Method for matching different-source remote sensing images with rotation change and scale difference
A remote sensing image and scale difference technology, which is applied in the field of heterogeneous remote sensing image matching, achieves the effect of small calculation, good effect and high precision
Active Publication Date: 2022-05-31
HARBIN INST OF TECH
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the problems of rotation changes and scale differences between SAR remote sensing images and optical remote sensing images, the present invention provides a heterogeneous remote sensing image matching method with rotation changes and scale differences
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
specific Embodiment approach 1
[0071] Specific implementation mode 1. Combination figure 1 4 to illustrate the present embodiment,
[0072] The invention provides a method for matching heterogeneous remote sensing images with rotation changes and scale differences, comprising the following steps:
[0073] Step 1, using the prior matching point pairs set in the heterogeneous remote sensing image to calculate the initial affine transformation matrix, and using the initial affine transformation matrix to divide the heterogeneous remote sensing image into corresponding image blocks;
[0074] The heterogeneous remote sensing images include SAR remote sensing images and optical remote sensing images;
[0075] Step 2, extract the corner points in the optical remote sensing image block based on the harris operator, and use the HOPC algorithm to determine the coordinate points on the SAR remote sensing image corresponding to the corner point coordinates on the optical remote sensing image block;
[0076] Step 3, t...
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 method for matching heterogenous remote sensing images with rotation change and scale difference, and relates to a heterogenous remote sensing image matching method. The invention aims to solve the problems of rotation change and scale difference in different-source remote sensing image matching. The method comprises the following steps: calculating an initial affine transformation matrix by using a priori matching point pair, dividing a heterogeneous remote sensing image into corresponding image blocks, extracting angular points in optical remote sensing image blocks based on a harris operator, and determining coordinate points on an SAR remote sensing image corresponding to angular point coordinates on the optical remote sensing image blocks by using an HOPC algorithm; intercepting sub-image blocks by taking the matching point pair as a center, obtaining a matching loss value based on a neural network, and further screening correct matching points; screening the matching points according to the loss values of the correct matching points in each pair of matching image blocks, obtaining the contribution degree of an affine transformation matrix according to the loss values, and obtaining a final affine transformation matrix through contribution degree weighting, thereby achieving the matching of the different-source remote sensing images. The method is mainly used for matching different-source remote sensing images.
Description
technical field [0001] The invention relates to a method for matching heterogeneous remote sensing images, which belongs to the field of processing SAR remote sensing images and optical remote sensing images. Background technique [0002] The matching technology of heterogeneous visual images is a key technology widely used in visual navigation, pattern recognition, guidance and terrain measurement of aircraft, remote sensing satellites and missiles. These systems often use sensors with different imaging mechanisms. The so-called heterogeneous image matching is a technique for matching images from different imaging sensors. These images are images of the same scene or object or target formed by different imaging sensors under different lighting conditions and different imaging mechanisms, mainly including visible light images, infrared images, radar images and other image types. Due to the differences in the structure and imaging principle of different types of sensors, the...
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 IPC IPC(8): G06T7/33G06T3/00G06T7/13
CPCG06T7/337G06T7/13G06T2207/10032G06T2207/10044G06T2207/20164G06T2207/20021G06T2207/20081G06T2207/20084G06T3/147
Inventor 张云袁浩轩李宏博冀振元
Owner HARBIN INST OF TECH