EUVIMEDScopri EUVIMED
Open access · CC BY-NC-ND 4.0

A lightweight underwater fish image semantic segmentation model based on U‐Net

Zhenkai Zhang, Wanghua Li, Boon‐Chong Seet

IET Image Processing · 2024-10 · 18 (12) · 3143-3155

DOI: 10.1049/ipr2.13161 ↗

At a glance

Journal article in IET Image Processing, published online on 2024-06-25. Written by Zhenkai Zhang and 2 co-authors. Cited 13 times so far (Crossref); 48 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: National Natural Science Foundation of China.

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Semantic 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.

Funding

  • National Natural Science Foundation of China

Cite

APA

Zhang, Z., Li, W., & Seet, B. (2024). A lightweight underwater fish image semantic segmentation model based on U‐Net. IET Image Processing, 18(12), 3143-3155. https://doi.org/10.1049/ipr2.13161

Vancouver

Zhang Z, Li W, Seet B. A lightweight underwater fish image semantic segmentation model based on U‐Net. IET Image Processing. 2024;18(12):3143-3155. doi:10.1049/ipr2.13161

BibTeX
@article{Zhang2024,
  author = {Zhang, Zhenkai and Li, Wanghua and Seet, Boon‐Chong},
  title = {A lightweight underwater fish image semantic segmentation model based on U‐Net},
  journal = {IET Image Processing},
  year = {2024},
  volume = {18},
  number = {12},
  pages = {3143--3155},
  doi = {10.1049/ipr2.13161}
}
Start for free →