A Study of Information Extraction Based on QuickBird Data --Taking the Extraction of Cultivated Land for an Example

Understanding timely of the changes in land resources, rapid and accurately access to land information has become one of the important foundations that solved the conflict between man and land. This paper selects a region study in the west of Chengdu, application of "QuickBird" data, measurement and statistics and other auxiliary data, combined with Erdas Imagine, eCogntion and ArcView and other software platform for information extraction of the cultivated land. The paper has a non-supervised classification method, respectively, maximum likelihood classification and object-oriented classification extraction of cultivated land area, and the error evaluation and accuracy Analysis. The results show that the study area results in good agreement with the field survey results, proved the "Quickbird" data and object-oriented classification of cultivated land in the effectiveness of information extraction, provide a certain reference value of the remote sensing information for land remote sensing information extraction research.