Abstract
Change detection method is an efficient way in the aim of land cover product updating on the basis of the existing products, and at the same time saving lots of cost and time. Considering the object-oriented change detection method for 30m resolution Landsat image, analysis of effect of different segmentation scales on the method of the object-oriented is firstly carried out. On the other hand, for analysing the effectiveness and availability of pixel-based change method, the two indices which complement each other are the differenced Normalized Difference Vegetation Index (dNDVI), the Change Vector (CV) were used. To demonstrate the performance of pixel-based and object-oriented, accuracy assessment of these two change detection results will be conducted by four indicators which include overall accuracy, omission error, commission error and Kappa coefficient.
Highlights
Detecting regions of change in images of the same scene taken at different times is of widespread interest due to a large number of applications in diverse disciplines (Richard, 2014a)
Considering large range of Land cover products, such as Globe Land30 of China, or the National Land Cover Database (NLCD) of U.S are made on the basis of 30m resolution image, we concentrate on discussing the application of object-oriented change detection method in the medium resolution remote sensing image in this paper by comparing the change detection accuracy of pixel-based with accuracy of object-oriented
In the process of object-oriented change detection for 30m resolution image, we adopt the approach of over-segmentation for the multi-temporal object change detection, which means that we use smaller scale for all kinds of classed of Land cover instead of the optimal segmentation scale for each kind of class
Summary
Detecting regions of change in images of the same scene taken at different times is of widespread interest due to a large number of applications in diverse disciplines (Richard, 2014a). Change detection algorithms of remote sensing image can be divided into two categories: pixel-based and object-oriented, according to the minimum processing unit (Zhenjian, 2014a). Considering large range of Land cover products, such as Globe Land of China, or the National Land Cover Database (NLCD) of U.S are made on the basis of 30m resolution image, we concentrate on discussing the application of object-oriented change detection method in the medium resolution remote sensing image in this paper by comparing the change detection accuracy of pixel-based with accuracy of object-oriented
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
