Vision Transformer Neural Nets Application for Object Recognition over Water in Um Qaser Port

Authors

  • Fatima Mallak Hanoon Department of Computers, faculty of Education for Pure Sciences, University of Basra, Iraq.
  • Khawla Hussein Ali Department of Computers, faculty of Education for Pure Sciences, University of Basra, Iraq.

Keywords:

unmanned surface vehicles, object recognition, deep neural network, com- puter vision, vision transformers

Abstract

The objective of this work is to give the of an experimental investigation into the efficiency of contemporary models of visual transformers utilized within the context of machine vision systems in robotic complexes for the purpose of object detection.On the basis of the findings of the research that was conducted, several suggestions have been developed on the application of models to the challenge of categorizing maritime traffic in Iraqi ports. Object recognition in ports is a crucial task for ensuring the safety and security of the port facilities. In this paper, Our study involved utilizing Vision Transformer (ViT) neural networks to identify above-water objects in Um Qaser port. We gathered a set of images of such objects from the port and employed the ViT model to train on this dataset. The outcomes of our study demonstrate that ViT neural networks perform better than conventional convolutional neural networks (CNNs) for this purpose, with a classification accuracy exceeding 90%.

Downloads

Download data is not yet available.

References

Howard A.G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T., An- dreetto M., Adam H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision // arXiv preprint. 2017. URL: https://arxiv.org/pdf/1704.04861.pdf

Xu, Q., Zhang, C., Zhang, L. Deep Convolutional Neural Network Based Un- manned Surface Vehicle Maneuvering // 2017 Chinese Automation Congress (CAC), Ji- nan, China, 2017, pp. 878- 881

Ivanov, Y. S., Zhiganov, S. V., Ivanova, T. I. Intelligent Deep Neuro-Fuzzy System Recognition of Abnormal Situations for Unmanned Surface Vehicles. In 2019 In- ternational Multi-Conference on Industrial Engineering and Modern Technologies FarEastCon-2019, Vladivostok, Russia, 2019, pp. 1-6. DOI: 10.1109/FarEastCon.2019.8934353

Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16x16 words: Transformers for image recognition at scale 2020. http://arxiv.org/abs/2010.11929

U. R. Acharya, N. K. Chowdhury, and S. M. Ramim, "Deep Learning for Above-Water Object Recognition in Harbors and Ports," in IEEE Access, vol. 9, pp. 43859-43868, 2021. doi: 10.1109/ACCESS.2021.3068374

Y. Zhang, L. Li, and S. Liu, "A Ship Detection Algorithm Based on Vision Transformer," in IEEE Access, vol. 9, pp. 115877-115887, 2021. doi: 10.1109/ACCESS.2021.3095073

R. Wang, Y. Fan, L. Liu, Y. Zhang, and F. Cheng, "Deep Learning for Ship Detection in Port Area," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 3, pp. 1652-1662, March 2021. doi: 10.1109/TITS.2020.3036502

S. Kang, S. Kim, S. Lee, and S. Yoon, "Ship Classification Using Vision Transformer and Augmentation Techniques," in IEEE Access, vol. 9, pp. 126604-126613, 2021. doi: 10.1109/ACCESS.2021.3105685

M. A. Alsheikh, N. A. Ali, M. M. Al-Jawad, and W. A. Al-Rikabi, "Deep Learning-Based Object Detection System for Port Security," in Journal of Applied Research and Technology, vol. 19, no. 4, pp. 344-353, 2021. doi: 10.1016/j.jart.2021.05.004

U. R. Acharya, N. K. Chowdhury, and S. M. Ramim, "Deep Learning for Above-Water Object Recognition in Harbors and Ports," in IEEE Access, vol. 9, pp. 43859-43868, 2021. doi: 10.1109/ACCESS.2021.3068374

Y. Zhang, L. Li, and S. Liu, "A Ship Detection Algorithm Based on Vision Transformer," in IEEE Access, vol. 9, pp. 115877-115887, 2021. doi: 10.1109/ACCESS.2021.3095073

R. Wang, Y. Fan, L. Liu, Y. Zhang, and F. Cheng, "Deep Learning for Ship Detection in Port Area," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 3, pp. 1652-1662, March 2021. doi: 10.1109/TITS.2020.3036502

S. Kang, S. Kim, S. Lee, and S. Yoon, "Ship Classification Using Vision Transformer and Augmentation Techniques," in IEEE Access, vol. 9, pp. 126604-126613, 2021. doi: 10.1109/ACCESS.2021.3105685

M. A. Alsheikh, N. A. Ali, M. M. Al-Jawad, and W. A. Al-Rikabi, "Deep Learning-Based Object Detection System for Port Security," in Journal of Applied Research and Technology, vol. 19, no. 4, pp. 344-353, 2021. doi: 10.1016/j.jart.2021.05.004

General architecture of Vision Transformer VIT

Downloads

Published

17.05.2023

How to Cite

Hanoon, F. M. ., & Ali, K. H. (2023). Vision Transformer Neural Nets Application for Object Recognition over Water in Um Qaser Port. International Journal of Intelligent Systems and Applications in Engineering, 11(6s), 428 –. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/2867

Issue

Vol. 11 No. 6s (2023)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.