Selection of an artificial pre-training neural network for the classification of inland vessels based on their images

• Autorzy: Bobkowska Katarzyna , Bodus-Olkowska Izabela

Identyfikatory

DOI

10.17402/480

• Języki publikacji: EN

Abstrakty

EN

Artificial neural networks (ANN) are the most commonly used algorithms for image classification problems. An image classifier takes an image or video as input and classifies it into one of the possible categories that it was trained to identify. They are applied in various areas such as security, defense, healthcare, biology, forensics, communication, etc. There is no need to create one’s own ANN because there are several pre-trained networks already available. The aim of the SHREC projects (automatic ship recognition and identification) is to classify and identify the vessels based on images obtained from closed-circuit television (CCTV) cameras. For this purpose, a dataset of vessel images was collected during 2018, 2019, and 2020 video measurement campaigns. The authors of this article used three pre-trained neural networks, GoogLeNet, AlexNet, and SqeezeNet, to examine the classification possibility and assess its quality. About 8000 vessel images were used, which were categorized into seven categories: barge, special-purpose service ships, motor yachts with a motorboat, passenger ships, sailing yachts, kayaks, and others. A comparison of the results using neural networks to classify floating inland units is presented.

Słowa kluczowe

EN

image classification; inland vessels; ANN; pre-trained neural network; GoogLeNet; AlexNet; SqeeezeNet

• Wydawca: Wydawnictwo Naukowe Akademii Morskiej w Szczecinie
• Czasopismo: Zeszyty Naukowe Akademii Morskiej w Szczecinie
• Rocznik: 2021
• Tom: nr 67 (139)
• Strony: 91--97
• Opis fizyczny: Bibliogr. 19 poz., rys., tab.

Twórcy

autor

Bobkowska Katarzyna

• Marine Technology Ltd. 4 lok. 6 Roszczynialskiego St., 81-521 Gdynia, Poland
• Gdańsk University of Technology, Faculty of Civil and Environmental Engineering 11/12 Gabriela Narutowicza St., 80-233 Gdańsk,Poland

• https://orcid.org/0000-0003-4968-3407

autor

Bodus-Olkowska Izabela

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

• https://orcid.org/0000-0003-4366-0116

Bibliografia

• 1. Alaskar, H., Alzhrani, N., Hussain, A. & Almarshed, F. (2019) The Implementation of Pretrained AlexNet on PCG Classification. In: D.-S. Huang, Z.-K. Huang, & A. Hussain (eds) Intelligent Computing Methodologies, ICIC 2019. Lecture Notes in Computer Science, vol 11645. Springer, Cham, pp. 784–794, doi: 10.1007/978-3-030-26766-7_71.
• 2. Basheer, I. & Hajmeer, M.N. (2001) Artificial Neural Networks: Fundamentals, Computing, Design, and Application. Journal of Microbiological Methods 43 (1), pp. 3–31, doi: 10.1016/S0167-7012(00)00201-3.
• 3. Bobkowska, K. & Bodus-Olkowska, I. (2020) Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification. Polish Maritime Research, 27(4), 170–178. doi: org/10.2478/pomr-2020-0077.
• 4. Bobkowska, K. & Wawrzyniak, N. (2019) The Hough transform in the classification process of inland ships. Scientific Journals of the Maritime University of Szczecin, Zeszyty Naukowe Akademii Morskiej w Szczecinie 58 (130), pp. 9–15, doi: 10.17402/331.
• 5. Danqing, L. (2017) A Practical Guide to ReLU. Medium. [Online] Available from: https://medium.com/@danqing/apractical-guide-to-relu-b83ca804f1f7 [Accessed: March, 23 2021].
• 6. Espinosa, J.E., Velastin, S.A. & Branch, J.W. (2017) Vehicle Detection Using Alex Net and Faster R-CNN Deep Learning Models: A Comparative Study BT. In: H. Badioze Zaman, P. Robinson, A.F. Smeaton, T.K. Shih, S. Velastin, T. Terutoshi, A. Jaafar & N. Mohamad Ali (eds) Advances in Visual Informatics, pp. 3–15. Springer International Publishing.
• 7. Gallo, C. (2015) Artificial Neural Networks: tutorial, Encyclopedia of Information Science and Technology, Edition: 3rd Ed. (10 Volumes), USA, https://www.researchgate.net/ publication/261392616.
• 8. Hassanpour, M. & Malek, H. (2020) Learning Document Image Features with SqueezeNet Convolutional Neural Network. International Journal of Engineering 33 (7), pp. 1201–1207, doi: 10.5829/ije.2020.33.07a.05.
• 9. Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J. & Keutzer, K. (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 1 MB model size. CoRR, abs/1602.0. http://arxiv.org/ abs/1602.07360.
• 10. Khan, R.U., Zhang, X. & Kumar, R. (2019) Analysis of ResNet and GoogleNet models for malware detection. Journal of Computer Virology and Hacking Techniques 15 (1), pp. 29–37, doi: 10.1007/s11416-018-0324-z.
• 11. Konovalov, D.A., Saleh, A., Bradley, M., Sankupellay, M., Marini, S. & Sheaves, M. (2019) Underwater Fish Detection with Weak Multi-Domain Supervision. International Joint Conference on Neural Networks (IJCNN), 1–8, doi: 10.1109/IJCNN.2019.8851907.
• 12. Lee, H.J., Ullah, I., Wan, W., Gao, Y. & Fang, Z. (2019) Real-Time Vehicle Make and Model Recognition with the Residual SqueezeNet Architecture. Sensors 19 (5), 982, doi: 10.3390/s19050982.
• 13. Polap, D. & Wlodarczyk-Sielicka, M. (2020) Classification of Non-Conventional Ships Using a Neural BagOf-Words Mechanism. Sensors 20 (6), 1608, doi: 10.3390/ s20061608.
• 14. Salavati, P. & Mohammadi, H.M. (2018) Obstacle Detection Using GoogleNet. 8th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 326– 332, doi: 10.1109/ICCKE.2018.8566315.
• 15. Sang-Geol, L., Yunsick, S., Yeon-Gyu, K. & Eui-Young, C. (2018) Variations of AlexNet and GoogLeNet to Improve Korean Character Recognition Performance. Journal of Information Processing Systems 14 (1), pp. 205–217, doi: 10.3745/JIPS.04.0061.
• 16. Ucar, F. & Korkmaz, D. (2020) COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Medical Hypotheses 140, 109761, doi: 10.1016/j.mehy.2020.109761.
• 17. Wang, S.-H., Xie, S., Chen, X., Guttery, D.S., Tang, C., Sun, J. & Zhang, Y.-D. (2019) Alcoholism Identification Based on an AlexNet Transfer Learning Model. Frontiers in Psychiatry 10, 205, doi: 10.3389/fpsyt.2019.00205.
• 18. Wawrzyniak, N. & Stateczny, A. (2018) Automatic Watercraft Recognition and Identification on Water Areas Covered by Video Monitoring as Extension for Sea and River Traffic Supervision Systems. Polish Maritime Research 25, pp. 5–13, doi: 10.2478/pomr-2018-0016.
• 19. Wlodarczyk-Sielicka, M. & Polap, D. (2019) Automatic Classification Using Machine Learning for Non-Conventional Vessels on Inland Waters. Sensors (Basel, Switzerland) 19 (14), 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).