[1]丁静,沈明霞,刘龙申,等.基于机器视觉的断奶仔猪腹泻自动识别方法[J].南京农业大学学报,2020,43(5):969-978.[doi:10.7685/jnau.201908003]
 DING Jing,SHEN Mingxia,LIU Longshen,et al.Automatic recognition of diarrhea in weaned piglets based on machine vision[J].Journal of Nanjing Agricultural University,2020,43(5):969-978.[doi:10.7685/jnau.201908003]
点击复制

基于机器视觉的断奶仔猪腹泻自动识别方法()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
43卷
期数:
2020年5期
页码:
969-978
栏目:
食品与工程
出版日期:
2020-09-15

文章信息/Info

Title:
Automatic recognition of diarrhea in weaned piglets based on machine vision
作者:
丁静1 沈明霞2 刘龙申2 孙玉文1 陆明洲2 姚文3 张海林1
1. 南京农业大学工学院, 江苏 南京 210031;
2. 南京农业大学人工智能学院, 江苏 南京 210031;
3. 南京农业大学动物科技学院, 江苏 南京 210095
Author(s):
DING Jing1 SHEN Mingxia2 LIU Longshen2 SUN Yuwen1 LU Mingzhou2 YAO Wen3 ZHANG Hailin1
1. College of Engineering, Nanjing Agricultural University, Nanjing 210031, China;
2. College of Artifical Interlligence, Nanjing Argricultural University, Nanjing 210031, China;
3. College of Animal Science and Technology, Nanjing Agricultural University, Nanjing 210095, China
关键词:
断奶仔猪腹泻机器视觉卷积神经网络时空信息融合判定
Keywords:
weaned pigletsdiarrheamachine visionconvolutional neural networktime-space fusion judgment
分类号:
TP391.4
DOI:
10.7685/jnau.201908003
摘要:
[目的] 断奶仔猪腹泻严重影响养猪业的经济效益,本试验基于机器视觉技术提出一种排泄姿态与异常粪便结合的断奶仔猪腹泻检测方法以实现断奶仔猪腹泻的快速、准确检测。[方法] 以深层卷积神经网络(convolutional neural networks,CNN)为基础构建腹泻检测分类模型,实现仔猪身份、姿态与异常粪便的一体化识别,对比不同迭代次数对模型效果的影响,选取最优模型;提出时空信息融合判定法,从时间序列先后和空间距离远近两方面,关联最优模型识别出的目标姿态与病便,实现断奶仔猪腹泻的视频检测。[结果] 在训练迭代25 000次时接近模型最优值,对姿态、病便等目标识别的平均精度均值和召回率分别为95.75%和89.13%;基于时空信息融合方法的断奶仔猪腹泻视频检测识别准确率和召回率分别为97.92%和95.92%。[结论] 深层卷积神经网络分类模型结合时空信息融合判定法为断奶仔猪腹泻自动识别提供了有力的技术支撑。
Abstract:
[Objectives] The development of pig farming industry is seriously restricted by diarrhea in weaned piglets. In order to realize the rapid and intelligent perception of diarrhea in weaned piglets,a method based on machine vision technology is proposed in this paper,which combines excretion posture with abnormal feces.[Methods] Based on convolution neural networks (CNN),a diarrhea detection and classification model was constructed to realize the integrated recognition of posture and abnormal feces. The effects of different iterations on the model were compared,and the optimal model was selected. Combined with the optimal model,the video detection of diarrhea in weanling piglets was realized by using the time-space fusion judgment method,which correlated the target posture and the disease stool from two aspects of time series and space distance.[Results] When the training iteration was 25 000 times,it approached the optimal value of the model. The average precision and recall of posture and stool recognition were 95.75% and 89.13%,respectively,while the recognition accuracy and recall of video detection of diarrhea in weaned piglets based on time-space fusion method were 97.92% and 95.92%,respectively.[Conclusions] Convolution neural network classification model combined with time-space fusion judgment method provided powerful technical support for the automatic identification of diarrhea in weaned piglets.

参考文献/References:

[1] 裘小波. 断奶仔猪腹泻的防控方案[J]. 今日畜牧兽医,2019,35(2):20-21. Qiu X B. Prevention and control of diarrhea in weaned piglets[J]. Today Animal Husbandry and Veterinary Medicine,2019,35(2):20-21(in Chinese).
[2] 冯驹. 断奶仔猪腹泻的诊治[J]. 现代农业科技,2019,48(8):232,234. Feng J. Diagnosis and treatment of diarrhea in weaned piglets[J]. Modern Agricultural Science and Technology,2019,48(8):232,234(in Chinese).
[3] 高君恺,刘浩飞,杨倩. 猪流行性腹泻病毒的研究进展[J]. 南京农业大学学报,2014,37(1):1-5. DOI:10.7685/j.issn. 1000-2030.2014.01.001. Gao J K,Liu H F,Yang Q. Research advances on porcine epidemic diarrhea virus[J]. Journal of Nanjing Agricultural University,2014,37(1):1-5(in Chinese with English abstract).
[4] 高云,郭继亮,黎煊,等. 基于深度学习的群猪图像实例分割方法[J]. 农业机械学报,2019,50(4):179-187. Gao Y,Guo J L,Li X,et al. Instance-level segmentation method for group pig images based on deep learning[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(4):179-187(in Chinese with English abstract).
[5] 汪开英,赵晓洋,何勇. 畜禽行为及生理信息的无损监测技术研究进展[J]. 农业工程学报,2017,33(20):197-209. Wang K Y,Zhao X Y,He Y. Advances in nondestructive monitoring techniques for livestock and poultry behavior and physiological information[J]. Transactions of the Chinese Society of Agricultural Engineering,2017,33(20):197-209(in Chinese with English abstract).
[6] 薛月菊,朱勋沐,郑婵,等. 基于改进Faster R-CNN识别深度视频图像哺乳母猪姿态[J]. 农业工程学报,2018,34(9):189-196. Xue Y J,Zhu X M,Zheng C,et al. Lactating sow postures recognition from depth image of videos based on improved Faster R-CNN[J]. Transactions of the Chinese Society of Agricultural Engineering,2018,34(9):189-196(in Chinese with English abstract).
[7] 闫丽,沈明霞,谢秋菊,等. 哺乳母猪高危动作识别方法研究[J]. 农业机械学报,2016,47(1):266-272. Yang L,Shen M X,Xie Q J,et al. Research on recognition method of lactating sows’ dangerous body movement[J]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):266-272(in Chinese with English abstract).
[8] Lao F,Brown-Brandl T,Stinn J P,et al. Automatic recognition of lactating sow behaviors through depth image processing[J]. Computers and Electronics in Agriculture,2016,125(1):56-62.
[9] Nasirahmadi A,Edwands S A,Sturm B. Implementation of machine vision for detecting behaviour of cattle and pigs[J]. Livestock Science,2017,202(1):25-38.
[10] Nasirahmadi A,Richter U,Hensel O,et al. Using machine vision for investigation of changes in pig group lying patterns[J]. Computers and Electronics in Agriculture,2015,119(1):184-190.
[11] Nasirahmadi A,Hensel O,Edwards S A,et al. Automatic detection of mounting behaviours among pigs using image analysis[J]. Computers and Electronics in Agriculture,2016,124(1):295-302.
[12] Ahmed S T,Mun H S,Islam M M,et al. Monitoring activity for recognition of illness in experimentally infected weaned piglets using received signal strength indication ZigBee-based wireless acceleration sensor[J]. Asian-Australasian Journal of Animal Sciences,2016,29(1):149-156.
[13] 施宏,沈明霞,刘龙申,等. 基于Kinect的哺乳期母猪姿态识别算法的研究[J]. 南京农业大学学报,2019,42(1):177-183. DOI:10.7685/jnau.201803025. Shi H,Shen M X,Liu L S,et al. Study on recognition method of lactating sows’ posture based on Kinect[J]. Journal of Nanjing Agricultural University,2019,42(1):177-183(in Chinese with English abstract).
[14] 朱伟兴,浦雪峰,李新城,等. 基于行为监测的疑似病猪自动化识别系统[J]. 农业工程学报,2010,26(1):188-192. Zhu W X,Pu X F,Li X C,et al. Automatic identification system of pigs with suspected case based on behavior monitoring[J]. Transactions of the Chinese Society of Agricultural Engineering,2010,26(1):188-192(in Chinese with English abstract).
[15] 李以翠,李保明,施正香,等. 猪排泄地点选择及其对圈栏污染程度的影响[J]. 农业工程学报,2006,22(2):108-111. Li Y C,Li B M,Shi Z X,et al. Selection of pig excretion site and its influence on pollution level of enclosure[J]. Transactions of the Chinese Society of Agricultural Engineering,2006,22(2):108-111(in Chinese with English abstract).
[16] Marquardt R. Passive protective effect of egg-yolk antibodies against enterotoxigenic Escherichia coli K+88 infection in neonatal and early-weaned piglets[J]. FEMS Immunology and Medical Microbiology,1999,23(4):283-288.
[17] 徐元庆,王哲奇,史彬林,等. 壳聚糖对断奶仔猪生长性能、粪便评分及血清激素和T淋巴细胞亚群的影响[J]. 动物营养学报,2017,29(5):1678-1686. Xu Y Q,Wang Z Q,Shi B L,et al. Effects of chitosan on growth performance,fecal score,serum hormones and T lymphocyte subset of weaned piglets[J]. Chinese Journal of Animal Nutrition,2017,29(5):1678-1686(in Chinese with English abstract).
[18] Hu C H,Gu L Y,Luan Z S,et al. Effects of montmorillonite-zinc oxide hybrid on performance,diarrhea,intestinal permeability and morphology of weanling pigs[J]. Animal Feed Science and Technology,2012,177(1/2):108-115.
[19] 张雪涛,孙蒙,王金双. 基于操作码的安卓恶意代码多粒度快速检测方法[J]. 网络与信息安全学报,2019,5(6):85-94. Zhang X T,Sun M,Wang J S. Multi-granularity Android malware fast detection based on opcode[J]. Chinese Journal of Network and Information Security,2019,5(6):85-94(in Chinese with English abstract).
[20] 师亚亭,李卫军,宁欣,等. 基于嘴巴状态约束的人脸特征点定位算法[J]. 智能系统学报,2016,11(5):578-585. Shi Y T,Li W J,Ning X,et al. A facial feature point locating algorithm based on mouth-state constraints[J]. CAAI Transactions on Intelligent Systems,2016,11(5):578-585(in Chinese with English abstract).
[21] 赵德安,刘晓洋,孙月平,等. 基于机器视觉的水下河蟹识别方法[J]. 农业机械学报,2019,50(3):151-158. Zhao D A,Liu X Y,Sun Y P,et al. Detection of underwater crabs based on machine vision[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(3):151-158(in Chinese with English abstract).
[22] He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR),June 27-30,2016. Las Vegas,NV,USA:IEEE,2016:770-778.
[23] 沈明霞,太猛,CEDRIC Okinda,等. 基于深层卷积神经网络的初生仔猪目标实时检测方法[J]. 农业机械学报,2019,50(8):270-279. Shen M X,Tai M,CEDRIC O,et al. Real-time detection method of newborn piglets based on deep convolution neural network[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(8):270-279(in Chinese with English abstract).
[24] Redmon J,Farhadi A. YOLOv3:An incremental improvement[Z/OL]. (2018-04-01)[2018-04-08]. https://arxiv.org/abs/1804.02767.

相似文献/References:

[1]王希春,吴金节,李义刚,等.高铜日粮对断奶仔猪血清及组织中铜、铁、锌沉积的影响[J].南京农业大学学报,2006,29(1):72.[doi:10.7685/j.issn.1000-2030.2006.01.016]
 WANG Xi-chun,WU Jin-jie,LI Yi-gang,et al.Effect of high level copper diets on the contents of copper,iron,zinc in serum and tissues of weanling piglets[J].Journal of Nanjing Agricultural University,2006,29(5):72.[doi:10.7685/j.issn.1000-2030.2006.01.016]
[2]韦习会 李淑敏 夏 东 丁宏标 李文义.不同来源铁和锌对断奶仔猪生长发育、血液生理生化指标及组织铁和锌含量的影响*[J].南京农业大学学报,1999,22(1):113.[doi:10.7685/j.issn.1000-2030.1999.01.027]
[3]左伟勇,洪伟鸣,陈高,等.低分子质量大豆肽对断奶仔猪肠道免疫功能的影响[J].南京农业大学学报,2013,36(5):108.[doi:10.7685/j.issn.1000-2030.2013.05.018]
 ZUO Weiyong,HONG Weiming,CHEN Gao,et al.Effect of low molecular weight soybean peptide on intestinal immunity in weanling piglets[J].Journal of Nanjing Agricultural University,2013,36(5):108.[doi:10.7685/j.issn.1000-2030.2013.05.018]
[4]李雪莉,虞徳夫,王超,等.植物乳杆菌制剂对断奶仔猪肠道黏膜功能和微生物菌群及短链脂肪酸的影响[J].南京农业大学学报,2018,41(3):504.[doi:10.7685/jnau.201706034]
 LI Xueli,YU Defu,WANG Chao,et al.Effects of Lactobacillus plantarum on intestinal mucosa function, microbial community and short chain fatty acids in weaning piglets[J].Journal of Nanjing Agricultural University,2018,41(5):504.[doi:10.7685/jnau.201706034]
[5]王彬,刘俊泽,陈志杰,等.甘蔗提取物对敌草快诱导断奶仔猪氧化损伤的防护效果及肠道微生物参与的机制[J].南京农业大学学报,2020,43(3):514.[doi:10.7685/jnau.201906025]
 WANG Bin,LIU Junze,CHEN Zhijie,et al.Protective effects of sugar cane extract against oxidative damage induced by diquat and mechanism mediated by intestinal microbiota in weaned piglets[J].Journal of Nanjing Agricultural University,2020,43(5):514.[doi:10.7685/jnau.201906025]
[6]徐庆磊,沈春彦,陈若男,等.断奶仔猪混群后的攻击行为与其个体生理和性格特征之间的典型相关分析[J].南京农业大学学报,2020,43(4):748.[doi:10.7685/jnau.201905029]
 XU Qinglei,SHEN Chunyan,CHEN Ruonan,et al.Canonical correlation between the aggressive behavior and physiological,personality traits of weaned pigs after mixing[J].Journal of Nanjing Agricultural University,2020,43(5):748.[doi:10.7685/jnau.201905029]
[7]魏思宇,甘振丁,韦文耀,等.姜黄素和白藜芦醇联用对断奶仔猪消化酶活性和胰腺抗氧化功能的影响[J].南京农业大学学报,2020,43(4):754.[doi:10.7685/jnau.201906068]
 WEI Siyu,GAN Zhending,WEI Wenyao,et al.Effects of curcumin and resveratrol on digestive enzyme activity and pancreatic antioxidant function in weaned piglets[J].Journal of Nanjing Agricultural University,2020,43(5):754.[doi:10.7685/jnau.201906068]

备注/Memo

备注/Memo:
收稿日期:2019-08-03。
基金项目:政府间国际科技创新合作重点专项(2017YFE0114400);国家自然科学基金青年基金项目(61503187)
作者简介:丁静,硕士研究生。
通信作者:沈明霞,教授,博士,主要从事机器视觉与信息农业研究,E-mail:mingxia@njau.edu.cn。
更新日期/Last Update: 1900-01-01