Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

State of the art applications of deep learning within tracking and detecting marine debris: A survey (2403.18067v1)

Published 26 Mar 2024 in cs.CV, cs.AI, and cs.LG

Abstract: Deep learning techniques have been explored within the marine litter problem for approximately 20 years but the majority of the research has developed rapidly in the last five years. We provide an in-depth, up to date, summary and analysis of 28 of the most recent and significant contributions of deep learning in marine debris. From cross referencing the research paper results, the YOLO family significantly outperforms all other methods of object detection but there are many respected contributions to this field that have categorically agreed that a comprehensive database of underwater debris is not currently available for machine learning. Using a small dataset curated and labelled by us, we tested YOLOv5 on a binary classification task and found the accuracy was low and the rate of false positives was high; highlighting the importance of a comprehensive database. We conclude this survey with over 40 future research recommendations and open challenges.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (104)
  1. Anthropogenic marine debris over beaches: Spectral characterization for remote sensing applications. Remote Sensing of Environment 217. doi:10.1016/j.rse.2018.08.008.
  2. Microplastics and nanoplastics in aquatic environments: Aggregation, deposition, and enhanced contaminant transport. doi:10.1021/acs.est.7b05559.
  3. Entanglement of grey seals halichoerus grypus at a haul out site in cornwall, uk. Marine Pollution Bulletin 64, 2815–2819. doi:10.1016/j.marpolbul.2012.09.005.
  4. Litter categorization of beaches in wales, uk by multi-layer neural networks. URL: https://www.jstor.org/stable/25743008?seq=1&cid=pdf-.
  5. Vision transformers for remote sensing image classification. Remote Sensing 13, 1–20. doi:10.3390/rs13030516.
  6. Automatic recognition of coccoliths by dynamical neural networks. Marine Micropaleontology 51, 57–73. doi:10.1016/j.marmicro.2003.09.003.
  7. Plastic ingestion by planktivorous fishes in the north pacific central gyre. Marine Pollution Bulletin 60, 2275–2278. URL: https://www.sciencedirect.com/science/article/pii/S0025326X10003814, doi:https://doi.org/10.1016/j.marpolbul.2010.08.007.
  8. 3-d underwater object recognition. IEEE Journal of Oceanic Engineering 27, 814–829. doi:10.1109/JOE.2002.805097.
  9. Marine debris and human impacts on sea turtles in southern brazil. Marine Pollution Bulletin 42, 1330–1334. URL: https://www.sciencedirect.com/science/article/pii/S0025326X01001473, doi:https://doi.org/10.1016/S0025-326X(01)00147-3.
  10. End-to-end object detection with transformers URL: http://arxiv.org/abs/2005.12872.
  11. Wireless sensor networks for underwater survelliance systems. Ad Hoc Networks 4, 431–446. doi:10.1016/j.adhoc.2004.10.008.
  12. Nature’s solution to climate change: A strategy to protect whales can limit greenhouse gases and global warming. Finance & Development 0056, A011. URL: https://www.elibrary.imf.org/view/journals/022/0056/004/article-A011-en.xml, doi:10.5089/9781498316880.022.A011.
  13. A cnn image classification analysis for ’clean-coast detector’ as tourism service distribution. Seed Science and Technology 18, 15–26. doi:10.15722/jds.17.12.20201.15.
  14. Impacts of lost fishing gear on coral reef sessile invertebrates in the florida keys national marine sanctuary. Biological Conservation 121, 221–230. doi:10.1016/j.biocon.2004.04.023.
  15. Plastic pollution: A worldwide oceanic problem.
  16. Jedi: The jellyfish database initiative.
  17. Microplastics in the edible and inedible tissues of pelagic fishes sold for human consumption in kerala, india. Environmental Pollution 266. doi:10.1016/j.envpol.2020.115365.
  18. Microplastics in the edible tissues of shellfishes sold for human consumption. Chemosphere 264. doi:10.1016/j.chemosphere.2020.128554.
  19. Microplastic contamination of seafood intended for human consumption: A systematic review and meta-analysis. doi:10.1289/EHP7171.
  20. The occurrence and characteristics of plastic pollution in alaska’s marine birds.
  21. An embeddable algorithm for automatic garbage detection based on complex marine environment. Sensors 21. doi:10.3390/s21196391.
  22. The pollution of the marine environment by plastic debris: a review jos e e g. URL: www.elsevier.com/locate/marpolbul.
  23. From natural environment to animal tissues: A review of microplastics(nanoplastics) translocation and hazards studies. doi:10.1016/j.scitotenv.2022.158686.
  24. A growing plastic smog, now estimated to be over 170 trillion plastic particles afloat in the world’s oceans—urgent solutions required. PLoS ONE 18. doi:10.1371/journal.pone.0281596.
  25. Daily accumulation rates of marine debris on sub-antarctic island beaches. Marine Pollution Bulletin 66. doi:10.1016/j.marpolbul.2012.08.026.
  26. The copernicus open access hub. URL: https://scihub.copernicus.eu/.
  27. Marine & ocean pollution statistics & facts 2023.
  28. Marine litter stormy wash-outs: Developing the neural network to predict them. Pollutants 1. doi:10.3390/pollutants1030013.
  29. A hierarchical classification system for object recognition in underwater environments.
  30. Marine debris and northern fur seals: A case study. Marine Pollution Bulletin 18. doi:10.1016/S0025-326X(87)80020-6.
  31. Robotic detection of marine litter using deep visual detection models, pp. 5752–5758. doi:10.1109/ICRA.2019.8793975.
  32. Trash-icra19: A bounding box labeled dataset of underwater trash. URL: https://conservancy.umn.edu/handle/11299/214366.
  33. Plasticizing the seafloor: An overview. Environmental Technology (United Kingdom) 18, 195–201. doi:10.1080/09593331808616527.
  34. A new svm-based architecture for object recogni-tion in color underwater images with classification refinement by shape descriptors.
  35. Combining 3d-cnn and squeeze-and-excitation networks for remote sensing sea ice image classification. Mathematical Problems in Engineering 2020. doi:10.1155/2020/8065396.
  36. Detection of underwater marine plastic debris using an augmented low sample size dataset for machine vision system: A deep transfer learning approach, Institute of Electrical and Electronics Engineers Inc.. pp. 82–86. doi:10.1109/SCOReD53546.2021.9652703.
  37. Trashcan 1.0 an instance-segmentation labeled dataset of trash observations. URL: https://doi.org/10.13020/g1gx-y834.
  38. Automatic detection of underwater chain links using a forward-looking sonar. doi:10.1109/OCEANS-Bergen.2013.6608106.
  39. A deep learning model for automatic plastic mapping using unmanned aerial vehicle (uav) data. Remote Sensing 12. doi:10.3390/RS12091515.
  40. Plastic waste inputs from land into the ocean. Science 347. doi:10.1126/science.1260352.
  41. JAMSTEC., 2009. Jamstec ofes (ocean general circulation model for the earth simulator) dataset.
  42. Improving the accuracy of the water surface cover type in the 30 m from-glc product. Remote Sensing 7, 13507–13527. doi:10.3390/rs71013507.
  43. Plastic grabber: Underwater autonomous vehicle simulation for plastic objects retrieval using genetic programming, Springer International Publishing. pp. 527–533.
  44. Marida: A benchmark for marine debris detection from sentinel-2 remote sensing data. PLoS ONE 17. doi:10.1371/journal.pone.0262247.
  45. A new paradigm for estimating the prevalence of plastic litter in the marine environment. Marine Pollution Bulletin 173. doi:10.1016/j.marpolbul.2021.113127.
  46. An intelligent way for discerning plastics at the shorelines and the seas. Environmental Science and Pollution Research 27. doi:10.1007/s11356-020-10105-7.
  47. Identifying floating plastic marine debris using a deep learning approach. Environmental Science and Pollution Research 26. doi:10.1007/s11356-019-05148-4.
  48. Quantitative overview of marine debris ingested by marine megafauna. doi:10.1016/j.marpolbul.2019.110858.
  49. Nanoplastics and human health: Hazard identification and biointerface. doi:10.3390/nano12081298.
  50. Impacts of Marine Debris: Entanglement of Marine Life in Marine Debris Including a Comprehensive List of Species with Entanglement and Ingestion Records. doi:10.1007/978-1-4613-8486-1_10.
  51. Contamination of polychlorinated biphenyls (pcbs) in sediments from kyeonggi bay and nearby areas, korea. Marine pollution bulletin 42, 273–279. doi:10.1016/S0025-326X(00)00124-7.
  52. Discovery and quantification of plastic particle pollution in human blood. Environment International 163. doi:10.1016/j.envint.2022.107199.
  53. Automated river plastic monitoring using deep learning and cameras. Earth and Space Science 7. doi:10.1029/2019EA000960.
  54. Microsoft coco: Common objects in context, Springer International Publishing. pp. 740–755.
  55. Marine debris detection model based on the improved yolov5, Institute of Electrical and Electronics Engineers Inc.. pp. 725–728. doi:10.1109/NNICE58320.2023.10105682.
  56. Swin transformer: Hierarchical vision transformer using shifted windows URL: http://arxiv.org/abs/2103.14030.
  57. Detection of river plastic using uav sensor data and deep learning. Remote Sensing 14. doi:10.3390/rs14133049.
  58. Plastic resin pellets as a transport medium for toxic chemicals in the marine environment. Environmental Science and Technology 35. doi:10.1021/es0010498.
  59. Plastic in the ocean: How much is out there? Significance 14. doi:10.1111/j.1740-9713.2017.01072.x.
  60. Lidar detection of underwater objects using a neuro-svm-based architecture. IEEE Transactions on Neural Networks 17, 717–731. doi:10.1109/TNN.2006.873279.
  61. A comparison of plastic and plankton in the north pacific central gyre. Marine Pollution Bulletin 42. doi:10.1016/S0025-326X(01)00114-X.
  62. Is the use of deep learning an appropriate means to locate debris in the ocean without harming aquatic wildlife? Marine Pollution Bulletin 181. doi:10.1016/j.marpolbul.2022.113853.
  63. NOAA, 2022. A guide to plastic in the ocean. URL: https://oceanservice.noaa.gov/hazards/marinedebris/plastics-in-the-ocean.html.
  64. NOAA, 2023a. What is ghost fishing? URL: https://oceanservice.noaa.gov/facts/ghostfishing.html#:~:text=Derelict%20fishing%20gear%2C%20sometimes%20referred,as%20a%20hazard%20to%20navigation.
  65. NOAA, 2023b. Microplastics. URL: https://marinedebris.noaa.gov/what-marine-debris/microplastics.
  66. Gender benders at the beach: Endocrine disruption in marine and estuarine organisms. doi:10.1002/etc.5620200103.
  67. PADI, . Aware:marine debris program.
  68. Aquavision: Automating the detection of waste in water bodies using deep transfer learning. Case Studies in Chemical and Environmental Engineering 2. doi:10.1016/j.cscee.2020.100026.
  69. Plastic marine debris: Sources, distribution and impacts on coastal and ocean biodiversity. PENCIL Publication of Biological Sciences (OCEANOGRAPHY). 3(1): 40-54. (ISSN: 2408-5561). 3, 40–54.
  70. Plastic debris in a nesting leatherback turtle in french guiana. Chelonian Conservation and Biology 9, 267–270. doi:10.2744/CCB-0857.1.
  71. Taco: Trash annotations in context for litter detection URL: http://arxiv.org/abs/2003.06975.
  72. Plastics in the marine environment: Problems and solutions. Chemistry and Ecology 6, 69–78. URL: https://doi.org/10.1080/02757549208035263, doi:10.1080/02757549208035263.
  73. The plasticizer market: An assessment of traditional plasticizers and research trends to meet new challenges. doi:10.1016/j.progpolymsci.2004.10.001.
  74. Plastic ingestion and pcbs in seabirds: Is there a relationship? Marine Pollution Bulletin 19, 174–176. URL: https://www.sciencedirect.com/science/article/pii/0025326X88906741, doi:https://doi.org/10.1016/0025-326X(88)90674-1.
  75. Development of automated marine floating plastic detection system using sentinel-2 imagery and machine learning models. Marine Pollution Bulletin 178. doi:10.1016/j.marpolbul.2022.113527.
  76. Enabling autonomous capabilities in underwater robotics, pp. 3628 – 3634. doi:10.1109/IROS.2008.4651158.
  77. A first approach to the automatic detection of marine litter in sar images using artificial intelligence. doi:10.1109/IGARSS47720.2021.9737038.
  78. Export of plastic debris by rivers into the sea. Environmental Science and Technology 51, 12246–12253. doi:10.1021/acs.est.7b02368.
  79. Microplastic pollution, a threat to marine ecosystem and human health: a short review. Environmental Science and Pollution Research 24. doi:10.1007/s11356-017-9910-8.
  80. Yolov5. URL: https://github.com/AarohiSingla/yolov5.
  81. Make Sense. https://github.com/SkalskiP/make-sense/.
  82. Microplastics in seafood and the implications for human health. doi:10.1007/s40572-018-0206-z.
  83. A review of ghost gear entanglement amongst marine mammals, reptiles and elasmobranchs. doi:10.1016/j.marpolbul.2016.06.034.
  84. The cleansea set: A benchmark corpus for underwater debris detection and recognition. doi:10.1007/978-3-031-04881-4_49.
  85. An experimental study on marine debris location and recognition using object detection. Pattern Recognition Letters 168, 154–161. doi:10.1016/j.patrec.2022.12.019.
  86. Components of plastic: Experimental studies in animals and relevance for human health. doi:10.1098/rstb.2008.0281.
  87. Deploying deep learning to estimate the abundance of marine debris from video footage. Marine Pollution Bulletin 183. doi:10.1016/j.marpolbul.2022.114049.
  88. Investigating detection of floating plastic litter from space using sentinel-2 imagery. Remote Sensing 12. doi:10.3390/RS12162648.
  89. A video marking system for an autonomous underwater vehicle. URL: https://www.researchgate.net/publication/267819192.
  90. Marine debris ingestion in loggerhead sea turtles, caretta caretta, from the western mediterranean. Marine pollution bulletin 44, 211–216. doi:10.1016/S0025-326X(01)00236-3.
  91. Remote sensing of sea surface artificial floating plastic targets with sentinel-2 and unmanned aerial systems (plastic litter project 2019). Remote Sensing 12. doi:10.3390/rs12122013.
  92. Detection of floating plastics from satellite and unmanned aerial systems (plastic litter project 2018). International Journal of Applied Earth Observation and Geoinformation 79. doi:10.1016/j.jag.2019.03.011.
  93. Training data-efficient image transformers & distillation through attention.
  94. Tzutalin, 2015. Labelimg. URL: https://github.com/tzutalin/labelImg.
  95. Characterization of marine debris in north carolina salt marshes. Marine Pollution Bulletin 62. doi:10.1016/j.marpolbul.2011.09.010.
  96. Sources of marine debris for seychelles and other remote islands in the western indian ocean. Marine Pollution Bulletin 187, 114497. URL: https://www.sciencedirect.com/science/article/pii/S0025326X22011791, doi:https://doi.org/10.1016/j.marpolbul.2022.114497.
  97. Quantifying floating plastic debris at sea using vessel-based optical data and artificial intelligence. Remote Sensing 13. doi:10.3390/rs13173401.
  98. Detection and tracking of objects in underwater video.
  99. Underwater and airborne monitoring of marine ecosystems and debris. Journal of Applied Remote Sensing 13, 1. doi:10.1117/1.jrs.13.044509.
  100. The physical impacts of microplastics on marine organisms: a review. doi:10.1016/j.envpol.2013.02.031.
  101. Deep-sea debris identification using deep convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14, 8909–8921. doi:10.1109/JSTARS.2021.3107853.
  102. An efficient deep-sea debris detection method using deep neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14, 12348–12360. doi:10.1109/JSTARS.2021.3130238.
  103. Yolotrashcan: A deep learning marine debris detection network. IEEE Transactions on Instrumentation and Measurement 72. doi:10.1109/TIM.2022.3225044.
  104. Zooniverse, 2023. Zooniverse. URL: https://www.zooniverse.org/.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now