An image registration method based on BRISK algorithm
An image registration and algorithm technology, applied in image analysis, image data processing, calculation, etc., to achieve fast speed, high image registration rate, and time-saving effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Examples
Embodiment Construction
[0021] This embodiment adopts the following technical solutions: its registration method is as follows:
[0022] Step 1: Extraction of BRISK features:
[0023] 1.1. Scale space key point extraction: extend FAST focus detection from image plane to scale space, and use FAST score to search for maximum value in image plane and scale space at the same time; the scale space pyramid of BRISK contains n surface layers c i and n inner layers d i , where n is a setting parameter, i={0,1,…,n-1}; for the original image c 0 Continuous half-sampling to get all surface layers, inner layer d 0 By modifying the original image c 0 It is obtained by downsampling by 1.5 times, and the other inner layers are obtained by continuous half-sampling d0; therefore, a 2 n layer pyramid;
[0024] 1.2. Extraction of BRISK key points: Use a string of binary numbers to identify, select a center point around the key point, and use the center point to make a circular component;
[0025] Step 2: Perform ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More