In the early 20th century,French vice-consul George Souliéde Morant encountered acupuncture during his visit to China,and then brought it back to France.After more than a century,his collection was transported fr...In the early 20th century,French vice-consul George Souliéde Morant encountered acupuncture during his visit to China,and then brought it back to France.After more than a century,his collection was transported from Paris,France to Kunming,China,and later recognized as a Chinese national third-class precious cultural heritage.Currently housed in the Museum of Western Studies on Chinese Medicine at Yunnan University of Chinese Medicine,this set of instruments includes one needle holder converted from a fan-shaped holder,ten acupuncture needles,and eleven paper tags handwritten in English with names of diseases and body parts.This article attempts to present the foundational information and historical significance of this collection of this set of late Qing dynasty acupuncture instruments by reviewing the collection and related research on acupuncture instruments,consulting acupuncture professionals,measuring the detailed information of the set of instruments,and employing a method of translating and summarizing the content of the attached tags.展开更多
马岗鹅的行为与其生长状况和福利状况密切相关,马岗鹅关键行为监测对评估其生长性能具有重要的现实意义。为了实现对群养栏马岗鹅关键行为高效率精准监测,该研究探索一种基于YoloX的群养马岗鹅关键行为监测算法(Magang geese behavior m...马岗鹅的行为与其生长状况和福利状况密切相关,马岗鹅关键行为监测对评估其生长性能具有重要的现实意义。为了实现对群养栏马岗鹅关键行为高效率精准监测,该研究探索一种基于YoloX的群养马岗鹅关键行为监测算法(Magang geese behavior monitoring of based on Double Head-YoloX,MGBM-DH-YoloX),该算法通过减少YoloX的头部数量提升检测效率、使用损失函数减少前景背景干扰、使用迁移训练方式提高网络训练效率等技术对马岗鹅采食、饮水、休息和应激等关键行为及其规律进行分析。MGBM-DH-YoloX首先用Mosaic和Mixup对马岗鹅图像进行数据增强,然后使用增强后的数据集训练模型,并且利用模型检测马岗鹅的关键行为,最后累计得出马岗鹅关键行为的发生时长和行为节律;试验训练集为1400幅、验证集200幅和测试集为400幅,连续活动视频10 d。结果表明,MGBM-DH-YoloX算法的平均精度为98.98%、检测速度达到81帧/s、内存消耗为2520.04 MB。对马岗鹅的10 d养殖数据分析发现,MGBM-DH-YoloX能有效观察到马岗鹅随着日龄增长采食次数逐渐减少;试验鹅每日采食与饮水行为同时出现的比例为83.74%,呈现整体相伴趋势,但也从90.78%降低到74.57%,说明马岗鹅采食与饮水行为随着日龄增加呈现出逐渐分离趋势;试验鹅随着日龄增长休息时间逐渐加多,呈现出肉鸭对笼养的适应性逐步增强;应激行为随机性很强,突发性明显,发现人员随机走动等不规范饲喂带来的应激行为占据很大比例。该研究显示MGBM-DH-YoloX算法能利用监控视频对马岗鹅的关键行为进行智能提取,可为家禽智能养殖监管提供技术支撑。展开更多
使用计算机视觉方法进行的发动机极性自动化测试是火箭地面测试中重要的测试环节,该环节存在进一步改进和提升的空间。将递归全对场变换(Recurrent All-pairs Field Transforms, RAFT)光流算法替代传统光流法检测技术用于发动机喷管实...使用计算机视觉方法进行的发动机极性自动化测试是火箭地面测试中重要的测试环节,该环节存在进一步改进和提升的空间。将递归全对场变换(Recurrent All-pairs Field Transforms, RAFT)光流算法替代传统光流法检测技术用于发动机喷管实时运动监测,并根据现场测试场景对光流算法进行了优化,提升了运动检测速度与测量精确度,使自动测试系统具备了摆角的估测能力;在软件系统设计层面,引入差异图像直方图法监听法辅助喷管动作识别,避免了光流法对于未处在监测流程中的摄像头的冗余监听资源消耗,降低了系统硬件设备的负载,同时实现了一种可视化在线判读软件的设计。提出的软件与算法方面的改进在当前已投入使用的极性自动化测试系统上实现了进一步的优化。展开更多
基金financed by the grants from Scientific Research Fund Project of Yunnan Provincial Department of Education(No.2022Y377)Youth Fund for Humanities and Social Sciences Research Project of the Ministry of Education(No.20YJCZH246)National Social Science Fund Project(No.16BXW055)。
文摘In the early 20th century,French vice-consul George Souliéde Morant encountered acupuncture during his visit to China,and then brought it back to France.After more than a century,his collection was transported from Paris,France to Kunming,China,and later recognized as a Chinese national third-class precious cultural heritage.Currently housed in the Museum of Western Studies on Chinese Medicine at Yunnan University of Chinese Medicine,this set of instruments includes one needle holder converted from a fan-shaped holder,ten acupuncture needles,and eleven paper tags handwritten in English with names of diseases and body parts.This article attempts to present the foundational information and historical significance of this collection of this set of late Qing dynasty acupuncture instruments by reviewing the collection and related research on acupuncture instruments,consulting acupuncture professionals,measuring the detailed information of the set of instruments,and employing a method of translating and summarizing the content of the attached tags.
文摘马岗鹅的行为与其生长状况和福利状况密切相关,马岗鹅关键行为监测对评估其生长性能具有重要的现实意义。为了实现对群养栏马岗鹅关键行为高效率精准监测,该研究探索一种基于YoloX的群养马岗鹅关键行为监测算法(Magang geese behavior monitoring of based on Double Head-YoloX,MGBM-DH-YoloX),该算法通过减少YoloX的头部数量提升检测效率、使用损失函数减少前景背景干扰、使用迁移训练方式提高网络训练效率等技术对马岗鹅采食、饮水、休息和应激等关键行为及其规律进行分析。MGBM-DH-YoloX首先用Mosaic和Mixup对马岗鹅图像进行数据增强,然后使用增强后的数据集训练模型,并且利用模型检测马岗鹅的关键行为,最后累计得出马岗鹅关键行为的发生时长和行为节律;试验训练集为1400幅、验证集200幅和测试集为400幅,连续活动视频10 d。结果表明,MGBM-DH-YoloX算法的平均精度为98.98%、检测速度达到81帧/s、内存消耗为2520.04 MB。对马岗鹅的10 d养殖数据分析发现,MGBM-DH-YoloX能有效观察到马岗鹅随着日龄增长采食次数逐渐减少;试验鹅每日采食与饮水行为同时出现的比例为83.74%,呈现整体相伴趋势,但也从90.78%降低到74.57%,说明马岗鹅采食与饮水行为随着日龄增加呈现出逐渐分离趋势;试验鹅随着日龄增长休息时间逐渐加多,呈现出肉鸭对笼养的适应性逐步增强;应激行为随机性很强,突发性明显,发现人员随机走动等不规范饲喂带来的应激行为占据很大比例。该研究显示MGBM-DH-YoloX算法能利用监控视频对马岗鹅的关键行为进行智能提取,可为家禽智能养殖监管提供技术支撑。
文摘使用计算机视觉方法进行的发动机极性自动化测试是火箭地面测试中重要的测试环节,该环节存在进一步改进和提升的空间。将递归全对场变换(Recurrent All-pairs Field Transforms, RAFT)光流算法替代传统光流法检测技术用于发动机喷管实时运动监测,并根据现场测试场景对光流算法进行了优化,提升了运动检测速度与测量精确度,使自动测试系统具备了摆角的估测能力;在软件系统设计层面,引入差异图像直方图法监听法辅助喷管动作识别,避免了光流法对于未处在监测流程中的摄像头的冗余监听资源消耗,降低了系统硬件设备的负载,同时实现了一种可视化在线判读软件的设计。提出的软件与算法方面的改进在当前已投入使用的极性自动化测试系统上实现了进一步的优化。
