Multiclass Image Segmentation using Deep Residual Encoder-Decoder Models in Highly Turbid Underwater Ambiances

Underwater environments, especially the coral reefs, are the habitat of many critically endangered species. Extensive monitoring of these aquatic ecosystems is essential for conserving and deep understanding of these vulnerable habitats. Monitoring by extracting details from underwater images of tur...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of mathematical, engineering and management sciences Ročník 9; číslo 6; s. 1510 - 1530
Hlavní autoři: Haridas, T. P. Mithun, Kamal, Suraj, Balakrishnan, Arun A., Thomas, Rosemol, Nezla, N. A., Balakrishnan, Kannan, Supriya, M. H.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Dehradun International Journal of Mathematical, Engineering and Management Sciences 01.12.2024
Ram Arti Publishers
Témata:
Datasets
encoder-decoder model
fish4knowledge
multi-class image segmentation
underwater image
underwater noise
India
ISSN:2455-7749, 2455-7749
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Underwater environments, especially the coral reefs, are the habitat of many critically endangered species. Extensive monitoring of these aquatic ecosystems is essential for conserving and deep understanding of these vulnerable habitats. Monitoring by extracting details from underwater images of turbid, hazy marine environments is extremely challenging. In this work, a novel annotated dataset is created for three classes of objects in the images of coral reef environment considering fish, rock/coral and background for the Fish4Knowledge dataset, a benchmark dataset primarily for binary segmentation. This work also proposes a multiclass ResUnet based image segmentation model for the newly created multiclass annotations. Various encoder-decoder convolutional architectures were analysed and found that ResUnet exhibits better robustness. The performance of the multiclass ResUnet model is also analysed by optimizing with different cost functions. Various underwater noisy conditions are simulated in the test images to find the robustness of the model, and observed that the proposed model optimised with Jaccard loss performs better even in extremely noisy scenarios.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2455-7749
2455-7749
DOI:10.33889/IJMEMS.2024.9.6.080