不同分辨率影像的撂荒地提取方法

Abandoned Land Extraction Methods for Different Resolution Images

撂荒地对土地利用有很大的影响,利用遥感影像识别并提取撂荒地可以进一步加强对其保护和利用,故撂荒地的影像特征提取具有极大的意义。本文着重研究基于不同分辨率影像的撂荒地信息的提取方法,对于高分辨率遥感影像直接采用目视解译的方法,中分辨率影像采用决策树分析法,低分辨率则是采用时间序列的生命周期法及归一化差分植被指数来提取撂荒地。针对不同分辨率影像选择不同方法来进行撂荒地的提取,并分析不同方法的优缺点,可为以后的研究提供思路。

Abandoned land is abandoned arable land,has a great influence on land use.So the use of the remote sensing images to recognize and extract the abandoned land can further enhance the protection and utilization of the wasteland. Therefore,it is of great significance to extract the image features of abandoned land. This paper focuses on the extraction of wasteland information based on different resolution images. For high resolution remote sensing images,the method of visual interpretation is adopted directly. The middle resolution images are analyzed by decision tree method,while the low resolution images are extracted by time series life cycle method and NDVI index. Discuss to choose different methods to extract wasteland using different resolution images and analyze the advantages and disadvantages of different methods,provide ideas for future research.