research-article

Real-time Ship Object Detection with YOLOR

Authors:

Kuntao CuiAuthors Info & Claims

SPML '22: Proceedings of the 2022 5th International Conference on Signal Processing and Machine Learning

Pages 203 - 210

https://doi.org/10.1145/3556384.3556415

Published: 29 October 2022 Publication History

Abstract

Real-time object detection technology is a key technology for USVs to perceive the environment. Accurately and quickly detecting the position and type of ship targets in images is the basis for intelligent navigation of USVs. In 2021, the YOLOR (You Only Learn One Representation) model outperformed all other real-time object detection models on the COCO dataset. The YOLOR model is a multi-task model obtained by adding implicit knowledge modeling on the basis of YOLOv4-csp (You Only Look Once version 4 -csp) and modifying the first CSPDark layer of YOLOv4-csp to a Dark layer, reducing the amount of computation by 40%. However, implicit knowledge modeling only adds less than ten thousand parameters and computation. In this paper, we trained four models using the public marine ship dataset Seaships (7000), investigate the effect of the YOLOR model on real-time ship object detection, and demonstrated that implicit knowledge modeling can significantly increase the model's detection accuracy. The experimental results indicate that of the model with implicit knowledge modeling is 96.7, and is 71.2%, which is 3.5% and 24.3% higher than the YOLOv4-csp model, respectively. Additionally, we discovered that implicit knowledge modeling significantly improves model detection accuracy at medium and low resolutions ( and ), but not at high resolutions ().

References

[1]

Justin E. Manley. 2008. Unmanned surface vehicles, 15 years of development. OCEANS 2008, IEEE Quebec City, QC, Canada, 1-4. https://doi.org/10.1109/OCEANS.2008.5152052

[2]

Huang Kaiqi, Ren Weiqiang, and Tan Tieniu. 2014. A Survey of Image Object Classification and Detection Algorithms. Chinese Journal of Computers 37(June 2014), 1225-1240.

[3]

Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. Lecture Notes in Computer Science, vol 12346. Springer, Cham. https://doi.org/10.1007/978-3-030-58452-8_13

Digital Library

[4]

Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2021. Transformers in Vision: A Survey. ACM Comput. Surv. Just Accepted (December 2021). https://doi.org/10.1145/3505244

Digital Library

[5]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (June 2017), 84–90. https://doi.org/10.1145/3065386

Digital Library

[6]

R. Girshick, J. Donahue, T. Darrell and J. Malik. 2014. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Columbus, OH, 580-587. https://doi.org/10.1109/CVPR.2014.81

Digital Library

[7]

S. Ren, K. He, R. Girshick and J. Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39. IEEE, 1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031

Digital Library

[8]

Z. Cai and N. Vasconcelos. 2018. Cascade R-CNN: Delving Into High Quality Object Detection. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, Salt Lake City, UT,6154-6162. https://doi.org/10.1109/CVPR.2018.00644

[9]

K. He, G. Gkioxari, P. Dollár and R. Girshick.2020. Mask R-CNN. In Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42. IEEE,386-397. https://doi.org/10.1109/TPAMI.2018.2844175

[10]

Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single Shot MultiBox Detector. Springer International Publishing, Cham, 21—37. https://doi.org/10.1007/978-3-319-46448-0_2

[11]

T. Y. Lin, P. Goyal, R. Girshick, K. He, and Dollár, P. 2017. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision. 2980–2988. https://doi.org/10.1109/ICCV.2017.324

[12]

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2016.91

[13]

Joseph Redmon and Ali Farhadi. 2017. YOLO9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7263–7271. https://doi.org/10.1109/CVPR.2017.690

[14]

Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018). https://doi.org/10.48550/arXiv.1804.02767

[15]

Bochkovskiy A, Wang C Y and Liao H Y M. 2020. YOLOv4: Optimal Speed and Accuracy of Object Detection[J]. https://doi.org/10.48550/arXiv.2004.10934

[16]

Chien-Yao Wang, I-Hau Yeh, and Hong-Yuan Mark Liao. 2021. You Only Learn One Representation: Unified Network for Multiple Tasks. arXiv preprint arXiv: 2105.04206 (2021). https://doi.org/10.48550/arXiv.2105.04206

[17]

Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, and Qi Tian. 2019. Centernet: Keypoint triplets for object detection. In Proceedings of the IEEE International Conference on Computer Vision. 6569-6578. https://doi.org/10.1109/ICCV.2019.00667

[18]

K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang and Q. Tian. CenterNet: Keypoint Triplets for Object Detection. 2019. In Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Seoul, Korea (South), 6568-6577. https://doi.org/10.1109/ICCV.2019.00667

[19]

Z. Tian, C. Shen, H. Chen, and T. He. 2019. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE international conference on computer vision. IEEE, Seoul, Korea (South),9627–9636. https://doi.org/10.1109/ICCV.2019.00972

[20]

X. Song, P. Jiang and H. Zhu. 2019. Research on Unmanned Vessel Surface Object Detection Based on Fusion of SSD and Faster-RCNN. In Proceedings of the 2019 Chinese Automation Congress (CAC). IEEE, Hangzhou, China, 3784-3788. https://doi.org/10.1109/CAC48633.2019.8997431.

[21]

Zhang, W., Gao, X. Z., Yang, C. F., Jiang, F., and Chen, Z. Y. 2020. A object detection and tracking method for security in intelligence of unmanned surface vehicles. J Ambient Intell Human Comput 13, 1279–1291. https://doi.org/10.1007/s12652-020-02573-z

[22]

Sun, X., Liu, T., Yu, X., and Pang, B. 2021. Unmanned surface vessel visual object detection under all-weather conditions with optimized feature fusion network in yolov4. J.Intelligent & Robotic Systems, 103(3). https://doi.org/10.1007/s10846-021-01499-8

Digital Library

[23]

Zhenfeng Shao, Wenjing Wu, Zhongyuan Wang, Wan Du, and Chengyuan Li. Seaships: A large-scale precisely annotated dataset for ship detection. IEEE Transactions on Multimedia, 20(10):2593–2604, 2018.

Cited By

Zhang BLiu JLiu RHuang Y(2025)Deep-learning-empowered visual ship detection and tracking: Literature review and future directionEngineering Applications of Artificial Intelligence10.1016/j.engappai.2024.109754141(109754)Online publication date: Feb-2025
https://doi.org/10.1016/j.engappai.2024.109754
Lombardi LMercaldo FSantone A(2025)Automatic Classification and Localization of Ancient Amphorae Through Object Detection in Underwater ArcheologyIntelligent Decision Technologies10.1007/978-981-97-7419-7_13(147-156)Online publication date: 7-Feb-2025
https://doi.org/10.1007/978-981-97-7419-7_13
Morales RQuispe JAguilar E(2023)Exploring multi-food detection using deep learning-based algorithms2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)10.1109/ICPRS58416.2023.10179037(1-7)Online publication date: 4-Jul-2023
https://doi.org/10.1109/ICPRS58416.2023.10179037
Show More Cited By

Real-time Ship Object Detection with YOLOR
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
    1. Machine learning approaches

Recommendations

A novel sarnede method for real-time ship detection from synthetic aperture radar image
Abstract
Deep learning-based ship detection from SAR data is one of the challenging problems in the remote sensing area. Also, SAR ship detection is precise object detection and pattern recognition task under the computer vision area. The main problems are ...
Evolutionary channel pruning for real-time object detection
Abstract
Real-time object detection plays a crucial role in edge devices applications. Pruning methods are usually used to effectively eliminate redundant parameters of the object detection network so that it can detect objects efficiently. However, ...
YOLOv7-ship: An Efficient Method for Marine Ship Detection Based on Wave Glider
ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition

Ship detection based on wave gliders plays an important role in tasks such as maritime patrols, target tracking, and maritime traffic control. However, the complex and diverse sea environment, as well as the large differences in the appearance and scale ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

SPML '22: Proceedings of the 2022 5th International Conference on Signal Processing and Machine Learning

August 2022

309 pages

ISBN:9781450396912

DOI:10.1145/3556384

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 29 October 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article
Research
Refereed limited

Conference

SPML 2022

SPML 2022: 2022 5th International Conference on Signal Processing and Machine Learning

August 4 - 6, 2022

Dalian, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
81
Total Downloads

Downloads (Last 12 months)7
Downloads (Last 6 weeks)0

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zhang BLiu JLiu RHuang Y(2025)Deep-learning-empowered visual ship detection and tracking: Literature review and future directionEngineering Applications of Artificial Intelligence10.1016/j.engappai.2024.109754141(109754)Online publication date: Feb-2025
https://doi.org/10.1016/j.engappai.2024.109754
Lombardi LMercaldo FSantone A(2025)Automatic Classification and Localization of Ancient Amphorae Through Object Detection in Underwater ArcheologyIntelligent Decision Technologies10.1007/978-981-97-7419-7_13(147-156)Online publication date: 7-Feb-2025
https://doi.org/10.1007/978-981-97-7419-7_13
Morales RQuispe JAguilar E(2023)Exploring multi-food detection using deep learning-based algorithms2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)10.1109/ICPRS58416.2023.10179037(1-7)Online publication date: 4-Jul-2023
https://doi.org/10.1109/ICPRS58416.2023.10179037
Coching JPe AYeung SAng CConcepcion RBillones R(2023)License Plate Recognition System for Improved Logistics Delivery in a Supply Chain with Solution Validation through Digital Twin Modeling2023 IEEE 15th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM)10.1109/HNICEM60674.2023.10589240(1-6)Online publication date: 19-Nov-2023
https://doi.org/10.1109/HNICEM60674.2023.10589240

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten