Spacecraft Recovery & Remote Sensing, Volume. 46, Issue 1, 21(2025)

Parameter Identification of Parachute Inflation Phase Based on YOLO

Ce LU1, Zhuangzhi WU2, Xiaopeng XUE3, Kang LIU1, and Wei RONG1
Author Affiliations
  • 1Beijing Institute of Space Mechanics & Electricity, Beijing 100094, China
  • 2School of Computer Science and Engineering, Beihang University, Beijing 100191, China
  • 3School of Automation Academy, Central South University, Changsha 410083, China
  • show less
    Figures & Tables(22)
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    • Table 1. Advantages and disadvantages of two segmentation algorithm

      View table
      View in Article

      Table 1. Advantages and disadvantages of two segmentation algorithm

      特性传统分割算法YOLOv8实例分割
      普适性 传统算法通常具有明确的物理意义和直观的解释性,易于理解和实现。然而,传统算法的普适性较差,对于不同类型的图像或任务可能需要设计不同的算法和参数 YOLOv8作为一种深度学习模型,具有较强的学习和泛化能力,通过调整模型参数和训练数据,可以适应不同场景下的实例分割任务。然而,YOLOv8需要大量的训练数据和计算资源来训练和优化模型
      实时性 传统算法通常计算简单、运算效率较高,能够在较低性能的硬件上运行。对于复杂图像或需要高精度分割的场景,传统算法通常需要多次迭代或优化参数,从而影响处理速度 YOLOv8的处理速度非常快,可以达到每秒处理数百张图像,其计算复杂度和模型参数数量也相对较高,一般需要在高性能硬件上运行才能充分发挥其性能
      准确性 在处理特定类型的图像时具有较高的精度,通常依赖于图像的局部特征或预设规则,难以处理复杂多变的场景 在复杂条件下可以实现较高精度的分割,但受到训练数据品质、模型复杂度等因素的影响
      可扩展性 传统算法通常代码简洁、结构清晰,易于维护和调试。用户可以根据需要修改算法参数或逻辑以适应新场景或任务,但是,部分情况中需要重新结合不同的算法来实现满意的分割效果 YOLOv8作为一种深度学习框架,具有良好的可扩展性和可维护性。用户可以根据自己的需求添加新的模块或功能,并对模型进行持续优化和更新
    • Table 2. Configuration of the experimental platform

      View table
      View in Article

      Table 2. Configuration of the experimental platform

      项目配置
      操作系统Windows 11
      显卡GeForce RTX 4060
      CUDA12.3.1
      Python3.8.8
      深度学习框架Pytorch 2.4.0
    • Table 3. The dimensions of the ring-sail parachute

      View table
      View in Article

      Table 3. The dimensions of the ring-sail parachute

      结构名称伞衣幅总长hg伞衣幅上宽lu伞衣幅下宽ld环高hr帆高hs
      结构尺寸/mm3 970529891 6402 250
    • Table 4. Key parameters for accuracy verification

      View table
      View in Article

      Table 4. Key parameters for accuracy verification

      关键参数第2环第3环 第4环
      比例因子/mm0.01550.01520.0148
      像素点/个 395.2 564.5726.9
      辨识长度/mm6.12568.580510.7587
      理论长度/mm6.072 8.54410.896
      相对误差/% 0.883 0.427−1.26
    Tools

    Get Citation

    Copy Citation Text

    Ce LU, Zhuangzhi WU, Xiaopeng XUE, Kang LIU, Wei RONG. Parameter Identification of Parachute Inflation Phase Based on YOLO[J]. Spacecraft Recovery & Remote Sensing, 2025, 46(1): 21

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Oct. 16, 2024

    Accepted: --

    Published Online: Apr. 2, 2025

    The Author Email:

    DOI:10.3969/j.issn.1009-8518.2025.01.003

    Topics