Tubular structure rapid tracking method based on curvature regularization perception grouping

A tubular structure and curvature technology, applied in the field of image processing, can solve a large number of problems such as manual interaction, time-consuming and labor-consuming, short cutting, etc., to achieve the effect of reducing manual interaction and improving tracking speed

Inactive Publication Date: 2021-10-22
SHANDONG ARTIFICIAL INTELLIGENCE INST
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still some limitations. The geodesics obtained by this type of model have the absolute value of the overall curvature and the minimum characteristic, while most tubular structures only have the minimum absolute value of the local curvature rather than the overall curvature and minimum characteristics, which in turn leads to the short cut problem. Therefore, the scope of application of this type of model needs to be further improved.
The limitations of the current geodesic model lead to: 1) Although interactive segmentation is robust, it requires a lot of manual interaction, which is time-consuming and labor-intensive; 2) It is difficult to effectively track structures with long Euclidean distances, large tortuousness, or complex backgrounds

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Step b) includes the following features:

[0058] b-1) by formula Calculate the response ψ(x,r) of the optimal directional gradient flux filter, where G σ is a Gaussian kernel function with standard deviation σ, for the core for G σ The Hessian matrix, r is the radius, r∈[R min , R max ], [R min , R max ] is the radius range, x is the point in the image, * is the convolution operator, is a circular area with radius r.

[0059] b-2) Decompose the response ψ(x,r) into eigenvalues ​​λ 1 (x,r) and λ 2 (x,r), via the formula Calculate the tubular structure probability map ψ(x), through the formula Calculate the eigenvalue λ 1 (x,r) corresponds to the optimal scale ρ(x).

[0060] b-3) by formula Build orientation-lifted spaces Realize the mapping of two-dimensional plane curves into three-dimensional space, Ω is the two-dimensional image space of image I, is the direction space, by formula Construct points in orientation-lifted space point It i...

Embodiment 2

[0063] Step c) comprises the following steps:

[0064] c-1) Realize the centerline pre-segmentation of the binary image of the tubular structure through skeletonization, and then remove the intersection points and branch points of the skeleton structure to obtain skeleton fragments that do not intersect each other.

[0065] c-2) Use the threshold method to remove the skeleton segment whose length is less than a given threshold, and obtain the pre-segmented centerline segment as N is the number of pre-segmented centerline segments.

Embodiment 3

[0067] Using the Euclidean distance between the pre-segmented centerline segments to search for adjacent pre-segmented centerline segments in step d) includes the following steps:

[0068] d-1) For each pre-segmented centerline segment from The two ends extend the length ι outward along the tangent direction to obtain the extended pre-segmented centerline segment

[0069] d-2) by formula Calculate the pre-segmented centerline segment Neighborhood M i , where τ is a given threshold.

[0070] d-3) By formula Finding and Pre-Segmenting Centerline Segments Adjacent pre-divided centerline segments For pre-segmented centerline segments The extended pre-segmentation centerline segment, j∈[0,N] and i≠j, φ is an empty set.

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

A tubular structure rapid tracking method based on curvature regularization perception grouping is disclosed. According to the method, prior information of local smooth change of tubular structure features is introduced into a model, and curvature regularization geodesic line model beam area curvature change is used for solving the problem of short cutting existing in tubular structure center line tracking of a geodesic line model; and a traditional geodesic line model-based pixel-by-pixel tracking mode is expanded into a curvature constraint-based pre-segmentation center line segment grouping tracking mode, so that the human interaction is effectively reduced, and the tracking speed and the accuracy in complex structure tracking are greatly improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fast tracking method for tubular structures based on curvature regularization perceptual grouping. Background technique [0002] Tubular structure tracking is one of the most challenging problems in the field of image processing and computer vision. Tubular object detection is achieved by searching the centerline of slender structures. Tubular structures are widely distributed, such as blood vessels in medical images and roads and rivers in remote sensing images. The morphological structure is complex and changeable, and it is difficult to track. It is difficult for current computer-aided technology to track tubular structures effectively and quickly, while manual tracking is time-consuming and subjective. powerful. [0003] The geodesic model is an effective shortest path search method, which needs to provide points as boundary conditions, and model the centerline of...

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): G06T7/136
CPCG06T7/136G06T2207/20112G06T2207/10012
Inventor 刘丽陈达舒明雷
Owner SHANDONG ARTIFICIAL INTELLIGENCE INST
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