何东健,孟凡昌,赵凯旋,张昭.基于视频分析的犊牛基本行为识别[J].农业机械学报,2016,47(9):294-300.
He Dongjian,Meng Fanchang,Zhao Kaixuan,Zhang Zhao.Recognition of Calf Basic Behaviors Based on Video Analysis[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(9):294-300.
摘要点击次数: 2357
全文下载次数: 2286
基于视频分析的犊牛基本行为识别   [下载全文]
Recognition of Calf Basic Behaviors Based on Video Analysis   [Download Pdf][in English]
投稿时间:2016-03-18  
DOI:10.6041/j.issn.1000-1298.2016.09.040
中文关键词:  犊牛  行为识别  视频分析  结构相似  行为序列
基金项目:国家自然科学基金面上项目(61473235)
作者单位
何东健 西北农林科技大学 
孟凡昌 西北农林科技大学 
赵凯旋 西北农林科技大学 
张昭 西北农林科技大学 
中文摘要:针对接触式获取动物行为信息的局限性,研究并提出基于视频分析的犊牛基本行为识别方法。首先对目标检测方法进行改进,提出基于最大连通区域的目标循环搜索环境建模、目标检测算法,以高效提取复杂自然环境下的犊牛目标;在提取犊牛的质心、轮廓等时序特征的基础上,采用基于结构相似的犊牛行为序列快速聚类算法,对犊牛基本行为进行识别。试验结果表明,环境建模、目标检测算法目标正负样本检测正确率分别达90.94%和98.98%,比背景相减法分别提高4.59和8.32个百分点;犊牛躺、站、走和跑跳的正确识别率分别为100%、96.17%、95.85%和97.26%,能快速对犊牛基本行为进行准确分类,为大型动物高级行为识别及理解奠定了基础。
He Dongjian  Meng Fanchang  Zhao Kaixuan  Zhang Zhao
Northwest A&F University,Northwest A&F University,Northwest A&F University and Northwest A&F University
Key Words:calf  behavior recognition  video analysis  structure similarity  behavior sequence
Abstract:Daily behaviors are the important indicators of health status for calves. The suitability of using behavioural changes to provide an early indication of calf’s disease was studied. The possibility of achieving a real time analysis of a number of specific changes in behaviours, such as lying, standing, walking, running, and jumping, is crucial for disease prevention. Considering the limitation for sensing animal behavior by contacting device and in order to improve the welfare of calves, a method based on video analysis was studied and applied to recognize calf basic behaviors. Firstly, a looping algorithm based on maximum connected region was proposed for fast detection of calf target under complex environment. Secondly, a real time model was built to renew the background and detect the calf’s target quickly and accurately. Thirdly, the position of the centroid, the ratio of the height and width of the target outline, and differences of the centroid moving curve were extracted as the features of behaviors. These features could be the characterizations of the internal properties of behaviors constituted the sequence structure of calf behaviors. Finally, a classifier based on structure similarity of behavior features was designed to recognize basic behaviors of the calf. By testing 162 videos, the results demonstrated that the recognition rate of lying, standing, walking and run jump were 100%, 96.17%, 95.85% and 97.26%, respectively. On the basis of these research outcomes, the proposed method is feasible for computing calf behavioural indices and the real time detection of behavioural changes, and also lays a foundation for recognizing and understanding senior behaviors of large animal.

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