Please wait a minute...
浙江大学学报(农业与生命科学版)  2018, Vol. 44 Issue (4): 499-506    DOI: 10.3785/j.issn.1008-9209.2018.06.113
论文     
基于图像处理和压缩感知的鱼群低溶氧胁迫异常行为检测方法
卢焕达,于欣*,刘广强
(浙江大学宁波理工学院,浙江 宁波 315100)
Abnormal behavior detection method of fish school under low dissolved oxygen stress based on image processing and compressed sensing#br#
LU Huanda, YU Xin*, LIU Guangqiang
(Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, Zhejiang, China)
 全文: PDF(4034 KB)   HTML (
摘要: 为了克服人工观测鱼群异常行为费时费力的问题,本文提出了一种基于图像处理和压缩感知算法的鱼群低溶氧胁迫异常行为的自动检测方法。以锦鲤(Cyprinus carpio)为研究对象,通过获取常氧和低氧2 种情况下的鱼群运动视频图像,利用图像处理技术得到鱼群位置直方图,提取鱼群位置的均值、方差、歪斜度、峰态和能量5 个参数,构成每幅图像的鱼群运动特征参数。在此基础上构建数据词典矩阵,并利用压缩感知分类方法实现低溶氧胁迫下的鱼群异常行为检测。实验结果表明,该方法能有效实现低溶氧胁迫下的鱼群异常行为检测,准确率达到98.50%。
关键词: 图像处理压缩感知鱼群行为低溶氧胁迫异常行为检测    
Abstract: In order to overcome the time-consuming and laborious problems of artificial observation, we proposed an automatic detection method of abnormal behavior of fish school under low dissolved oxygen stress based on image processing and compressed sensing algorithm. Taking Cyprinus carpio as the research object, by obtaining the video images of fish school behaviors under two conditions of normoxia and hypoxia, we used the image processing technology to get the location histogram of fish school, of which the average, variance, skewness, kurtosis and energy were extracted to form the fish movement characteristic parameters of each image. On this basis, the data dictionary matrix was constructed, and the abnormal behavior detection of fish school under low dissolved oxygen stress was implemented by compressed sensing classification. The results showed that the detection method can effectively detect the abnormal behavior of fish school under the low dissolved oxygen stress, with the detection accuracy rate of 98.50%.
Key words: image processing    compressed sensing    fish school behavior    low dissolved oxygen stress    abnormal behavior detection 
出版日期: 2018-09-13
CLC:  TP 391.41  
基金资助: 国家自然科学基金(31402352,3140131018);国家星火计划(2015GA701031,2014GA701031);浙江省宁波市自然科学基金(2015610131,2014A610185);浙江省自然科学基金(LY17C190008);浙江省教育厅课题(Y201432753);农业农村部设施农业装备与信
息化重点实验室开放课题。
通讯作者: 于欣(https://orcid.org/0000-0002-8648-0812)     E-mail: yuxin@zju.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
卢焕达
于欣
刘广强

引用本文:

卢焕达, 于欣, 刘广强. 基于图像处理和压缩感知的鱼群低溶氧胁迫异常行为检测方法[J]. 浙江大学学报(农业与生命科学版), 2018, 44(4): 499-506.

LU Huanda, YU Xin, LIU Guangqiang. Abnormal behavior detection method of fish school under low dissolved oxygen stress based on image processing and compressed sensing#br#. Journal of Zhejiang University (Agriculture and Life Sciences), 2018, 44(4): 499-506.

链接本文:

http://www.zjujournals.com/agr/CN/10.3785/j.issn.1008-9209.2018.06.113        http://www.zjujournals.com/agr/CN/Y2018/V44/I4/499

[1] 宋革联1, 韩瑞珍2,3, 张永华3*, 何勇2*. 基于无线传输技术的农田害虫检测与识别系统的开发[J]. 浙江大学学报(农业与生命科学版), 2014, 40(5): 585-590.
[2] 邹伟,方慧,刘飞,周康韵,鲍一丹,何勇. 基于高光谱图像技术的油菜籽品种鉴别方法研究[J]. 浙江大学学报(农业与生命科学版), 2011, 37(2): 175-180.