Weeds Discrimination Using Near Infrared/Visible Spectral Analysis Technology

摘要：

The spectral reflectance of cotton, rice and weeds were determined in the range from 350 to 2500nm using the Analytical Spectral Device Full Range FieldSpee Pro (ASD) in laboratory. The discrimination analysis was done using the statistical software package SAS. The spectral reflectance at the green peak (555nm) was chosen as denominator, wavelength ratios were calculated as variables to discriminate. Wavelength ratios were selected using the STEPDISC procedure. With the selected variables, discriminant models were developed using the DISCRIM procedure in SAS. Five wavelength ratios selected, which are 395/555, 535/555, 705/555 and 1105/555, gained good classification performance (100% accuracy) for distinguishing barnyard-grass from rice. The ratio of spectral reflectance at 705nm in the red edge to spectral reflectance at 555nm contributes more to discrimination.

关键词： Spectrum analysis Dicotyledon Monocotyledon Weeds discrimination

作者: CHEN Shuren SHEN Baoguo

作者单位: Key Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education & Jiangsu Province, Jiangsu University, Zhenjiang, Jiangsu, 212013, P.R.China

会议类型: 国际会议

会议名称: 2008 International Conference on IAEA(2008农业信息化、自动化与电气化国际会议)

会议地点: 镇江

会议语种:英文

页码: 638-642

在线出版日期: 2008-11-01（万方平台首次上网日期，不代表论文的发表时间）