基于高光谱成像技术的甘蔗茎节识别与定位方法研究

张卫正; 张伟伟; 张焕龙; 陈启强; 丁臣臣

doi:10.3969/j.issn.2096-1553.2017.5.013

CN 41-1437/TS ISSN 2096-1553

基于高光谱成像技术的甘蔗茎节识别与定位方法研究

张卫正 , 张伟伟 , 张焕龙 , 陈启强 , 丁臣臣

张卫正, 张伟伟, 张焕龙, 等. 基于高光谱成像技术的甘蔗茎节识别与定位方法研究[J]. 轻工学报, 2017, 32(5): 95-102. doi: 10.3969/j.issn.2096-1553.2017.5.013

引用本文: 张卫正, 张伟伟, 张焕龙, 等. 基于高光谱成像技术的甘蔗茎节识别与定位方法研究[J]. 轻工学报, 2017, 32(5): 95-102. doi: 10.3969/j.issn.2096-1553.2017.5.013

ZHANG Wei-zheng, ZHANG Wei-wei, ZHANG Huan-long, et al. Research on identification and location method of sugarcane node based on hyperspectral imaging technology[J]. Journal of Light Industry, 2017, 32(5): 95-102. doi: 10.3969/j.issn.2096-1553.2017.5.013

Citation: ZHANG Wei-zheng, ZHANG Wei-wei, ZHANG Huan-long, et al. Research on identification and location method of sugarcane node based on hyperspectral imaging technology[J]. Journal of Light Industry, 2017, 32(5): 95-102. doi: 10.3969/j.issn.2096-1553.2017.5.013

基于高光谱成像技术的甘蔗茎节识别与定位方法研究

郑州轻工业学院计算机与通信工程学院, 河南郑州 450001;
郑州轻工业学院电气信息工程学院, 河南郑州 450002
基金项目: 国家自然科学基金项目（61403349，61503173）；郑州轻工业学院博士科研基金资助项目（JSJ20170017）
中图分类号: S566.1;TP391.4

Research on identification and location method of sugarcane node based on hyperspectral imaging technology

College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China;
College of Electric and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
Received Date: 2017-02-06
Available Online: 2017-09-15
CLC number: S566.1;TP391.4

摘要: 针对甘蔗茎节与茎间颜色相近和由于表皮上白色果粉的干扰导致茎节难以识别的问题，提出了一种基于高光谱成像技术的茎节识别与定位方法.采集236个茎节和茎间样本的高光谱图像（874~1734 nm），采用连续投影算法（SPA）提取5个特征波长（1022 nm，1062 nm，1456 nm，1609 nm和1649 nm），建立偏最小二乘法（PLS）分类模型，利用该模型对20组甘蔗高光谱图像进行识别，生成甘蔗茎节的二值化图像，采用图像处理的方法进行茎节定位.实验结果表明，高光谱成像技术测量结果的标准差为0.7 mm，绝对误差的最大值为2.6 mm，能够有效识别与定位甘蔗茎节，为蔗种的防伤芽自动切割提供技术支持.
- 高光谱成像 /
- 甘蔗茎节识别与定位 /
- 连续投影算法 /
- 图像处理
Abstract: Due to the fact that the color of sugarcane nodes and internodes are similar to each other,and the interference of white fruit powder on the skin,node recognition and location were affected seriously.A method for node identification and localization was proposed based on hyperspectral imaging.236 sugarcane samples (874~1734 nm) were collected by the hyperspectral imaging acquisition system.Using successive projections algorithm (SPA) to extract characteristics band (1022 nm,1062 nm,1456 nm,1609 nm and 1649 nm),the PLS discriminant model were established by these 5 characteristic bands.The 20 groups of sugarcane hyperspectral images were identified by the established model,the binary image of sugarcane was gotten,image processing was used to locate the position of node.The experimental result showed the standard deviation was 0.7 mm,the maximum absolute error was 2.6 mm,and it could identify and locate the sugarcane node effectively,provide technical support for automatic cutting of sugarcane which could prevent injury buds.
- hyperspectral imaging /
- identification and location of sugarcane node /
- successive projections algorithm(SPA) /
- image processing
1. [1]
  卢庆南,梁贤,陆宇明,等.论广西蔗糖产业经济及其发展战略[J].安徽农业科学,2008,36(36):16095.
2. [2]
  陆尚平,文友先,葛维,等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190.
3. [3]
  陆尚平,马翠龙,贺敏超,等.图像灰度统计梯度特性的甘蔗茎节识别研究[J].广西农业机械化,2012(6):21.
4. [4]
  MOSHASHAI K,ALMASI M,MINAEI S,et al.Identification of sugarcane nodes using image processing and machine vision technology[J].International Journal of Agricultural Research,2008,3(5):357.
5. [5]
  黄亦其,乔曦,唐书喜,等.基于Matlab的甘蔗茎节特征分布定位与试验[J].农业机械学报,2013,44(10):93.
6. [6]
  胡鹏程,孙晔,吴海伦,等.高光谱图像对白萝卜糠心的无损检测[J].食品科学,2015,36(12):171.
7. [7]
  RIVERA N V,GóMEZ-SANCHIS J,CHANONA-PéREZ J,et al.Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning[J].Biosystems Engineering,2014,122(3):91.
8. [8]
  ZHAO M,ESQUERRE C,DOWNEY G,et al.Process analytical technologies for fat and moisture determination in ground beef-A comparison of guided microwave spectroscopy and near infrared hyperspectral imaging[J].Food Control,2017,73:1082.
9. [9]
  CEN H,LU R,ZHU Q,et al.Nondestructive detection of chilling injury in cucumber fruit using hyperspectral imaging with feature selection and supervised classification[J].Postharvest Biology and Technology,2016,111:352.
10. [10]
  WOLD J P,KERMIT M,SEGTNAN V H.Chemical imaging of heterogeneous huscle foods using near-infrared hyperspectral imaging in transmission mode[J].Applied spectroscopy,2016,70(6):953.
11. [11]
  GASPARDO B,ZOTTO S D,TORELLI E,et al.A rapid method for detection of fumonisins B1 and B2 in corn meal using Fourier transform near infrared (FT-NIR) spectroscopy implemented with integrating sphere[J].Food Chemistry,2012,135(3):1608.
12. [12]
  WU D,SHI H,WANG S J,et al.Rapid prediction of moisture content of dehydrated prawns using online hyperspectral imaging system[J].Analytica Chimica Acta,2012,726:57.
13. [13]
  丛智博,孙兰香,辛勇,等.基于激光诱导击穿光谱的合金钢组分偏最小二乘法定量分析[J].光谱学与光谱分析,2014,34(02):542.
14. [14]
  吴翔,张卫正,陆江锋,等.基于高光谱技术的玉米种子可视化鉴别研究[J].光谱学与光谱分析,2016,36(2):511.
15. [15]
  陆婉珍.现代近红外光谱分析技术[M].北京:中国石化出版社,2007.
16. [16]
  张卫正,董寿银,齐晓祥,等.基于图像处理的甘蔗茎节识别与定位[J].农机化研究,2016(4):217.
1. [1]
  张建栋 , 杨忠泮 , 吴恋恋 , 徐大勇 , 朱萍 , 张雯晶 , 堵劲松 . 基于高光谱成像及机器学习的烟叶糖料液施加量判别模型. 轻工学报, 2024, 39(5): 86-94. doi: 10.12187/2024.05.010
2. [2]
  吴晓东 , 刘畅 , 李俊 , 胡良志 , 贺凌晨 , 袁海霞 , 李强 , 黄锦标 . 基于高光谱检测的烟丝加香均匀性表征方法. 轻工学报, 2024, 39(5): 95-101. doi: 10.12187/2024.05.011
3. [3]
  贾尚羲 , 张怡雪 , 石盼盼 , 王昱 , 李可 . 不同时长超声波处理对鹰嘴豆分离蛋白乳化液稳定性的影响. 轻工学报, 2024, 39(5): 40-49. doi: 10.12187/2024.05.005
4. [4]
  张伟伟 , 姬远鹏 , 元春波 , 王君婷 , 齐晓任 , 张卫正 , 李萌 , 饶智 . 基于改进Mask R-CNN模型的粘连烟丝识别方法. 轻工学报, 2024, 39(5): 78-85. doi: 10.12187/2024.05.009
5. [5]
  池哲翔 , 廖敏 , 史尚 , 李声毅 , 廖芸 , 丁冬 . 国外烟草活性成分提取及纤维材料利用现状与展望. 轻工学报, 2024, 0(0): -.
6. [6]
  李艳坤 , 张伟 , 刘彦伶 . 数据融合策略在食用油真实性鉴别中的研究与应用进展. 轻工学报, 2024, 39(5): 50-59. doi: 10.12187/2024.05.006

点击查看大图

计量

PDF下载量: 69
文章访问数: 1312
引证文献数: 0

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

张卫正, 张伟伟, 张焕龙, 等. 基于高光谱成像技术的甘蔗茎节识别与定位方法研究[J]. 轻工学报, 2017, 32(5): 95-102. doi: 10.3969/j.issn.2096-1553.2017.5.013

基于高光谱成像技术的甘蔗茎节识别与定位方法研究

郑州轻工业学院计算机与通信工程学院, 河南郑州 450001;
郑州轻工业学院电气信息工程学院, 河南郑州 450002

收稿日期: 2017-02-06
网络出版日期: 2017-09-15

基金项目: 国家自然科学基金项目（61403349，61503173）；郑州轻工业学院博士科研基金资助项目（JSJ20170017）

关键词:

摘要: 针对甘蔗茎节与茎间颜色相近和由于表皮上白色果粉的干扰导致茎节难以识别的问题，提出了一种基于高光谱成像技术的茎节识别与定位方法.采集236个茎节和茎间样本的高光谱图像（874~1734 nm），采用连续投影算法（SPA）提取5个特征波长（1022 nm，1062 nm，1456 nm，1609 nm和1649 nm），建立偏最小二乘法（PLS）分类模型，利用该模型对20组甘蔗高光谱图像进行识别，生成甘蔗茎节的二值化图像，采用图像处理的方法进行茎节定位.实验结果表明，高光谱成像技术测量结果的标准差为0.7 mm，绝对误差的最大值为2.6 mm，能够有效识别与定位甘蔗茎节，为蔗种的防伤芽自动切割提供技术支持.

English Abstract

Research on identification and location method of sugarcane node based on hyperspectral imaging technology

College of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China;
College of Electric and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China

Received Date: 2017-02-06
Available Online: 2017-09-15

Abstract: Due to the fact that the color of sugarcane nodes and internodes are similar to each other,and the interference of white fruit powder on the skin,node recognition and location were affected seriously.A method for node identification and localization was proposed based on hyperspectral imaging.236 sugarcane samples (874~1734 nm) were collected by the hyperspectral imaging acquisition system.Using successive projections algorithm (SPA) to extract characteristics band (1022 nm,1062 nm,1456 nm,1609 nm and 1649 nm),the PLS discriminant model were established by these 5 characteristic bands.The 20 groups of sugarcane hyperspectral images were identified by the established model,the binary image of sugarcane was gotten,image processing was used to locate the position of node.The experimental result showed the standard deviation was 0.7 mm,the maximum absolute error was 2.6 mm,and it could identify and locate the sugarcane node effectively,provide technical support for automatic cutting of sugarcane which could prevent injury buds.

参考文献 (16) 相关文章 (6)