Cotton Identification and Extraction Using Near Infrared Sensor and Object-Oriented Spectral Segmentation Technique
DENG Jin-song1, 2, SHI Yuan-yuan1, 2, CHEN Li-su1, 2, WANG Ke1, 2*, ZHU Jin-xia1, 2
1. Institute of Remote Sensing & Information Technique, Zhejiang University, Hangzhou 310029, China 2. Ministry of Education Key Laboratory of Environmental Remediation and Ecological, Health, Zhejiang University, Hangzhou 310029, China
Abstract:The real-time, effective and reliable method of identifying crop is the foundation of scientific management for crop in the precision agriculture. It is also one of the key techniques for the precision agriculture. However, this expectation cannot be fulfilled by the traditional pixel-based information extraction method with respect to complicated image processing and accurate objective identification. In the present study, visible-near infrared image of cotton was acquired using high-resolution sensor. Object-oriented segmentation technique was performed on the image to produce image objects and spatial/spectral features of cotton. Afterwards, nearest neighbor classifier integrated the spectral, shape and topologic information of image objects to precisely identify cotton according to various features. Finally, 300 random samples and an error matrix were applied to undertake the accuracy assessment of identification. Although errors and confusion exist, this method shows satisfying results with an overall accuracy of 96.33% and a KAPPA coefficient of 0.926 7, which can meet the demand of automatic management and decision-making in precision agriculture.
[1] LIN Kai-yan, XU Li-hong, WU Jun-hui(林开颜, 徐立鸿, 吴军辉). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2004, 20(2): 279. [2] QIU Bai-jing, LIU Bao-ling, WU Chun-du, et al(邱白晶, 刘保玲, 吴春笃,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2005, 21(5): 102. [3] FENG Lei, FANG Hui, ZHOU Wei-jun, et al(冯雷, 方慧, 周伟军,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2006, 26(9): 1749. [4] MAO Wen-hua, WANG Yue-qing, WANG Yi-ming, et al(毛文华, 王月青, 王一鸣,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2005, 25(6): 1984. [5] JIANG Huan-yu, YING Yi-bin, XIE Li-juan(蒋焕煜, 应义斌, 谢丽娟). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2008, 28(6): 1300. [6] CAO Bao, QIN Qi-ming, MA Hai-jian, et al(曹宝, 秦其明, 马海建,等). Geography and Geo-Information Science(地理与地理信息科学), 2006, 22(2): 46. [7] Lobo A, Chic O, Conese C. International Journal of Remote Sensing, 1996, 17: 537. [8] Volker W. ISPRS Journal of Photogrammetry & Remote Sensing, 2004, 58: 225. [9] Geneletti D, Gorte B G H. International Journal of Remote Sensing, 2003, 24: 1273. [10] CHEN Qiu-xiao, LUO Jian-cheng, ZHOU Cheng-hu, et al(陈秋晓, 骆剑承, 周成虎,等). Journal of Remote Sensing(遥感学报), 2004, 8(3): 2396. [11] ZHANG Yu-jin(章毓晋). Image Segmentation(图像分割). Beijing: Science Press(北京:科学出版社), 2001. [12] Ursula C B, Peter H, Gregor W, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2004, 58: 239. [13] YANG Guang, LIU Xiang-nan, ZHANG Bai, et al(杨桄, 刘湘南, 张柏,等). Journal of Jilin University(Earth Science Edition)(吉林大学学报·地球科学版). 2005, 35(2): 257. [14] Anssi P. Remote Sensing of Environment, 2002, 82: 349. [15] CHEN Yun-hao, FENG Tong, SHI Pei-jun, et al(陈云浩, 冯通, 史培军,等). Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版), 2006, 31(4): 316.