SAR image multi-target fuzzy change detection method based on decomposition
A change detection and multi-target technology, applied in image enhancement, image data processing, instruments, etc., can solve the problems of speckle noise processing, weak image analysis ability of denoising, etc., to improve robustness, improve discrimination ability, and better detection effect of effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] This embodiment provides a method for detecting multi-target fuzzy changes in SAR images based on decomposition, see figure 1 , the method includes:
[0061] S1 obtains two SAR images of the same area in different periods through remote sensing satellites, and preprocesses the original images to obtain two SAR remote sensing satellite images with the same size.
[0062] S2 analyzes from the two conflicting perspectives of retaining details and removing noise, and constructs the corresponding target difference image. The logarithmic ratio operator is used to obtain the differential image that retains image information to the greatest extent, and wavelet filtering and a frequency domain-based saliency detection method are used to obtain the denoised differential image.
[0063] S3 constructs its objective function in an appropriate way according to different objective characteristics. We use FCM as the objective function for preserving details and FLICM as the objective...
Embodiment 2
[0095]This embodiment provides a decomposition-based two-target fuzzy change detection method. This example uses the detection results of the Yellow River dataset as an example for illustration, which includes two SAR images collected in June 2008 and June 2009, respectively. These are two SAR images that capture the changes in the area near the mouth of the Yellow River. This dataset records land surface changes due to cultivated land in the area near the mouth of the Yellow River.
[0096] In the embodiment, the experimental results are evaluated from two angles: one is the final binary change detection map, and the other is analysis using some quantitative means.
[0097] Five metrics were used to evaluate the effectiveness of the algorithm, including false positives (FP), false negatives (FN), total errors (OE), percent correct classification (PCC) and Kappa coefficient. Among them, assuming that the total number of pixels in the image is N, the number of false positives ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


