﻿ 基于机器视觉技术的猪行为活动无接触识别系统
 计算机系统应用  2020, Vol. 29 Issue (4): 113-117 PDF

Contactless Identification System for Pig Behavior Based on Machine Vision
WU Shi-Hai, BAO Yi-Dong, CHEN Guo, CHEN Qiu-Shi
Guizhou Aerospace Smart Agriculture Co. Ltd., Guiyang 550081, China
Foundation item: Major Program of Science and Technology Bureau, Guizhou Province (QK[2016]3001)
Abstract: In the future, the main development mode of pig breeding industry is information and intelligence. In order to monitor the behavior of pigs intelligently, so as to monitor the health and growth of pigs, this paper presents a system technology for contactless identification and monitoring pig behavior based on machine vision. The system collects pig behavior sequence images by CCD camera, then extracts the depth features of those images using convolution neural network. After that, the feature fusion method is used to fuse the depth features of the behavior sequence images. Finally, the pig’s behavior activities are identified according to the fusion depth feature. The system realizes the high-precision identification of pig’s motion behavior, claudication behavior, volt behavior, breathing behavior, eating behavior, and excretion behavior under natural scenes. The accuracy rates of recognizing all kinds of behavior are more than 94%, which are higher than the state-of-the-art methods.
Key words: pig behavior recognition     pig breeding     machine learning technology     contactless identification

1 猪目标行为图像的获取与分类

2 猪行为活动实时无接触监测系统

2.1 CCD相机系统

2.2 猪行为识别方法

 图 1 基于机器视觉技术的猪行为活动无接触识别系统数据处理结构图

 ${F_i} = f({X_i}\left| w \right.,b)$ (1)

 $F = \left( {{F_{\rm{1}}},{F_2},\cdots,{F_{30}}} \right)$ (2)

 $F' = g(F \times w' + b')$ (3)
 ${Y_{\rm {pre}}} = softmax (F')$ (4)

 $Loss = L({Y_{\rm pre}},{Y_{\rm label}})$ (5)
2.3 实验数据处理平台

3 结果与分析

4 结论和展望

 [1] Reiners K, Hegger A, Hessel EF, et al. Application of RFID technology using passive HF transponders for the individual identification of weaned piglets at the feed trough. Computers and Electronics in Agriculture, 2009, 68(2): 178-184. DOI:10.1016/j.compag.2009.05.010 [2] Ringgenberg N, Bergeron R, Devillers N. Validation of accelerometers to automatically record sow postures and stepping behaviour. Applied Animal Behaviour Science, 2010, 128(1–4): 37-44. DOI:10.1016/j.applanim.2010.09.018 [3] Martínez-Avilés M, Fernández-Carrión E, López García-Baones JM, et al. Early detection of infection in pigs through an online monitoring system. Transboundary and Emerging Diseases, 2017, 64(2): 364-373. DOI:10.1111/tbed.12372 [4] Madsen TN, Kristensen AR. A model for monitoring the condition of young pigs by their drinking behaviour. Computers and Electronics in Agriculture, 2005, 48(2): 138-154. DOI:10.1016/j.compag.2005.02.014 [5] 张五一, 赵强松, 王东云. 机器视觉的现状及发展趋势. 中原工学院学报, 2008, 19(1): 9-12, 15. DOI:10.3969/j.issn.1671-6906.2008.01.003 [6] 段玉瑶, 马丽, 刘刚. 猪舍场景下的生猪目标跟踪和行为检测方法研究. 农业机械学报, 2015, 46(S1): 187-193. DOI:10.6041/j.issn.1000-1298.2015.S0.031 [7] 孙龙清, 李玥, 邹远炳, 等. 基于改进Graph Cut算法的生猪图像分割方法. 农业工程学报, 2017, 33(16): 196-202. DOI:10.11975/j.issn.1002-6819.2017.16.026 [8] 钱蓉, 詹凯, 王重龙. 基于机器视觉技术的动物行为自动识别和分类. 中国家禽, 2016, 38(3): 55-57. [9] Lind NM, Vinther M, Hemmingsen RP, et al. Validation of a digital video tracking system for recording pig locomotor behaviour. Journal of Neuroscience Methods, 2005, 143(2): 123-132. DOI:10.1016/j.jneumeth.2004.09.019 [10] Nasirahmadi A, Hensel O, Edwards SA, et al. A new approach for categorizing pig lying behaviour based on a Delaunay triangulation method. Animal, 2017, 11(1): 131-139. DOI:10.1017/S1751731116001208 [11] Shao B, Xin HW. A real-time computer vision assessment and control of thermal comfort for group-housed pigs. Computers and Electronics in Agriculture, 2008, 62(1): 15-21. DOI:10.1016/j.compag.2007.09.006 [12] Kashiha M, Bahr C, Haredasht SA, et al. The automatic monitoring of pigs water use by cameras. Computers and Electronics in Agriculture, 2013, 90: 164-169. DOI:10.1016/j.compag.2012.09.015 [13] 浦雪峰, 朱伟兴, 陆晨芳. 基于对称像素块识别的病猪行为监测系统. 计算机工程, 2009, 35(21): 250-252. DOI:10.3969/j.issn.1000-3428.2009.21.084 [14] 吴琼. 基于机器视觉的生猪行为检测跟踪技术研究[硕士学位论文]. 北京: 中国农业大学, 2012. [15] 吴燕. 基于星状骨架模型的猪的跛脚识别[硕士学位论文]. 镇江: 江苏大学, 2014. [16] 高云, 郁厚安, 雷明刚, 等. 基于头尾定位的群养猪运动轨迹追踪. 农业工程学报, 2017, 33(2): 220-226. DOI:10.11975/j.issn.1002-6819.2017.02.030 [17] Stavrakakis S, Li W, Guy JH, et al. Validity of the Microsoft Kinect sensor for assessment of normal walking patterns in pigs. Computers and Electronics in Agriculture, 2015, 117: 1-7. DOI:10.1016/j.compag.2015.07.003 [18] 谢海员, 纪滨, 胡宏智, 等. 基于曲率特征猪腹式呼吸运动波形图建模方法. 苏州科技学院学报(自然科学版), 2016, 33(3): 66-70. [19] 谢徵. 基于决策树支持向量机的猪只姿态分类与异常行为分析[硕士学位论文]. 太原: 太原理工大学, 2015. [20] 李文心. 基于视觉的目标跟踪控制系统研究[硕士学位论文]. 西安: 西安理工大学, 2019.