Underwater Fish Segmentation Algorithm Based on Improved PSPNet Network
Sensors · 2023
DOI: 10.3390/s23198072 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Yanling Han und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Technology, Shanghai Ocean University, Shanghai 201306, China. Hauptthemen laut MEDLINE: Algorithms, Fisheries. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Resources Foundation, National Natural Science Foundation of China, National Key R&D Program of China.
Abstract (Originalsprache)
With the sustainable development of intelligent fisheries, accurate underwater fish segmentation is a key step toward intelligently obtaining fish morphology data. However, the blurred, distorted and low-contrast features of fish images in underwater scenes affect the improvement in fish segmentation accuracy. To solve these problems, this paper proposes a method of underwater fish segmentation based on an improved PSPNet network (IST-PSPNet). First, in the feature extraction stage, to fully perceive features and context information of different scales, we propose an iterative attention feature fusion mechanism, which realizes the depth mining of fish features of different scales and the full perception of context information. Then, a SoftPool pooling method based on fast index weighted activation is used to reduce the numbers of parameters and computations while retaining more feature information, which improves segmentation accuracy and efficiency. Finally, a triad attention mechanism module, triplet attention (TA), is added to the different scale features in the golden tower pool module so that the space attention can focus more on the specific position of the fish body features in the channel through cross-dimensional interaction to suppress the fuzzy distortion caused by background interference in underwater scenes. Additionally, the parameter-sharing strategy is used in this process to make different scale features share the same learning weight parameters and further reduce the numbers of parameters and calculations. The experimental results show that the method presented in this paper yielded better results for the DeepFish underwater fish image dataset than other methods, with 91.56% for the Miou, 46.68 M for Params and 40.27 G for GFLOPS. In the underwater fish segmentation task, the method improved the segmentation accuracy of fish with similar colors and water quality backgrounds, improved fuzziness and small size and made the edge location of fish clearer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Technology, Shanghai Ocean University, Shanghai 201306, China.
- College of Marine Science, Shanghai Ocean University, Shanghai 201306, China.
ORCID-Profile: Yanling Han
Förderung
- The National Natural Resources Foundation
- National Natural Science Foundation of China
- National Key R&D Program of China
Zitieren
APA
Han, Y., Zheng, B., Kong, X., Huang, J., Wang, X., Ding, T., & Chen, J. (2023). Underwater Fish Segmentation Algorithm Based on Improved PSPNet Network. Sensors. https://doi.org/10.3390/s23198072
Vancouver
Han Y, Zheng B, Kong X, Huang J, Wang X, Ding T, et al. Underwater Fish Segmentation Algorithm Based on Improved PSPNet Network. Sensors. 2023. doi:10.3390/s23198072
BibTeX
@article{Han2023,
author = {Han, Yanling and Zheng, Bowen and Kong, Xianghong and Huang, Junjie and Wang, Xiaotong and Ding, Tianhong and Chen, Jiaqi},
title = {Underwater Fish Segmentation Algorithm Based on Improved PSPNet Network},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23198072}
}
EUVIMED