肖德琴,冯爱晶,杨秋妹,刘俭,张哲.基于视频追踪的猪只运动快速检测方法[J].农业机械学报,2016,47(10):351-357,331.
Xiao Deqin,Feng Aijing,Yang Qiumei,Liu Jian,Zhang Zhe.Fast Motion Detection for Pigs Based on Video Tracking[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(10):351-357,331.
摘要点击次数: 783
全文下载次数: 756
基于视频追踪的猪只运动快速检测方法   [下载全文]
Fast Motion Detection for Pigs Based on Video Tracking   [Download Pdf][in English]
投稿时间:2016-05-13  
DOI:10.6041/j.issn.1000-1298.2016.10.045
中文关键词:    视频追踪  运动检测  行为分类
基金项目:广东省科技计划项目(2015A020209149、2015A020224042)和NSFC— 广东联合基金(第二期)超级计算科学应用研究专项
作者单位
肖德琴 华南农业大学 
冯爱晶 华南农业大学 
杨秋妹 华南农业大学 
刘俭 华南农业大学 
张哲 华南农业大学 
中文摘要:自然条件下猪只日常运动时间、距离、速度等构成的运动数据,可作为猪只健康与舒适度状况分析的重要依据。为快速准确地捕获及检测猪场猪只的各种运动信息,探讨了基于视频追踪的猪只运动信息检测方法,该方法在基于颜色特征与轮廓特征相结合的多猪只目标分割基础上,通过基于最小化代价函数的椭圆拟合和最短距离匹配的目标跟踪,设计了运动位移、运动速度、运动加速度和运动角速度4个运动信息的检测算法。进一步探索了基于运动信息检测猪只日常活跃状态、活动规律及行为识别方面的初步应用。试验结果表明,该算法能够识别多种颜色的纯色猪只;分割粘连猪只成功率达92.6%;通过连续4d在广州市力智猪场种猪室实时视频测试表明,猪只日常活跃状态、活动规律和行为类别等信息均可通过猪只运动信息表现出来。所提方案可快速、有效检测猪只运动信息,为猪只行为分析、健康与舒适度评估提供了依据。
Xiao Deqin  Feng Aijing  Yang Qiumei  Liu Jian  Zhang Zhe
South China Agricultural University,South China Agricultural University,South China Agricultural University,South China Agricultural University and South China Agricultural University
Key Words:pigs  video tracking  motion checking  behavior classification
Abstract:Pigs’ motion data, such as daily motion duration, distance, speed, etc., are important bases for analysis of pigs’ health and performance. Manual monitoring is real-timely difficult, low accuracy, time-consuming and also easy missing for human fatigue. It can not meet the requirement of large-scale farming. Comparing with RFID (radio frequency identification technology) and sensor technology, video technology for development of animal husbandry had a profound influence without physical contact with animals. It was low cost with simple hardware deployment, which can monitor and manage large-scale farms. A scheme for pigs’ motion detection was designed based on video tracking for capturing and detecting a variety of motion information of farm pigs quickly and accurately. Firstly, color channel was selected adaptively to identify field pigs. A target segment method was provided based on characteristics of color and contour. Then each pig was fitted by an ellipse based on minimizing the cost function and tracks of pigs based on the shortest distance matching algorithm. Extraction algorithm for four motion parameters was proposed, which were displacement, velocity, acceleration and angular velocity. Finally, experiments related pigs’ motion detection, such as pigs’ daily activity, daily activity patterns and pigs daily behavior recognition, were carried out. Experimental results showed that the proposed channel selection method could identify a variety of solid colors pigs;the success rate of adhered pigs’ segmentation was 926%. The real-time video in Guangzhou Lizhi male pig farms was tested from November 21, 2015 to November 24, 2015 from 09:00 to 17:00. It showed that the characteristics of pigs daily activity, daily activity patterns and pigs daily behavior recognition could be manifested by the motion information. Therefore, this scheme was effective for pigs’ motion detection dynamically, and it provided a basic support for pigs’ health, behavior analysis and performance analysis.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器