高级检索

    基于视觉与水质特征融合的鱼类摄食行为识别模型

    Fish feeding behavior recognition model based on the fusion of visual and water quality features

      摘要
    • 摘要:
      目的 提升工厂化水产养殖中鱼类摄食行为识别的准确度。
      方法 本研究提出一种基于视觉和水质特征融合的鱼类摄食行为识别模型 MC-ConvNeXtV2。为更好地捕捉不同聚集程度的全局特征和摄食行为的细节特征，在ConvNeXtV2-T的每个卷积阶段，引入空间区域感知的局部注意力机制(Context-aware local attention mechanism, Cloatt)；为提高模型在高密度养殖下的行为识别性能，设计多模态特征融合模块(Multimodal feature fusion module，MFFM)，以实现视觉特征与溶解氧、温度、pH等水质特征的自适应融合。在养殖密度为160尾/m3的大口黑鲈Micropterus salmoides养殖工厂中进行模型测试。
      结果 测试结果表明，对于鱼群4种摄食行为分类任务，MC-ConvNeXtV2模型的识别准确率、精确率和召回率分别为96.89%、96.34%和96.59%，比ConvNeXtV2-T分别提升了3.11、2.42和2.72个百分点。
      结论 本研究提出的鱼类摄食行为识别模型为智能化养殖管理提供了新思路。

       

      Abstract:
      Objective To improve the accuracy of fish feeding behavior recognition in industrial aquaculture environment.
      Method A fish feeding behavior recognition model was proposed based on the fusion of visual and water quality features, namely MC-ConvNeXtV2. To better capture the global features of different aggregation levels and the detailed features of feeding behavior, a context-aware local attention mechanism (Cloatt) was introduced in each convolution stage of ConvNeXtV2-T. To improve the behavior recognition performance of the model in high-density aquaculture, a multimodal feature fusion module (MFFM) was designed to achieve adaptive fusion of visual features and dissolve oxygen, temperature, and pH of water quality features. The model test was conducted in a Micropterus salmoides culture factory with a culture density of 160 fish/m3.
      Result The test results showed that for the task of four feeding behaviors classification of fish school, the recognition accuracy, precision and recall of MC-ConvNeXtV2 model were 96.89%, 96.34%, and 96.59%, respectively. Compared with ConvNeXtV2-T, these indicators increased by 3.11, 2.42, and 2.72 percentage points, respectively.
      Conclusion The proposed fish feeding behavior recognition model offers a new approach for intelligent aquaculture management.

       

      • HTML全文
      • 参考文献(23)
      • 相关文章
      • 施引文献
    • 资源附件(0)

    /

    返回文章
    返回