CN116051638A - Blood vessel positioning device and method based on multi-source heterogeneous information fusion technology - Google Patents
Blood vessel positioning device and method based on multi-source heterogeneous information fusion technology Download PDFInfo
- Publication number
- CN116051638A CN116051638A CN202310024867.XA CN202310024867A CN116051638A CN 116051638 A CN116051638 A CN 116051638A CN 202310024867 A CN202310024867 A CN 202310024867A CN 116051638 A CN116051638 A CN 116051638A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- image
- positioning
- network
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000004927 fusion Effects 0.000 title claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000002792 vascular Effects 0.000 claims abstract description 14
- 238000003709 image segmentation Methods 0.000 claims abstract description 10
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 10
- 230000004807 localization Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 210000001367 artery Anatomy 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010241 blood sampling Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/269—Analysis of motion using gradient-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a blood vessel positioning device and a method based on a multisource heterogeneous information fusion technology in the technical field of positioning, wherein the positioning device comprises a memory, an image acquisition module, a preprocessing module, an image segmentation module and a positioning module which are connected through signals; the method comprises the following steps: s1, an image acquisition module acquires blood vessel image data; s2, extracting a main blood vessel network based on mapping positioning; s3, the preprocessing module enhances the image based on the multi-source heterogeneous information; s4, segmenting the blood vessel image based on the global threshold and the local threshold; s5, positioning based on the recombined vascular network. According to the scheme, the multi-source heterogeneous information is utilized to construct a secondary vascular network, the vascular image is segmented based on the global threshold value and the local threshold value, the vascular network distribution with more accurate parameters can be obtained, the positioning module is utilized to sequentially position the first target blood vessel in the main blood vessel and the second target blood vessel in the tiny blood vessel, and more accurate positioning information can be obtained in the vascular network with complex distribution.
Description
Technical Field
The invention belongs to the technical field of positioning, and particularly relates to a blood vessel positioning device and method based on a multi-source heterogeneous information fusion technology.
Background
In the process of puncturing, operating or automatic blood sampling, proper blood vessels are often required to be selected for operation and blood sampling, the infrared images of the blood vessels are usually acquired when the blood vessels are selected, then the target blood vessels are tracked, the purpose of positioning the blood vessels is achieved, and the subsequent operation or puncturing and blood sampling are facilitated.
For example, chinese patent, publication No. CN107292928A discloses a method and apparatus for locating a blood vessel, the method comprising: acquiring image data obtained by image reconstruction; acquiring image data of a target area where a preset artery to be positioned is located from the image data; and positioning the preset artery to be positioned according to the image data of the target area.
The patent adopts image data of a target area to position the preset artery, the preset artery to be positioned is positioned according to the known characteristics of the preset artery to be positioned, and the accuracy of blood vessel positioning is improved, but because blood vessels of tiny parts such as eyes and the like are tiny, and the blood vessels of the eyes and the veins are distributed in a staggered way, the method is difficult to track the blood vessels of the artery, so that the device and the method for positioning the blood vessels based on the multi-source heterogeneous information fusion technology are provided.
Disclosure of Invention
The invention aims to solve the problem that the arterial blood vessels are difficult to track by adopting the prior art because blood vessels of tiny parts such as eyes and the like are distributed in a staggered way, and provides a blood vessel positioning device and a blood vessel positioning method based on a multi-source heterogeneous information fusion technology.
In order to achieve the above object, the technical scheme of the present invention is as follows: a blood vessel positioning device based on a multi-source heterogeneous information fusion technology comprises a memory, an image acquisition module, a preprocessing module, an image segmentation module and a positioning module which are connected through signals;
the memory is used for storing blood vessel image data;
the image acquisition module is used for acquiring blood vessel image data;
the preprocessing module is used for mapping and extracting main blood vessels and enhanced images;
the image segmentation module is used for reconstructing a vascular network;
the positioning module is used for positioning the position of the target blood vessel.
Further, a vessel positioning method based on a multi-source heterogeneous information fusion technology comprises the following steps:
s1, an image acquisition module acquires blood vessel image data;
s2, a preprocessing module extracts a main blood vessel network based on mapping and positioning;
s3, the preprocessing module enhances the image based on multi-source heterogeneous information, wherein the multi-source heterogeneous information comprises width information and direction information;
s4, an image segmentation module segments the blood vessel image based on the global threshold and the local threshold;
s5, the positioning module performs positioning based on the recombined vascular network.
Further, the step of S2 of extracting the main vessel network based on mapping and positioning specifically includes:
s21, carrying out channel decomposition on the blood vessel image, and extracting a green channel image;
s22, adopting morphological bottom cap transformation: performing a closing operation on the gray image, and subtracting the original gray image
Wherein, the green channel image to be processed is a structural element and the rotation angle of the structural element;
the transformed image is:
wherein R is a set of rotation angles θ;
s23, extracting a highest-order plane by adopting a bit plane cutting method to obtain a binary blood vessel image;
s24, determining the central horizontal coordinate of the main blood vessel network;
s25, determining the central vertical coordinate of the main blood vessel network.
Further, the step S3 of enhancing the image based on the multi-source heterogeneous information specifically includes:
s31, performing multi-scale gray scale stretching on a blood vessel image by adopting multi-scale Hessian matrix filtering;
s32, multidirectional two-dimensional matched filtering is adopted to carry out multidirectional gray scale stretching on the blood vessel image;
s33, fusing the multi-scale stretched image and the multi-direction stretched image.
Further, the step S31 of performing multi-scale gray stretching on the blood vessel image by using multi-scale Hessian matrix filtering specifically includes:
s311, constructing scale space derivative T based on Gaussian function ab ：
Wherein T is an input image, and sigma is a scale factor;
s312, extracting eigenvalue lambda based on Hessian matrix 1 And lambda (lambda) 2 Constructing a linear model Z by a blood vessel similarity filter a (σ)：
Wherein R is B As a characteristic value lambda 1 And lambda (lambda) 2 Is S is lambda 1 And lambda (lambda) 2 And β and c are respectively related to R B And S, and 0 < Z a (sigma) < 1,0 being the lowest similarity, 1 being the highest similarity;
s313, expressing the scale factor sigma by the width of the blood vessel, substituting the scale factor sigma, and calculating Z under each scale a Selecting the maximum Z a The value is the enhancement effect:
f(x,y)＝max[Z a (x,y,σ)]。
further, the S33 fuses the multi-scale stretched image and the multi-directional stretched image:
defining the enhancement result of multi-scale Hessian matrix filtering as f 1 The enhancement result of multidirectional two-dimensional matched filtering is f 2 Contrast analysis of each pixel f ij F of the corresponding position of (2) 1 And f 2 Is selected from the value of f 1 And f 2 The middle maximum value is f ij Final value of (2):
f(i,j)＝max{f 1 (i,j),f 2 (i,j)；i＝1,2,…m,j＝1,2,…n}。
further, the S4 segments the blood vessel image based on the global threshold and the local threshold:
s41, segmenting a main vessel network with a good enhancement effect by adopting a global threshold two-dimensional maximum entropy algorithm;
s42, segmenting the tiny blood vessels with poor enhancement effect by adopting a local threshold moving average algorithm;
s43, combining the main blood vessel network and the tiny blood vessels based on regional connectivity, and obtaining the recombined blood vessel network after denoising.
Further, the S5 performs localization based on the recombinant vascular network:
s51, a positioning module positions a first target blood vessel based on the recombined blood vessel network, wherein the first target blood vessel is positioned in a main blood vessel network;
s52, after the first target blood vessel is positioned, the positioning module adopts a pyramid optical flow tracking method to position a second target blood vessel based on the recombined blood vessel network, and the second target blood vessel is positioned in a tiny blood vessel range similar to the main blood vessel network.
After the scheme is adopted, the following beneficial effects are realized:
compared with the prior art, due to tiny blood vessels at tiny parts such as eyes and the like, the problems that the arterial blood vessels are difficult to track by adopting the prior art are solved, the scheme utilizes multi-source heterogeneous information to construct a secondary blood vessel network, then segments blood vessel images based on a global threshold value and a local threshold value, can obtain blood vessel network distribution with more accurate parameters, and utilizes a positioning module to sequentially position a first target blood vessel in a main blood vessel and a second target blood vessel in tiny blood vessels, so that more accurate positioning information can be obtained in the blood vessel network with complex distribution.
Drawings
Fig. 1 is a schematic block diagram of a vascular positioning device according to an embodiment of the present invention.
Fig. 2 is a flow chart of a blood vessel positioning method according to an embodiment of the invention.
Detailed Description
The following is a further detailed description of the embodiments:
an example is substantially as shown in figures 1-2 of the accompanying drawings:
a blood vessel positioning device based on a multi-source heterogeneous information fusion technology comprises a memory, an image acquisition module, a preprocessing module, an image segmentation module and a positioning module which are connected through signals;
the memory is used for storing blood vessel image data;
the image acquisition module is used for acquiring blood vessel image data;
the preprocessing module is used for mapping and extracting main blood vessels and enhanced images;
the image segmentation module is used for reconstructing a vascular network;
the positioning module is used for positioning the position of the target blood vessel.
The specific implementation process is as follows:
a blood vessel positioning method based on a multisource heterogeneous information fusion technology comprises the following specific steps:
s1, an image acquisition module acquires blood vessel image data;
s2, a preprocessing module extracts a main blood vessel network based on mapping and positioning;
s21, carrying out channel decomposition on the blood vessel image, and extracting a green channel image;
s22, adopting morphological bottom cap transformation: performing a closing operation on the gray image, and subtracting the original gray image
Wherein f is the green channel image to be processed, b θ Is a structural element, and theta is the rotation angle of the structural element;
the transformed image is:
wherein R is a set of rotation angles θ;
s23, extracting a highest-order plane by adopting a bit plane cutting method to obtain a binary blood vessel image;
s24, determining the central horizontal coordinate of the main blood vessel network;
s25, determining the central vertical coordinate of the main blood vessel network.
S3, the preprocessing module enhances the image based on multi-source heterogeneous information, wherein the multi-source heterogeneous information comprises width information and direction information:
s31, carrying out multi-scale gray scale stretching on the blood vessel image by adopting multi-scale Hessian matrix filtering:
s311, constructing scale space derivative T based on Gaussian function ab ：
Wherein T is an input image, and sigma is a scale factor;
s312, extracting eigenvalue lambda based on Hessian matrix 1 And lambda (lambda) 2 Constructing a linear model Z by a blood vessel similarity filter a (σ)：
Wherein R is B As a characteristic value lambda 1 And lambda (lambda) 2 Is S is lambda 1 And lambda (lambda) 2 And β and c are respectively related to R B And S, and 0 < Z a (sigma) < 1,0 being the lowest similarity, 1 being the highest similarity;
s313, expressing the scale factor sigma by the width of the blood vessel, substituting the scale factor sigma, and calculating Z under each scale a Selecting the maximum Z a The value is the enhancement effect:
f(x,y)＝max[Z a (x,y,σ)]；
s32, multidirectional two-dimensional matched filtering is adopted to carry out multidirectional gray scale stretching on the blood vessel image;
s33, fusing the image after multi-scale stretching and the image after multi-direction stretching:
defining the enhancement result of multi-scale Hessian matrix filtering as f 1 The enhancement result of multidirectional two-dimensional matched filtering is f 2 Contrast analysis of each pixel f ij F of the corresponding position of (2) 1 And f 2 Is selected from the value of f 1 And f 2 The middle maximum value is f ij Final value of (2):
f(i,j)＝max{f 1 (i,j),f 2 (i,j)；i＝1,2,…m,j＝1,2,…n}。
s4, an image segmentation module segments the blood vessel image based on the global threshold and the local threshold:
s41, segmenting a main vessel network with a good enhancement effect by adopting a global threshold two-dimensional maximum entropy algorithm;
s42, segmenting the tiny blood vessels with poor enhancement effect by adopting a local threshold moving average algorithm;
s43, combining the main blood vessel network and the tiny blood vessels based on regional connectivity, and obtaining the recombined blood vessel network after denoising.
S5, the positioning module performs positioning based on the recombined vascular network:
s51, a positioning module positions a first target blood vessel based on the recombined blood vessel network, wherein the first target blood vessel is positioned in a main blood vessel network;
s52, after the first target blood vessel is positioned, the positioning module adopts a pyramid optical flow tracking method to position a second target blood vessel based on the recombined blood vessel network, and the second target blood vessel is positioned in a tiny blood vessel range similar to the main blood vessel network.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The foregoing is merely an embodiment of the present invention, and a specific structure and characteristics of common knowledge in the art, which are well known in the scheme, are not described herein, so that a person of ordinary skill in the art knows all the prior art in the application day or before the priority date of the present invention, and can know all the prior art in the field, and have the capability of applying the conventional experimental means before the date, so that a person of ordinary skill in the art can complete and implement the present embodiment in combination with his own capability in the light of the present application, and some typical known structures or known methods should not be an obstacle for a person of ordinary skill in the art to implement the present application. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these should also be considered as the scope of the present invention, which does not affect the effect of the implementation of the present invention and the utility of the patent. The protection scope of the present application shall be subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (8)
1. A blood vessel positioning device based on a multisource heterogeneous information fusion technology is characterized in that: the system comprises a memory, an image acquisition module, a preprocessing module, an image segmentation module and a positioning module which are connected through signals;
the memory is used for storing blood vessel image data;
the image acquisition module is used for acquiring blood vessel image data;
the preprocessing module is used for mapping and extracting main blood vessels and enhanced images;
the image segmentation module is used for reconstructing a vascular network;
the positioning module is used for positioning the position of the target blood vessel.
2. A blood vessel positioning method based on a multisource heterogeneous information fusion technology is characterized by comprising the following steps of: the method comprises the following steps:
s1, an image acquisition module acquires blood vessel image data;
s2, a preprocessing module extracts a main blood vessel network based on mapping and positioning;
s3, the preprocessing module enhances the image based on multi-source heterogeneous information, wherein the multi-source heterogeneous information comprises width information and direction information;
s4, an image segmentation module segments the blood vessel image based on the global threshold and the local threshold;
s5, the positioning module performs positioning based on the recombined vascular network.
3. The vessel localization method based on the multi-source heterogeneous information fusion technology according to claim 2, wherein the vessel localization method is characterized in that: the step S2 of extracting the main blood vessel network based on mapping positioning specifically comprises the following steps:
s21, carrying out channel decomposition on the blood vessel image, and extracting a green channel image;
s22, adopting morphological bottom cap transformation: performing a closing operation on the gray image, and subtracting the original gray image
Wherein, the green channel image to be processed is a structural element and the rotation angle of the structural element;
the transformed image is:
wherein R is a set of rotation angles θ;
s23, extracting a highest-order plane by adopting a bit plane cutting method to obtain a binary blood vessel image;
s24, determining the central horizontal coordinate of the main blood vessel network;
s25, determining the central vertical coordinate of the main blood vessel network.
4. A vessel localization method based on a multi-source heterogeneous information fusion technique as defined in claim 3, wherein: the S3 enhancement image based on the multi-source heterogeneous information specifically comprises the following steps:
s31, performing multi-scale gray scale stretching on a blood vessel image by adopting multi-scale Hessian matrix filtering;
s32, multidirectional two-dimensional matched filtering is adopted to carry out multidirectional gray scale stretching on the blood vessel image;
s33, fusing the multi-scale stretched image and the multi-direction stretched image.
5. The vessel localization method based on the multi-source heterogeneous information fusion technology according to claim 4, wherein the vessel localization method is characterized in that: the step S31 of carrying out multi-scale gray scale stretching on the blood vessel image by adopting multi-scale Hessian matrix filtering specifically comprises the following steps:
s311, constructing scale space derivative T based on Gaussian function ab ：
Wherein T is an input image, and sigma is a scale factor;
s312, extracting eigenvalue lambda based on Hessian matrix 1 And lambda (lambda) 2 Constructing a linear model Z by a blood vessel similarity filter a (σ)：
Wherein R is B As a characteristic value lambda 1 And lambda (lambda) 2 Is S is lambda 1 And lambda (lambda) 2 And β and c are respectively related to R B And S, and 0 < Z a (sigma) < 1,0 being the lowest similarity, 1 being the highest similarity;
s313, expressing the scale factor sigma by the width of the blood vessel, substituting the scale factor sigma, and calculating Z under each scale a Selecting the maximum Z a The value is the enhancement effect:
f(x,y)＝max[Z a (x,y,σ)]。
6. the vessel localization method based on the multi-source heterogeneous information fusion technique according to claim 5, wherein: the S33 fuses the image after multi-scale stretching and the image after multi-directional stretching:
defining the enhancement result of multi-scale Hessian matrix filtering as f 1 The enhancement result of multidirectional two-dimensional matched filtering is f 2 Contrast analysis of each pixel f ij F of the corresponding position of (2) 1 And f 2 Is selected from the value of f 1 And f 2 The middle maximum value is f ij Final value of (2):
f(i,j)＝max{f 1 (i,j),f 2 (i,j)；i＝1,2,…m,j＝1,2,…n}。
7. the vessel localization method based on the multi-source heterogeneous information fusion technique of claim 6, wherein: and S4, segmenting the blood vessel image based on the global threshold and the local threshold:
s41, segmenting a main vessel network with a good enhancement effect by adopting a global threshold two-dimensional maximum entropy algorithm;
s42, segmenting the tiny blood vessels with poor enhancement effect by adopting a local threshold moving average algorithm;
s43, combining the main blood vessel network and the tiny blood vessels based on regional connectivity, and obtaining the recombined blood vessel network after denoising.
8. The vessel localization method based on the multi-source heterogeneous information fusion technique of claim 7, wherein: the S5 is positioned based on the recombined vascular network:
s51, a positioning module positions a first target blood vessel based on the recombined blood vessel network, wherein the first target blood vessel is positioned in a main blood vessel network;
s52, after the first target blood vessel is positioned, the positioning module adopts a pyramid optical flow tracking method to position a second target blood vessel based on the recombined blood vessel network, and the second target blood vessel is positioned in a tiny blood vessel range similar to the main blood vessel network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310024867.XA CN116051638A (en) | 2023-01-09 | 2023-01-09 | Blood vessel positioning device and method based on multi-source heterogeneous information fusion technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310024867.XA CN116051638A (en) | 2023-01-09 | 2023-01-09 | Blood vessel positioning device and method based on multi-source heterogeneous information fusion technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116051638A true CN116051638A (en) | 2023-05-02 |
Family
ID=86123316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310024867.XA Withdrawn CN116051638A (en) | 2023-01-09 | 2023-01-09 | Blood vessel positioning device and method based on multi-source heterogeneous information fusion technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116051638A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116746926A (en) * | 2023-08-16 | 2023-09-15 | 深圳市益心达医学新技术有限公司 | Automatic blood sampling method, device, equipment and storage medium based on image recognition |
-
2023
- 2023-01-09 CN CN202310024867.XA patent/CN116051638A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116746926A (en) * | 2023-08-16 | 2023-09-15 | 深圳市益心达医学新技术有限公司 | Automatic blood sampling method, device, equipment and storage medium based on image recognition |
| CN116746926B (en) * | 2023-08-16 | 2023-11-10 | 深圳市益心达医学新技术有限公司 | Automatic blood sampling method, device, equipment and storage medium based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765363B (en) | Coronary artery CTA automatic post-processing system based on artificial intelligence | |
| CN111797716B (en) | Single target tracking method based on Siamese network | |
| CN107169998B (en) | A kind of real-time tracking and quantitative analysis method based on hepatic ultrasound contrast enhancement image | |
| CN108062525B (en) | Deep learning hand detection method based on hand region prediction | |
| CN106339998B (en) | Multi-focus image fusing method based on contrast pyramid transformation | |
| JP7026826B2 (en) | Image processing methods, electronic devices and storage media | |
| CN109389129A (en) | A kind of image processing method, electronic equipment and storage medium | |
| CN108830818A (en) | A kind of quick multi-focus image fusing method | |
| CN107563328A (en) | A kind of face identification method and system based under complex environment | |
| CN109766796B (en) | Deep pedestrian detection method for dense crowd | |
| Sun et al. | Global Mask R-CNN for marine ship instance segmentation | |
| Yun-Peng et al. | Hand vein recognition based on the connection lines of reference point and feature point | |
| CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
| CN109886170A (en) | A kind of identification of oncomelania intelligent measurement and statistical system | |
| CN116051638A (en) | Blood vessel positioning device and method based on multi-source heterogeneous information fusion technology | |
| Huo et al. | Tongue shape classification integrating image preprocessing and convolution neural network | |
| Das et al. | Human skin region segmentation based on chrominance component using modified watershed algorithm | |
| Mohan et al. | Exudate localization in retinal fundus images using modified speeded up robust features algorithm | |
| CN113706514B (en) | Focus positioning method, device, equipment and storage medium based on template image | |
| CN106960199A (en) | A kind of RGB eye is as the complete extraction method in figure white of the eye region | |
| CN117876690A (en) | Ultrasonic image multi-tissue segmentation method and system based on heterogeneous UNet | |
| Rong et al. | Picking point recognition for ripe tomatoes using semantic segmentation and morphological processing | |
| CN113761995A (en) | Cross-mode pedestrian re-identification method based on double-transformation alignment and blocking | |
| Ma et al. | MSMA-Net: An Infrared Small Target Detection Network by Multi-scale Super-resolution Enhancement and Multi-level Attention Fusion | |
| CN113627255B (en) | Method, device and equipment for quantitatively analyzing mouse behaviors and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230502 |
|
| WW01 | Invention patent application withdrawn after publication |