基于改进三次B样条曲线的奶牛点云缺失区域修复方法
|
摘要
奶牛三维点云包含的尺寸和体型等信息对奶牛体型评价、尺寸测量和健康评定等具有重要意义。在奶牛活动场和挤奶间栏杆通道获取奶牛点云时,由于栏杆遮挡导致获取的点云缺失区域较大,严重影响奶牛三维建模精度。为了修复缺失的大区域点云,提出一种基于三次B样条曲线的奶牛点云缺失区域修复方法。该方法先对Kinect v2传感器获取的奶牛点云进行预处理,去除周围环境背景,然后沿点云坐标系x轴方向对提取的奶牛点云进行切片投影处理,对每个切片点列中间距较大的相邻点进行补点,再用三次B样条曲线进行拟合。在试验分析补点操作中参数h和L较优取值的基础上,对45头荷斯坦奶牛共225帧点云进行修复试验。结果表明,所提方法比三次B样条方法修复得到的点云均匀性和逼近性能更好,平均帧逼近误差降低了26.7%,为大面积点云缺失修复提供了有效方法。
The dimensional and size information contained in the 3 D point cloud of dairy cows are of great importance to the body evaluation,size measurement and health assessment. While capturing the point cloud of dairy cows from the aisle between the dairy farm and the milking parlor,the missing area on the point cloud happens frequently,which greatly affects the accuracy of the three-dimensional modeling of the dairy cows and the extraction of body size parameters. In order to fix the large missing area on the point cloud,a cubic B-spline curve based method was proposed to repair it. Firstly,the surrounding background was removed from the dairy cow's point cloud acquired by Kinect v2. Then,the extracted dairy cow's point clouds were sliced and projected along the x-axis direction of the point cloud coordinate system. In each slice points,some points were filled in the adjacent points with larger spacing. Finally,cubic B-spline curves were used for fitting the filled slice points. The optimal values of parameters h and L were analyzed in the experiment,and a total of 225 frames of 45 Holstein dairy cows' point clouds were repaired by using the optimal values of parameters h and L. The results showed that the average frame approximation error was reduced by 26. 7%,and the large missing area on the point clouds was repaired and the sparseness of point clouds was also improved. The proposed algorithm had better uniformity and approximation performance than the cubic B-spline method,which provided an effective method for repairing large missing point cloud area.
The dimensional and size information contained in the 3 D point cloud of dairy cows are of great importance to the body evaluation,size measurement and health assessment. While capturing the point cloud of dairy cows from the aisle between the dairy farm and the milking parlor,the missing area on the point cloud happens frequently,which greatly affects the accuracy of the three-dimensional modeling of the dairy cows and the extraction of body size parameters. In order to fix the large missing area on the point cloud,a cubic B-spline curve based method was proposed to repair it. Firstly,the surrounding background was removed from the dairy cow's point cloud acquired by Kinect v2. Then,the extracted dairy cow's point clouds were sliced and projected along the x-axis direction of the point cloud coordinate system. In each slice points,some points were filled in the adjacent points with larger spacing. Finally,cubic B-spline curves were used for fitting the filled slice points. The optimal values of parameters h and L were analyzed in the experiment,and a total of 225 frames of 45 Holstein dairy cows' point clouds were repaired by using the optimal values of parameters h and L. The results showed that the average frame approximation error was reduced by 26. 7%,and the large missing area on the point clouds was repaired and the sparseness of point clouds was also improved. The proposed algorithm had better uniformity and approximation performance than the cubic B-spline method,which provided an effective method for repairing large missing point cloud area.
引文
1李顺.中国畜牧业发展历程分析及趋势预测[J].中国畜牧杂志,2010,46(12):25-28.LI Shun.Analysis on China livestock development process and trend forecast[J].Chinese Journal of Animal Science,2010,46(12):25-28.(in Chinese)
2刘长全,杨洋.中国奶业产业政策的发展及成效[J].中国奶牛,2017(10):58-64.
3莫佳蓓,刘庆友.中国和日本奶牛养殖业规模化发展的比较分析[J].江苏农业科学,2017,45(9):303-307.
4何东健,刘冬,赵凯旋.精准畜牧业中动物信息智能感知与行为检测研究进展[J/OL].农业机械学报,2016,47(5):231-244.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20160532&flag=1.DOI:10.6041/j.issn.1000-1298.2016.05.032.HE Dongjian,LIU Dong,ZHAO Kaixuan.Review of perceiving animal information and behavior in precision livestock farming[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2016,47(5):231-244.(in Chinese)
5邵小宁.基于Kinect的植物三维点云获取与重建方法研究[D].杨凌:西北农林科技大学,2016.SHAO Xiaoning.Research on 3D point cloud acquisition and reconstruction method of plant based on Kinect[D].Yangling:Northwest A&F University,2016.(in Chinese)
6陈相,童小华.基于三角格网的点云空洞修补算法及精度研究[J].测绘通报,2013(4):1-3.CHEN Xiang,TONG Xiaohua.Research on points cloud hole filling algorithm and accuracy in triangle mesh[J].Bulletin of Surveying and Mapping,2013(4):1-3.(in Chinese)
7王果,崔希民,俞世炜,等.应用扫描光线重建法的建筑立面遮挡点云恢复[J].测绘通报,2014(5):63-65.WANG Guo,CUI Ximin,YU Shiwei,et al.Recovery of occluded building facade point cloud based on the reconstructed scan light and planar segmentation[J].Bulletin of Surveying and Mapping,2014(5):63-65.(in Chinese)
8 WANG J,OLIVEIRA M M.Filling holes on locally smooth surfaces reconstructed from point clouds[J].Image and Vision Computing,2007,25(1):103-113.
9 CHALMOVIANSKY P,JUTTLER B.Filling holes in point clouds[J].Lecture Notes in Computer Science,2003,2768:196-212.
10 MARCHANDISE E,PIRET C,REMACLE J F.CAD and mesh repair with radial basis functions[J].Journal of Computational Physics,2012,231(5):2376-2387.
11 NGO T M,LEE W S.Feature-first hole filling strategy for 3D meshes[M].Springer Berlin Heidelberg,2013:53-68.
12 QUINSAT Y,LARTIGUE C.Filling holes in digitized point cloud using a morphing-based approach to preserve volume characteristics[J].International Journal of Advanced Manufacturing Technology,2015,81(1-4):411-421.
13蒋刚.基于SVM和空间投影的点云空洞修补方法[J].计算机工程,2009,35(22):269-271.JIANG Gang.Point cloud hole filling method based on SVM and space projection[J].Computer Engineering,2009,35(22):269-271.(in Chinese)
14晏海平,吴禄慎,陈华伟.基于径向基函数的散乱点云孔洞修复算法[J].计算机工程与设计,2014,35(4):1253-1257.YAN Haiping,WU Lushen,CHEN Huawei.Hole repairing algorithm in scattered point cloud based on radial basis function[J].Computer Engineering and Design,2014,35(4):1253-1257.(in Chinese)
15 RUSU R B,MARTON Z C,BLODOW N,et al.Towards 3D point cloud based object maps for household environments[J].Robotics and Autonomous Systems,2008,56(11):927-941.
16朱德海.点云库PCL学习教程[M].北京:北京航空航天大学出版社,2012.
17刘俊焱,云挺,周宇,等.基于最小二乘的点云叶面拟合算法研究[J].西北林学院学报,2014,30(5):70-77.LIU Junyan,YUN Ting,ZHOU Yu,et al.Leaf surface fitting of point cloud based on least square method[J].Journal of Northwest Forestry University,2014,30(5):70-77.(in Chinese)
18闫蓓,王斌,李媛.基于最小二乘法的椭圆拟合改进算法[J].北京航空航天大学学报,2008,34(3):295-298.YAN Bei,WANG Bin,LI Yuan.Optimal ellipse fitting method based on least-square principle[J].Journal of Beijing University of Aeronautics and Astronautics,2008,34(3):295-298.(in Chinese)
19田垅,刘宗田.最小二乘法分段直线拟合[J].计算机科学,2012,39(6A):482-484.TIAN Long,LIU Zongtian.Least-squares method piecewise linear fitting[J].Computer Science,2012,39(6A):482-484.(in Chinese)
20苗莎,郑晓薇.三次插值样条曲线拟合多核并行算法[J].计算机应用,2010,30(12):3194-3196.MIAO Sha,ZHENG Xiaowei.Multi-core parallel algorithm for cubic spline curve fitting[J].Journal of Computer Applications,2010,30(12):3194-3196.(in Chinese)
21海啸,朱志杰.最小二乘法和三次样条曲线拟合的比色测温误差修正对比分析[J].激光杂志,2015,36(6):72-76.HAI Xiao,ZHU Zhijie.The comparison between the least square method and cubic spline interpolation in errors of colorimetry temperature measurement[J].Laser Journal,2015,36(6):72-76.(in Chinese)
22喻德生,程程.基于离散曲率的三次均匀B样条的局部光顺算法[J].浙江大学学报:理学版,2011,38(5):511-517.YU Desheng,CHENG Cheng.On local fairing algorithm for cubic B-spline with discrete curvature[J].Journal of Zhejiang University:Science Edition,2011,38(5):511-517.(in Chinese)
23韩江,江本赤,夏链,等.基于轮廓关键点的B样条曲线拟合算法[J].应用数学和力学,2015,36(4):423-431.HAN Jiang,JIANG Benchi,XIA Lian,et al.A B-spline curve fitting algorithm based on contour key points[J].Applied Mathematics and Mechanics,2015,36(4):423-431.(in Chinese)
24王文珂,李思昆.无序B样条曲线的曲面拟合算法[J].计算机辅助设计与图形学学报,2013,25(5):679-685.WANG Wenke,LI Sikun.B-spline surface fitting to unorganized curves[J].Journal of Computer-Aided Design&Computer Graphics,2013,25(5):679-685.(in Chinese)
25段振云,王宁,杨旭,等.一种改进B样条曲线拟合算法研究[J].机械设计与制造,2016(5):17-19.DUAN Zhenyun,WANG Ning,YANG Xu,et al.An algorithm of improved B-spline curve fitting[J].Machinery Design&Manufacture,2016(5):17-19.(in Chinese)
2刘长全,杨洋.中国奶业产业政策的发展及成效[J].中国奶牛,2017(10):58-64.
3莫佳蓓,刘庆友.中国和日本奶牛养殖业规模化发展的比较分析[J].江苏农业科学,2017,45(9):303-307.
4何东健,刘冬,赵凯旋.精准畜牧业中动物信息智能感知与行为检测研究进展[J/OL].农业机械学报,2016,47(5):231-244.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20160532&flag=1.DOI:10.6041/j.issn.1000-1298.2016.05.032.HE Dongjian,LIU Dong,ZHAO Kaixuan.Review of perceiving animal information and behavior in precision livestock farming[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2016,47(5):231-244.(in Chinese)
5邵小宁.基于Kinect的植物三维点云获取与重建方法研究[D].杨凌:西北农林科技大学,2016.SHAO Xiaoning.Research on 3D point cloud acquisition and reconstruction method of plant based on Kinect[D].Yangling:Northwest A&F University,2016.(in Chinese)
6陈相,童小华.基于三角格网的点云空洞修补算法及精度研究[J].测绘通报,2013(4):1-3.CHEN Xiang,TONG Xiaohua.Research on points cloud hole filling algorithm and accuracy in triangle mesh[J].Bulletin of Surveying and Mapping,2013(4):1-3.(in Chinese)
7王果,崔希民,俞世炜,等.应用扫描光线重建法的建筑立面遮挡点云恢复[J].测绘通报,2014(5):63-65.WANG Guo,CUI Ximin,YU Shiwei,et al.Recovery of occluded building facade point cloud based on the reconstructed scan light and planar segmentation[J].Bulletin of Surveying and Mapping,2014(5):63-65.(in Chinese)
8 WANG J,OLIVEIRA M M.Filling holes on locally smooth surfaces reconstructed from point clouds[J].Image and Vision Computing,2007,25(1):103-113.
9 CHALMOVIANSKY P,JUTTLER B.Filling holes in point clouds[J].Lecture Notes in Computer Science,2003,2768:196-212.
10 MARCHANDISE E,PIRET C,REMACLE J F.CAD and mesh repair with radial basis functions[J].Journal of Computational Physics,2012,231(5):2376-2387.
11 NGO T M,LEE W S.Feature-first hole filling strategy for 3D meshes[M].Springer Berlin Heidelberg,2013:53-68.
12 QUINSAT Y,LARTIGUE C.Filling holes in digitized point cloud using a morphing-based approach to preserve volume characteristics[J].International Journal of Advanced Manufacturing Technology,2015,81(1-4):411-421.
13蒋刚.基于SVM和空间投影的点云空洞修补方法[J].计算机工程,2009,35(22):269-271.JIANG Gang.Point cloud hole filling method based on SVM and space projection[J].Computer Engineering,2009,35(22):269-271.(in Chinese)
14晏海平,吴禄慎,陈华伟.基于径向基函数的散乱点云孔洞修复算法[J].计算机工程与设计,2014,35(4):1253-1257.YAN Haiping,WU Lushen,CHEN Huawei.Hole repairing algorithm in scattered point cloud based on radial basis function[J].Computer Engineering and Design,2014,35(4):1253-1257.(in Chinese)
15 RUSU R B,MARTON Z C,BLODOW N,et al.Towards 3D point cloud based object maps for household environments[J].Robotics and Autonomous Systems,2008,56(11):927-941.
16朱德海.点云库PCL学习教程[M].北京:北京航空航天大学出版社,2012.
17刘俊焱,云挺,周宇,等.基于最小二乘的点云叶面拟合算法研究[J].西北林学院学报,2014,30(5):70-77.LIU Junyan,YUN Ting,ZHOU Yu,et al.Leaf surface fitting of point cloud based on least square method[J].Journal of Northwest Forestry University,2014,30(5):70-77.(in Chinese)
18闫蓓,王斌,李媛.基于最小二乘法的椭圆拟合改进算法[J].北京航空航天大学学报,2008,34(3):295-298.YAN Bei,WANG Bin,LI Yuan.Optimal ellipse fitting method based on least-square principle[J].Journal of Beijing University of Aeronautics and Astronautics,2008,34(3):295-298.(in Chinese)
19田垅,刘宗田.最小二乘法分段直线拟合[J].计算机科学,2012,39(6A):482-484.TIAN Long,LIU Zongtian.Least-squares method piecewise linear fitting[J].Computer Science,2012,39(6A):482-484.(in Chinese)
20苗莎,郑晓薇.三次插值样条曲线拟合多核并行算法[J].计算机应用,2010,30(12):3194-3196.MIAO Sha,ZHENG Xiaowei.Multi-core parallel algorithm for cubic spline curve fitting[J].Journal of Computer Applications,2010,30(12):3194-3196.(in Chinese)
21海啸,朱志杰.最小二乘法和三次样条曲线拟合的比色测温误差修正对比分析[J].激光杂志,2015,36(6):72-76.HAI Xiao,ZHU Zhijie.The comparison between the least square method and cubic spline interpolation in errors of colorimetry temperature measurement[J].Laser Journal,2015,36(6):72-76.(in Chinese)
22喻德生,程程.基于离散曲率的三次均匀B样条的局部光顺算法[J].浙江大学学报:理学版,2011,38(5):511-517.YU Desheng,CHENG Cheng.On local fairing algorithm for cubic B-spline with discrete curvature[J].Journal of Zhejiang University:Science Edition,2011,38(5):511-517.(in Chinese)
23韩江,江本赤,夏链,等.基于轮廓关键点的B样条曲线拟合算法[J].应用数学和力学,2015,36(4):423-431.HAN Jiang,JIANG Benchi,XIA Lian,et al.A B-spline curve fitting algorithm based on contour key points[J].Applied Mathematics and Mechanics,2015,36(4):423-431.(in Chinese)
24王文珂,李思昆.无序B样条曲线的曲面拟合算法[J].计算机辅助设计与图形学学报,2013,25(5):679-685.WANG Wenke,LI Sikun.B-spline surface fitting to unorganized curves[J].Journal of Computer-Aided Design&Computer Graphics,2013,25(5):679-685.(in Chinese)
25段振云,王宁,杨旭,等.一种改进B样条曲线拟合算法研究[J].机械设计与制造,2016(5):17-19.DUAN Zhenyun,WANG Ning,YANG Xu,et al.An algorithm of improved B-spline curve fitting[J].Machinery Design&Manufacture,2016(5):17-19.(in Chinese)