다시점 영상 집합을 활용한 선체 블록 분류를 위한 CNN 모델 성능 비교 연구

다국어 초록 (Multilingual Abstract)

It is important to identify the location of ship hull blocks with exact block identification number when scheduling the shipbuilding process. The wrong information on the location and identification number of some hull block can cause low productivity by spending time to find where the exact hull block is. In order to solve this problem, it is necessary to equip the system to track the location of the blocks and to identify the identification numbers of the blocks automatically. There were a lot of researches of location tracking system for the hull blocks on the stockyard. However there has been no research to identify the hull blocks on the stockyard. This study compares the performance of 5 Convolutional Neural Network (CNN) models with multi-view image set on the classification of the hull blocks to identify the blocks on the stockyard. The CNN models are open algorithms of ImageNet Large-Scale Visual Recognition Competition (ILSVRC). Four scaled hull block models are used to acquire the images of ship hull blocks. Learning and transfer learning of the CNN models with original training data and augmented data of the original training data were done. 20 tests and predictions in consideration of five CNN models and four cases of training conditions are performed. In order to compare the classification performance of the CNN models, accuracy and average F1-Score from confusion matrix are adopted as the performance measures. As a result of the comparison, Resnet-152v2 model shows the highest accuracy and average F1-Score with full block prediction image set and with cropped block prediction image set.

참고문헌 (Reference)

1 김병철, "합성곱 신경망을 이용한 3차원 스캐닝 점군 데이터의 플랜트 기자재 형상 인식" 대한기계학회 42 (42): 863-869, 2018

2 박성욱, "전이학습에 방법에 따른 컨벌루션 신경망의영상 분류 성능 비교" 한국멀티미디어학회 21 (21): 1387-1395, 2018

3 변영현, "자동차 주행환경에서 보행자 분류를 위한 딥러닝 모델의 전이학습 및 성능비교" 한국정보기술학회 16 (16): 83-92, 2018

4 남병욱, "의사결정트리 학습을 적용한 조선소 블록 적치 위치 선정에 관한 연구" 대한조선학회 54 (54): 421-429, 2017

5 Zeiler, M. D., "Visualizing and understanding convolutional networks" 818-833, 2014

6 Simonyan, K., "Very deep convolutional networks for large-scale image recognition" 2014

7 Lee, Y. H., "Study on the positioning system for logistics of ship-block" 68-75, 2008

8 Szegedy, C., "Rethinking the inception architecture for computer vision" 2818-2826, 2016

9 Mun, S. H., "Real time block locating system for shipbuilding through GNSS and IMU fusion" Pusan National University 2019

10 이장현, "PDA 및 GPS를 이용한 옥외 작업장 블록 위치 추적 시스템 개발" 대한조선학회 43 (43): 803-811, 2006

11 Zhou, B., "Object detectors emerge in deep scene cnns" 2014

12 Zoph, B., "Learning transferable architectures for scalable image recognition" 8697-8710, 2018

13 Zhou, B., "Learning deep features for discriminative localization" 2921-2929, 2016

14 Krizhevsky, A., "Imagenet classification with deep convolutional neural networks" 1097-1105, 2012

15 Standford University, "ILSVRC"

16 Yosinski, J., "How transferable are features in deep neural networks?" 3320-3328, 2014

17 LeCun, Y., "Gradient-based learning applied to document recognition" 86 (86): 2278-2324, 1998

18 Szegedy, C., "Going deeper with convolutions" 1-9, 2014

19 Srivastava, N., "Dropout : a simple way to prevent neural networks from overfitting" 15 (15): 1929-1958, 2014

20 Kim, J.O., "Development of real time location measuring and logistics system for assembled block in shipbuilding" 834-839, 2009

21 Kim, M. S., "Determination of arrangement and take-out path in ship block stockyard considering available space and obstructive block" 433-438, 2013

22 Huang, G., "Densely connected convolutional networks" 4700-4708, 2017

23 He, K., "Deep residual learning for image recognition" 770-778, 2016

24 Francois, C., "Deep learning with Python" Gilbut Publichin Co,. Ltd 2018

25 Saito, G., "Deep learning from scratch" Hanbit Media, lnc 2017

26 Donahue, J., "Decaf: A deep convolutional activation feature for generic visual recognition" 647-655, 2014

27 Cho, D. Y., "Block and logistics simulation" 48 (48): 24-29, 2011

28 Pan, S. J., "A survey on transfer learning" 22 (22): 1345-1359, 2009

29 Kang, J. H., "A study on mobile block logistics system for shipyard" Mokpo National Unive 2014