羊只体尺参数是评估其生长发育状况和经济价值的重要指标.本研究针对单侧点云局部方向估计不稳定的问题,提出了一种基于多尺度方向一致性的羊只点云体尺测量方法.首先在3个尺度下计算局部主方向,并根据特征值各向异性进行置信度加权融合,随后结合区域生长算法完成个体点云分割.针对测量点定位偏差和腿部干扰问题,提出一种基于区域约束与曲率分析的体尺测量方法.该方法通过腹线最低点识别羊只前后腿位置并划分4个区域,采用Alpha Shapes算法提取目标轮廓,结合曲率分析定位测量点,并通过分割腿部来消除深度测量干扰.实验结果表明,多尺度融合方法的平均交并比为92.99%,较最佳单尺度方案提升了2.16个百分点.从成功分割的样本中筛选21只点云完整的羊只,对其体斜长、体高、胸深、腹深和十字部高5项体尺参数进行测量,结果显示去除腿部后,胸深和腹深的测量误差分别降低了61.0%和50.2%,5项体尺参数的平均绝对误差为2.11 cm,平均相对误差为4.85%,满足实际生产中的精度要求.
Sheep body size measurement is important for evaluating growth, development, and economic value. In this study, to address the problem of unstable local direction estimation in single-sided point clouds, a multi-scale directional consistency-based method for sheep point cloud body size measurement was proposed. Local principal directions were first calculated at three scales and fused using confidence weights based on eigenvalue anisotropy, and individual segmentation was then completed through region- 引用格式:何梦腾,潘浩文,邓洪兴,等.基于点云多尺度方向一致性的羊只体尺测量方法［J］.河北大学学报(自然科学版),2026,46(2):113-127.引用格式:何梦腾,潘浩文,邓洪兴,等.基于点云多尺度方向一致性的羊只体尺测量方法［J］.河北大学学报(自然科学版),2026,46(2):113-127.DOI:10.3969/j.issn.1000-1565.2026.02.001基于点云多尺度方向一致性的羊只体尺测量方法何梦腾1,2,潘浩文1,2,邓洪兴1,2,许兴时1,2,宋怀波1,2(1.西北农林科技大学 机械与电子工程学院,陕西 杨凌 712100;2.陕西省农业信息感知与智能服务重点实验室,陕西 杨凌 712100)摘 要:羊只体尺参数是评估其生长发育状况和经济价值的重要指标.本研究针对单侧点云局部方向估计不稳定的问题,提出了一种基于多尺度方向一致性的羊只点云体尺测量方法.首先在3个尺度下计算局部主方向,并根据特征值各向异性进行置信度加权融合,随后结合区域生长算法完成个体点云分割.针对测量点定位偏差和腿部干扰问题,提出一种基于区域约束与曲率分析的体尺测量方法.该方法通过腹线最低点识别羊只前后腿位置并划分4个区域,采用Alpha Shapes算法提取目标轮廓,结合曲率分析定位测量点,并通过分割腿部来消除深度测量干扰.实验结果表明,多尺度融合方法的平均交并比为92.99%,较最佳单尺度方案提升了2.16个百分点.从成功分割的样本中筛选21只点云完整的羊只,对其体斜长、体高、胸深、腹深和十字部高5项体尺参数进行测量,结果显示去除腿部后,胸深和腹深的测量误差分别降低了61.0%和50.2%,5项体尺参数的平均绝对误差为2.11 cm,平均相对误差为4.85%,满足实际生产中的精度要求.关键词:羊只;体尺测量;点云分割;点云多尺度融合;点云方向一致性中图分类号:TP391.4 文献标志码:A 文章编号:1000-1565(2026)02-0113-15DOI:10.3969/j.issn.1000-1565.2026.02.001Sheep body size measurement method based on point cloud multi-scale directional consistencyHE Mengteng1,2, PAN Haowen1,2, DENG Hongxing1,2, XU Xingshi1,2, SONG Huaibo1,2(1. College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, China;2. Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service, Yangling 712100, China)Abstract: Sheep body size measurement is important for evaluating growth, development, and economic value. In this study, to address the problem of unstable local direction estimation in single-sided point clouds, a multi-scale directional consistency-based method for sheep point cloud body size measurement was proposed. Local principal directions were first calculated at three scales and fused using confidence weights based on eigenvalue anisotropy, and individual segmentation was then completed through region- 收稿日期:2025-11-28;修回日期:2026-01-09 基金项目:国家重点研发计划项目(2024YFD1300600);宁夏回族自治区重点研发计划项目(2024BBF02029) 第一作者:何梦腾(2002—),男,西北农林科技大学在读硕士研究生,主要从事家畜体尺测量方向研究.E-mail:2024056017@nwafu.edu.cn 通信作者:宋怀波(1980—),男,西北农林科技大学教授,博士生导师,主要从事模式识别的理论研究.E-mail:songyangfeifei@163.com 第2期何梦腾等:基于点云多尺度方向一致性的羊只体尺测量方法河北大学学报(自然科学版) 第46卷growing. To address the difficulties in measurement point localization and leg interference, a measurement method based on region constraints and curvature analysis was proposed. Front and rear leg positions were identified through the lowest points of the abdominal line and the point cloud was divided into four regions. The Alpha Shapes algorithm was then employed to extract contours, and measurement points were located through curvature analysis while leg segmentation eliminated depth measurement interference. The experimental results indicated that the multi-scale fusion method achieved an average intersection over union(IoU)of 92.99%, representing a 2.16 percentage point improvement over the best single-scale scheme. For the measurement of five body parameters(body slanting length, body height, chest depth, abdominal depth, and cross height)on 21 sheep with complete point clouds selected from the successfully segmented samples, the measurement errors for chest depth and abdominal depth were reduced by 61.0% and 50.2%, respectively, after leg removal. The overall mean absolute error(MAE)and mean absolute percentage error(MAPE)for the five parameters were 2.11 cm and 4.85%, respectively, which meet the accuracy requirements for practical applications.
[1] 邱良伟,何庆玲,谭学桃.规模化羊养殖场标准化管理措施[J].中国畜禽种业, 2022, 18(3): 133-134. DOI:10.3969/j.issn.1673-4556.2022.03.076.
[2] Gang G, Gao R H, Zhao H, et al. Effects of diet supplemented with water extracts of Artemisia annua L. on small intestinal immune and antioxidative indexes in lambs[J]. Front Vet Sci, 2025, 12: 1545729. DOI:10.3389/fvets.2025.1545729.
[3] 耿宁,李秉龙.中国肉羊生产技术效率的影响因素及其区域差异分析:基于随机前沿分析方法[J].技术经济, 2013, 32(12): 25-32. DOI:10.3969/j.issn.1002-980X.2013.12.006.
[4] 刘玉凤,王明利,石自忠,等.我国肉羊生产技术效率及科技进步贡献分析[J].中国农业科技导报, 2014, 16(3): 156-161. DOI:10.13304/j.nykjdb.2014.072.
[5] 张丽娜,武佩,宣传忠,等.羊只体尺参数测量及其形态评价研究进展[J].农业工程学报, 2016, 32(增刊1): 190-197. DOI:10.11975/j.issn.1002-6819.2016.z1.027.
[6] Grochowska E, Lisiak D, Akram M Z, et al. Association of a polymorphism in exon 3 of the IGF1R gene with growth, body size, slaughter and meat quality traits in Colored Polish Merino sheep[J]. Meat Sci, 2021, 172: 108314. DOI:10.1016/j.meatsci.2020.108314.
[7] Shalaldeh A, Page S, Anthony P, et al. Body composition estimation in breeding ewes using live weight and body parameters utilizing image analysis[J]. Animals, 2023, 13(14): 2391. DOI:10.3390/ani13142391.
[8] Bakhshalizadeh S, Hashemi A, Gaffari M, et al. Estimation of genetic parameters and genetic trends for biometric traits in Moghani sheep breed[J]. Small Rumin Res, 2016, 134: 79-83. DOI:10.1016/j.smallrumres.2015.12.030.
[9] 李世鹏,汪富文,史颖超,等.云岭牛HMGA2基因InDel多态及其与生长性状的关联分析[J].河北大学学报(自然科学版), 2020, 40(4): 421-426. DOI:10.3969/j.issn.1000-1565.2020.04.013.
[10] Pezzuolo A, Guarino M, Sartori L, et al. On-barn pig weight estimation based on body measurements by a Kinect v1 depth camera[J]. Comput Electron Agric, 2018, 148: 29-36. DOI:10.1016/j.compag.2018.03.003.
[11] Huang L W, Guo H, Rao Q Q, et al. Body dimension measurements of Qinchuan cattle with transfer learning from LiDAR sensing[J]. Sensors, 2019, 19(22): 5046. DOI:10.3390/s19225046.
[12] Hafid H. Performances body dimensions of Bali cattle of traditional livestock in southeast Sulawesi[J]. Indonesian J Agric Res, 2020, 3(2): 136-144. DOI:10.32734/injar.v3i2.3997.
[13] Deng H X, Yang G Y, Xu X S, et al. Fusion of CREStereo and MobileViT-Pose for rapid measurement of cattle body size[J]. Comput Electron Agric, 2025, 232: 110103. DOI:10.1016/j.compag.2025.110103.
[14] Pu L R, Zhao Y J, Kang H Y, et al. DenseDFFNet: Dense connected dual-stream feature fusion network for calf manure segmentation and diarrhea recognition[J]. Comput Electron Agric, 2025, 234: 110328. DOI:10.1016/j.compag.2025.110328.
[15] 李忠慧,刘晨曦,马为红,等.绵羊和山羊肉用性能表型鉴定研究现状与展望[J]. 中国科学:生命科学, 2023, 53(7): 989-1001.DOI:10.1360/SSV-2022-0294.
[16] 赵宇亮,曾繁国,贾楠,等.基于DeepLabCut算法的猪只体尺快速测量方法研究[J].农业机械学报, 2023, 54(2): 249-255. DOI:10.6041/j.issn.1000-1298.2023.02.025.
[17] 邓洪兴,许兴时,王云飞,等.基于双目立体匹配与改进YOLOv8n-Pose关键点检测的奶牛体尺测量方法[J].华南农业大学学报, 2024, 45(5): 802-811. DOI:10.7671/j.issn.1001-411X.202404001.
[18] 刘刚,曾雪婷,刘晓文,等.基于改进YOLO v5-pose的群养生猪体尺自动测量方法[J].农业机械学报, 2025, 56(5): 455-465. DOI:10.6041/j.issn.1000-1298.2025.05.043.
[19] 耿艳利,季燕凯,岳晓东,等.基于点云语义分割的猪只体尺测量方法研究[J].农业机械学报, 2023, 54(7): 332-338, 380. DOI:10.6041/j.issn.1000-1298.2023.07.033.
[20] 赵健,周国源,王智文,等.基于SGPointNet++模型的奶牛点云分割与表型自动测定系统设计[J].农业机械学报, 2025, 56(3): 180-187. DOI:10.6041/j.issn.1000-1298.2025.03.018.
[21] Li J W, Ma W H, Zhao C J, et al. Extraction of key regions of beef cattle based on bidirectional tomographic slice features from point cloud data[J]. Comput Electron Agric, 2022, 199: 107190. DOI:10.1016/j.compag.2022.107190.
[22] 黄霞,余松科,刘兴明,等.基于点云的生猪体尺参数自动提取方法[J].农业机械学报, 2025, 56(8): 496-506. DOI:10.6041/j.issn.1000-1298.2025.08.047.
[23] 初梦苑,李孟飞,李前,等.基于关键帧提取与头颈部去除的奶牛体尺测量方法[J].农业机械学报, 2022, 53(增刊2): 226-233. DOI:10.6041/j.issn.1000-1298.2022.S2.026.
[24] 李振波,孙浩翔,郭倩男,等.机器视觉技术在大体型家畜无接触体尺测量中的研究进展[J].农业工程学报, 2025, 41(7): 1-12. DOI:10.11975/j.issn.1002-6819.202410110.
[25] Qiao G F, Zhang Z B, Niu B, et al. Plant stem and leaf segmentation and phenotypic parameter extraction using neural radiance fields and lightweight point cloud segmentation networks[J]. Front Plant Sci, 2025, 16: 1491170. DOI:10.3389/fpls.2025.1491170.
[26] Li J L, Li Y T, Long J, et al. SAP-net: A simple and robust 3D point cloud registration network based on local shape features[J]. Sensors, 2021, 21(21): 7177. DOI:10.3390/s21217177.
[27] 张欣,徐永潇,王兵.基于三维曲面重建的CT图像肺边界缺陷修复[J].河北大学学报(自然科学版), 2021, 41(1): 87-92. DOI:10.3969/j.issn.1000-1565.2021.01.013.
[28] Wang K, Guo H, Ma Q, et al. A portable and automatic Xtion-based measurement system for pig body size[J]. Comput Electron Agric, 2018, 148: 291-298. DOI:10.1016/j.compag.2018.03.018.
[29] Hou Z X, Zhang Q, Zhang B, et al. CattlePartNet: an identification approach for key region of body size and its application on body measurement of beef cattle[J]. Comput Electron Agric, 2025, 232: 110013. DOI:10.1016/j.compag.2025.110013. (
