基于光谱时间序列拟合的中国南方水稻遥感识别方法研究

发布时间：2018-08-02 20:02

【摘要】：多云多雾现象是农作物遥感分类经常遇到的问题,影响分类精度。为解决此类问题,本文提出一种基于时间序列GF-1号遥感影像识别水稻方法。利用多时相时间序列的GF-1号遥感影像提取中稻、晚稻的近红外波段(NIR)反射率、红光(R)波段反射率、归一化植被指数(NDVI)特征;拟合光谱和植被指数时间序列特征曲线;分析多时相影像离散近红外波段、红光波段、NDVI值落在拟合中稻、晚稻近红外波段、红光波段、NDVI时间序列曲线两侧的敏感性区域的比例,该区域也可以视为水稻作物识别特征的目标特征区域,只有达到一定的比例才能视为某类水稻作物。在此情形下,需要综合3种情况进行集中投票决定其最终分类结果。研究表明:该方法可以在多云雾地区对中稻和晚稻精确识别,中稻和晚稻用户精度可达95.97%和95.95%,总体精度为95.76%,kappa系数为0.9335。实验结果表明了NIR、R、NDVI时间序列曲线拟合的有效性,以及拟合曲线目标特征区域设置的合理性。
[Abstract]:Cloud and fog phenomenon is a common problem in crop classification by remote sensing, which affects the classification accuracy. In order to solve this problem, a rice recognition method based on time series GF-1 remote sensing image is proposed in this paper. The near infrared (NIR) reflectance, red light (R) band reflectance, normalized vegetation index (NDVI) feature, fitting spectrum and vegetation index time series characteristic curves of middle rice and late rice were extracted by GF-1 remote sensing image of multitemporal time series. The ratio of NDVI value of red light band to the sensitive region on the two sides of the time series curve of mid-rice, late rice and late rice was analyzed by analyzing the discrete near infrared band of multitemporal image, and the ratio of NDVI value of red light band to the two sides of the curve of NDVI time series. The region can also be regarded as the target feature area of rice crop identification, and only a certain proportion can be regarded as a certain type of rice crop. In this case, the final classification results need to be determined by centralized voting in three cases. The results show that this method can be used to identify middle and late rice in cloudy and foggy areas. The user accuracy of middle and late rice can reach 95.97% and 95.95% respectively, and the overall precision is 95.76% and 0.933 5. The experimental results show the validity of curve fitting and the rationality of setting the target region of the fitting curve.
【作者单位】：东华理工大学测绘工程学院;中国科学院遥感与数字地球研究所;中国科学院大学;
【基金】：国家自然科学基金面上项目(41571422) 国家自然科学青年基金项目(41301497) 中国科学院重点部署项目(KZZD-EW-08-05) 高分辨率对地观测系统重大专项(00-Y30B15-9001-14/16-2)
【分类号】：S511;S127

【相似文献】