DyFish-DETR: Underwater Fish Image Recognition Based on Detection Transformer
Journal of Marine Science and Engineering · 22.05.2024 · 12 (6) · 864
DOI: 10.3390/jmse12060864 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 22.05.2024. Verfasst von Zhuowei Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangzhou Science and Technology Plan Project.
Abstract (Originalsprache)
Due to the complexity of underwater environments and the lack of training samples, the application of target detection algorithms to the underwater environment has yet to provide satisfactory results. It is crucial to design specialized underwater target recognition algorithms for different underwater tasks. In order to achieve this goal, we created a dataset of freshwater fish captured from multiple angles and lighting conditions, aiming to improve underwater target detection of freshwater fish in natural environments. We propose a method suitable for underwater target detection, called DyFish-DETR (Dynamic Fish Detection with Transformers). In DyFish-DETR, we propose a DyFishNet (Dynamic Fish Net) to better extract fish body texture features. A Slim Hybrid Encoder is designed to fuse fish body feature information. The results of ablation experiments show that DyFishNet can effectively improve the mean Average Precision (mAP) of model detection. The Slim Hybrid Encoder can effectively improve Frame Per Second (FPS). Both DyFishNet and the Slim Hybrid Encoder can reduce model parameters and Floating Point Operations (FLOPs). In our proposed freshwater fish dataset, DyFish-DETR achieved a mAP of 96.6%. The benchmarking experimental results show that the Average Precision (AP) and Average Recall (AR) of DyFish-DETR are higher than several state-of-the-art methods. Additionally, DyFish-DETR, respectively, achieved 99%, 98.8%, and 83.2% mAP in other underwater datasets.
Förderung
- Guangzhou Science and Technology Plan Project
Zitieren
APA
Wang, Z., Ruan, Z., & Chen, C. (2024). DyFish-DETR: Underwater Fish Image Recognition Based on Detection Transformer. Journal of Marine Science and Engineering, 12(6), 864. https://doi.org/10.3390/jmse12060864
Vancouver
Wang Z, Ruan Z, Chen C. DyFish-DETR: Underwater Fish Image Recognition Based on Detection Transformer. Journal of Marine Science and Engineering. 2024;12(6):864. doi:10.3390/jmse12060864
BibTeX
@article{Wang2024,
author = {Wang, Zhuowei and Ruan, Zhukang and Chen, Chong},
title = {DyFish-DETR: Underwater Fish Image Recognition Based on Detection Transformer},
journal = {Journal of Marine Science and Engineering},
year = {2024},
volume = {12},
number = {6},
pages = {864},
doi = {10.3390/jmse12060864}
}
EUVIMED