TM影像中大棚菜地信息提取技术研究

Study on Technique of Extracting Greenhouse Vegetable Information from Landsat TM Image

大棚菜地在我国北方呈不断发展之势,快速、准确地获取其面积及分布状况,是蔬菜业健康发展和科学管理的客观需求。为探索快速准确的大棚菜地信息提取技术方法,以山东省青州市为例,采用TM数字图像,深入分析各主要地物光谱特征的基础上,构建了能够突出反映大棚菜地信息的大棚菜地指数模型,同时通过对图像的分区、掩膜处理,以及研究区背景数据及专家知识的应用,准确提取了大棚菜地信息。结果显示:青州市2002年4月14日的大棚菜地面积为21375.4hm2,集中分布于青州东北部平原区的谭坊、郑母、黄楼等乡镇。本研究技术方法对于大棚菜地信息的遥感提取有积极参考价值,为研究区及山东蔬菜业的合理发展提供重要技术支撑。

Green house vegetable land is increasing rapidly in north China. The area and spatial information of green house vegetable is indispensable to reasonable development and scientific management of vegetable industry. This paper intends to explore rapid and accurate information acquisition methods of green house vegetable. Taking Qingzhou city of Shandong province as the study area, using digital TM data, based on the systematic spectral analysis of main land use types, we built an index model which can make greenhouse vegetable information exceptional. Meanwhile, through determination of green house vegetable distribution area, employing masking and using the background data and expert knowledge, the greenhouse vegetable land information was accurately extracted. The results show that there is 21 375.4 hm^2 greenhouse vegetable land in Qingzhou at 2002.4.14, which concentrate in Tanfang, Zhengmu and Huanglou town. This technique will have a consulting value to the greenhouse vegetable information extraction using remote sensing technique and provide technical support for the rational development of the vegetable industry in the study area as well as in Shandong province.