An Imaging Coordinate Correction Method Based on Matching Error Suppression
A technology of imaging coordinates and correction methods, applied in the field of geometric correction, can solve the problems of complex methods, low scene adaptability, blurred image contours, etc., to reduce interference, reduce calibration errors, and improve parameter accuracy and model accuracy. Effect
Active Publication Date: 2021-08-06
HEFEI UNIV OF TECH
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the method is complex, the scene adaptability is low, and the image outline is somewhat blurred
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
[0086] Such as figure 1 As shown, an imaging coordinate correction method based on matching error suppression includes the following steps: background area selection, interest point matching in the background area, geometric correction modeling based on background, noise matching point suppression based on geometric correction error, based on Geometry-correct modeling and foot-point fine-tuning for noise-matched point suppression;
[0087] In the background area selection, input the measurement image and multiple reference images, and select the background area in the measurement image;
[0088] The interest point matching in the background area extracts and retains the interest points in the measurement image and the background area of the reference image according to the intensity of the Harris corner points, extracts the SIFT interest point descriptor, and calculates the SIFT point pairs of the two images according to the Euclidean distance Describe the sub-similarity ma...
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 imaging coordinate correction method based on matching error suppression, which manually marks the background area of a measurement image and obtains its matching point pairs. And based on the matching point pairs, the geometric correction mapping matrix is modeled by the iterative error method, which improves the accuracy of the experimental results. Accordingly, the noise matching points are detected and suppressed by using the Euclidean distance and the threshold. Iterative error fitting is used again to solve the new mapping matrix and correct the reference image. Fuse the measured image with the edge binary mask to obtain the foot coordinates. Then, the edge of the measured image is fused with the geometrically corrected reference image, and the reference image for foot alignment is obtained by horizontal translation according to the foot point error. The invention has the advantages of intuition, effectiveness, strong robustness, and high scene adaptability. It can not only solve the interference of background information, complex structure mixed information, and foot neighbor structure information in the alignment calibration of imaging coordinates, but also solve the problem of multiple reference frames. Inconsistencies in image fitting results.
Description
technical field [0001] The invention relates to the technical field of geometric correction, in particular to an imaging coordinate correction method based on matching error suppression. Background technique [0002] Geometric correction is error correction for geometric distortion. In practical applications, such as registration of multi-spectral and multi-temporal images, mapping of remote sensing images, and calibration of human bodies in the scene to solve the problem of height measurement, etc., due to the ambiguity of the image and the amount of calculation, the geometric correction The correctness faces many challenges. The commonly used image geometric correction methods include spatial transformation method and grayscale interpolation method. The imaging coordinate correction method based on matching error suppression generally does not require complex preprocessing of the image, but uses some statistical information of the image itself to measure the similarity of...
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 Patents(China)
IPC IPC(8): G06T5/00G06T7/13G06T7/136G06T7/33
CPCG06T7/13G06T7/136G06T7/337G06T5/80
Inventor 杨兴明谢昭张鹿鸣吴克伟纪松孙永宣周亚辉童赟
Owner HEFEI UNIV OF TECH