Cow behavior recognition based on image analysis and activities
Cow behavior recognition based on image analysis and activities
复制标题
基于图像分析和活动的奶牛行为识别
DOI：
10.25165/ijabe.v10i3.3080
复制
发表时间：
2017
影响因子：
2.4
通讯作者：
Huarui Wu
中科院分区：
文献类型：
--
作者：
Jingqiu Gu;Zhihai Wang;Ronghua Gao;Huarui Wu
摘要： 为了从海量监控视频中快速、准确地识别奶牛的繁殖情况和健康行为，本研究以400头青年奶牛和哺乳期奶牛为研究对象，从奶牛活动区和奶厅坡道对奶牛的行为进行分析。针对复杂背景下奶牛运动目标行为的识别，提出基于图像熵的目标识别方法。计算最小边界框和等高线映射用于实时捕获车辙跨度行为和蹄或背部特征。然后，结合奶牛7 d的连续图像特征和运动，该方法可以快速区分奶牛的异常行为和健康繁殖，提高了奶牛特征识别的准确性。提出基于图像分析和活动的奶牛行为识别，以捕获对健康繁殖有害的异常行为，提高奶牛行为识别的准确性。实验结果表明，通过目标检测、分类和识别，奶牛繁殖健康中蹄病和发情的识别率均大于80%，发情和蹄病的假阴性率分别为3.28%和5.32%。该方法可以增强对奶牛的实时监控，节省时间，提高规模化养殖的管理效率。
关键词: 奶牛行为, 目标分割, 图像熵, 图像矩, 活动, 智能分析
DOI：10.3965/j.ijabe.20171003.3080
引用: 顾建群，王忠华，高瑞华，吴华瑞。基于图像分析和活动的奶牛行为识别。国际农业与生物工程杂志，2017； 10（3）：165-174。
Abstract: For the rapid and accurate identification of cow reproduction and healthy behavior from mass surveillance video, in this study, 400 head of young cows and lactating cows were taken as the research object and analyzed cow behavior from the dairy activity area and milk hall ramp. The method of object recognition based on image entropy was proposed, aiming at the identification of motional cow object behavior against a complex background. Calculating a minimum bounding box and contour mapping were used for the real-time capture of rutting span behavior and hoof or back characteristics. Then, by combining the continuous image characteristics and movement of cows for 7 d, the method could quickly distinguish abnormal behavior of dairy cows from healthy reproduction, improving the accuracy of the identification of characteristics of dairy cows. Cow behavior recognition based on image analysis and activities was proposed to capture abnormal behavior that has harmful effects on healthy reproduction and to improve the accuracy of cow behavior identification. The experimental results showed that, through target detection, classification and recognition, the recognition rates of hoof disease and heat in the reproduction and health of dairy cows were greater than 80%, and the false negative rates of oestrus and hoof disease were 3.28% and 5.32%, respectively. This method can enhance the real-time monitoring of cows, save time and improve the management efficiency of large-scale farming.
Keywords: cow behavior, target segmentation, image entropy, image moment, activities, intelligent analysis
DOI: 10.3965/j.ijabe.20171003.3080
Citation: Gu J Q, Wang Z H, Gao R H, Wu H R. Cow behavior recognition based on image analysis and activities. Int J Agric & Biol Eng, 2017; 10(3): 165–174.