摘要
养殖场中肉牛较为活跃,采集得到的图像数据中肉牛姿态多变,肉牛姿态端正帧较少,导致自动测量肉牛体尺困难。针对以上问题,本研究通过分析肉牛骨架特征和肉牛图像边缘轮廓特征,提出一种多姿态肉牛体尺自动测量方法。首先,利用深度相机Azure Kinect DK从正上方采集肉牛俯视深度视频数据,对视频数据进行分帧处理;其次,对原始深度图像进行预处理,将肉牛从复杂的背景中提取出来;再次,利用Zhang-Suen算法提取目标图像肉牛骨架,检测骨架交点和端点,分析肉牛头部特征,并确定头部去除点,去除图像中肉牛头部信息;最后,利用改进的U弦长曲率算法提取肉牛轮廓曲率曲线,根据曲率值确定体尺测点,将体尺测点转换到三维空间中,计算体尺参数。本研究通过分析大量深度图像数据,将图像中肉牛姿态分为左歪、右歪、姿态端正、低头和抬头五类。试验结果表明,本研究提出的基于骨架的多姿态肉牛头部去除方法在5种姿态下的头部去除成功率均高于92%;在23头肉牛不同姿态共46帧深度图像中,利用基于改进U弦长曲率的体尺测点提取方法,测得体直长测量的平均绝对误差为2.73 cm,体高测量的平均绝对误差为2.07 cm,腹宽测量的平均绝对误差为1.47 cm。研究结果可为精确测量多姿态下肉牛体尺提供支撑。
Beef cattle in the farm are active,which leads the collection of posture of the beef cattle changeable,so it is difficult to automatically measure the body size of the beef cattle.Aiming at the above problems,an automatic measurement method for beef cattle’s body size under multi-pose was proposed by analyzing the skeleton features of beef cattle head and the edge contour features of beef cattle images.Firstly,the consumer-grade depth camera Azure Kinect DK was used to collect the top-view depth video data directly above the beef cattle and the video data were divided into frames to obtain the original depth image.Secondly,the original depth image was processed by shadow interpolation,normalization,image segmentation and connected domain to remove the complex background and obtain the target image containing only beef cattle.Thirdly,the Zhang-Suen algorithm was used to extract the beef cattle skeleton of the target image,and calculated the intersection points and endpoints of the skeleton,so as to analyze the characteristics of the beef cattle head to determine the head removal point,and to remove the beef cattle head information from the image.Finally,the curvature curve of the beef cattle profile was obtained by the improved U-chord curvature method.The body measurement points were determined according to the curvature value and converted into three-dimensional spaces to calculate the body size parameters.In this paper,the postures of beef cattle,which were analyzed by a large amount of depth image data,were divided into left crooked,right crooked,correct posture,head down and head up,respectively.The test results showed that the head removal method proposed based on the skeleton in multiple postures hads head removel success rate higher than 92%in the five postures.Using the body measurement point extraction method based on the improved U-chord curvature proposed,the average absolute error of body length measurement was 2.73 cm,the average absolute error of body height measurement was 2.07 cm,and the average
作者
叶文帅
康熙
贺志将
李孟飞
刘刚
YE Wenshuai;KANG Xi;HE Zhijiang;LI Mengfei;LIU Gang(Key Lab of Smart Agriculture Systems,Ministry of Education,China Agricultural University,Beijing 100083,China;Key Laboratory of Agricultural Information Acquisition Technology,Ministry of Agriculture and Rural Affairs,China Agricultural University,Beijing 100083,China;School of Computing and Data Engineering,NingboTech University,Ningbo 315200,China)
基金
国家重点研发计划项目(2021YFD1300502)。
