Investigation Of Identification Of Unauthorized Construction Of City Based On Aerial Image

The city's identification and monitoring of unauthorized construction is an important task of urban planning department. With the development of GIS and RS technology, accurate and efficient of the city's identification and monitoring of unauthorized construction is a new opportunity. Building extraction and identification of unauthorized construction is a very difficult issue in the field of image processing and pattern recognition. Fully mature technology requires further study. Considering of reducing the cost of urban planning, around the theory and the key technologies of the building extraction and identification of unauthorized construction, this thesis discusses some of the problems and puts forward the corresponding solutions. The main functions includes:(1)The basic theory and techniques of Aerial Image-Based unauthorized construction identification of the cityThis thesis defines the unauthorized structures which is based on RS and GIS, and analysis the model of the identification of unauthorized construction in depth, and studies the technology framework of the city's identification of unauthorized construction.(2)Integration of gray and spatial information on building extraction AlgorithmThis thesis presents a model for building imaging and characteristic of the buildings in aerial images. Considering of increasing the accuracy and decreasing the algorithm amount, firstly, divide the gray levels according to the concept of image roughness, and use the incremental growth algorithm to form the initial image segmentation. Then the initial regions are hierarchically merged based on the region distance defined by color and spatial information. A new criteria is proposed to decide the termination of the merging process. Finally, rectify the region of the building target.(3)Investigation and realization of the identification of unauthorized construction based on clustering strategy. This thesis firstly introduced the functions of GIS and the application in urban planning and then discussed further into the model for spatial analysis and the effect of vector accuracy on the change-detection, presented the representation styles in logic expressions. Subsequently the thesis proposed a new clustering strategy and algorithm for the identification of unauthorized construction. Lastly this thesis arranged experiment of Identification of unauthorized construction on the basis the vector data.