• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于 3D 混合滤波器和卷积神经网络的猪体质量估计

Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network.

机构信息

College of Engineering, Nanjing Agricultural University, Nanjing 210031, China.

Key Laboratory of Breeding Equipment, Ministry of Agriculture and Rural Affairs, Nanjing 210031, China.

出版信息

Sensors (Basel). 2023 Sep 7;23(18):7730. doi: 10.3390/s23187730.

DOI:10.3390/s23187730
PMID:37765787
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10537768/
Abstract

The measurement of pig weight holds significant importance for producers as it plays a crucial role in managing pig growth, health, and marketing, thereby facilitating informed decisions regarding scientific feeding practices. On one hand, the conventional manual weighing approach is characterized by inefficiency and time consumption. On the other hand, it has the potential to induce heightened stress levels in pigs. This research introduces a hybrid 3D point cloud denoising approach for precise pig weight estimation. By integrating statistical filtering and DBSCAN clustering techniques, we mitigate weight estimation bias and overcome limitations in feature extraction. The convex hull technique refines the dataset to the pig's back, while voxel down-sampling enhances real-time efficiency. Our model integrates pig back parameters with a convolutional neural network (CNN) for accurate weight estimation. Experimental analysis indicates that the mean absolute error (MAE), mean absolute percent error (MAPE), and root mean square error (RMSE) of the weight estimation model proposed in this research are 12.45 kg, 5.36%, and 12.91 kg, respectively. In contrast to the currently available weight estimation methods based on 2D and 3D techniques, the suggested approach offers the advantages of simplified equipment configuration and reduced data processing complexity. These benefits are achieved without compromising the accuracy of weight estimation. Consequently, the proposed method presents an effective monitoring solution for precise pig feeding management, leading to reduced human resource losses and improved welfare in pig breeding.

摘要

猪体重的测量对生产者来说非常重要，因为它在管理猪的生长、健康和销售方面起着至关重要的作用，从而有助于就科学喂养实践做出明智的决策。一方面，传统的手动称重方法效率低下且耗时。另一方面，它有可能增加猪的压力水平。本研究提出了一种混合 3D 点云去噪方法，用于精确估计猪的体重。通过整合统计滤波和 DBSCAN 聚类技术，我们减轻了体重估计的偏差，并克服了特征提取的局限性。凸壳技术将数据集细化到猪的背部，而体素下采样则提高了实时效率。我们的模型将猪背参数与卷积神经网络（CNN）集成在一起，以实现准确的体重估计。实验分析表明，本研究提出的体重估计模型的平均绝对误差（MAE）、平均绝对百分比误差（MAPE）和均方根误差（RMSE）分别为 12.45 千克、5.36%和 12.91 千克。与目前基于 2D 和 3D 技术的体重估计方法相比，所提出的方法具有简化设备配置和降低数据处理复杂性的优点。在不影响体重估计准确性的情况下实现了这些优势。因此，该方法为精确的猪饲养管理提供了有效的监测解决方案，减少了人力资源的损失，并提高了猪养殖的福利。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/5c1d30fbd5f9/sensors-23-07730-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/1768692c19f5/sensors-23-07730-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/1b3f6a61370a/sensors-23-07730-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/2d8efc8f4fc1/sensors-23-07730-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/ee8442068856/sensors-23-07730-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/830932527b65/sensors-23-07730-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/aa8865f7515e/sensors-23-07730-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/9e5cdc5c4e48/sensors-23-07730-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/4b6e0a2c0866/sensors-23-07730-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/d8f0ef4af1a3/sensors-23-07730-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/4513a23d7497/sensors-23-07730-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/569808ef3c33/sensors-23-07730-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/2bede86540fd/sensors-23-07730-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/b3393d0f8b8f/sensors-23-07730-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/cdf5d1137d0e/sensors-23-07730-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/cfe0c9388847/sensors-23-07730-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/a42ad68de47d/sensors-23-07730-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/12de946ed252/sensors-23-07730-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/29a905cd8321/sensors-23-07730-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/d7c34300582e/sensors-23-07730-g019a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/819148d6eb86/sensors-23-07730-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/9c3b647b6c16/sensors-23-07730-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/5c1d30fbd5f9/sensors-23-07730-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/1768692c19f5/sensors-23-07730-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/1b3f6a61370a/sensors-23-07730-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/2d8efc8f4fc1/sensors-23-07730-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/ee8442068856/sensors-23-07730-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/830932527b65/sensors-23-07730-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/aa8865f7515e/sensors-23-07730-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/9e5cdc5c4e48/sensors-23-07730-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/4b6e0a2c0866/sensors-23-07730-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/d8f0ef4af1a3/sensors-23-07730-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/4513a23d7497/sensors-23-07730-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/569808ef3c33/sensors-23-07730-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/2bede86540fd/sensors-23-07730-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/b3393d0f8b8f/sensors-23-07730-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/cdf5d1137d0e/sensors-23-07730-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/cfe0c9388847/sensors-23-07730-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/a42ad68de47d/sensors-23-07730-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/12de946ed252/sensors-23-07730-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/29a905cd8321/sensors-23-07730-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/d7c34300582e/sensors-23-07730-g019a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/819148d6eb86/sensors-23-07730-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/9c3b647b6c16/sensors-23-07730-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/092b/10537768/5c1d30fbd5f9/sensors-23-07730-g022.jpg

相似文献

1
Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network.基于 3D 混合滤波器和卷积神经网络的猪体质量估计
Sensors (Basel). 2023 Sep 7;23(18):7730. doi: 10.3390/s23187730.
2
Estimation of Weight and Body Measurement Model for Pigs Based on Back Point Cloud Data.基于背部点云数据的猪体重与体尺测量模型估计
Animals (Basel). 2024 Mar 29;14(7):1046. doi: 10.3390/ani14071046.
3
Detection, segmentation, and 3D pose estimation of surgical tools using convolutional neural networks and algebraic geometry.使用卷积神经网络和代数几何进行手术工具的检测、分割和三维姿态估计。
Med Image Anal. 2021 May;70:101994. doi: 10.1016/j.media.2021.101994. Epub 2021 Feb 7.
4
Pig Weight and Body Size Estimation Using a Multiple Output Regression Convolutional Neural Network: A Fast and Fully Automatic Method.利用多输出回归卷积神经网络估算猪体重和体型：一种快速且全自动的方法。
Sensors (Basel). 2021 May 6;21(9):3218. doi: 10.3390/s21093218.
5
Dual-Stream Fusion Network with ConvNeXtV2 for Pig Weight Estimation Using RGB-D Data in Aisles.基于Aisles中RGB-D数据的、采用ConvNeXtV2的双流融合网络用于猪体重估计
Animals (Basel). 2023 Dec 5;13(24):3755. doi: 10.3390/ani13243755.
6
Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic computed tomography from magnetic resonance imaging.使用 2D 和 3D 卷积神经网络从磁共振成像生成男性骨盆合成 CT 的深度学习方法。
Med Phys. 2019 Sep;46(9):3788-3798. doi: 10.1002/mp.13672. Epub 2019 Jul 26.
7
Comparison of data analytics strategies in computer vision systems to predict pig body composition traits from 3D images.计算机视觉系统中数据分析策略的比较，以从 3D 图像预测猪体组成性状。
J Anim Sci. 2020 Aug 1;98(8). doi: 10.1093/jas/skaa250.
8
A Spatiotemporal Convolutional Network for Multi-Behavior Recognition of Pigs.一种用于猪多行为识别的时空卷积网络。
Sensors (Basel). 2020 Apr 22;20(8):2381. doi: 10.3390/s20082381.
9
Automated Video Behavior Recognition of Pigs Using Two-Stream Convolutional Networks.使用双流卷积网络的猪自动视频行为识别。
Sensors (Basel). 2020 Feb 17;20(4):1085. doi: 10.3390/s20041085.
10
Pig Weight Estimation Method Based on a Framework Combining Mask R-CNN and Ensemble Regression Model.基于Mask R-CNN与集成回归模型相结合框架的生猪体重估计方法
Animals (Basel). 2024 Jul 20;14(14):2122. doi: 10.3390/ani14142122.

引用本文的文献

1
A Novel Dual-Network Approach for Real-Time Liveweight Estimation in Precision Livestock Management.一种用于精准畜牧管理中实时体重估计的新型双网络方法。
Adv Sci (Weinh). 2025 Jun;12(22):e2417682. doi: 10.1002/advs.202417682. Epub 2025 Apr 26.
2
Monitoring Pig Structural Soundness and Body Weight in Pork Production Systems Using Computer Vision Approaches.利用计算机视觉方法监测猪肉生产系统中猪的结构健全性和体重
Animals (Basel). 2025 Feb 21;15(5):635. doi: 10.3390/ani15050635.
3
A Review of Visual Estimation Research on Live Pig Weight.

本文引用的文献

1
Review: Pork quality attributes from farm to fork. Part I. Carcass and fresh meat.综述：从农场到餐桌的猪肉品质属性。第一部分。胴体和鲜肉。
Animal. 2022 Feb;16 Suppl 1:100402. doi: 10.1016/j.animal.2021.100402. Epub 2021 Nov 23.
2
Accurate assessment of body weights using morphometric measurements in Landlly pigs.利用 Landlly 猪的形态测量学指标准确评估体重。
Trop Anim Health Prod. 2021 Jun 17;53(3):362. doi: 10.1007/s11250-021-02803-2.
3
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects.卷积神经网络综述：分析、应用与展望
生猪活体重量视觉估测研究综述
Sensors (Basel). 2024 Nov 4;24(21):7093. doi: 10.3390/s24217093.
IEEE Trans Neural Netw Learn Syst. 2022 Dec;33(12):6999-7019. doi: 10.1109/TNNLS.2021.3084827. Epub 2022 Nov 30.
4
A Plane Extraction Approach in Inverse Depth Images Based on Region-Growing.基于区域生长的逆深度图像平面提取方法。
Sensors (Basel). 2021 Feb 6;21(4):1141. doi: 10.3390/s21041141.
5
A novel automated system to acquire biometric and morphological measurements and predict body weight of pigs via 3D computer vision.一种通过 3D 计算机视觉获取生物特征和形态测量值并预测猪体重的新型自动化系统。
J Anim Sci. 2019 Jan 1;97(1):496-508. doi: 10.1093/jas/sky418.
6
Environmental assessment of the entire pork value chain in Catalonia - A strategy to work towards Circular Economy.加泰罗尼亚全猪肉价值链的环境评估-迈向循环经济的策略。
Sci Total Environ. 2017 Jul 1;589:122-129. doi: 10.1016/j.scitotenv.2017.02.186.
7
The effects of lairage time and handling procedure prior to slaughter on stress and meat quality parameters in pigs.屠宰前的待宰时间和处理程序对猪的应激及肉质参数的影响。
Meat Sci. 2014 Oct;98(2):220-6. doi: 10.1016/j.meatsci.2014.06.003. Epub 2014 Jun 11.
8
Production systems and influence on eating quality of pork.猪肉生产体系及其对食用品质的影响。
Meat Sci. 2010 Feb;84(2):293-300. doi: 10.1016/j.meatsci.2009.03.013. Epub 2009 Apr 5.