高级检索
    邓洪兴, 许兴时, 王云飞, 等. 基于双目立体匹配与改进YOLOv8n-Pose关键点检测的奶牛体尺测量方法[J]. 华南农业大学学报, 2024, 45(5): 802-811. DOI: 10.7671/j.issn.1001-411X.202404001
    引用本文: 邓洪兴, 许兴时, 王云飞, 等. 基于双目立体匹配与改进YOLOv8n-Pose关键点检测的奶牛体尺测量方法[J]. 华南农业大学学报, 2024, 45(5): 802-811. DOI: 10.7671/j.issn.1001-411X.202404001
    shu
    DENG Hongxing, XU Xingshi, WANG Yunfei, et al. Dairy cow body size measurement method based on binocular stereo matching and improved YOLOv8n-Pose keypoint detection[J]. Journal of South China Agricultural University, 2024, 45(5): 802-811. DOI: 10.7671/j.issn.1001-411X.202404001
    Citation: DENG Hongxing, XU Xingshi, WANG Yunfei, et al. Dairy cow body size measurement method based on binocular stereo matching and improved YOLOv8n-Pose keypoint detection[J]. Journal of South China Agricultural University, 2024, 45(5): 802-811. DOI: 10.7671/j.issn.1001-411X.202404001
    shu

    基于双目立体匹配与改进YOLOv8n-Pose关键点检测的奶牛体尺测量方法

    Dairy cow body size measurement method based on binocular stereo matching and improved YOLOv8n-Pose keypoint detection

      摘要
    • 摘要:
      目的 实现奶牛体尺准确测量，精准评定奶牛体型。
      方法 针对奶牛体尺测量精度有限、自动化程度低等问题，提出一种基于双目立体匹配和改进YOLOv8n-Pose的奶牛体尺测量方法，利用CREStereo获取深度信息，在YOLOv8n-Pose中引入SimAM注意力机制，使网络更加关注奶牛个体识别及奶牛关键点位置信息，并采用CoordConv卷积改进网络结构，增强网络空间坐标感知能力。
      结果 改进的YOLOv8n-Pose可快速准确检测奶牛体尺测量关键点，检测精度为94.3%，模型参数量为2.99 M，浮点计算量为8.40 G，检测速度为55.6帧/s。融合双目立体匹配与改进YOLOv8n-Pose关键点检测的奶牛体尺测量最大平均相对误差为4.19%。
      结论 所提出的体尺测量方法具有较高的精度及较快的检测速度，能够满足奶牛体尺测量的实用要求。

       

      Abstract:
      Objective To realize accurate measurement of dairy cow body size, and preicisely assess dairy cow body shape.
      Method Addressing the challenges of limited accuracy and low automation in measuring dairy cow body size, a body size measurement method based on binocula stereo matching and improved YOLOv8n-Pose was proposed. The deep learning-based CREStereo was applied for stereo matching to obtain depth information. In YOLOv8n-Pose, the SimAM attention mechanism was introduced to focus more on individual dairy cow identification and key point information. Additionally, the CoordConv was employed to enhance the network’s spatial coordinate perception capability.
      Result The improved YOLOv8n-Pose achieved rapid and accurate detection of body size measurement key points for dairy cows. It attained a precision of 94.3%, with model parameters totaling 2.99 M and floating-point operations amounting to 8.40 G. The detection speed reached 55.6 frames/s. By combining stereo matching and improved YOLOv8n-Pose, the maximum average relative error in body size measurement was reduced to 4.19%.
      Conclusion The body size measurement method proposed in this paper achieves high accuracy and rapid detection speed, which can meet the practical requirements of body size measurement.

       

      • HTML全文
      • 参考文献(27)
      • 相关文章
      • 施引文献
    • 资源附件(0)

    /

    返回文章
    返回