A method and system for matching heterogeneous image region features, and computer equipment.
By using a rotation- and scale-independent region feature descriptor method, the problem of suboptimal feature extraction and matching in heterogeneous image matching is solved, achieving efficient matching of corresponding points and adapting to image rotation and scale changes.
CN117830672BActive Publication Date: 2026-05-26WUHAN UNIV
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202311848692.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-29
- Publication Date
- 2026-05-26
- Estimated Expiration
- 2043-12-29
AI Technical Summary
Technical Problem
Existing technologies do not yield ideal results in feature extraction and matching in heterogeneous image matching, especially since the differences between thermal infrared and visible light images lead to poor performance of traditional methods.
Method used
We employ a rotation- and scale-independent region feature descriptor method to obtain feature regions through edge detection, calculate gray-level centroid and principal direction, generate feature vectors, and perform Euclidean distance matching to improve matching accuracy.
Benefits of technology
It effectively narrows the search range of corresponding points, improves the efficiency and accuracy of heterogeneous image matching, and solves the problems of image rotation and scale changes.
✦ Generated by Eureka AI based on patent content.
Abstract
This invention provides a method, system, and computer device for feature matching of heterogeneous images. The method includes acquiring two heterogeneous images, extracting image edges to obtain feature regions as targets for matching; calculating the gray-level centroid of each target region; determining the principal direction of each target region, using the principal direction as the starting direction and clockwise as the positive direction, drawing several rays clockwise from the origin of each region, calculating the Euclidean distance between the corresponding intersection points and the origin of each region, arranging them in the generation order, removing several maximum and minimum values, and normalizing the remaining ordered array to form a feature vector; calculating the Euclidean distance between the feature vectors of each target region, and considering a successful match when the Euclidean distance between the feature vectors of two target regions is less than a preset threshold. This invention effectively solves the region matching problem caused by image rotation and scale changes in heterogeneous images, significantly improving the region matching results.
Need to check novelty before this filing date? Find Prior Art