基于光流法与特征统计的鱼群异常行为检测

被引:27
作者
于欣 [1 ]
侯晓娇 [1 ,2 ]
卢焕达 [1 ]
余心杰 [1 ]
范良忠 [1 ]
刘鹰 [3 ]
机构
[1] 浙江大学宁波理工学院
[2] 太原科技大学电子信息工程学院
[3] 中国科学院海洋研究所
关键词
水产养殖; 鱼群检测; 光流法; 标准互信息(NMI); 局部距离异常因子(LDOF);
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
鱼类群体行为的异常检测能够为鱼类健康监控与预警提供重要的方法和手段,对研究鱼类行为的机理,提升水产养殖过程中的信息化水平具有非常重要的意义。该文通过计算机视觉和图像处理技术,基于鱼群运动特征统计方法,对鱼群异常行为检测进行研究。利用Lucas-Kanade光流法得到目标鱼群的运动矢量,并对目标运动的行为特征进行统计,得到速度与转角这2个行为特征的联合直方图与联合概率分布。最后,在联合概率分布的基础上,基于标准互信息(normalized mutual information-NMI)和局部距离异常因子(local distance-based outlier factor-LDOF)2种方法对鱼群行为进行异常检测。试验结果表明,2种异常检测方法均达到99.5%以上的准确率。
引用
收藏
页码:162 / 168
页数:7
相关论文
共 17 条
[11]  
Real-time monitoring of water quality using temporal trajectory of live fish[J] . Heng Ma,Tsueng-Fang Tsai,Chia-Cheng Liu.Expert Systems With Applications . 2009 (7)
[12]  
The effects of temperature and salinity on the swimming ability of whiteleg shrimp, Litopenaeus vannamei[J] . Peidong Zhang,Xiumei Zhang,Jian Li,Guoqiang Huang.Comparative Biochemistry and Physiology, Part A . 2006 (1)
[13]   Behavioral responses of tilapia (Oreochromis niloticus) to acute fluctuations in dissolved oxygen levels as monitored by computer vision [J].
Xu, Jianyu ;
Liu, Ying ;
Cui, Shaorong ;
Miao, Xiangwen .
AQUACULTURAL ENGINEERING, 2006, 35 (03) :207-217
[14]  
A computer image processing system for quantification of zebrafish behavior[J] . Satoru Kato,Takashi Nakagawa,Masato Ohkawa,Kenichiro Muramoto,Osamu Oyama,Akihito Watanabe,Hiroshi Nakashima,Tetsu Nemoto,Kayo Sugitani.Journal of Neuroscience Methods . 2003 (1)
[15]  
Video analysis of fish schooling behavior in finite space using a mathematical model[J] . Katsuya Suzuki,Tsutomu Takagi,Tomonori Hiraishi.Fisheries Research . 2002 (1)
[16]  
A quantification of goldfish behavior by an image processing system[J] . S. Kato,K. Tamada,Y. Shimada,T. Chujo.Behavioural Brain Research . 1996 (1)
[17]   PERFORMANCE OF OPTICAL-FLOW TECHNIQUES [J].
BARRON, JL ;
FLEET, DJ ;
BEAUCHEMIN, SS .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) :43-77