基于多光谱成像选取四季豆叶片的特征波段

曹鹏飞; 李宏宁; 罗艳琳; 林立波; 许海滨; 冯洁

doi:doi:10.3788/lop51.011101

激光与光电子学进展, 2014, 51 (1): 011101, 网络出版: 2013-12-26

基于多光谱成像选取四季豆叶片的特征波段

Selection of Feature Bands for Phaseolus vulgaris Leaves Based on Multi-Spectral Imaging

论文大纲

曹鹏飞 ^*李宏宁罗艳琳林立波许海滨冯洁

作者单位

云南师范大学物理与电子信息学院，云南昆明 650500

成像系统特征波段多光谱成像四季豆叶片分类精度 imaging systems feature band multi-spectral imaging Phaseolus vulgaris leaves classification accuracy

摘要

在400~720 nm波段范围，基于液晶可调谐滤波器(LCTF)和CMOS相机组合的多光谱成像系统，以四季豆叶片为研究对象每隔5 nm进行成像。根据图像亮度信息法和波段指数法的相关原理，首先分别计算得到各波段四季豆叶片的波段指数值和可识别度；然后对四季豆叶片的波段指数值和可识别度进行排序，综合图像的灰度离散、亮度信息丰富和波段的相关性小等特点，得出545、630、645、720、650和570 nm波段有较大的波段指数值和较好的识别度；最后根据最小欧氏距离法和光谱角度匹配法分别对四季豆叶片的特征波段的分类精度予以计算，两种方法的分类精度分别为100.00%和83.33%，得出选取的特征波段对四季豆叶片具有较好的分类精度。因此，545、630、645、720、650 和570 nm波段可作为四季豆叶片的特征波段。

Abstract

Multi-spectral images of Phaseolus vulgaris leaves at the wavelength range of 400~720 nm with an interval of 5 nm are captured by using a multi-spectral imaging system which mainly consists of liquid crystal tunable filter (LCTF) and CMOS camera. Firstly，according to the principles of image brightness and band index, the value of band index and identifiability for Phaseolus vulgaris leaves are calculated respectively among every band. Then, through sorting the value of band index and identifiability for Phaseolus vulgaris leaves, it can be concluded that bands 545, 630, 645, 720, 650 and 570 nm have preferable identification with considering the characteristics of discrete gray levels and rich brightness of images and little correlation coefficient among different bands. Finally, the classification accuracy for Phaseolus vulgaris leaves is calculated according to the principles of minimum Euclidean distance and minimum spectral angle matching. The classification accuracy of characteristic bands for Phaseolus vulgaris leaves is 100.00% and 83.33% separately through using these two methods. We can draw a conclusion that these bands have ideal classification accuracy. Therefore, bands 545, 630, 645, 720, 650 and 570 nm can be used as feature bands for Phaseolus vulgaris leaves.

参考文献

[1] 冯洁, 李宏宁, 杨卫平, 等. 园艺作物病害的多光谱组合分类[J]. 光谱学与光谱分析, 2010, 30(2): 426-429.

Feng Jie, Li Hongning, Yang Weiping, et al.. Horticultural plant diseases multispectral classification using combined classified methods[J]. Spectroscopy and Spectral Analysis, 2010, 30(2): 426-429.

[2] 林文鹏, 王长耀, 储德平, 等. 基于光谱特征分析的主要秋季作物类型提取研究[J]. 农业工程学报, 2006, 22(9): 128-132.

Lin Wenpeng, Wang Changyao, Chu Deping, et al.. Extraction of fall crop types based on spectral analysis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2006, 22(9): 128-132.

[3] 郭琳, 王飞, 张寅, 等. 农作物遥感监测业务管理系统设计与实现[J]. 农业工程学报, 2013, 29(3): 132-138.

Guo Lin, Wang Fei, Zhang Yin, et al.. Design and implementation of business management system for crop remote sensing monitoring[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(3): 132-138.

[4] Hardeberg J Y, Schmitt F, Brettel H. Multispectral color image capture using a liquid crystal tunable filter[J]. Opt Eng, 2002, 41(10): 2532-2548.

[5] 杜丽丽, 易维宁, 张冬英, 等. 基于LCTF的多光谱面阵CCD相机的辐射定标[J]. 光谱学与光谱分析, 2011, 31(1): 272-276.

Du Lili, Yi Weining, Zhang Dongying, et al.. Radiometric calibration of LCTF-based multispectral area CCD camera[J]. Spectroscopy and Spectral Analysis, 2011, 31(1): 272-276.

[6] Zjakic I, Parac-Osterman D, Bates I. New approach to metamerism measurement on halftone color images[J]. Measurement, 2011, 44(8): 1441-1447.

[7] Steidley C, Bachnak R, Dannelly R S, et al.. A multi-spectral imaging system for geo-spatial applications[J]. J Computational Methods in Sciences and Engineering, 2005, 5(1 suppl): S93-S109.

[8] Wang H C, Tsai M T, Chiang C P. Visual perception enhancement for detection of cancerous oral tissue by multi-spectral imaging[J]. J Optics, 2013, 15(5): 055301.

[9] 陈蓉蓉, 周治国, 曹卫星, 等. 基于GIS的农田土壤、作物特征空间变异性及其相互关系[J]. 应用生态学报, 2004, 15(9): 1678-1680.

Chen Rongrong, Zhou Zhiguo, Cao Weixing, et al.. Spatial variability and quantitative analysis of field factors based on GIS[J]. Chinese J Applied Ecology, 2004, 15(9): 1678-1680.

[10] 押辉远, 李卫涛, 王卫东, 等. 基于EF1-a基因对常见禾本科作物的聚类分析[J]. 郑州大学学报, 2012, 44(2): 108-113.

Ya Huiyuan, Li Weitao, Wang Weidong, et al.. Cluster analysis of some common gramineous plants based on the sequences of EF1-a[J]. J Zhengzhou University, 2012, 44(2): 108-113.

[11] 姜莉莉, 齐清文, 张岸. 基于网格的精准农业数据库及示范应用——以黑龙江农场双山基地为例[J]. 地理信息科学学报, 2011, 13(6): 804-809.

Jiang Lili, Qi Qingwen, Zhang An. Grid-based precision agriculture database and its demonstrative application: taking Shuangshan Farm in Heilongjiang Province as an example[J]. J Geo-Information Science, 2011, 13(6): 804-809.

[12] 冯洁, 李宏宁, 刘微, 等. 用亮度信息提取黄瓜霜霉病害窄带多光谱图像特征波段[J]. 中国激光, 2011, 38(s1): s109003.

Feng Jie, Li Hongning, Liu Wei, et al.. Extract spectral feature bands of pseudoperonospora cubensis′s narrow-band multispectral images using brightness[J]. Chinese J Lasers, 2011, 38(s1): s109003.

[13] 姜小光, 王长耀, 王成. 成像光谱数据的光谱信息特点及最佳波段选择——以北京顺义区为例[J]. 干旱区地理, 2000, 23(3): 214-220.

Jiang Xiaoguang, Wang Changyao, Wang Cheng. Optimum band selection of hyperspectrral remote sensing data[J]. Arid Land Geography, 2000, 23(3): 214-220.

[14] Yang A, Cao T, Li R F, et al.. A hybird gene selection method for cancer classification based on clustering algorithm and Euclidean distance[J]. J Computational and Theoretical Nanoscience, 2012, 9(4): 611-615.

[15] 张新乐, 张树文, 李颖, 等. 基于光谱角度匹配方法提取黑土边界[J]. 光谱学与光谱分析, 2009, 29(4): 1056-1059.

Zhang Xinle, Zhang Shuwen, Li Ying, et al.. Extracting black soil border in heilongjiang province based on spectral angle match method[J]. Spectroscopy and Spectral Analysis, 2009, 29(4): 1056-1059.

曹鹏飞, 李宏宁, 罗艳琳, 林立波, 许海滨, 冯洁. 基于多光谱成像选取四季豆叶片的特征波段[J]. 激光与光电子学进展, 2014, 51(1): 011101. Cao Pengfei, Li Hongning, Luo Yanlin, Lin Libo, Xu Haibin, Feng Jie. Selection of Feature Bands for Phaseolus vulgaris Leaves Based on Multi-Spectral Imaging[J]. Laser & Optoelectronics Progress, 2014, 51(1): 011101.

基于多光谱成像选取四季豆叶片的特征波段

关于本站 Cookie 的使用提示

全站搜索

基于多光谱成像选取四季豆叶片的特征波段

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索