Skip to content
2000
Volume 18, Issue 4
  • ISSN: 2666-2558
  • E-ISSN: 2666-2566

Abstract

Background

With the development of intelligent ship technology, computer vision technology has been widely utilized in the field of maritime monitoring. This is of great significance in ensuring the safety of navigation and improving the efficiency of shipping. However, complex and changing sea conditions and arbitrary traveling ships pose more accurate and faster requirements for the target detection algorithm used in the intelligent ship systems.

Objective

The primary objective of this paper is to propose an optimized version of the ship lightweight target detection algorithm based on YOLOv5s architecture. This enhancement involves the innovative fusion of the Shufflenetv2 network and the NAM attention mechanism, collectively termed as SN-YOLOv5s. This integration seeks to elevate the algorithm’s performance in detecting ship targets, offering improved accuracy and efficiency.

Methods

Firstly, the Shufflenetv2 network and NAM attention mechanism are used to replace the backbone network, significantly reducing the number of network parameters and improves the model detection accuracy. Secondly, in the process of converting the feature map to a fixed-size feature vector, SimSPPF is used to replace the fast pyramid pooling SPPF module, ensuring the efficiency and minimizing information loss. Lastly, EIOU is utilized to replace the bounding box regression loss function CIOU to make the model converge faster and with higher accuracy.

Results

Test results on the SeaShips dataset show that compared to the original YOLOv5s network, the average accuracy of target detection using the SN-YOLOv5s network is improved by 4.7%, the amount of computation is reduced by 40%, the amount of parameters is reduced by 20.6%, and the volume of model weights is decreased by 15.4%.

Conclusion

The experimental results fully demonstrate that the algorithm can significantly reduce the running cost of the model and improve the detection accuracy of the model, thus effectively guaranteeing the efficiency and quality of ship target detection.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/rascs/10.2174/0126662558327827240920035158
2024-10-03
2025-09-08

  • From This Site

    /content/journals/rascs/10.2174/0126662558327827240920035158
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. WuW. LiuH. LiL. LongY. WangX. WangZ. LiJ. ChangY. Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image.PLoS One20211610e025928310.1371/journal.pone.025928334714878
     [Google Scholar]
  2. WuT.H. WangT.W. LiuY.Q. Real-Time Vehicle and Distance detection based on improved Yolo v5 Network.2021 3rd World Symposium on Artificial Intelligence (WSAI)18-20 June 2021, Guangzhou, China, 2021, pp. 24-28.10.1109/WSAI51899.2021.9486316
     [Google Scholar]
  3. DuX. CaiY. WangS. Overview of deep learning.2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC) 11-13 Nov, 2016, Wuhan, China, 2016, pp. 159-164.10.1109/YAC.2016.7804882
     [Google Scholar]
  4. YaoJ. QiJ. ZhangJ. ShaoH. YangJ. LiX. A real-time detection algorithm for Kiwifruit defects based on YOLOv5.Electronics (Basel)20211014171110.3390/electronics10141711
     [Google Scholar]
  5. LiuR.W. YuanW. ChenX. LuY. An enhanced CNN-enabled learning method for promoting ship detection in maritime surveillance system.Ocean Eng.202123510943510.1016/j.oceaneng.2021.109435
     [Google Scholar]
  6. DongX. YanS. DuanC. A lightweight vehicles detection network model based on YOLOv5.Eng. Appl. Artif. Intell.202211310491410.1016/j.engappai.2022.104914
     [Google Scholar]
  7. DuanJ.Y. LiB. DongC. Detection and classification of ship target based on YOLOv2.Computer Engineering and Design202041617011707
     [Google Scholar]
  8. YueB. HanS. A SAR ship detection method based on improved faster R-CNN.Comp. Modern.2019201999095
     [Google Scholar]
  9. SunX.M. ZhangY.J. WangH. DuY.X. Research on ship detection of optical remote sensing image based on Yolo V5.J. Phys. Conf. Ser.20222215101202710.1088/1742‑6596/2215/1/012027
     [Google Scholar]
  10. FuH. SongG. WangY. Improved YOLOv4 marine target detection combined with CBAM.Symmetry (Basel)202113462310.3390/sym13040623
     [Google Scholar]
  11. JiangP. ErguD. LiuF. CaiY. MaB. A Review of Yolo Algorithm Developments.Procedia Comput. Sci.20221991066107310.1016/j.procs.2022.01.135
     [Google Scholar]
  12. TianY. YangG. WangZ. WangH. LiE. LiangZ. Apple detection during different growth stages in orchards using the improved YOLO-V3 model.Comput. Electron. Agric.201915741742610.1016/j.compag.2019.01.012
     [Google Scholar]
  13. DuJ. Understanding of object detection based on CNN family and YOLO.J. Phys. Conf. Ser.2018100401202910.1088/1742‑6596/1004/1/012029
     [Google Scholar]
  14. FangY. GuoX. ChenK. ZhouZ. YeQ. Accurate and automated detection of surface knots on sawn timbers using YOLO-V5 model.BioResources20211635390540610.15376/biores.16.3.5390‑5406
     [Google Scholar]
  15. LiuT. ZhouB.J. ZhaoY.S. Ship Detection Algorithm based on Improved YOLO V5.2021 6th International Conference on Automation, Control and Robotics Engineering (CACRE)15-17 July 2021, Dalian, China, 2021, pp. 483-487.
     [Google Scholar]
  16. NieX. LiuW. WuW. Ship detection based on enhanced YOLOv3 under complex environments.Jisuanji Yingyong2020400925612570
     [Google Scholar]
  17. WangF. YangX. ZhangY. YuanJ. Ship Target Detection Algorithm Based on YOLOv3.Navigation of China2020430116216610.1145/3422713.3422721
     [Google Scholar]
  18. GuoL. YuH.Y. ZhouZ.Q. Nearshore ship detection method based on SimAM attention mechanism.J. Harbin Inst. Technol.202355051421
     [Google Scholar]
  19. JinM. LiX.Y. ZhangL.G. Ship detection algorithm based on enhanced YOLOV4.Ship Engineering20224410100106
     [Google Scholar]
  20. GuJ. ZhuZ.Y. An infrared ship target detection algorithm based on lmproved YOLOv5.Elect. Opt. Cont.202330102126
     [Google Scholar]
  21. WangW.J. HeX.H. QinL.B. Improved YOLOv5 ship detection algorithm and embedded implementation.Wuxiandian Gongcheng2022521221162123
     [Google Scholar]
  22. ZhouF. ZhaoH. NieZ. Safety helmet detection based on YOLOv5.2021 IEEE International conference on power electronics, computer applications (ICPECA)22-24 January 2021, Shenyang, China, 2021, pp. 6-11.10.1109/ICPECA51329.2021.9362711
     [Google Scholar]
  23. WangD. HeD. Channel pruned YOLO V5s-based deep learning approach for rapid and accurate apple fruitlet detection before fruit thinning.Biosyst. Eng.202121027128110.1016/j.biosystemseng.2021.08.015
     [Google Scholar]
  24. GuoK. HeC. YangM. WangS. A pavement distresses identification method optimized for YOLOv5s.Sci. Rep.2022121354210.1038/s41598‑022‑07527‑335241746
     [Google Scholar]
  25. ZhangC. DingH. ShiQ. WangY. Grape cluster real-time detection in complex natural scenes based on YOLOv5s deep learning network.Agriculture2022128124210.3390/agriculture12081242
     [Google Scholar]
  26. LiA. SunS. ZhangZ. FengM. WuC. LiW. A multi-scale traffic object detection algorithm for road scenes based on improved YOLOv5.Electronics (Basel)202312487810.3390/electronics12040878
     [Google Scholar]
  27. TangJ. LiuS. ZhengB. Smoking behavior detection based on improved YOLOv5s algorithm.2021 9th International Symposium on Next Generation Electronics (ISNE)09-11 July 2021, Changsha, China, 2021, pp. 1-4.10.1109/ISNE48910.2021.9493637
     [Google Scholar]
  28. XiaoB. GuoJ. HeZ. Real-time object detection algorithm of autonomous vehicles based on improved YOLOv5s.2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)29-31 October 2021, Tianjin, China, 2021, pp. 1-6.10.1109/CVCI54083.2021.9661149
     [Google Scholar]
  29. ShenL. SuJ. HeR. SongL. HuangR. FangY. SongY. SuB. Real-time tracking and counting of grape clusters in the field based on channel pruning with YOLOv5s.Comput. Electron. Agric.202320610766210.1016/j.compag.2023.107662
     [Google Scholar]
  30. ZhangY.J. XiaoF.S. LuZ.M. Helmet wearing state detection based on improved YOLOv5s.Sensors (Basel)20222224984310.3390/s2224984336560211
     [Google Scholar]
  31. LiuX. JiangX. HuH. Traffic sign recognition algorithm based on improved YOLOv5s2021 International Conference on Control, Automation and Information Sciences (ICCAIS)14-17 October 2021, Xi'an, China, 2021, pp. 980-985.10.1109/ICCAIS52680.2021.9624657
     [Google Scholar]
  32. ZhaoZ. YangX. ZhouY. SunQ. GeZ. LiuD. Real-time detection of particleboard surface defects based on improved YOLOV5 target detection.Sci. Rep.20211112177710.1038/s41598‑021‑01084‑x34741057
     [Google Scholar]
  33. ZhengY. ZhangY. QianL. ZhangX. DiaoS. LiuX. CaoJ. HuangH. A lightweight ship target detection model based on improved YOLOv5s algorithm.PLoS One2023184e028393210.1371/journal.pone.028393237023092
     [Google Scholar]
  34. JiangT. LiC. YangM. WangZ. An improved YOLOv5s algorithm for object detection with an attention mechanism.Electronics (Basel)20221116249410.3390/electronics11162494
     [Google Scholar]
  35. LiT. SunM. HeQ. ZhangG. ShiG. DingX. LinS. Tomato recognition and location algorithm based on improved YOLOv5.Comput. Electron. Agric.202320810775910.1016/j.compag.2023.107759
     [Google Scholar]
  36. ZhouS. ZhaoJ. ShiY.S. WangY.F. MeiS.Q. Research on improving YOLOv5s algorithm for fabric defect detection.Int. J. Cloth. Sci. Technol.20233518810610.1108/IJCST‑11‑2021‑0165
     [Google Scholar]
  37. WenG. LiS. LiuF. LuoX. ErM.J. MahmudM. WuT. YOLOv5s-CA: A modified YOLOv5s network with coordinate attention for underwater target detection.Sensors (Basel)2023237336710.3390/s2307336737050427
     [Google Scholar]
  38. ZhangP. LiD. EPSA-YOLO-V5s: A novel method for detecting the survival rate of rapeseed in a plant factory based on multiple guarantee mechanisms.Comput. Electron. Agric.202219310671410.1016/j.compag.2022.106714
     [Google Scholar]
  39. ZhaiX. WeiH. HeY. ShangY. LiuC. Underwater sea cucumber identification based on improved YOLOv5.Appl. Sci. (Basel)20221218910510.3390/app12189105
     [Google Scholar]
  40. LiS. LiC. YangY. ZhangQ. WangY. GuoZ. Underwater scallop recognition algorithm using improved YOLOv5.Aquacult. Eng.20229810227310.1016/j.aquaeng.2022.102273
     [Google Scholar]
  41. WangY. HaoZ. ZuoF. PanS. A fabric defect detection system based improved yolov5 detector.J. Phys. Conf. Ser.20212010101219110.1088/1742‑6596/2010/1/012191
     [Google Scholar]
  42. WanF. SunC. HeH. LeiG. XuL. XiaoT. YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s.EURASIP J. Adv. Signal Process.2022202219810.1186/s13634‑022‑00931‑x
     [Google Scholar]
  43. XuZ. HuangX. HuangY. SunH. WanF. A real-time zanthoxylum target detection method for an intelligent picking robot under a complex background, based on an improved YOLOv5s architecture.Sensors (Basel)202222268210.3390/s2202068235062643
     [Google Scholar]
  44. YingZ. LinZ. WuZ. LiangK. HuX.D. A modified-YOLOv5s model for detection of wire braided hose defects.Measurement202219011068310.1016/j.measurement.2021.110683
     [Google Scholar]
  45. WangP. HuangH. WangM. LiB. YOLOv5s-FCG: An improved YOLOv5 method for inspecting Riders’ helmet wearing.J. Phys. Conf. Ser.20212024101205910.1088/1742‑6596/2024/1/012059
     [Google Scholar]
  46. GuJ. HuJ. JiangL. WangZ. ZhangX. XuY. ZhuJ. FangL. Research on object detection of overhead transmission lines based on optimized YOLOv5s.Energies2023166270610.3390/en16062706
     [Google Scholar]
  47. MaN. ZhangX. ZhengH.T. Shufflenet v2: Practical guidelines for efficient cnn architecture design.Proceedings of the European conference on computer vision (ECCV)09 October 2018, Cham, pp. 116-131.10.1007/978‑3‑030‑01264‑9_8
     [Google Scholar]
  48. ChenZ. YangJ. ChenL. JiaoH. Garbage classification system based on improved ShuffleNet v2.Resour. Conserv. Recycling202217810609010.1016/j.resconrec.2021.106090
     [Google Scholar]
  49. LiuY. ShaoZ. TengY. NAM: Normalization-based attention module2111.124192021
  50. ZhangX.H. YanJ.X. MaB. Research on abnormal detection method of side guard based on improved YOLOv5s.Chinese Journal of Engineering Design20222906665675
     [Google Scholar]
  51. ZhouQ. LiuH. QiuY. ZhengW. Object detection for construction waste based on an improved YOLOv5 model.Sustainability (Basel)202215168110.3390/su15010681
     [Google Scholar]
  52. LiC. LiL. GengY. Yolov6 v3. 0: A full-scale reloading2301.055862023
  53. ZhengZ. WangP. LiuW. LiJ. YeR. RenD. Distance-IoU loss: Faster and better learning for bounding box regression.Proc. Conf. AAAI Artif. Intell.2020347129931300010.1609/aaai.v34i07.6999
     [Google Scholar]
  54. YangY. LiaoY. ChengL. Remote Sensing Image Aircraft Target Detection Based on GIoU-YOLO v3.2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP)09-11 April 2021, Xi'an, China, 2021, pp. 474-478.10.1109/ICSP51882.2021.9408837
     [Google Scholar]
  55. WangY. NingX. LengB. Ship detection based on deep learning.2019 IEEE International Conference on Mechatronics and Automation (ICMA)04-07 August 2019, Tianjin, China, 2019, pp. 275-279.10.1109/ICMA.2019.8816265
     [Google Scholar]
  56. LiuL.Z. LiuG. XuH.P. Optimal design of loss function for one-stage object detection.Elect. Optic. Cont.2023-11-16
     [Google Scholar]
  57. LiuF. SunJ. ZhangS. Infrared ship target detection algorithm based on YOLOv5.Hongwai Yu Jiguang Gongcheng20235210222233
     [Google Scholar]
  58. DuS. ZhangB. ZhangP. An improved bounding box regression loss function based on CIOU loss for multi-scale object detection.2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML)16-18 July 2021, Chengdu, China, 2021, pp. 92-98.10.1109/PRML52754.2021.9520717
     [Google Scholar]
  59. ZhangZ. DengZ. WuZ. An improved EIoU-Yolov5 algorithm for blood cell detection and counting.2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI)19-21 August 2022, Chengdu, China, 2022, pp. 989-993.10.1109/PRAI55851.2022.9904093
     [Google Scholar]
  60. QiW. ChenH. YeY. Indoor object recognition based on YOLOv5 with EIOU loss function.Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023)10 October, 2023, Kuala Lumpur, Malaysia, pp. 880-885.
     [Google Scholar]
  61. GuX. ShuW. Research on the lane line detection method based on YOLOv5.Fifth International Conference on Artificial Intelligence and Computer Science (AICS 2023)16 October, 2023, Wuhan, China, pp. 323-328.10.1117/12.3009519
     [Google Scholar]
  62. LiZ. JiangX. ShuaiL. ZhangB. YangY. MuJ. A real-time detection algorithm for sweet cherry fruit maturity based on YOLOX in the natural environment.Agronomy (Basel)20221210248210.3390/agronomy12102482
     [Google Scholar]
  63. HanW. RenH. ZhuX. Research and implementation of PCB defect detection based on improved YOLOv5 algorithm.2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA)26-28 May 2023, Chongqing, China, 2023, pp. 1475-1478.10.1109/ICIBA56860.2023.10165010
     [Google Scholar]
  64. YangZ. WangX. LiJ. EIoU: an improved vehicle detection algorithm based on vehiclenet neural network.J. Phys. Conf. Ser.20211924101200110.1088/1742‑6596/1924/1/012001
     [Google Scholar]
  65. ShaoZ. WuW. WangZ. DuW. LiC. Seaships: A large-scale precisely annotated dataset for ship detection.IEEE Trans. Multimed.201820102593260410.1109/TMM.2018.2865686
     [Google Scholar]
  66. LiC.X. YangF. ZhouY. Substation grounding wire status target detection method based on improved YOLOv5.C.N. Patent 117253188, 2023.
  67. SunY.Y. HangH.J. WuY.L. A gesture recognition method based on improved YOLOv5.C.N. Patent 117238024, 2023.
  68. HuF. ZhaoJ.H. ChenB. Improved YOLOv5 model training method and occlusion pedestrian detection method.C.N. Patent 117237985, 2023.
/content/journals/rascs/10.2174/0126662558327827240920035158
Loading
SN-YOLOv5s: Ship Target Detection Algorithm Based on Improved YOLOv5s Algorithm
Recent Advances in Computer Science and Communications 18, E26662558327827 (2025); https://doi.org/10.2174/0126662558327827240920035158
/content/journals/rascs/10.2174/0126662558327827240920035158
/content/journals/rascs/10.2174/0126662558327827240920035158
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): attention mechanism; lightweighting; loss function; maritime monitoring; Target detection; YOLOv5s

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test