Study On The Feasibility Of Object-oriented Classification In Land Survey

Land Resource Survey is a national integrated investigation and evaluation engineering, and it is a basic, public welfare and strategic work. It is necessary to strengthen land management, we must first of all to grasp the land-use information, which need to keep the latest land-use database is in the state. Therefore, how to integrate new technologies and new methods to achieve land-use information extraction, land and natural resources management is yet to be resolved.The development of the remote sensing technology makes us obtain very abundant information of nature, especially with the appearance of high resolution remote sensing image, it extends the visual field of the nature. But the challenge that faces us is how to make use of the data effectively and obtain more useful information through some processing. High resolution remote sensing data such as Quick Bird and SPOT5 have a lot of characteristics such as spectral, shape, texture and context and so on compared to the other remote sensing data. Though the technology of the remote sensing image classification has made considerable progress, it will result in not only reducing the classification accuracy but also making the spatial data redundant and wasting the resource when the single traditional classification method is applied to the high resolution remote sensing image.The object-oriented image classification concept which is concerted in recent years uses not only spectral information, and also special structure and texture information, even experience and knowledge of the human visual recognition. ECognition follows the concept that important semantic information necessary to interpret an image is not represented in single pixels but in meaningful image objects and their mutual relations. Therefore, the software delivers results noticeably better than conventional methods. It leads to improve high-resolution remote sensing automatic classification accuracy and efficiency.This paper introduces object-oriented classification concept and technique into landscape information obtaining field, which has realized landscape information's obtaining through mufti-scale image division, establishment of class hierarchy structure and semantic structure, and classification role and reference.This research sampled Wu Lingyuan District in Zhang Jiajie and Ziliang Village in Shimen County, which uses SPOTS merging images of 2.5- meter spatial resolution and the method of object-oriented classification to automatically extract information to the construction of land- use database. It was shown in the result that this method can satisfy the demand of precision for extraction of land-use information basically, save time effectively, lighten the working load and provide advanced technological means for the second national land survey.Innovation: This paper first does a research on the information extraction in the construction of land-use database of land and resources survey with object-oriented classification to achieve a flexible output of land-use status. And object-oriented classification method will be first introduced in the experiment which uses high-resolution remote sensing images to calculate the arable ridge coefficient.