Optimized feature matching method based on Harris corner detection in oblique photography

A technology of oblique photography and corner detection, which is applied in image data processing, instruments, calculations, etc., can solve the problems of low matching efficiency of SIFT algorithm, affect the accuracy of true 3D model, and long process of spatial triangulation, and achieve spatial triangulation Excellent calculation effect, improved matching accuracy, and uniform distribution

Pending Publication Date: 2022-02-22
大连云海创新科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The aerial triangulation calculation process of oblique photographic post-processing software often uses the SIFT algorithm, such as figure 1 As shown, but due to the low matching efficiency of the SIFT algorithm, the aerotriangulation process is longer, and the accuracy of the aerotriangulation directly affects the accuracy of the true 3D model

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Optimized feature matching method based on Harris corner detection in oblique photography
  • Optimized feature matching method based on Harris corner detection in oblique photography
  • Optimized feature matching method based on Harris corner detection in oblique photography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The optimized feature matching method based on Harris corner detection of the present invention, such as figure 2 As shown, the principle mainly includes multi-scale Harris corner detection feature points, the BRISK operator describes the extracted feature points, and then uses the nearest neighbor distance ratio and two-way matching fusion matching algorithm to perform preliminary matching on the extracted feature point pairs, and finally adopts The RANSAC algorithm purifies the feature matching point pairs.

[0035] (1) Feature point detection:

[0036] The optimization algorithm uses the Harris corner detection algorithm in the feature point detection, but because the feature points extracted by the Harris corner detection algorithm are mainly based on the extreme points of the main curvature of the edge feature of the single-scale space image, it does not have scale invariance. The present invention establishes a multi-scale Harris corner point detection algorithm...

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

No PUM Login to view more

Abstract

The invention discloses an optimized feature matching method based on Harris corner detection in oblique photography. The method comprises the following steps: (1) feature point detection; (2) feature description; (3) feature matching; (4) RANSAC algorithm purification. Compared with a series of feature point detection operators, the number of feature points extracted by an optimization algorithm is the maximum, and the distribution is more uniform; by comparing an optimal matching algorithm with similar matching algorithms, the matching precision of the optimal matching algorithm is obviously improved compared with that of the similar matching algorithms; compared with an SIFT algorithm applied in the mainstream oblique photography modeling software aerial triangulation calculation process, the optimization algorithm proves an obviously higher positive matching logarithm than that of the SIFT algorithm in different earth surface states, and the aerial triangulation calculation effect is better; besides, the SIFT algorithm is high in mismatching rate under the condition of similar terrains, however, the algorithm can still ensure the matching effect; in addition, the operation speed of the optimization algorithm is higher than that of the SIFT algorithm.

Description

technical field [0001] The invention relates to the technical field of urban three-dimensional modeling. Background technique [0002] With the continuous expansion and extension of urban space by human beings, many cities have begun to vigorously promote the construction of digital cities. In order to further improve the rational layout and management functions of urban space, 3D modeling of large-scale cities has gradually become a new research hotspot. [0003] The current mainstream urban 3D modeling methods mainly include: traditional artificial 3D modeling, 3D laser scanning technology, airborne Lidar technology and aerial photogrammetry. However, as people continue to improve the time and accuracy requirements for 3D modeling, the traditional 3D modeling of cities cannot meet the needs of 3D modeling of cities: traditional artificial 3D modeling has problems such as long modeling time, high cost and generated 3D The model lacks geographic information and other defec...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/33
CPCG06T7/33G06T2207/10004G06T2207/20016G06T2207/20164
Inventor 吴立志谭玥
Owner 大连云海创新科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap