Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep Learning Innovations for Underwater Waste Detection: An In-Depth Analysis (2405.18299v4)

Published 28 May 2024 in cs.CV, cs.AI, cs.LG, and cs.RO

Abstract: Addressing the issue of submerged underwater trash is crucial for safeguarding aquatic ecosystems and preserving marine life. While identifying debris present on the surface of water bodies is straightforward, assessing the underwater submerged waste is a challenge due to the image distortions caused by factors such as light refraction, absorption, suspended particles, color shifts, and occlusion. This paper conducts a comprehensive review of state-of-the-art architectures and on the existing datasets to establish a baseline for submerged waste and trash detection. The primary goal remains to establish the benchmark of the object localization techniques to be leveraged by advanced underwater sensors and autonomous underwater vehicles. The ultimate objective is to explore the underwater environment, to identify, and remove underwater debris. The absence of benchmarks (dataset or algorithm) in many researches emphasizes the need for a more robust algorithmic solution. Through this research, we aim to give performance comparative analysis of various underwater trash detection algorithms.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (83)
  1. doi:https://doi.org/10.1016/j.cscee.2020.100010. URL https://www.sciencedirect.com/science/article/pii/S2666016420300086
  2. doi:10.3389/feart.2020.00028.
  3. doi:10.48550/ARXIV.1803.10813. URL https://arxiv.org/abs/1803.10813
  4. doi:10.1007/s11042-020-08976-6. URL https://doi.org/10.1007/s11042-020-08976-6
  5. doi:https://doi.org/10.1016/j.marpolbul.2022.113853. URL https://www.sciencedirect.com/science/article/pii/S0025326X22005355
  6. arXiv:1908.03673.
  7. doi:https://doi.org/10.1016/j.marpolbul.2022.113431. URL https://www.sciencedirect.com/science/article/pii/S0025326X22001138
  8. doi:https://doi.org/10.1016/j.marpolbul.2018.06.028. URL https://www.sciencedirect.com/science/article/pii/S0025326X18304259
  9. Tensorflow, "tensorflow object detection zoo (accessed: 2017). URL https://github.com/tensorflow/models/blob/master/research/objectdetection/g3doc/detectionmodelzoo.md
  10. doi:https://doi.org/10.1016/S0025-326X(02)00220-5. URL https://www.sciencedirect.com/science/article/pii/S0025326X02002205
  11. doi:10.1109/CARE.2013.6733698.
  12. e. a. M Bernstein, Learning-based event response for marine robotics (2013) 3362–3367.
  13. doi:https://doi.org/10.1016/j.neucom.2023.01.081. URL https://www.sciencedirect.com/science/article/pii/S0925231223001133
  14. doi:https://doi.org/10.1016/j.compeleceng.2022.107898. URL https://www.sciencedirect.com/science/article/pii/S0045790622001847
  15. doi:https://doi.org/10.1016/j.patcog.2021.108324. URL https://www.sciencedirect.com/science/article/pii/S0031320321005045
  16. doi:10.1109/ESCI50559.2021.9397025.
  17. doi:10.1007/s11356-019-05148-4.
  18. doi:10.1109/JSTARS.2021.3130238.
  19. doi:10.1109/GUCON50781.2021.9573722.
  20. doi:10.1109/JSTARS.2021.3107853.
  21. doi:10.1016/j.jvcir.2022.103656.
  22. doi:10.1016/j.patrec.2022.12.019. URL https://doi.org/10.1016/j.patrec.2022.12.019
  23. doi:10.1109/TIM.2022.3225044.
  24. doi:10.1016/j.isprsjprs.2023.01.007.
  25. doi:https://doi.org/10.1016/j.marpolbul.2020.111327. URL https://www.sciencedirect.com/science/article/pii/S0025326X20304458
  26. doi:https://doi.org/10.1016/j.dib.2022.108072. URL https://www.sciencedirect.com/science/article/pii/S2352340922002839
  27. doi:10.1109/TSMCC.2008.919147.
  28. doi:null.
  29. doi:DOI:10.1007/s11042-022-12535-6.
  30. doi:10.1109/OCEANSChennai45887.2022.9775361.
  31. doi:https://doi.org/10.1016/j.jag.2022.102890. URL https://www.sciencedirect.com/science/article/pii/S1569843222000929
  32. doi:10.3390/app11125644. URL https://www.mdpi.com/2076-3417/11/12/5644
  33. doi:10.1038/s41598-018-34590-6.
  34. doi:https://doi.org/10.1016/j.coesh.2020.10.002. URL https://www.sciencedirect.com/science/article/pii/S2468584420300659
  35. doi:10.1016/j.scitotenv.2019.133581.
  36. doi:10.1109/ICCSEA49143.2020.9132871.
  37. doi:10.5120/ijca2017914765.
  38. doi:https://doi.org/10.1016/j.marpolbul.2021.112347. URL https://www.sciencedirect.com/science/article/pii/S0025326X21003817
  39. doi:10.1109/TNNLS.2022.3143887.
  40. arXiv:2108.06800. URL https://arxiv.org/abs/2108.06800
  41. doi:10.1007/s11042-022-12535-6. URL https://doi.org/10.1007/s11042-022-12535-6
  42. doi:10.1016/j.scitotenv.2023.162826.
  43. doi:10.1016/j.jvcir.2022.103656. URL https://doi.org/10.1016/j.jvcir.2022.103656
  44. doi:10.1016/j.marpolbul.2022.113853. URL http://dx.doi.org/10.1016/j.marpolbul.2022.113853
  45. doi:10.1016/j.patrec.2022.12.019.
  46. Yolotrashcan: A deep learning marine debris detection network, IEEE Transactions on Instrumentation and Measurement (2022).
  47. doi:10.3390/app11125644.
  48. doi:10.1109/ICRA.2019.8793975.
  49. doi:10.1007/978-3-031-43360-3_24. URL https://doi.org/10.1007%2F978-3-031-43360-3_24
  50. doi:https://doi.org/10.1016/j.wasman.2021.12.001. URL https://www.sciencedirect.com/science/article/pii/S0956053X21006474
  51. doi:10.48550/ARXIV.2105.06808. URL https://arxiv.org/abs/2105.06808
  52. arXiv:1805.09300.
  53. doi:10.1109/INDICON52576.2021.9691547.
  54. doi:10.3390/jmse11081532.
  55. doi:10.48550/arxiv.2308.04218.
  56. doi:10.1109/ccdc58219.2023.10326901.
  57. doi:10.1109/icict54344.2022.9850497.
  58. arXiv:1311.2524.
  59. R. Girshick, Fast r-cnn (2015). arXiv:1504.08083.
  60. arXiv:1506.01497.
  61. doi:10.1109/CVPR.2017.106.
  62. arXiv:1506.02640.
  63. doi:10.1109/CVPR.2017.690.
  64. doi:10.1007/978-3-319-46448-0_2. URL http://dx.doi.org/10.1007/978-3-319-46448-0_2
  65. doi:10.5281/zenodo.3908559. URL https://github.com/ultralytics/ultralytics
  66. doi:10.48550/ARXIV.2207.02696. URL https://arxiv.org/abs/2207.02696
  67. doi:10.5281/zenodo.7347926. URL https://doi.org/10.5281/zenodo.7347926
  68. doi:10.48550/ARXIV.1512.03385. URL https://arxiv.org/abs/1512.03385
  69. doi:10.1109/CVPR.2013.423.
  70. doi:10.1007/s11263-013-0620-5.
  71. doi:10.1109/ICME.2008.4607625.
  72. doi:10.1007/978-3-319-10578-9_23. URL http://dx.doi.org/10.1007/978-3-319-10578-9_23
  73. doi:10.1007/978-3-319-10602-1_26.
  74. arXiv:1603.08695.
  75. arXiv:1506.06204.
  76. arXiv:1512.04412.
  77. arXiv:1409.1556.
  78. arXiv:1703.06870.
  79. arXiv:1903.00241.
  80. arXiv:2010.16061.
  81. doi:10.1007/978-0-387-39940-9_492. URL https://doi.org/10.1007/978-0-387-39940-9_492
  82. doi:10.1007/978-3-642-40994-3_29. URL https://doi.org/10.1007/978-3-642-40994-3_29
  83. R. Horner, “the ocean currents brought us in a lovely gift today… - youtube.” (2019). URL https://www.youtube.com/watch?v=AWgfOND2y68
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Jaskaran Singh Walia (11 papers)
  2. Pavithra L K (1 paper)
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
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets