[1]高启,李毅念,金典,等.基于单幅图像的玉米果穗数量性状测量方法[J].南京农业大学学报,2018,41(3):562-569.[doi:10.7685/jnau.201706028]
 GAO Qi,LI Yinian,JIN Dian,et al.Measurement method for quantitative characteristics of maize based on single image[J].Journal of Nanjing Agricultural University,2018,41(3):562-569.[doi:10.7685/jnau.201706028]
点击复制

基于单幅图像的玉米果穗数量性状测量方法()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
41卷
期数:
2018年3期
页码:
562-569
栏目:
出版日期:
2018-05-15

文章信息/Info

Title:
Measurement method for quantitative characteristics of maize based on single image
作者:
高启 李毅念 金典 龚成杰 范亮亮 李刘阳洋
南京农业大学工学院, 江苏 南京 210031
Author(s):
GAO Qi LI Yinian JIN Dian GONG Chengjie FAN Liangliang LI Liuyangyang
College of Engineering, Nanjing Agricultural University, Nanjing 210031, China
关键词:
玉米果穗数量性状机器视觉累计像素值分布线性插值
Keywords:
ear of maizequantitative characteristicscomputer visionaccumulated pixel values histogramlinear interpolation
分类号:
TP391.41;S333.3
DOI:
10.7685/jnau.201706028
摘要:
[目的]玉米果穗数量性状是玉米考种和产量预测的重要参数,主要包括穗行数、行粒数和总粒数。快速精确地测量果穗数量性状是玉米自动化考种的难点问题。[方法]选用干玉米果穗进行试验,以单幅果穗图像为研究对象,在改进YCrCb色彩空间的基础上利用双峰法提取果穗轮廓,将图像沿穗轴等分为20部分,对每部分采用像素累计法得到穗行的定位点,对定位点线性插值得到穗行线,通过分析穗行线上的像素变化得到行粒数,利用果穗横截面的几何模型估算穗行数,并采用补偿法校正单幅果穗图像的成像误差以提高其计算精度,最后将行粒数与行数相乘得到总粒数。[结果]该方法对光照环境和图像背景要求较低,能适应较强的背景反光与阴影;避免对穗粒进行图像分割,使穗行线与行间隙定位的可靠性和准确性提高;校正单幅果穗图像的成像误差,使穗行数估算结果的准确性提高。统计结果显示:定位穗行线的失误率在6%以下,穗行数、行粒数和总籽粒数平均计算精度分别为98.84%、96.33%和95.67%,其中穗行数估算的零误差率为90.91%,平均测量速度达到每穗1.936 s。[结论]该方法能快速而精确地测量玉米果穗数量性状。
Abstract:
[Objectives] The quantitative characteristics of maize ears are significant indexes for genetic traits measuring and production forecasting, including rows per ear, kernels per row and total kernels. Fast and accurate calculation for quantitative characteristics is a difficult problem of automatically measuring genetic traits of maize seed. [Methods] In this study, single image of maize ear was used as research object. An image acquisition device, which consisted of complementary metal oxide semiconductor(CMOS)camera, light emitting diode(LED)lights, light controller, stage and computer, was designed to capture images of maize ears. A maize ear was placed horizontally on the stage, and the inclination angle of ear was corrected by Radon formula after excessive image erosion. Based on the improved YCrCb color space, the contour of maize ear was obtained by bimodal method. Then the image was divided equally into 20 parts along the axis of ear. And the location points of ear rows in every part were obtained by pixel accumulation method. The lines of ear rows were obtained through linear interpolation of location points. Based on the changes of pixel values along the lines of ear rows, the kernels per row were accurately calculated. Through a geometric model of ear axis cross section, the rows per ear were accurately calculated. And an imaging error of single image was corrected by compensation method in order to improve its calculation accuracy. Finally, the total kernels were obtained by multiplying kernels per row with rows per ear. [Results] Experiment with dry corn demonstrated that the method, which was able to resist background reflections and shadows, had a low requirement to light environment and image background. And it avoided performing image segmentation for kernels of ear, thus the reliability and accuracy of positioning the ear rows’ lines and gaps could be increased. And it corrected an imaging error of single image of maize ear, therefore the calculation accuracy of rows per ear could be increased. The experiment result demonstrated that the error rate of positioning lines of ear rows was below 6%. And the average calculation accuracy of rows per ear, kernels per row and total kernels were 98.84%, 96.33% and 95.67%, respectively. The zero error rate of calculation for rows per ear was 90.91%. The average computation speed could reach 1.936 s per ear. [Conclusions] The method can measure quantitative characteristics of maize ears, quickly and accurately.

参考文献/References:

[1] 韩仲志,杨锦忠.计数玉米穗行数的机器视觉研究[J]. 玉米科学,2010,18(2):146-148,152. Han Z Z,Yang J Z. Vision research on the machine of counting ear rows in maize[J]. Journal of Maize Sciences,2010,18(2):146-148,152(in Chinese with English abstract).
[2] Xiong Y,Pulli K. Fast panorama stitching for high-quality panoramic images on mobile phones[J]. IEEE Transactions on Consumer Electronics,2010,56(2):298-306.
[3] 王传宇,郭新宇,吴升,等. 采用全景技术的机器视觉测量玉米果穗考种指标[J]. 农业工程学报,2013,29(24):155-162. Wang C Y,Guo X Y,Wu S,et al. Investigate maize ear traits using machine vision with panoramic photography[J]. Transactions of the Chinese Society of Agricultural Engineering,2013,29(24):155-162(in Chinese with English abstract).
[4] 柳冠伊,杨小红,白明,等. 基于线阵扫描图像的玉米果穗性状检测技术[J]. 农业机械学报,2013,44(11):276-280. Liu G Y,Yang X H,Bai M,et al. Detecting techniques of maize ear characters based on line scan image[J]. Transactions of the Chinese Society for Agricultural Machinery,2013,44(11):276-280(in Chinese with English abstract).
[5] 刘长青,陈兵旗.基于机器视觉的玉米果穗参数的图像测量方法[J]. 农业工程学报,2014,30(6):131-138. Liu C Q,Chen B Q. Method of image detection for ear of corn based on computer vision[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(6):131-138(in Chinese with English abstract).
[6] 杜建军,郭新宇,王传宇,等. 基于穗粒分布图的玉米果穗表型性状参数计算方法[J]. 农业工程学报,2016,32(13):168-176. Du J J,Guo X Y,Wang C Y,et al. Computation method of phenotypic parameters based on distribution map of kernels for corn ears[J]. Transactions of the Chinese Society of Agricultural Engineering,2016,32(13):168-176(in Chinese with English abstract).
[7] 梁秀英.基于机器视觉的玉米性状参数与近红外光谱的玉米组分含量检测方法研究[D]. 武汉:华中农业大学,2013:47-49. Liang X Y.Research on automatic extraction of maize yield-related traits based on machine vision and measurement of maize components content based on NIR[D]. Wuhan:Huazhong Agricultural University,2013:47-49(in Chinese with English abstract).
[8] 周金辉,马钦,朱德海,等. 基于机器视觉的玉米果穗产量组分性状测量方法[J]. 农业工程学报,2015,31(3):221-227. Zhou J H,Ma Q,Zhu D H,et al. Measurement method for yield component traits of maize based on machine vision[J]. Transactions of the Chinese Society of Agricultural Engineering,2015,31(3):221-227(in Chinese with English abstract).
[9] Ambrose A,Kandpa L M,Kim M S,et al. High speed measurement of corn seed viability using hyperspectral imaging[J]. Infrared Physics and Technology,2016,75:173-179.
[10] Hruska Z,Yao H,Kincaid R,et al. Fluorescence imaging spectroscopy(FIS)for comparing spectra from corn ears naturally and artificially infected with aflatoxin producing fungus[J]. Journal of Food Science,2013,78(8):T1313-T1320.
[11] Pearson T. Hardware-based image processing for high-speed inspection of grains[J]. Computers and Electronics in Agriculture,2009,69:12-18.
[12] 孟庆宽,何洁,仇瑞承,等. 基于机器视觉的自然环境下作物行识别与导航线提取[J]. 光学学报,2014,34(7):180-186. Meng Q K,He J,Qiu R C,et al. Crop recognition and navigation line detection in natural environment based on machine vision[J]. Acta Optica Sinica,2014,34(7):180-186(in Chinese with English abstract).
[13] 徐庆,石跃祥,谢文兰,等. 基于改进YUV空间的人脸检测方法[J]. 计算机工程与应用,2008,44(34):158-162. Xu Q,Shi Y X,Xie W L,et al. Method of face detection based on improved YUV color space[J]. Computer Engineering and Applications,2008,44(34):158-162(in Chinese with English abstract).
[14] 熊俊涛,邹湘军,陈丽娟,等. 基于机器视觉的自然环境中成熟荔枝识别[J]. 农业机械学报,2011,42(9):162-166. Xiong J T,Zou X J,Chen L J,et al. Recognition of mature litchi in natural environment based on machine vision[J]. Transactions of the Chinese Society for Agricultural Machinery,2011,42(9):162-166(in Chinese with English abstract).
[15] 魏康丽,王振杰,孙柯,等. 基于计算机视觉对苹果脆片外观品质分级[J]. 南京农业大学学报,2017,40(3):547-555. DOI:10.7685/jnau.201609031. Wei K L,Wang Z J,Sun K,et al. External quality classification of apple chips based on computer vision[J]. Journal of Nanjing Agricultural University,2017,40(3):547-555(in Chinese with English abstract).
[16] Zhang H,Fritts J E,Goldman S A. Image segmentation evaluation:a survey of unsupervised methods[J]. Computer Vision and Image Understanding,2008,110:260-280.
[17] 吴丽丽,余春艳. 基于Sobel算子和Radon变换的车牌倾斜校正方法[J]. 计算机应用,2013,33(S1):220-222. Wu L L,Yu C Y. Tilt correction method of license plate based on Sobel operator and Radon transform[J]. Journal of Computer Applications,2013,33(S1):220-222(in Chinese with English abstract).

相似文献/References:

[1]曹锡文,刘兵,章元明.植物数量性状分离分析Windows软件包SEA的研制[J].南京农业大学学报,2013,36(6):1.[doi:10.7685/j.issn.1000-2030.2013.06.001]
 CAO Xiwen,LIU Bing,ZHANG Yuanming.SEA:a software package of segregation analysis of quantitative traits in plants[J].Journal of Nanjing Agricultural University,2013,36(3):1.[doi:10.7685/j.issn.1000-2030.2013.06.001]

备注/Memo

备注/Memo:
收稿日期:2017-06-19。
基金项目:国家大学生创新创业训练计划项目(201610307096)
作者简介:高启,硕士研究生。
通信作者:李毅念,副教授,主要从事农业装备新技术研究,E-mail:liyinian@163.com。
更新日期/Last Update: 1900-01-01