Abstract
The process of loading and unloading containers at the port is very important to be automated in order to increase productivity, revenues, efficiency and safety in the logistics transportation process especially in a maritime country like Indonesia. To achieve this, identification and tracking of container positions need to be done accurately so that container transfers can occur precisely and smoothly. In this study, YOLO deep learning is used to detect moving containers. The model is trained using container images, and then the validation and testing process are carried out on the model using other container images. The results of training are stored in several checkpoints which will be compared to get the most accurate model. Obtained YOLO gave good results for tracking containers with MAP value of 68.63% and LAMR of 0.31.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Perkovic, M., Gucma, M., Luin, B., Gucma, L., Brcko, T.: Accommodating larger container vessels using an integrated laser system for approach and berthing. Microprocess. Microsyst. 2, 106–116 (2017)
Yu, M., Qi, X.: Storage space allocation models for inbound containers in an automatic container terminal. Eur. J. Oper. Res. 226(1), 32–45 (2013)
Henning, K., Bruns, M.: Design of an automatic control system for train-to-train container transfer. IFAC Proc. Vol. 16(4), 165–173 (1983)
Wu, W., Liu, Z., Chen, M., Yang, X., He, X.: An automated vision system for container-code recognition. Expert Syst. Appl. 39(3), 2842–2855 (2012)
Girshick, R, Donahue, J, Darrell, T, et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. Comput. Sci, 580–587 (2013)
Girshick, R.: Fast R-CNN. IEEE International Conference on Computer Vision, 1440–1448 (2015)
Wei, L., Dragomir, A.: SSD: Single Shot MultiBox Detector. arXiv preprint arXiv:1512.02325v5 (2016)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. arXiv preprint arXiv:1506.02640 (2015)
Lan, W., Dang, J., Wang, Y., Wang, S.: Pedestrian detection based on YOLO network model. In: 2018 IEEE International Conference on Mechatronics and Automation (ICMA). doi:https://doi.org/10.1109/icma.2018.8484698 (2018)
Berg, A.: Learning to Analyze what is Beyond the Visible Spectrum (Vol. 2024). Linköping University Electronic Press (2019)
Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT Press (2016)
Rosebrock, A.: Deep learning for computer vision with python: starter bundle. PyImageSearch (2017)
Basha, S.H., Dubey, S.R., Pulabaigari, V., Mukherjee, S.: Impact of fully connected layers on performance of convolutional neural networks for image classification. arXiv preprint arXiv:1902.02771 (2019)
Hendry, & Chen, R.-C.: Automatic license plate recognition via sliding-window Darknet-Yolo deep learning. Image Vision Comput. doi: https://doi.org/10.1016/j.imavis.2019.04.007 (2019).
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88(2), 303–338 (2010)
Braun, M., Krebs, S., Flohr, F., Gavrila, D.M.: The eurocity persons dataset: A novel benchmark for object detection. arXiv preprint arXiv:1805.07193 (2018)
Acknowledgements
The first author is grateful to the Ministry of Education and Culture of the Universitas Pembangunan Nasional “Veteran” Jawa Timur, Faculty of Computer Science, Indonesia, who funded this research publication. E. Joelianto and P. Siregar are supported by the Ministry of Research, Technology and Higher Education under Higher Education Applied Research Grant 2018-2019, Indonesia.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Rahmat, B. et al. (2021). Video-Based Container Tracking System Using Deep Learning. In: Joelianto, E., Turnip, A., Widyotriatmo, A. (eds) Cyber Physical, Computer and Automation System. Advances in Intelligent Systems and Computing, vol 1291. Springer, Singapore. https://doi.org/10.1007/978-981-33-4062-6_8
Download citation
DOI: https://doi.org/10.1007/978-981-33-4062-6_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4061-9
Online ISBN: 978-981-33-4062-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)