Abstract:The improvement of segmentation algorithm and the optimization of feature space are the key factors of improving the accuracy of tree-crown information extraction, and are also the urgent problems of tree-crown information extraction using high resolution images. In the present study, the spectral threshold method was used on the first-class segmentation of QuickBird multi-spectral image to obtain vegetation regions. On the second-class segmentation, the improved algorithm based on edge was used to segment the panchromatic image, which was processed by the non-linear filtering. Afterwards, the feature space consisting of spectrum, shape and texture features was selected to extract tree-crown information. 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 84.67% and a KAPPA coefficient of 0.795 3. The corresponding results of the traditional method are 67.67% and 0.627 3. The method in this paper can achieve a more precise information extraction of the tree-crown and the results can meet the demand of accurate monitoring and decision-making.
吴 见, 彭道黎* . 基于面向对象的QuickBird影像退耕地树冠信息提取 [J]. 光谱学与光谱分析, 2010, 30(09): 2533-2536.
WU Jian, PENG Dao-li* . Tree-Crown Information Extraction of Farmland Returned to Forests Using QuickBird Image Based on Object-Oriented Approach . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(09): 2533-2536.
[1] YE Shi-ping, CHEN Chao-xiang, WEI Yu-zhang, et al(叶时平,陈超祥, 魏玉璋,等). Journal on Communications(通信学报), 2008, 29(8): 129. [2] WAN You-chuan, HUANG Jun(万幼川,黄 俊). Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版), 2009, 34(7): 794. [3] CHEN Zhong, ZHAO Zhong-ming(陈 忠,赵忠明). Computer Engineering(计算机工程), 2006, 32(23): 186. [4] AN Qiong, YANG Bang-jie, GUO Lin(安 琼,杨邦杰,郭 琳). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2008, 24(4): 181. [5] HAN Min, LIN Xiao-feng(韩 敏, 林晓峰). J. Infrared Millim. Waves(红外与毫米波学报), 2008, 27(4): 280. [6] FENG Mei-chen, YANG Wu-de, ZHANG Dong-yan, et al(冯美臣,杨武德,张东彦,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2009, 25(3): 103. [7] GUAN Hai-yan, DENG Fei, ZHANG Jian-qing, et al(管海燕,邓 非,张剑清,等). Geomatics and Information Science of Wuhan University(武汉大学学报·信息科学版), 2009, 34(7): 830. [8] GUO Jian-cong, LI Pei-jun, XIAO Xiao-bai(郭建聪,李培军,肖晓柏). Acta Scientiarum Naturalium Universitatis Pekinensis(北京大学学报·自然科学版), 2009, 45(2): 306. [9] CHEN Hai-lin,WU Xiu-qing,HU Jun-hua(陈海林,吴秀清,胡俊华). Opto-Electronic Engineering(光电工程), 2009, 36(3): 33. [10] ZHANG Xiu-ying, FENG Xue-zhi, DING Xiao-dong, et al(张秀英,冯学智,丁晓东,等). Journal of Zhejiang University·Agric. & Life Sci.(浙江大学学报·农业与生命科学版), 2007, 33(5): 568. [11] Deng Y, Kenney C, Moore M S, et al. Peer Group Filtering and perceptual color image quantization. Proc. of IEEE International Symposium on Circuits and Systems, 1999. 21. [12] XU Dong, YUAN Xiao-hui, XIA Liang-zheng, et al(许 东,袁晓辉,夏良正,等). J. Infrared Millim. Waves(红外与毫米波学报), 2002, 21(1): 49. [13] Lobregt S, Viergever A. IEEE Trans. Medical Imaging, 1995, 14(1): 14. [14] HUANG Jian-wen, JU Hong-bo, ZHAO Feng, et al(黄建文,鞠洪波,赵 峰,等). Journal of Remote Sensing(遥感学报), 2007, 11(6): 899.