摘要
应用计算机视觉技术对镜鲤鱼群的摄食行为进行识别,减少养殖过程中人力的损耗,提出了一种基于图像纹理的鱼群摄食的自动检测识别方法。首先利用相机采集鱼群正常状态和摄食时的图片,之后对图片进行预处理,利用灰度差分统计法、灰度共生矩阵和高斯马尔科夫随机场模型提取鱼群的13个纹理特征,最后利用支持向量机(support vector machine,简称SVM)算法对鱼群图像进行分类识别。结果表明,支持向量机对测试集的识别率达到96.5%,运行时间为39.04 s,且使用主成分分析(principal component analysis,简称PCA)算法后,支持向量机对测试集的识别率达到93.5%,运行时间为0.63 s,可以达到对鱼群摄食自动识别的要求。
引文
[1]Liu Z Y,Li X,Fan L Z,et al.Measuring feeding activity of fish in RAS using computer vision[J].Aquacultural Engineering,2014,60(1):20-27.
[2]周应祺,王军,钱卫国,等.鱼类集群行为的研究进展[J].上海海洋大学学报,2013,22(5):734-743.
[3]胡金有,王靖杰,张小栓,等.水产养殖信息化关键技术研究现状与趋势[J].农业机械学报,2015,46(7):251-263.
[4]陈红,夏青,左婷,等.基于纹理分析的香菇品质分选方法[J].农业工程学报,2014,30(3):285-292.
[5]Israeli D,Kimmel E.Monitoring the behavior of hypoxia-stressed Carassiu sauratus using computer vision[J].Aquacultural Engineering,1996,15(6):423-440.
[6]Wu T H,Huang Y,Chen J M.Development of an adaptive neuralbased fuzzy inference system for feeding decision-making assessment in silver perch(Bidyanus bidyanus)culture[J].Aquacultural Engineering,2015,66:42-51.
[7]Mallet D,Pelletier D.Underwater video techniques for observing coastal marine biodiversity:a review of sixty years of publications(1952—2012)[J].Fisheries Research,2014,154(3):44-62.
[8]Papadakis V M,Papadakis I E,Lamprianidou F,et al.A computervision system and methodology for the analysis of fish behavior[J].Aquacultural Engineering,2012,46(2):53-59.
[9]李贤,范良忠,刘子毅,等.基于计算机视觉的大菱鲆对背景色选择习性研究[J].农业工程学报,2012,28(10):189-193.
[10]段延娥,李道亮,李振波,等.基于计算机视觉的水产动物视觉特征测量研究综述[J].农业工程学报,2015,31(15):1-11.
[11]Kato S,Tamada K,Shimada Y,et al.A quantification of goldfish behavior by an image processing system[J].Behavioural Brain Research,1996,80(1/2):51-55.
[12]Ma H,Tsai T F,Liu C C.Real-time monitoring of water quality using temporal trajectory of live fish[J].Expert Systems With Applications,2010,37(7):5158-5171.
[13]张志强,牛智有,赵思明.基于机器视觉技术的淡水鱼品种识别[J].农业工程学报,2011,27(11):388-392.
[14]于欣,侯晓娇,卢焕达,等.基于光流法与特征统计的鱼群异常行为检测[J].农业工程学报,2014,30(2):162-168.
[15]任立辉,李文东,慈兴华,等.基于LIBSVM的石油录井中岩屑岩性识别方法研究[J].中国海洋大学学报(自然科学版),2010,40(9):131-136.
[16]Sadoul B,Mengues P E,Friggens N C,et al.A new method for measuring group behaviours of fish shoals from recorded videos taken in near aquaculture conditions[J].Aquaculture,2014,430:179-187.
[17]Pautsina A,Cisar P,Stys D,et al.Infrared reflection system for indoor 3D tracking of fish[J].Aquacultural Engineering,2015,69:7-17.
[18]Zhao J,Gu Z B,Shi M M,et al.Spatial behavioral characteristics and statistics-based kinetic energy modeling in special behaviors detection of a shoal of fish in a recirculating aquaculture system[J].Computers and Electronics in Agriculture,2016,127:271-280.
[19]Rakowitz G,Tu2er M,Sˇíha M,et al.Use of high-frequency imaging sonar(DIDSON)to observe fish behaviour towards a surface trawl[J].Fisheries Research,2012,123-124(3):37-48.
[20]徐小军,邵英,郭尚芬.基于灰度共生矩阵的火焰图像纹理特征分析[J].计算技术与自动化,2007,26(4):64-67.
[21]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-635.
[22]范良忠,刘鹰,余心杰,等.基于计算机视觉技术的运动鱼检测算法[J].农业工程学报,2011,27(7):226-230.
[23]王慧勤,雷刚.基于LIBSVM的风速预测方法研究[J].科学技术与工程,2011,11(22):5440-5442,5450.
[24]Ashley P J.Fish welfare:current issues in aquaculture[J].Applied Animal Behaviour Science,2007,104(4):199-235.
[25]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42