Skip to content
2000
Volume 19, Issue 6
  • ISSN: 1872-2121
  • E-ISSN: 2212-4047

Abstract

Seaweeds, macroscopic algae known for their diverse applications across industries such as agriculture, biomedicine, and personal care, pose challenges in underwater detection due to the lack of suitable image datasets. Underwater photography is often hindered by light fluctuations and artificial light-induced haze and noise, complicating accurate object recognition. To address these challenges, this study leverages openly available open-source datasets such as Algae detection Dataset, seaweed-detection-test Dataset, and Fish detection Dataset. From these datasets, seaweed-spotted images, along with sea creatures and coral reefs, are segregated for employment in this research work. Employing a supervised learning algorithm facilitated by Roboflow software and the YOLOv5 architecture, the method achieves a commendable accuracy of 82.3% in identifying seaweed presence in underwater images. The investigation not only highlights the potential of seaweeds as renewable resources but also underscores the intricate nature of underwater detection. Moreover, the approach offers a promising avenue for refining Underwater Object Detection (UOD) algorithms, benefiting not only seaweed detection but also the identification of various marine species. Additionally, acknowledgment is made of the diversity of patented underwater object detection technologies, each with its own set of advantages, disadvantages, and application scenarios. To address the challenge of detecting seaweeds underwater, a supervised learning algorithm was developed utilizing the Roboflow software and YOLOv5 architecture. The selection of the dataset was guided by the need for a diverse representation of underwater scenes containing seaweeds, sea creatures, and coral reefs. Openly available open-source datasets, including the Algae detection Dataset, seaweed-detection-test Dataset, and Fish detection Dataset, were chosen based on their coverage of these underwater environments. From these datasets, seaweed-spotted images, alongside images of sea creatures and coral reefs, were segregated to form a comprehensive training dataset. This selection was made to ensure the inclusion of diverse underwater scenes containing seaweeds, thus enhancing the robustness of the model. Data augmentation techniques, including rotation, scaling, and flipping, were applied to increase dataset diversity and robustness. During the training process, model parameters were iteratively optimized to achieve accurate seaweed detection. This involved fine-tuning the YOLOv5 architecture and adjusting training parameters based on the characteristics of the selected dataset. By utilizing openly available datasets and employing data augmentation techniques, the methodology ensures the inclusion of diverse underwater scenes containing seaweeds, effectively addressing the challenges associated with underwater detection. The study evaluated the performance of the YOLOv5 algorithm in detecting underwater objects, focusing on Fish, Seaweed, and Starfish classes. Seaweed detection demonstrated high precision (0.925) and mAP50 (0.823), with an accuracy rate of 82.3% across diverse underwater images. Fish detection showed moderate precision (0.769) and mAP50 (0.512), while Starfish detection exhibited exceptional accuracy (Precision: 0.872, Recall: 1, mAP50: 0.995). These findings emphasize the algorithm's effectiveness in identifying underwater objects, particularly seaweed and starfish, highlighting its potential for marine species identification tasks. In conclusion, the YOLOv5 algorithm demonstrated remarkable accuracy in identifying seaweed, achieving an initial accuracy of 82.3%. Through subsequent retraining, both classification and detection accuracy significantly improved, reaching 77.7% and 99.5%, respectively. Additionally, the mAP50 value for seaweed also reaches 82.3%, indicating robust performance. However, for fish species, the accuracy is recorded at 51.2%, with detection accuracy also reaching 99.5%. These findings underscore the versatility and effectiveness of the YOLOv5 algorithm in underwater object detection tasks, highlighting its potential for enhancing marine species identification and ecological research.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/eng/10.2174/0118722121303581240527070227
2024-05-30
2025-07-15

  • From This Site

    /content/journals/eng/10.2174/0118722121303581240527070227
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. ChristensenJ.H. MogensenL.V. GaleazziR. AndersenJ.C. Detection, Localization and Classification of Fish and Fish Species in Poor Conditions using Convolutional Neural NetworksIEEE/OES Autonomous Underwater Vehicle Workshop (AUV)20181610.1109/AUV.2018.8729798
     [Google Scholar]
  2. CuiS. ZhouY. WangY. ZhaiL. Fish Detection Using Deep Learning.Appl. Comput. Intell. Soft Comput.2020202011310.1155/2020/3738108
     [Google Scholar]
  3. MahmoodA. OspinaA.G. BennamounM. AnS. SohelF. BoussaidF. HoveyR. FisherR.B. KendrickG.A. Automatic hierarchical classification of kelps using deep residual features.Sensors202020244744710.3390/s2002044731941132
     [Google Scholar]
  4. HanF. YaoJ. ZhuH. WangC. Marine organism detection and classification from underwater vision based on the deep CNN method.Math. Probl. Eng.2020202011110.1155/2020/3937580
     [Google Scholar]
  5. KalaiarasiG AshokJ A deep learning approach to detecting objects in underwater images.Cybernet. Syst.202316
     [Google Scholar]
  6. AliS A KhanZ HussainA AtharA KimH C Computer vision based deep learning approach for the detection and classification of algae species using microscopic images.Water20221414221910.3390/w14142219
     [Google Scholar]
  7. ChawlaK.S. SinghA. VermaP.K. Fish species identification in underwater videos using deep learning.International Conference on Signal Processing and Integrated Networks (SPIN)20195055
     [Google Scholar]
  8. BhatnagarR. HoangT. NguyenN.P. Under-water object detection using deep learning: A review.International Conference on Advanced Technologies for Communications (ATC)2018392397
     [Google Scholar]
  9. WuY. ZhouX. WangS. ZhanX. YuX. Underwater species detection and recognition: A review.IEEE J. Oceanic Eng.2021462687703
     [Google Scholar]
  10. LouchartX. DelebecqueC. A survey of image and video-based deep learning methods for marine species recognition.J. Ocean Eng. Sci.202161120
     [Google Scholar]
  11. TanS. ShaoW. WangL. Underwater Species Detection with YOLOv5 and Data AugmentationProceedings of the 2021 International Conference on Robotics and Automation Sciences2021186190
     [Google Scholar]
  12. LiuY. XuF. SunX. Underwater Object Detection with Enhanced YOLOv5 Algorithm.Proceedings of the 2021 International Conference on Computer Information and Big Data Applications2021129133
     [Google Scholar]
  13. ChenY. WangQ. HuangJ. A Fast and Accurate Underwater Fish Detection Method Based on YOLOv5.Proceedings of the 2021 International Conference on Intelligent Robotics and Control Engineering20215560
     [Google Scholar]
  14. LiuC. LiC. HuangJ. A Novel Approach for Underwater Object Detection Based on YOLOv5 and Improved Feature Pyramid Network.Proceedings of the 2021 International Conference on Intelligent Transportation and Smart City2021314319
     [Google Scholar]
  15. LiH. LiX. LiY. Underwater Fish Detection Based on Improved YOLOv5 Algorithm.Proceedings of the 2021 International Conference on Electronics2021168172
     [Google Scholar]
  16. LiuY. FengY. YuZ. ZhangH. A low-cost and efficient underwater object detection system using stereo vision.IEEE Access20197109165109175
     [Google Scholar]
  17. WangX. XieG. WeiJ. ZhangJ. Underwater object detection and recognition based on deep learning.IEEE Access201974299843007
     [Google Scholar]
  18. ZhangD. ZouY. ChenX. Underwater object detection and tracking based on a convolutional neural network.Sensors201919232032030650524
     [Google Scholar]
  19. LiJ. ChengH. WuY. ZuoL. ZhaoS. Underwater object detection based on improved Faster R-CNN.IET Image Process.2019131016481655
     [Google Scholar]
  20. ChenM. WangX. XuZ. Underwater object detection and tracking using the YOLOv3 network.J. Mar. Sci. Eng.202068
     [Google Scholar]
  21. SongY. GaoX. LiuX. Underwater object detection based on deep learning and infrared image enhancement.Infrared Phys. Technol.2020112
     [Google Scholar]
  22. LiR. ZhangL. LiX. WangY. A real-time underwater object detection system based on improved YOLOv3 algorithm.J. Sensors20202020
     [Google Scholar]
  23. SunS. WangM. LuoJ. WangX. A deep learning-based underwater object detection and recognition system.J. Sens.202120212021
     [Google Scholar]
  24. YangL. SunF. LiH. LiuX. Sea cucumber detection based on convolutional neural network.International Conference on Computer Application and System Modeling (ICCASM)2019453457
     [Google Scholar]
  25. ThanhD.T. MinhT.T. HoangH.T. ThanhT.Q. Detection and classification of sea creatures using convolutional neural networks.International Conference on Green Technology and Sustainable Development (GTSD)202016
     [Google Scholar]
  26. GaoY. ShanJ. Underwater object detection using deep learning: A review.IEEE Access201864441944438
     [Google Scholar]
  27. JiangJ. LiY. ZhangY. Underwater object detection using deep learning: A survey.IEEE Trans. Ind. Electron.201966430753085
     [Google Scholar]
  28. WanD. LuR. WangS. ShenS. XuT. LangX. YOLO-HR: Improved YOLOv5 for object detection in high-resolution optical remote sensing images.Remote Sens.202315361410.3390/rs15030614
     [Google Scholar]
  29. LiC. YanH. QianX. ZhuS. A domain adaptation YOLOv5 model for industrial defect inspection, Measurement.Elsevier2023213112725
     [Google Scholar]
  30. KrishnanA. KumarS.V. Real-Time Face Mask Detection Using YOLOv5.Proceedings of the 2021 International Conference on Communication and Signal Processing (ICCSP)2021321326
     [Google Scholar]
  31. LiuB. GaoF. LiY. Cost-sensitive YOLOv5 for detecting surface defects of industrial products.Sensors2023235261010.3390/s2305261036904815
     [Google Scholar]
  32. YangG. Face Mask Recognition System with YOLOV5 Based on Image RecognitionIEEE 6th International Conference on Computer and Communications (ICCC) 11-14 December, Chengdu, China, 2020, pp. 1398-1404.10.1109/ICCC51575.2020.9345042
     [Google Scholar]
  33. GuanX. LuoX. WangD. YOLOv5-UOD: Underwater Object Detection Method Based on Improved YOLOv5.Proceedings of the 2023 13th International Conference on Information Science and Technology (ICIST) 08-14 December, Cairo, Egypt, 2023, pp. 157-166.10.1109/ICIST59754.2023.10367136
     [Google Scholar]
  34. TanS. ShaoW. WangL. Underwater Species Detection with YOLOv5 and Data AugmentationProceedings of the 2021 International Conference on Robotics and Automation Sciences2021186190
     [Google Scholar]
  35. WangN. ChenT. LiuS. WangR. KarimiH.R. LinY. Deep learning-based visual detection of marine organisms: A survey.Neurocomputing202353213210.1016/j.neucom.2023.02.018
     [Google Scholar]
  36. KrishnanV. Hybridization of deep convolutional neural network for underwater object detection and tracking model.Microprocess. Microsyst.20229410462810.1016/j.micpro.2022.104628
     [Google Scholar]
  37. ZhangL. XingB. WangW. XuJ. Sea cucumber detection algorithm based on deep learning.Sensors20222215571710.3390/s2215571735957274
     [Google Scholar]
  38. AhnJ. NishidaY. IshiiK. UraT. A sea creatures classification method using convolutional neural networks.18th International Conference on Control, Automation and Systems (ICCAS) 17-20 October, PyeongChang, Korea (South), 2018, pp. 420-423.
     [Google Scholar]
  39. LiuK. PengL. TangS. Underwater object detection using TC-YOLO with attention mechanisms.Sensors2023235256710.3390/s2305256736904769
     [Google Scholar]
  40. LiuY. XuF. SunX. Underwater Object Detection with Enhanced YOLOv5 Algorithm.Proceedings of the 2021 International Conference on Computer Information and Big Data Applications2021129133
     [Google Scholar]
  41. LiH. LiX. LiY. Underwater Fish Detection Based on Improved YOLOv5 Algorithm.Proceedings of the 2021 International Conference on Electronics2021168172
     [Google Scholar]
  42. LingJ.B. ChrobakL.V. Underwater camera biomass prediction aggregation.U.S. Patent 118424732023
     [Google Scholar]
  43. HoweR. LizerZ. SarrettJ.W. AbrahamsonP.J. LittleJ.T. Method and system for external fish parasite monitoring in aquaculture.U.S. Patent 118497072023
     [Google Scholar]
  44. SnellgroveT. PuriR. KrojzlT. RuegerE. Under water image color correctionU.S. Patent 111642912021
     [Google Scholar]
  45. PrabhakarG. AyyanarN. RajaramS. BalamuruganN. B. Soft pneumatic sea weed gripper.Government of India Design 388163-0012024
     [Google Scholar]
  46. HeY. SuY. WangX. YuJ. LuoY. An improved method MSS-YOLOv5 for object detection with balancing speed-accuracy.Front. Phys.202310110192310.3389/fphy.2022.1101923
     [Google Scholar]
  47. WuT. DongY. YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition.Appl. Sci.202313241297710.3390/app132412977
     [Google Scholar]
  48. LiC. YanH. QianX. ZhuS. A domain adaptation YOLOv5 model for industrial defect inspection, Measurement.Elsevier2023213112725
     [Google Scholar]
  49. YoussryN. KhattabA. Accurate Real-Time Face Mask Detection Framework Using YOLOv5.IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS) 06-09 June, Cairo, Egypt, 2022, pp. 01-06.10.1109/DTS55284.2022.9809855
     [Google Scholar]
  50. ZhouC. LuZ. LvZ. MengM. TanY. XiaK. LiuK. ZuoH. Metal surface defect detection based on improved YOLOv5.Sci. Rep.20231312080310.1038/s41598‑023‑47716‑238012224
     [Google Scholar]
  51. SapakovaS. SapakovA. YilibuleY. A YOLOv5-based model for real-time mask detection in challenging environments.Procedia Comput. Sci.202423126727410.1016/j.procs.2023.12.202
     [Google Scholar]
  52. ZhuD. DaiL. DuP. CCE-YOLOv5s: An Improved YOLOv5 Model for UAV Small Target Detection.IEEE 5th International Conference on Civil Aviation Safety and Information Technology (ICCASIT)Dali, China202382482910.1109/ICCASIT58768.2023.10351744
     [Google Scholar]
  53. LiW. WeiY. A lightweight YOLOv5 model used for safety helmet and reflective clothing detection.International Conference on Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI) 21-23 October, Guangzhou, China, 2022, pp. 582-587.10.1109/AHPCAI57455.2022.10087510
     [Google Scholar]
  54. ZhaoT. QiaoN. Research on target detection technology of aircraft satellite images based on improved YOLOv5 modelInternational Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)Nanjing, China2023899410.1109/ICBASE59196.2023.10303177
     [Google Scholar]
  55. JoshiN. KumarD. KukrejaV. SarangiP. Automated Tea Leaves Recognition: Multi-Classification Using YOLOv5 and Inception V3 ModelInternational Conference on Computing Communication and Networking Technologies (ICCCNT)Delhi, India20231610.1109/ICCCNT56998.2023.10306542
     [Google Scholar]
  56. LiuTiande The Research on Lightweight Traffic Sign Recognition Algorithm Based on Improved YOLOv5 ModelIEEE 3rd International Conference on Computer Communication and Artificial Intelligence (CCAI) 26-28 May, Taiyuan, China, 2023, pp. 284-288.10.1109/CCAI57533.2023.10201317
     [Google Scholar]
  57. ZhangX. FanH. ZhuH. HuangX. WuT. ZhouH. Improvement of YOLOV5 Model Based on the Structure of Multiscale Domain Adaptive Network for CrowdscapeIEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) 07-08 November, Xi'an, China, 2021, pp. 171-175.10.1109/CCIS53392.2021.9754600
     [Google Scholar]
  58. DetectionS. seaweed-detection-test DatasetRoboflow Universe. Roboflow2023Available from: https://universe.roboflow.com/seaweed-detection/seaweed-detection-test
    [Google Scholar]
  59. UnderwaterA. D. Algae detection DatasetRoboflow Universe. RoboflowAvailable from: https://universe.roboflow.com/gmt/algae-detection 2023
     [Google Scholar]
  60. Fish detection DatasetRoboflow Universe. RoboflowAvailable from: c.ness@stud.uis.no. https://universe.roboflow.com/c-nessstud-uis-no/fish-detection-3yokr 2022
     [Google Scholar]
  61. RanoloE. GorroK. IlanoA. PinedaH. SintosC. GorroA.J. Underwater and Coastal Seaweeds Detection for Fluorescence Seaweed Photos and Videos using YOLOV3 and YOLOV5International Conference for Innovation in Technology (INOCON) 03-05 March, Bangalore, India, 2023, pp. 1-5.10.1109/INOCON57975.2023.10101342
     [Google Scholar]
  62. LinQ. ZhangS. XuS. Construction of Traffic Moving Object Detection System Based on Improved YOLOv5 AlgorithmInternational Conference on 3D Immersion, Interaction and Multi-sensory Experiences (ICDIIME)Madrid, Spain202326827210.1109/ICDIIME59043.2023.00057
     [Google Scholar]
  63. ZhengB. LiP. LuH. Research on moving target detection technology based on Yolov5 modelInternational Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP)Hangzhou, China202330530910.1109/AIIIP61647.2023.00065
     [Google Scholar]
  64. HuL. An improved YOLOv5 algorithm of target recognitionInternational Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) 24-26 February, Changchun, China, 2023, pp. 1373-1377.10.1109/EEBDA56825.2023.10090620
     [Google Scholar]
  65. ChenH. ZhangZ. Improved YOLOv5 algorithm for power insulator defect detectionInternational Conference on Power, Energy and Electrical Engineering (CPEEE)Tokyo, Japan202330130510.1109/CPEEE56777.2023.10217485
     [Google Scholar]
  66. NingJ. WangJ. Automatic driving scene target detection algorithm based on improved YOLOv5 networkInternational Conference on Computer Network, Electronic and Automation (ICCNEA) 23-25 September, Xi'an, China, 2022, pp. 218-222.10.1109/ICCNEA57056.2022.00056
     [Google Scholar]
  67. LeiF. TangF. LiS. Underwater target detection algorithm based on improved YOLOv5.J. Marine Sci. Eng.202210331010.3390/jmse10030310
     [Google Scholar]
  68. GuoG. ZhangZ. Road damage detection algorithm for improved YOLOv5.Sci. Rep.2022121552310.1038/s41598‑022‑19674‑8
     [Google Scholar]
  69. QiuZ. Application of an improved YOLOv5 algorithm in real-time detection of foreign objects by ground penetrating radar.Remote Sens.2022148189510.3390/rs14081895
     [Google Scholar]
  70. GuoS. Research on mask-wearing detection algorithm based on improved YOLOv5.Sensors.20222213493310.3390/s22134933
     [Google Scholar]
  71. YangR. KPE-YOLOv5: An improved small target detection algorithm based on YOLOv5.Electronics202312481710.3390/electronics12040817
     [Google Scholar]
  72. WangT. An intelligent method for detecting surface defects in aluminium profiles based on the improved YOLOv5 algorithm.Electronics20221115230410.3390/electronics11152304
     [Google Scholar]
  73. HongW. Detection of green asparagus in complex environments based on the improved YOLOv5 algorithm.Sensors2023233156210.3390/s23031562
     [Google Scholar]
  74. WuF. CaiZ. FanS. SongR. WangL. CaiW. Fish target detection in underwater blurred scenes based on improved YOLOv5.IEEE Access20231112291112292510.1109/ACCESS.2023.3328940
     [Google Scholar]
  75. ShenG. LiX. WeiY. Improved algorithm for pedestrian detection of lane line based on YOLOv5s modelIEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) 03-05 October, Beijing, China, 2022, pp. 405-409.10.1109/IAEAC54830.2022.9930101
     [Google Scholar]
  76. YaoJ. QiJ. ZhangJ. ShaoH. YangJ. LiX. A real-time detection algorithm for Kiwifruit defects based on YOLOv5.Electronics20211014171110.3390/electronics10141711
     [Google Scholar]
  77. ZhaoY. ShiY. WangZ. The improved YOLOV5 algorithm and its application in small target detection.Springer, Cham.20221345867968810.1007/978‑3‑031‑13841‑6_61
     [Google Scholar]
  78. ZhangZ. AoD. ZhouL. YuanX. LuoM. Laboratory behavior detection method based on improved Yolov5 modelInternational Conference on Cyber-Physical Social Intelligence (ICCSI) 18-20 December, Beijing, China, 2021, pp. 1-6.10.1109/ICCSI53130.2021.9736251
     [Google Scholar]
  79. LiuS. FengJ. ZhangQ. PengB. A real-time smoke and fire warning detection method based on an improved YOLOv5 modelInternational Conference on Pattern Recognition and Artificial Intelligence (PRAI) 19-21 August, Chengdu, China, 2022, pp. 728-734.10.1109/PRAI55851.2022.9904105
     [Google Scholar]
  80. KnausgårdK.M. WiklundA. SørdalenT.K. HalvorsenK.T. KleivenA.R. JiaoL. GoodwinM. Temperate fish detection and classification: A deep learning based approach.Appl. Intell.20225266988700110.1007/s10489‑020‑02154‑9
     [Google Scholar]
/content/journals/eng/10.2174/0118722121303581240527070227
Loading
YOLOv5-based Enhanced Underwater Seaweed Detection Using Open-Source Datasets
Recent Pat Eng 19, E300524230521 (2025); https://doi.org/10.2174/0118722121303581240527070227
/content/journals/eng/10.2174/0118722121303581240527070227
/content/journals/eng/10.2174/0118722121303581240527070227
Loading

Data & Media loading...


  • Article Type:     Review Article
Keyword(s): accuracy; open-source datasets; roboflow software; Seaweeds; underwater object detection; YOLOv5

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