The Research And System Development Of Automatic Change Monitoring Technology For Geographic Condition Monitoring Data

With the rapid and steady development of Chinese economy,the surface of natural and cultural information change more frequently,in order to meet the needs of the government,the society and the public to grasp the real-time information of the geographical conditions,our country has comprehensively carried out geography national condition monitoring.The traditional geographical national condition monitoring method has the disadvantages of large workload,low work efficiency,and low automation degree,which limits the update period of geographic national conditions data.Remote sensing technology is a kind of non direct contact detection technology,which has the advantages of wide detection range,fast access to the real information on the surface,short cycle,etc.,and can be used for the rapid and wide range monitoring of the geographical national conditions.But,the data source of the traditional remote sensing technology change detection is two and more than two remote sensing images,but the change detection data source in the normalization of the national condition monitoring is vector data and remote sensing image.Therefore,in order to solve the problem of vector data pre update in geographical national condition monitoring problems,we proposed a change detection method of vector data type and remote sensing image which based on Category heterogeneity.The main contents of this paper are as follows:First,the concept and process of the change detection technology based on vector data and remote sensing image are described.and in accordance with the need to select the sample will be divided into the law of supervision and non supervision method.Three key techniques of this change detection technology besides image segmentation,feature extraction and automatic threshold extraction are summarized and analyzed.Second,the change detection method of vector data and remote sensing image based on class heterogeneity is studied.This method uses Mark watershed algorithm to make the vector data as image prior boundary to segment the image,which can obtain homogeneous image disk;After extracting image feature,we can building category heterogeneity.By automatic threshold technology,we can acquire thresholds of category heterogeneity of every classes.Finally,do change detection by those thresholds.This method realizes the automatic change detection of vector data and remote sensing imagesThird,researched of Geographical National Conditions Normalization Monitoring Data Change Detection System.The vector data type and remote sensing image which based on Category heterogeneity method as the foundation,using GDAL(Geospatial Data Abstraction Library)and ArcEngine mixed programming technology to construct the geographical national conditions normalization monitoring data change detection system.The system uses the C#language,in the Microsoft Visual Studio 2010 platform,using GDAL to deal with the raster data,using ArcEngine to process vector data.The system realized functions of raster images and vector data display,secondary segmentation,image feature extraction,distance measurement,threshold acquisition,change detection,manual editing(add,delete and modify),parameter setting(segmentation parameters),data output(segmentation results,change detection results),late editing,and so on.The system can realize the automaticly change detection.Compared with the traditional visual interpretation,the change detection efficiency is greatly improved.Finally,Using the Xindu 2015 national census geographic vector data and the correspondent 2016 high resolution remote sensing images to do change detection,change detection accuracy,false rate and missing rate were 84.3%,15.6%,and 16.1%,which verified the feasibility and effectiveness of this method and meet the precision requirement of geography national condition monitoring.The change detection results show that the method is feasible and.effective The change detection also proves that the researched system can effectively assist the discovery of change regions in the geographical conditions of the country and improve the efficiency of the intra industry updating.