奶牛呼吸频率是反映奶牛生理健康状况的重要指标. 传统基于RGB图像的方法在实际牧场中易受光照变化与局部遮挡影响,为此本文提出了一种基于RGB-D(red green blue-depth)数据和关键点动态定位的侧卧奶牛呼吸频率检测方法. 首先利用YOLOv8n-Pose(You Only Look Once version 8 nano-Pose)对奶牛耆甲点、前膝关节、跗关节、后膝关节4个关键部位进行检测,并基于关键点空间关系动态确定腹部感兴趣区域,从而避免固定区域选取带来的定位偏差. 在此基础上,通过对齐RGB与深度视频流,提取腹部区域的连续深度均值信号,并采用高斯滤波与自动多尺度峰值检测(automatic multiscale-based peak detection,AMPD)算法实现呼吸计数. 试验结果表明:所提出方法在牧场环境下呼吸频率检测精度达到93.3%,均方根误差为3.75次/min,决定系数为0.94,验证了基于关键点的动态定位策略与深度信息在奶牛呼吸频率检测中的有效性.
代昕
,
牟世源
,
陈新超
,
刘洋
,
王鑫杰
,
李晏兴
,
付晓
,
沈维政
,
戴百生
. 基于RGB-D数据和关键点动态定位的侧卧奶牛呼吸频率检测方法[J]. 河北大学学报(自然科学版), 2026
, 46(5)
: 449
-461
.
DOI: 10.3969/j.issn.1000-1565.2026.05.001
[1] 殷海全,彭来营.奶牛热应激的危害及预防措施[J].北方牧业, 2023(20): 29.
[2] 刘宣岐,董婧,张倩,等.奶牛疾病数字化和智能化平台研究进展[J].现代农业科技, 2024(1): 186-188. DOI:10.3969/j.issn.1007-5739.2024.01.043.
[3] 刘云玲,魏艳辉,徐小伟,等.奶牛健康监测设备与技术研究及应用进展综述[J].农业机械学报, 2023, 54(增刊1): 303-314. DOI:10.6041/j.issn.1000-1298.2023.S1.033.
[4] 李爱杰,何蒲明.奶牛养殖的适度规模化问题研究[J].湖北农业科学, 2022, 61(19): 105-109. DOI:10.14088/j.cnki.issn0439-8114.2022.19.020.
[5] Tuan S A, Rustia D J A, Hsu J T, et al. Frequency modulated continuous wave radar-based system for monitoring dairy cow respiration rate[J]. Comput Electron Agric, 2022, 196: 106913. DOI:10.1016/j.compag.2022.106913.
[6] Fioranelli F, Li H B, Le Kernec J, et al. Radar-based evaluation of lameness detection in ruminants: preliminary results[C] //2019 IEEE MTT-S International Microwave Biomedical Conference(IMBioC). May 6-8, 2019, Nanjing, China. IEEE, 2019: 1-4. DOI:10.1109/IMBIOC.2019.8777830.
[7] Stewart M, Wilson M T, Schaefer A L, et al. The use of infrared thermography and accelerometers for remote monitoring of dairy cow health and welfare[J]. J Dairy Sci, 2017, 100(5): 3893-3901. DOI:10.3168/jds.2016-12055.
[8] Lowe G, Sutherland M, Waas J, et al. Infrared thermography-a non-invasive method of measuring respiration rate in calves[J]. Animals, 2019, 9(8): 535. DOI:10.3390/ani9080535.
[9] Kim S, Hidaka Y. Breathing pattern analysis in cattle using infrared thermography and computer vision[J]. Animals, 2021, 11(1): 207. DOI:10.3390/ani11010207.
[10] Chen X C, Dai B S, Wang X J, et al. Respiratory rate detection of dairy cows based on infrared thermography in head movement scenarios[J]. J Therm Biol, 2025, 130: 104154. DOI:10.1016/j.jtherbio.2025.104154.
[11] 郑卫民,马萌阳,辛亚平.奶牛福利及其关键点控制[J].畜牧兽医杂志, 2019, 38(3): 86-88. DOI:10.3969/j.issn.1004-6704.2019.03.030.
[12] 赵凯旋,何东健,王恩泽.基于视频分析的奶牛呼吸频率与异常检测[J].农业机械学报, 2014, 45(10): 258-263. DOI:10.6041/j.issn.1000-1298.2014.10.040
[13] 宋怀波,吴頔华,阴旭强,等.基于Lucas-Kanade稀疏光流算法的奶牛呼吸行为检测[J].农业工程学报, 2019, 35(17): 215-224. DOI:10.11975/j.issn.1002-6819.2019.17.026.
[14] Wu D H, Han M X, Song H B, et al. Monitoring the respiratory behavior of multiple cows based on computer vision and deep learning[J]. J Dairy Sci, 2023, 106(4): 2963-2979. DOI:10.3168/jds.2022-22501.
[15] Wu D H, Yin X Q, Jiang B, et al. Detection of the respiratory rate of standing cows by combining the Deeplab V3+ semantic segmentation model with the phase-based video magnification algorithm[J]. Biosyst Eng, 2020, 192: 72-89. DOI:10.1016/j.biosystemseng.2020.01.012.
[16] Shu H, Bindelle J, Gu X H. Non-contact respiration rate measurement of multiple cows in a free-stall barn using computer vision methods[J]. Comput Electron Agric, 2024, 218: 108678. DOI:10.1016/j.compag.2024.108678.
[17] Jagadev P, Giri L I. Non-contact monitoring of human respiration using infrared thermography and machine learning[J]. Infrared Phys Technol, 2020, 104: 103117. DOI:10.1016/j.infrared.2019.103117.
[18] Tun S C, Onizuka T, Tin P, et al. Revolutionizing cow welfare monitoring: a novel top-view perspective with depth camera-based lameness classification[J]. J Imaging, 2024, 10(3): 67. DOI:10.3390/jimaging10030067.
[19] Li Y X, Dai X, Dai B S, et al. Cow depth image restoration method based on RGB guided network with modulation branch in the cowshed environment[J]. Comput Electron Agric, 2025, 229: 109773. DOI:10.1016/j.compag.2024.109773.
[20] 黄子岩,娄小平.RGB-D相机深度图与彩色图配准方法研究[J].现代计算机, 2022, 28(6): 66-72. DOI:10.3969/j.issn.1007-1423.2022.06.012.
[21] Scholkmann F, Boss J, Wolf M. An efficient algorithm for automatic peak detection in noisy periodic and quasi-periodic signals[J]. Algorithms, 2012, 5(4): 588-603. DOI:10.3390/a5040588.
