Supervision change detection method of high-resolution remote sensing images
A technology of change detection and remote sensing images, applied in the field of remote sensing, can solve the problems of reducing the accuracy of change detection and affecting the results of change detection
Active Publication Date: 2014-04-16
WUHAN UNIV
View PDF6 Cites 13 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, the classification accuracy of the images in the two periods seriously affects the accuracy of the change detection results, and the pixel-level classification method is prone to produce "salt and pepper" noise for high-resolution images, thereby reducing the accuracy of change detection
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0040] The embodiment uses the SPOT5 satellite data acquired in two periods for experiments. The size of the experimental data is 1120×480 pixels, and the acquisition time is April 2008 (t1) and February 2009 (t2). The experimental data is based on the multispectral image generated by the fusion of panchromatic band (2.5 meters) and multispectral band (10 meters). Its spatial resolution is 2.5 meters and contains three bands.
[0041] please see figure 1 , diagram 2-1 , Figure 2-2 with Figure 2-3 , the technical scheme adopted in the present invention is: a method for supervised change detection of high-resolution remote sensing images, comprising the following steps:
[0042] Step 1: Perform image registration on the multi-band high-resolution remote sensing images of the two periods.
[0043] Step 2: Superimpose th...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a supervision change detection method of high-resolution remote sensing images. The supervision change detection method comprises overlaying two different periods of images to serve as a period of images; performing segmentation on the overlaid images on the basis to generate segmentation image spots which comprise the homogenous area and performing pixel level classification on the overlaid images according to the spectral information to generate the pixel level change detection result; performing fusion on the image spots generated by the segmentation and the pixel level change detection result by a voting method according to a space and spectrum combined method to obtain the final change detection result. According to the supervision change detection method of the high-resolution remote sensing images, the classification after the two periods of images are overlaid and the space and spectrum combined theory are introduced into the supervision change detection and accordingly the effect on the change detection result of the classification accuracy is weakened and meanwhile salt and pepper noise in the change detection result is greatly eliminated.
Description
technical field [0001] The invention relates to the field of remote sensing, in particular to a method for supervised change detection of high-resolution remote sensing images, in particular to a method for supervised change detection of high-resolution images that combines spatial and spectral information by using primary classification. Background technique [0002] In the field of remote sensing, change detection technology has been widely used in land cover change detection, disaster detection and forest, agricultural monitoring and other fields. Since supervised change detection can provide the change category, that is, the change from "what to what", and can weaken the influence of the atmosphere on the change detection results, it has been widely used. [0003] Traditional supervised change detection performs pixel-level classification on remote sensing images of the same area acquired in two periods, and then compares the classification results to detect surface chan...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06K9/46
Inventor 史文中郝明
Owner WUHAN UNIV