A Lightweight Underwater Fish Image Semantic Segmentation Model Based on U-Net

Simple item page
aut.relation.journalIET Image Processing
aut.relation.pages13
dc.contributor.authorZhang, Zhenkai
dc.contributor.authorLi, Wanghua
dc.contributor.authorSeet, Boon-Chong
dc.date.accessioned2024-06-27T01:56:20Z
dc.date.available2024-06-27T01:56:20Z
dc.date.issued2024-06-25
dc.description.abstractSemantic segmentation of underwater fish images is vital for monitoring fish stocks, assessing marine resources, and sustaining fisheries. To tackle challenges such as low segmentation accuracy, inadequate real-time performance, and imprecise location segmentation in current methods, a novel lightweight U-Net model is proposed. The proposed model acquires more segmentation details by applying a multiple-input approach at the first four encoder levels. To achieve both lightweight and high accuracy, a multi-scale residual structure (MRS) module is proposed to reduce parameters and compensate for the accuracy loss caused by the reduction of channels. To improve segmentation accuracy, a multi-scale skip connection (MSC) structure is further proposed, and the convolution block attention mechanism (CBAM) is introduced at the end of each decoder level for weight adjustment. Experimental results demonstrate a notable reduction in model volume, parameters, and floating-point operations by 94.20%, 94.39%, and 51.52% respectively, compared to the original model. The proposed model achieves a high mean intersection over union (mIOU) of 94.44%, mean pixel accuracy (mPA) of 97.03%, and a frame rate of 43.62 frames per second (FPS). With its high precision and minimal parameters, the model strikes a balance between accuracy and speed, making it particularly suitable for underwater image segmentation.
dc.identifier.citationIET Image Processing, ISSN: 1751-9659 (Print); 1751-9667 (Online), Wiley. doi: 10.1049/ipr2.13161
dc.identifier.doi10.1049/ipr2.13161
dc.identifier.issn1751-9659
dc.identifier.issn1751-9667
dc.identifier.urihttp://hdl.handle.net/10292/17705
dc.publisherWiley
dc.relation.urihttps://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ipr2.13161
dc.rights© 2024 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.
dc.rights.accessrightsOpenAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject0801 Artificial Intelligence and Image Processing
dc.subject0906 Electrical and Electronic Engineering
dc.subjectArtificial Intelligence & Image Processing
dc.subject4603 Computer vision and multimedia computation
dc.subject4607 Graphics, augmented reality and games
dc.titleA Lightweight Underwater Fish Image Semantic Segmentation Model Based on U-Net
dc.typeJournal Article
pubs.elements-id558524
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
IET Image Processing - 2024 - Zhang - A lightweight underwater fish image semantic segmentation model based on U‐Net.pdf
Size:
1.68 MB
Format:
Adobe Portable Document Format
Description:
Journal article
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau