 |
S. G. Chernyi, A. N. Ivanovskii Automated System for Ship Draught Measurement with Component of Intelligent Systems |
 |
|
Abstract.
Knowing ship draught is vital for calculating cargo mass onboard of marine vessel. Even small error in its measurement can lead to significant loss of cargo. Although many tools and methods for ship draught reading have been developed, none of them can provide sufficient accuracy. Also, every known method assumes human participation in measurement process. To eliminate the human factor, we propose to develop automated system which will provide sufficient for practical needs accuracy. It includes UAV with digital camera based on it, ship clinometers and computing section. We consider a method, based on processing of draught marks video with neural networks. YOLOv5 convolutional neural network has been used for digits detection, and U-Net convolutional neural network for segmentation of water surface area on each frame. Of note, we look over the concept of ship draught in term of stochastic process and took into account ship heel and trim, as they significantly affect the final result.
Keywords:
UAV, intelligent, ship draught, neural networks, YOLOv5, U-Net.
PP. 59-69.
DOI 10.14357/20718632220207 References
1. ECE/ENERGY/19 – Code of uniform standards and procedures for the performance of draught surveys of coal cargoes. Economic Commission for Europe, United Nations. 1992. – 192 p. 2. Elnoury A., Gaber E. Accuracy of draught survey process and affecting factors // International Journal of Research in Engineering & Technology. 2018. p. 19–27. 3. Final loading manual, Universal Bangkok. – Shanghai, Ref. No. 12-044531, 2012. 642 p. 4. Ferreira J., Fernandes M., Santos C., Vassalo R. Character recognition for automatic draught survey. 2018 13th IEEE International Conference on Industry Applications (INDUSCON) // IEEE, 2018. С. 332-338. 5. Gu H.W., Zhang W., Xu W.H. Digital Measurement System for Ship Draught Survey // Applied Mechanics & Materials. 2013. 312–316. 6. Karatzas D. ICDAR 2015 competition on robust reading. 2015 13th International Conference on Document Analysis and Recognition (ICDAR) // IEEE 2015. 1156 – 1160. 7. Okamoto A., Yoshida H., Tanaka N., Hirono K. A draught reading method by image processing with the robustness of measurement distance // The Journal of Japan Institute of Navigation. 2014. Т. 130. p. 135–140. 8. Carlos Tao “Scene Text Localization & Recognition Resources” Internet: https://github.com/chongyangtao/Awesome-Scene-Text-Recognition, Jul. 30, 2018 [Aug. 6, 2021]. 9. Tsujii T., Yoshida H., Iiguni Y. Automatic draught reading based on image processing // Optical Engineering. 2016. 55(10). 1-9. 10. Vinogradov V.N. Correlation theory of filtration and control of multidimensional random processes: Linear correlation theory of filtration and control. M.: KRASAND, 2012. – 320 p. 11. Wang, Bangping, Zhiming Liu, and Haoran Wang. Computer vision with deep learning for ship draught reading // Optical Engineering 60, 2 (2021): 024105. 12. Ivanovsky N., Chernyi S., Sokolov S., Zhilenkov A., Zinchenko A. Algorithm design for ship’s steering with specified limitations under various weather conditions // Brodogradnja, vol. 72, no. 4, pp. 19-32, 2021. Available: 10.21278/brod72402 13. Yemelyanov V., Chernyi S., Yemelyanova N., Varadarajan V. Application of neural networks to forecast changes in the technical condition of critical production facilities // Computers & Electrical Engineering, vol. 93, p. 107225, 2021. Available: 10.1016/j.compeleceng.2021.107225 14. Zhilenkov A.A., Chernyi S.G., Firsov A. Autonomous underwater robot fuzzy motion control system for operation under parametric uncertainties // Journal of Information Technologies and Computing Systems. 2021. № 1. С. 50-57.
|
