关键生育期冬小麦和油菜遥感分类方法

Winter Wheat and Rapeseed Classification during Key Growth Period by Integrating Multi-Source Remote Sensing Data

农作物空间分布的遥感识别是地理学、生态学和农学等多学科研究的前沿和热点,多源遥感数据在其中发挥着重要的作用。本研究结合冬小麦和油菜的种植及生长特点,以安徽省合肥市为研究区域,利用ZY-3、Sentinel-2和GF-1等多源遥感影像数据,以高程、坡度等数据为辅助信息,结合以多尺度分割、最邻近法和阈值法等为主要步骤的面向对象的分类方法,提取研究区合肥市冬小麦和油菜种植的空间分布信息。结合来自于GVG农情采样系统和Google Earth高分辨率影像上获得的地面验证数据进行分类精度验证,计算得到分类结果的混淆矩阵,并根据混淆矩阵数据计算出分类的总体精度为94.43%,Kappa系数为0.914。结果表明,本研究提出的方法能够有效地区分在冬小麦和油菜的混种区域里两种作物种植区域的空间分布,且这种多种策略相结合的分类方法体系,能够适用于其它区域甚至是更加大尺度上的作物分类。

As the cutting-edge technology of modern information technology, remote sensing has the advantages of large coverage, short detection period, strong current situation, and low cost, which makes it possible to quickly and accurately extract large-scale crop planting information. Accurate crop type identification and spatial distribution information can provide basic and necessary information for subsequent crop monitoring applications. Identification of crop spatial distribution by remote sensing is the frontier and a hotspot of multidisciplinary research in geography, ecology, and agronomy. Multi-source remote sensing data plays an important role. Combining the characteristics of winter wheat and rapeseed during their planting and growing stages, this study took Hefei City in Anhui Province as the study area, and used multi-source remote sensing imagery such as ZY-3, Sentinel-2, and GF-1, with elevation and slope data as auxiliary information. Utilizing the object-oriented classification method with multi-scale segmentation, nearest neighbor method, and threshold method as the main steps, the spatial distribution information of winter wheat and rapeseed planting in Hefei City was extracted. Ground truth data from the GVG agricultural sampling system and Google Earth highresolution imagery were combined to verify the accuracy of the classification results. By confusion matrix analysis, the overall accuracy and the kappa Coefficient were calculated, the values of which were 94.43% and 0.914, respectively. The results show that, to a large extent, the proposed method can effectively distinguish the planting areas of winter wheat and rapeseed in the mixed planting regions and the combination of those various strategies can be applied to the crop classification in other regions with similar characteristics and at even larger scales. Future research can explore the feasibility of using multi-source remote sensing data to map winter wheat and rapeseed for remote sensing monitoring, and can establish a suitable technical system.