CFFI-Vit: Enhanced Vision Transformer for the Accurate Classification of Fish Feeding Intensity in Aquaculture

文献类型： 外文期刊

第一作者： Liu, Jintao

作者： Liu, Jintao;Becerra, Alfredo Tolon;Bienvenido-Barcena, Jose Fernando;Liu, Jintao;Yang, Xinting;Zhao, Zhenxi;Zhou, Chao;Liu, Jintao;Yang, Xinting;Zhao, Zhenxi;Zhou, Chao;Liu, Jintao;Yang, Xinting;Zhao, Zhenxi;Zhou, Chao

作者机构：

关键词： aquaculture; fish feeding intensity classification; vision transformer; residual network

期刊名称：JOURNAL OF MARINE SCIENCE AND ENGINEERING （ 影响因子：2.7； 五年影响因子：2.8 ）

ISSN：

年卷期： 2024 年 12 卷 7 期

页码：

收录情况： SCI

摘要： The real-time classification of fish feeding behavior plays a crucial role in aquaculture, which is closely related to feeding cost and environmental preservation. In this paper, a Fish Feeding Intensity classification model based on the improved Vision Transformer (CFFI-Vit) is proposed, which is capable of quantifying the feeding behaviors of rainbow trout (Oncorhynchus mykiss) into three intensities: strong, moderate, and weak. The process is outlined as follows: firstly, we obtained 2685 raw feeding images of rainbow trout from recorded videos and classified them into three categories: strong, moderate, and weak. Secondly, the number of transformer encoder blocks in the internal structure of the ViT was reduced from 12 to 4, which can greatly reduce the computational load of the model, facilitating its deployment on mobile devices. And finally, a residual module was added to the head of the ViT, enhancing the model's ability to extract features. The proposed CFFI-Vit has a computational load of 5.81 G (Giga) Floating Point Operations per Second (FLOPs). Compared to the original ViT model, it reduces computational demands by 65.54% and improves classification accuracy on the validation set by 5.4 percentage points. On the test set, the model achieves precision, recall, and F1 score of 93.47%, 93.44%, and 93.42%, respectively. Additionally, compared to state-of-the-art models such as ResNet34, MobileNetv2, VGG16, and GoogLeNet, the CFFI-Vit model's classification accuracy is higher by 6.87, 8.43, 7.03, and 5.65 percentage points, respectively. Therefore, the proposed CFFI-Vit can achieve higher classification accuracy while significantly reducing computational demands. This provides a foundation for deploying lightweight deep network models on edge devices with limited hardware capabilities.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序