving hundreds of hull blocks of ships, it is important to mark the locations of the hull blocks with the correct block identification number. Incorrect information about the locations and the identification numbers of hull blocks causes disruption in the shipbuilding scheduling process of the shipyard. Therefore, it is necessary to have a system for tracking the locations and identification numbers of hull blocks in order to avoid time loss due to incorrectly identified blocks. This paper proposes a method to mark the identification numbers, which are necessary for the tracking system of hull blocks. In order to do this, 3 CNN (convolutional neural network) models, VGG-19, Resnet-152V2, and Densenet-201, are used to classify the hull blocks. A set of multi-view images acquired from 3D CAD data are used as training data to obtain a trained CNN model, and images from 3D printer-printed hull block models are used for the test of the trained CNN model. The datasets used for training and prediction are Non-Thr and Thr datasets, that each included both binarized and non-binarized datasets. As a result of end-to-end classification experiments with Non-Thr datasets, the highest prediction accuracy was 0.68 with Densenet-201. A total of 4050 experimental conditions were constructed by combining the threadhold of the Thr training and testing dataset. As a result of experiments with Thr datasets, the highest prediction accuracy of 0.96 was acquired with Resnet-152V2, which was trained with a threshold of 72 and predicted with a threshold of 50. In conclusion, the classification of ship hull blocks using a CNN model with binarized datasets of 3D CAD data is more effective than that using a CNN model with non-binarized datasets.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] MULTI-VIEW IMAGE COLOR CORRECTION USING 3D POINT SET REGISTRATION
    Jeong, Hyeonwoo
    Yoon, Byunghyun
    Jeong, Honggu
    Choi, Kang-Sun
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 1744 - 1748
  • [2] Volumetric and Multi-View CNNs for Object Classification on 3D Data
    Qi, Charles R.
    Su, Hao
    Niessner, Matthias
    Dai, Angela
    Yan, Mengyuan
    Guibas, Leonidas J.
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 5648 - 5656
  • [3] Multi-view expressive graph neural networks for 3D CAD model classification
    Li, Shuang
    Corney, Jonathan
    COMPUTERS IN INDUSTRY, 2023, 151
  • [4] Multi-View Image Capture for Glasses Free Multi-View 3D Displays
    Gurbuz, Sabri
    Yano, Sumio
    Iwasawa, Shoichiro
    Ando, Hiroshi
    IDW'10: PROCEEDINGS OF THE 17TH INTERNATIONAL DISPLAY WORKSHOPS, VOLS 1-3, 2010, : 2091 - 2094
  • [5] 3D Object Localisation from Multi-View Image Detections
    Rubino, Cosimo
    Crocco, Marco
    Del Bue, Alessio
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (06) : 1281 - 1294
  • [6] Multi-view Consensus CNN for 3D Facial Landmark Placement
    Paulsen, Rasmus R.
    Juhl, Kristine Aavild
    Haspang, Thilde Marie
    Hansen, Thomas
    Ganz, Melanie
    Einarsson, Gudmundur
    COMPUTER VISION - ACCV 2018, PT I, 2019, 11361 : 706 - 719
  • [7] Multi-view 3D display using waveguides
    Lee, Byoungho
    Lee, Chang-Kun
    INTERNATIONAL CONFERENCE ON OPTICAL AND PHOTONIC ENGINEERING (ICOPEN 2015), 2015, 9524
  • [8] Multi-view 3D reconstruction of seedling using 2D image contour
    Chen, Qingguang
    Huang, Shentao
    Liu, Shuang
    Zhong, Mingwei
    Zhang, Guohao
    Song, Liang
    Zhang, Xinghao
    Zhang, Jingcheng
    Wu, Kaihua
    Ye, Ziran
    Kong, Dedong
    BIOSYSTEMS ENGINEERING, 2024, 243 : 130 - 147
  • [9] Classification of 3D Archaeological Objects Using Multi-View Curvature Structure Signatures
    Canul-Ku, Mario
    Hasimoto-Beltran, Rogelio
    Jimenez-Badillo, Diego
    Ruiz-Correa, Salvador
    Roman-Rangel, Edgar
    IEEE ACCESS, 2019, 7 : 3298 - 3313
  • [10] Unsupervised Multi-View CNN for Salient View Selection and 3D Interest Point Detection
    Ran Song
    Wei Zhang
    Yitian Zhao
    Yonghuai Liu
    International Journal of Computer Vision, 2022, 130 : 1210 - 1227