引用本文:
【打印本页】   【下载PDF全文】   View/Add Comment  Download reader   Close
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 1237次   下载 844 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于计算机视觉的头足类角质颚特征研究Ⅱ:形态学参数测量
贺芊菡1, 孙翁杰2, 刘必林1,3,4,5,6, 孔祥洪1,4, 林龙山7
1.上海海洋大学海洋科学学院 上海 201306;2.上海海洋大学信息学院 上海 201306;3.大洋渔业资源可持续开发教育部重点实验室 上海 201306;4.国家远洋渔业工程技术研究中心 上海海洋大学 上海 201306;5.农业农村部大洋渔业开发重点实验室 上海 201306;6.农业农村部大洋渔业资源环境科学观测实验站 上海 201306;7.自然资源部第三海洋研究所 厦门 361005
摘要:
角质颚形态被广泛应用于头足类种类鉴定与种群判别,基于游标卡尺的手动径向测量是获取角质颚形态参数最常用的方法。本文提出一种利用计算机视觉提取角质颚形态参数的方法,首先通过MATLAB编程提取角质颚特征点及空间坐标,然后计算特征点间的空间距离,最后将提取的角质颚形态学参数值与手动径向测量的结果进行比较。研究结果表明:利用两种方法对每个头足类角质颚样本进行十次重复测定所得形态学参数的算术平均值接近,除形态学参数上脊突长之外,计算机视觉所测的数据平均绝对误差和平均相对误差都小于手动测量数据的平均绝对误差和平均相对误差,说明计算机视觉所测量结果准确,更加逼近真值;分析标准差和离散系数可知,计算机视觉重复多次提取每个样本的角质颚形态学参数的结果离散程度更低,测量值更加聚集于真实值附近,精密度更高。计算机视觉不仅为头足类角质颚参数测量提供了一种快速、准确方法,同时还将大幅促进角质颚形态学参数在头足类种群判别与种类鉴定等领域的广泛应用。
关键词:  角质颚  形态参数  计算机视觉  手动测量
DOI:10.11693/hyhz20200300075
分类号:Q954;Q959.216;TP399
基金项目:国家重点研发计划,2019YFD0901404号;国家自然科学基金面上项目,NSFC41876141号;全球变化与海气相互作用专项,GASI-01-EIND-YD01aut/02aut号;上海市“浦江人才”计划项目,18PJ1404100号;上海市高校特聘教授“东方学者”岗位计划项目,0810000243号;上海市科技创新行动计划,19DZ1207502号。
MORPHOLOGICAL STUDY OF CEPHALOPOD BEAK BASED ON COMPUTER VISION Ⅱ: MORPHOLOGICAL PARAMETER MEASUREMENT
HE Qian-Han1, SUN Weng-Jie2, LIU Bi-Lin1,3,4,5,6, KONG Xiang-Hong1,4, LIN Long-Shan7
1.College of Marine Sciences, Shanghai Ocean University, Shanghai 201306, China;2.College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;3.The Key Laboratory of Sustainable Exploitation of Oceanic Fisheries Resources, Ministry of Education, Shanghai 201306, China;4.National Distant-water Fisheries Engineering Research Center, Shanghai Ocean University, Shanghai 201306, China;5.Key Laboratory of Oceanic Fisheries Exploration, Ministry of Agriculture and Rural Affairs, Shanghai 201306, China;6.Scientific Observing and Experimental Station of Oceanic Fishery Resources, Ministry of Agriculture and Rural Affairs, Shanghai 201306, China;7.Third Institute of Oceanography, Ministry of Natural Resources, Xiamen 361005, China
Abstract:
The beak morphology is widely used in cephalopod species identification and population discrimination. Manual radial measurement based on vernier calipers is the most commonly used method to obtain beak morphology parameters. A method for extracting beak morphological parameters using computer vision was proposed. First, the beak feature points and spatial coordinates were extracted using MATLAB. Next, the spatial distance between the feature points was calculated. Finally, the values of extracted beak morphological parameter were compared with the measured result. The results indicate that the arithmetic mean values of the 10 measurements obtained by the two methods were very close. The average absolute error, average relative error, standard deviation, and dispersion coefficient of computer vision measurements were less than manual measurements results obtained, except for the morphological parameter of the upper crest length. The arithmetic mean of the morphological parameters obtained from 10 repeated measurements of each cephalopod beak sample using two methods was close, but the average absolute error and average relative error of the data measured by computer vision were less than the average absolute error of the manually measured data. In addition, the average relative error indicates that the measurement results of computer vision were accurate and closer to the true value. Analysis of the standard deviation and dispersion coefficient shows that computer vision could repeatedly extract the morphological parameters of the beak of each sample multiple times. It was more concentrated near the true value and the precision was greater. Computer vision not only provided a fast and accurate method for measuring the parameters of cephalopod beak, but also greatly promoted the widespread application of beak morphology parameterization in the fields of cephalopod population discrimination and species identification.
Key words:  beak  morphological parameters  computer vision  manual measurement
Copyright ©  Editorial Office for Oceanologia et Limnologia Sinica    Copyright©2008 All Rights Reserved
Supervised by: China Association for Science and Technology   Sponsored by: Chinese Society for Oceanology and Limnology, Institute of Oceanology and Limnology, CAS.
Address: 7 Nanhai Road, Qingdao, China.    Postcode: 266071    Tel: 0532-82898753  E-mail: liuxiujuan@qdio.ac.cn  
Technical support: Beijing E-Tiller Co.,Ltd.