Potential and use of the googlenet ann for the purposes of inland water ships classification

• Autorzy: Bobkowska Katarzyna , Bodus-Olkowska Izabela

Identyfikatory

DOI

10.2478/pomr-2020-0077

• Języki publikacji: EN

Abstrakty

EN

This article presents an analysis of the possibilities of using the pre-degraded GoogLeNet artificial neural network to classify inland vessels. Inland water authorities monitor the intensity of the vessels via CCTV. Such classification seems to be an improvement in their statutory tasks. The automatic classification of the inland vessels from video recording is a one of the main objectives of the Automatic Ship Recognition and Identification (SHREC) project. The image repository for the training purposes consists about 6,000 images of different categories of the vessels. Some images were gathered from internet websites, and some were collected by the project’s video cameras. The GoogLeNet network was trained and tested using 11 variants. These variants assumed modifications of image sets representing (e.g., change in the number of classes, change of class types, initial reconstruction of images, removal of images of insufficient quality). The final result of the classification quality was 83.6%. The newly obtained neural network can be an extension and a component of a comprehensive geoinformatics system for vessel recognition.

Słowa kluczowe

EN

ship classification; image classification; geoinformatics; artificial intelligence; artificial neural network

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2020
• Tom: nr 4
• Strony: 170--178
• Opis fizyczny: Bibliogr. 28 poz., rys., tab.

Twórcy

autor

Bobkowska Katarzyna

• Gdańsk University of Technology, Narutowicza 11/12, 80-233 Gdańsk, Poland
• Marine Technology Sp. z o.o., ul. Roszczynialskiego 4, lok. 6, 81-521 Gdynia, Poland

autor

Bodus-Olkowska Izabela

• Maritime University of Szczecin, ul. Wały Chrobrego 1-2, 70-500 Szczecin, Poland

Bibliografia

• 1. Wawrzyniak, N.; Stateczny, A. Automatic watercraft recognition and identification on water areas covered by video monitoring as extension for sea and river traffic supervision systems. Polish Marit. Res. 2018, 25, 5–13, doi: 10.2478/pomr-2018-0016.
• 2. Kanjir, U.; Greidanus, H.; Oštir, K. Vessel detection and classification from spaceborne optical images: A literature survey. Remote Sens. Environ. 2018, 207, 1–26, doi: 10.1016/j. rse.2017.12.033.
• 3. Bobkowska, K. Analysis of the objects images on the sea using Dempster-Shafer theory. In 2016 17th Int. Radar Symp. (IRS); 2016; pp. 78–81, doi: 10.1109/irs.2016.7497280.
• 4. Wang, C.; Jiang, S.; Zhang, H.; Wu, F.; Zhang, B. Ship detection for high-resolution SAR images based on feature analysis. IEEE Geosci. Remote Sens. Lett. 2014, 11, 119–123, doi: 10.1109/LGRS.2013.2248118.
• 5. Stateczny, A. Full implementation of the River Information Services of border and lower section of the Odra in Poland. In 2016 Baltic Geodetic Congress (BGC Geomatics); 2016; pp. 140–146, doi: 10.1109/BGC.Geomatics.2016.33.
• 6. Shao, Z.; Wang, L.; Wang, Z.; Du, W.; Wu, W. Saliency-aware convolution neural network for ship detection in surveillance video. IEEE Trans. Circuits Syst. Video Technol. 2019, doi: 10.1109/TCSVT.2019.2897980.
• 7. Wawrzyniak, N.; Hyla, T. Automatic ship identification approach for video surveillance systems. In Proceedings of ICONS 2019 The Fourteenth International Conference on Systems, IARIA, Valencia, Spain; 2019; pp. 65–68.
• 8. Wawrzyniak, N.; Hyla, T.; Popik, A. Vessel detection and tracking method based on video surveillance. Sensors (Switzerland) 2019, 19, 23, doi: 10.3390/s19235230.
• 9. Ferreira, J. C.; Branquinho, J.; Ferreira, P. C.; Piedade, F. Computer vision algorithms fishing vessel monitoring – Identification of vessel plate number. In International Symposium on Ambient Intelligence; 2017; pp. 9–17.
• 10. Bobkowska, K.; Wawrzyniak, N. The Hough transform in the classification process of inland ships. Sci. JOURNALS Marit. Univ. SZCZECIN-ZESZYTY Nauk. Akad. MORSKIEJ W SZCZECINIE 2019, 58, 9–15, doi: 10.17402/331.
• 11. Akiyama, T.; Kobayashi, Y.; Kishigami, J.; Muto, K. CNNbased boat detection model for alert system using surveillance video vamera. In 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE); 2018; pp. 669–670, doi: 10.1109/GCCE.2018.8574704.
• 12. Zhang, M. M.; Choi, J.; Daniilidis, K.; Wolf, M. T.; Kanan, C. Vais: A dataset for recognizing maritime imagery in the visible and infrared spectrums. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops; 2015; pp. 10–16, doi: 10.1109/CVPRW.2015.7301291.
• 13. Solmaz, B.; Gundogdu, E.; Yucesoy, V.; Koç, A.; Alatan, A. A. Fine-grained recognition of maritime vessels and land vehicles by deep feature embedding. IET Comput. Vis. 2018, 12, 1121–1132, doi: 10.1049/iet-cvi.2018.5187.
• 14. Zhong, Z.; Jin, L.; Xie, Z. High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR); 2015; pp. 846–850, doi: 10.1109/ICDAR.2015.7333881.
• 15. Tang, P.; Wang, H.; Kwong, S. G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition. Neurocomputing 2017, 225, 188–197, doi: 10.1016/j. neucom.2016.11.023.
• 16. Al-Qizwini, M.; Barjasteh, I.; Al-Qassab, H.; Radha, H. Deep learning algorithm for autonomous driving using GoogLeNet. In 2017 IEEE Intelligent Vehicles Symposium (IV); 2017; pp. 89–96, doi: 10.1109/IVS.2017.7995703.
• 17. Aswathy, P.; Siddhartha; Mishra, D. Deep GoogLeNet features for visual object tracking. In 2018 IEEE 13th International Conference on Industrial and Information Systems (ICIIS); 2018; pp. 60–66, doi: 10.1109/ICIINFS.2018.8721317.
• 18. Xie, S.; Zheng, X.; Chen, Y.; Xie, L.; Liu, J.; Zhang, Y.; Yan, J.; Zhu, H.; Hu, Y. Artifact removal using improved GoogLeNet for sparse-view CT reconstruction. Sci. Rep. 2018, 8, 6700, doi: 10.1038/s41598-018-25153-w.
• 19. Wu, C.; Wen, W.; Afzal, T.; Zhang, Y.; Chen, Y. A compact DNN: Approaching GoogLeNet-level accuracy of classification and domain adaptation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017, doi: 10.1109/CVPR.2017.88.
• 20. Shin, H.; Roth, H.; Gao, M.; Lu, L.; Xu, Z.; Nogues, I.; Yao, J.; Mollura, D.; Summers, R. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 2016, 35, doi: 10.1109/TMI.2016.2528162 .
• 21. Castro, W.; Oblitas, J.; De-La-Torre, M.; Cotrina, C.; Bazán, K.; Avila-George, H. Classification of cape gooseberry fruit according to its level of ripeness using machine learning techniques and different color spaces. IEEE Access 2019, 7, 27389–27400, doi: 10.1109/ACCESS.2019.2898223.
• 22. Szymak, P. Recognition of underwater objects using deep learning in Matlab. In International Conference on Applied Mathematics & Computational Science (ICAMCS.NET), 2018, doi: 10.1109/ICAMCS.NET46018.2018.00018.
• 23. https://www.mathworks.com/help/deeplearning/examples/ train-deep-learning-network-to-classify-new-images.html.
• 24. Hyla, T.; Wawrzyniak, N. Automatic ship detection on inland waters: Problems and a preliminary solution. In Proceedings of ICONS 2019 The Fourteenth International Con-ference on Systems, IARIA, Valencia, Spain; 2019; pp. 56–60.
• 25. Popik, A.; Zaniewicz, G.; Wawrzyniak, N. On-water video surveillance: data management for a ship identification system. Zesz. Nauk. Akad. Morskiej w Szczecinie 2019, 60, 56–63, doi: 10.17402/372.
• 26. Wawrzyniak, N.; Hyla, T. Ships detection on inland waters using video surveillance system. In FIP International Conference on Computer Information Systems and Industrial Management; Springer, Cham, 2019; pp. 39–49, doi: 10.1007/978-3-030-28957-7_4.
• 27. Tharwat, A. Classification assessment methods. Appl. Comput. Informatics 2018, doi: 10.1016/j.aci.2018.08.003.
• 28. Wlodarczyk-Sielicka, M.; Polap, D. Automatic Classification Using Machine Learning for Non-Conventional Vessels on Inland Waters. Sensors (Basel). 2019, 19, 3051, doi: 10.3390/ s19143051.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).