Wang Rong, Gao Ronghua, Li Qifeng, Zhao Chunjiang, Ma Weihong, Yu Ligen, Ding Luyu
Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, 100097, China.
College of Information Engineering, Northwest A&F University, Yangling, 712100, China.
Sci Rep. 2023 Oct 13;13(1):17418. doi: 10.1038/s41598-023-40757-7.
To improve the detection speed of cow mounting behavior and the lightness of the model in dense scenes, this study proposes a lightweight rapid detection system for cow mounting behavior. Using the concept of EfficientNetV2, a lightweight backbone network is designed using an attention mechanism, inverted residual structure, and depth-wise separable convolution. Next, a feature enhancement module is designed using residual structure, efficient attention mechanism, and Ghost convolution. Finally, YOLOv5s, the lightweight backbone network, and the feature enhancement module are combined to construct a lightweight rapid recognition model for cow mounting behavior. Multiple cameras were installed in a barn with 200 cows to obtain 3343 images that formed the cow mounting behavior dataset. Based on the experimental results, the inference speed of the model put forward in this study is as high as 333.3 fps, the inference time per image is 4.1 ms, and the model mAP value is 87.7%. The mAP value of the proposed model is shown to be 2.1% higher than that of YOLOv5s, the inference speed is 0.47 times greater than that of YOLOv5s, and the model weight is 2.34 times less than that of YOLOv5s. According to the obtained results, the model proposed in the current work shows high accuracy and inference speed and acquires the automatic detection of cow mounting behavior in dense scenes, which would be beneficial for the all-weather real-time monitoring of multi-channel cameras in large cattle farms.
为提高奶牛爬跨行为的检测速度以及模型在密集场景下的轻量化程度，本研究提出了一种用于奶牛爬跨行为的轻量化快速检测系统。利用EfficientNetV2的概念，采用注意力机制、倒置残差结构和深度可分离卷积设计了一个轻量化主干网络。接下来，使用残差结构、高效注意力机制和Ghost卷积设计了一个特征增强模块。最后，将YOLOv5s、轻量化主干网络和特征增强模块相结合，构建了一个用于奶牛爬跨行为的轻量化快速识别模型。在一个装有200头奶牛的牛舍中安装了多个摄像头，获取了3343张图像，形成了奶牛爬跨行为数据集。基于实验结果，本研究提出的模型推理速度高达333.3 fps，每张图像的推理时间为4.1毫秒，模型的平均精度均值（mAP）为87.7%。结果表明，所提模型的mAP值比YOLOv5s高2.1%，推理速度是YOLOv5s的0.47倍，模型权重比YOLOv5s少2.34倍。根据所得结果，当前工作中提出的模型具有较高的准确率和推理速度，能够在密集场景下实现奶牛爬跨行为的自动检测，这将有利于大型奶牛场多通道摄像头的全天候实时监测。
