Aerial image feature point matching diffusion recursive calibration method
A feature point matching and aerial image technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as unstable effects, achieve the effects of improving anti-interference ability, improving efficiency, and simplifying complexity
Active Publication Date: 2019-10-25
SOUTHEAST UNIV
View PDF3 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The biggest interference in aerial imagery is the brightness change caused by light. The Sift-like algorithm cannot overcome it very well. Although the Mean Shift algorithm has advantages, the effect is unstable.
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
[0033] The technical solutions of the present invention will be further introduced below in conjunction with specific embodiments.
[0034] This specific embodiment discloses an aerial image feature point matching diffusion recursive calibration method, such as figure 1 shown, including the following steps:
[0035] S1: divide the density unit for the reference image and the matching image respectively;
[0036] S2: Perform the following operations on both the reference image and the matching image: set a threshold n according to the number of feature points in the density cells, mark the density cells with the number of feature points ≥ n as high-density cells, and mark other density cells as low-density cells ; The total number of high-density cells does not exceed 20% of the sum of the high-density cells and low-density cells;
[0037] S3: Perform the following operations on both the reference image and the matching image: extract the connected high-density cells to obtai...
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 an aerial image feature point matching diffusion recursion calibration method. The method comprises the following steps: S1, respectively dividing density units for a referenceimage and a matching image; S2, executing the following operations on the reference image and the matching image: setting a threshold n according to the number of the feature points in the density units, marking the density units with the number of the feature points greater than or equal to n as high-density units, and marking the other density units as low-density units; S3, executing the following operations on the reference image and the matching image: extracting the communicated high-density units to obtain a high-density region of the aerial image; S4, performing the following operations on the reference image and the matching image: performing position marking on all high-density regions; and S5, matching the high-density regions of the reference image and the matched image. According to the aerial image feature point matching diffusion recursion calibration method, the anti-interference capability and efficiency are effectively improved.
Description
technical field [0001] The invention relates to the field of aerial photogrammetry, in particular to an aerial image feature point matching diffusion recursive calibration method. Background technique [0002] The influence of light and darkness and the angle rotation when the aircraft is shooting makes it more difficult to match the feature points in the aerial triangulation image. In order to solve this problem, the present invention proposes a region calibration algorithm based on the distribution density of feature points, so that the feature point matching algorithm has scale invariance and enhances the matching robustness. There are many ways to make the feature point matching have scale invariance. There are mainly two ways to explore the feature direction represented by the Sift operator and to find the overall feature information of the image represented by the Mean Shift algorithm. The biggest interference in aerial images is the brightness change caused by light,...
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): G06T7/33G06T7/11G06K9/62
CPCG06T7/33G06T7/11G06F18/22
Inventor 张志伟周文宗胡伍生沙月进
Owner SOUTHEAST UNIV