Font Size: a A A

A Study On The Classification Of Land Use/land Cover Supported By The ERDAS Software

Posted on:2003-08-07Degree:MasterType:Thesis
Country:ChinaCandidate:M G ZhengFull Text:PDF
GTID:2156360062990028Subject:Physical geography
Abstract/Summary:PDF Full Text Request
At present, there is a far-reaching use of remote sensing (RS) imagine in the field of land use/land cover (IU/LC) research .How to improve the accuracy of RS interpretation in order to promote the utility of RS technology is a urgent problem in RS application. In this paper, using the Landsat TM data, supported by the software of ERDAS IMAGINE 8.4,in the process of LU/LC mapping of zhengzhou city, an inquiration into how to improve the classification accuracy of Bayes Supervised classification method is made from two aspects: the improvement of data quality of the training area and the consideration of the influence of prior probability.The whole paper includes six parts except the preface and postscript:Parti:lt is the RS summary .the RS definition; principle, current situation and trend are simply introduced.Part2: the RS application in LU/LC research was introduced. The present RS classification methods are mainly introduced, including the traditional classification methods and some advanced methods which are yet in the stage of being perfected and argued.Part3: It gives a detailed introduction about the key technology in the process of RS mapping,and a through illumination of the author's train of thought and the technology ,the methods which would be used in the paper.Part 4:lt gives a simple introduction about the character of TM imagine data and the imagine used in part 5.PartS: the whole process of the LU/LC mapping of zhengzhou city is introduced, which is based on the TM data and supported by the ERADS software. In the process, there is a comparison of classification accuracy by common training area with that by the training area processed by majority filter, and a study of variation of the classification accuracy when we consider the influence of the prior probability.PartS: based on the Part 5, the final research result and imperfection are given.
Keywords/Search Tags:Remote sensing, land use, land cover, training area, prior probability
PDF Full Text Request
Related items