Research on Crop-Weed Discrimination Using a Field Imaging Spectrometer
LIU Bo1,2,FANG Jun-yong1,LIU Xue1,ZHANG Li-fu1,ZHANG Bing3,TONG Qing-xi1
1. State Key Lab of Remote Sensing Scince, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China 2. Graduate University of Chinese Academy of Sciences, Beijing 100049, China 3. Center for Earth Observation and Digital Earth, Chinese Academy of Sciences, Beijing 100080, China
Abstract:Discrimination of weeds from crop is the first and important step for variable herbicides application and precise physical weed control. Using a new field imaging spectrometer developed by our group, hyperspectral images in the wavelength range 380-870 nm were taken in the wild for the investigation of crop-weed discrimination. After normalizing the data to reduce or eliminate the influence of varying illuminance, stepwise forward variable selection was employed to select the proper band sets and fisher linear discriminant analysis (LDA) was performed to discriminate crop and weeds. For the case of considering each species as a different class, classification accuracy reached 85% with eight selected bands while for the case of considering overall weed species as a class, classification accuracy was higher than 91% with seven selected bands. In order to develop a low-cost device and system in future, all combinations of two and three bands were evaluated to find the best combinations. The result showed that the best three bands can achieve a performance of 89% comparable to the performance achieved by five bands selected using stepwise selection. The authors also found that “red edge” could afford abundant information in the discrimination of weed and crop.
刘 波1,2,方俊永1,刘 学1,张立福1,张 兵3,童庆禧1 . 基于成像光谱技术的作物杂草识别研究[J]. 光谱学与光谱分析, 2010, 30(07): 1830-1833.
LIU Bo1,2,FANG Jun-yong1,LIU Xue1,ZHANG Li-fu1,ZHANG Bing3,TONG Qing-xi1 . Research on Crop-Weed Discrimination Using a Field Imaging Spectrometer . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(07): 1830-1833.
[1] Wang N,Zhang N,Dowell F E Y S, et al. Transactions of the ASAE,2001,44(2):409. [2] Alchanatis V,Ridel L,Hetzroni A,et al. Computer and Electronics in Agriculture,2005,47:243. [3] Goel P K,Prasher S O,Patel R M,et al. Transactions of the ASAE,2002,45(2): 443. [4] Onyango C M,Marchant J A. Computer and Electronics in Agriculture,2003,39:141. [5] Tillett N D,Hague T,Miles S J. Computer and Electronics in Agriculture,2001,32:229. [6] Perez A,Lopez F,Benlloch J V,et al. Computer and Electronics in Agriculture,2000,25:197. [7] Virndts E,De Baerdemaeker J,Ramon H. Precision Agriculture,2002,3:63. [8] Borregaard T,Nielsen H,Norgaard L,et al. Journal of Agricultural Engineering Research,2000,75(4):389. [9] Fevaerts F,Van Gool L. Pattern Recognition Letters,2001,22:667. [10] Piron A,Leemans V,Kleynen O,et al. Computer and Electronics in Agriculture,2008,62:141. [11] CHEN Shu-ren,LI Yi-xin,MAO Han-ping,et al(陈树人,栗移新,毛罕平,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2009,29(2):463. [12] FANG Jun-yong, QI Hong-xing, LIU Xue,et al(方俊永,亓洪兴,刘 学,等). Proceedings of the 7th Technology and Application of Imaging Spectroscopy(第七届成像光谱技术与应用研讨会文集),2009. 148. [13] TONG Qing-xi,ZHANG Bing,ZHENG Lan-fen(童庆禧,张 兵,郑兰芬). Hyperspectral Remote Sensing Principle, Technology and Application(高光谱遥感原理、技术与应用). Beijing: Higher Education Press(北京:高等教育出版社),2006. 22. [14] Theodoridis S,Koutroumbas K. Pattern Recognition. Beijing:China Machine Press(北京: 中国机械出版社),2006.