Inclined image matching method and device, computer equipment and readable storage medium
A technology of oblique image and matching method, which is applied in the field of computer vision, can solve the problems of not being able to know the rotation angle of oblique image, low robustness, and low efficiency of oblique image
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] figure 1 It is a flow chart of an oblique image matching method provided in Embodiment 1 of the present invention, and the method includes the following steps:
[0052] Step S11: Using the reference image and the camera tilt angle, filter out a plurality of related images intersecting with the reference image from the plurality of oblique images through a preset filtering algorithm.
[0053] In the embodiment of the present invention, oblique image matching is a necessary step in the operation process of drones in the fields of image stitching, high-precision stereoscopic mapping, 3D city model reconstruction, and image retrieval, and it is also a key technology in the field of computer vision. Among them, the above-mentioned UAV includes multiple perspective cameras, such as the following perspective cameras, front perspective cameras, rear perspective cameras, left perspective cameras, and right perspective cameras, etc. Image stitching refers to the splicing of images ...
Embodiment 2
[0066] figure 2 It is a flow chart of screening related images provided by Embodiment 2 of the present invention, including the following steps:
[0067] Step S21: Calculate the outer orientation element of the oblique image according to the tilt angle of the camera and the initial outer orientation element of the down-looking image.
[0068] In the embodiment of the present invention, the above-mentioned outer orientation elements include a straight line element, a heading angle element, a pitch angle element and a roll angle element. The outer orientation elements of the remaining four viewing angles can be calculated according to the camera tilt angle and the initial outer orientation elements of the downward-looking image. Wherein, the remaining four viewing angles include a left viewing angle, a right viewing angle, a front viewing angle and a rear viewing angle.
[0069] Step S22: Calculate the coverage area of the oblique image according to the outer orientation el...
Embodiment 3
[0074] image 3 It is a flow chart for calculating the rotation angle provided by Embodiment 3 of the present invention, including the following steps:
[0075] Step S31: performing a down-sampling process with a preset ratio on the reference image and the related image.
[0076] In the embodiment of the present invention, the preset ratio of the down-sampling process is generally set to be 1000 for the longest side, and then the down-sampling is performed according to the aspect ratio of the original image. Assuming that the width of the image is w and the height is h, the sampling formula is: if w>h, the sampling ratio is If w
[0077] Step S32: After the down-sampling process, use the ASIFT algorithm to extract initial matching feature points from the reference image and the related image.
[0078] In the embodiment of the present invention, when using the ASIFT algorithm to extract matching feature points, the parameter setting of the ASIFT algorithm may be n=5.
[00...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


