Single end-point characteristic description based line segment matching method
A feature description and line segment matching technology, applied in the field of computer vision, can solve the problems of lack of correctness check, poor robustness, large amount of calculation, etc., and achieve the effect of correctness verification, robustness improvement, and elimination of wrong matching
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0019] There are currently two images to be matched with the same structure locally. The process of using the present invention to carry out line segment matching of two images is as follows: figure 1 shown.
[0020] Step 1: Input two images to be matched.
[0021] The second step: construct the scale space. Using the method in the SIFT algorithm, the two images to be matched are successively down-sampled five times to construct an image pyramid.
[0022] The third step: LSD line segment detection. Use the LSD algorithm to detect line segments in each layer of the two image pyramids to be matched, and remove the i-th layer image whose length is less than TH i line segment, TH i =20 / i, 1≤i≤5, LEN_TH=20.
[0023] Step 4: Construct a collection of feature description units. For each line segment such as P 1 P 2 Construct two feature description units: one with endpoint P 1 Main feature point {P M =P 1 ,P A =P 2}, the other end point P 2 Main feature point {P M =P ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com