Venipuncture target positioning method based on depth camera and near-infrared camera

Abstract

A venipuncture target spot positioning method based on a depth camera and a near-infrared camera comprises the steps that (1) a depth image and a color image of a hand are obtained through the depth camera, and a near-infrared image of the hand is obtained through the near-infrared camera; 2) calculating a transformation matrix of the color image and the near-infrared image, and solving a transformed near-infrared image; (3) obtaining a target puncture target spot by using the converted near-infrared image; and 4) calculating the space coordinates of the target puncture target spot. According to the method, the near-infrared camera is aligned with the depth camera, the depth information of the puncture target spot has the same precision as that of the depth camera, target spot recommendation is performed in combination with the expert model, the optimal puncture target spot can be quickly positioned, the spatial position information of the puncture target spot can be obtained, the target spot recognition precision is improved, and the positioning efficiency is high.

Description

Technical Field

[0001] The present invention relates to the technical field of intravenous puncture target positioning, and particularly to a method for positioning an intravenous puncture target based on a depth camera and a near-infrared camera. Background Art

[0002] Currently, intravenous puncture is usually performed manually by nurses. During the operation, medical staff will select obvious, thick and straight vein sites, such as the back of the hand, forearm or elbow, to reduce patient discomfort and the occurrence of complications, and perform operations such as disinfection and needle insertion. To improve puncture accuracy and reduce patient pain, auxiliary puncture devices have been widely used. These devices can help medical staff better identify the blood vessel area and recommend suitable puncture targets and puncture directions. There are many existing vascular recognition algorithm solutions for auxiliary puncture devices. A common type is to identify venous blood vessels through an ultrasonic probe, which can obtain morphological information of the blood vessels. However, due to the compression of the ultrasonic probe, the three-dimensional information of the blood vessels may change, resulting in recognition errors. Another type is to identify puncture targets based on neural network and image processing technology. This method usually calculates on the two-dimensional image of the blood vessels and ignores the three-dimensional information of the blood vessels, resulting in a certain error in the calculated puncture target in space. Therefore, the puncture accuracy still needs to be improved. Summary of the Invention

[0003] To solve the defects of the prior art, the purpose of the present invention is to provide a method for positioning an intravenous puncture target based on a depth camera and a near-infrared camera, which improves the accuracy of target recognition and quickly locates the best puncture target.

[0004] To achieve the above purpose, the method for positioning an intravenous puncture target based on a depth camera and a near-infrared camera provided by the present invention includes:

[0005] 1) Obtain a depth image and a color image of the hand through a depth camera, and obtain a near-infrared image of the hand through a near-infrared camera;

[0006] 2) Calculate the transformation matrix between the color image and the near-infrared image, and obtain the transformed near-infrared image;

[0007] 3) Use the transformed near-infrared image to obtain the target puncture target;

[0008] 4) Calculate the spatial coordinates of the target puncture target.

[0009] Further, step 2) further includes:

[0010] 21) Extract feature points from the grayscale image of the color image and the near-infrared image respectively;

[0011] Extract descriptors corresponding to each feature point;

[0012] 22) Match the descriptors of the feature points through a matching algorithm to find the pairs of matching feature points in the two images;

[0013] 23) Calculate the homography transformation matrix according to the matching result;

[0014] 24) Use the homography transformation matrix to find the near-infrared image after homography transformation.

[0015] Further, step 3) further includes:

[0016] 31) Enhance the near-infrared image after homography transformation by using an image enhancement algorithm;

[0017] 32) Perform vascular segmentation on the enhanced near-infrared image to obtain the vascular region;

[0018] 33) Extract the vascular centerline from the vascular region;

[0019] 34) Divide the vascular centerline into multiple segments, and use each segmentation point as a candidate target point;

[0020] 35) Use an expert model to screen out the target puncture target points from the candidate target points.

[0021] Further, step 31) further includes:

[0022] Divide the image into multiple image blocks;

[0023] For each image block, calculate its histogram to obtain the number of pixels at each gray level;

[0024] Calculate the cumulative distribution; when calculating the cumulative distribution, limit the contrast;

[0025] Perform equalization processing on the trimmed histogram, and calculate the equalized gray value according to the cumulative distribution probability of each gray level;

[0026] Traverse the image blocks and perform bilinear interpolation between blocks to smoothly transition the contrast change between different blocks;

[0027] Mix the processed image with the original image to obtain the final enhanced image.

[0028] Further, step 35) further includes:

[0029] 51) Collect target point data; the target point data includes: the straightness, diameter, and puncturable length of the blood vessel where the target point is located, and it is scored by senior puncture workers;

[0030] 52) Establish a regression model with the straightness, diameter, and puncturable length of the blood vessel where the target point is located as the model inputs and the target point score as the model output;

[0031] 53) Use the collected target point data to train the regression model to obtain the weight values of the straightness, diameter, and puncturable length of the blood vessel where the target point is located;

[0032] 54) Perform regression analysis on multiple candidate target points within the same image according to the weights calculated in step 53) to obtain the scores of each candidate target point;

[0033] 55) Sort the candidate target points according to their scores;

[0034] 56) Recommend the candidate target point with the highest score as the target puncture point.

[0035] Furthermore, step 4) further includes:

[0036] 61) Obtain the depth value of the corresponding depth image according to the pixel coordinates of the target puncture point;

[0037] 62) Use the depth value and the internal parameters of the depth camera to obtain the three-dimensional spatial coordinates of the target puncture point.

[0038] To achieve the above object, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is configured to execute the computer program stored in the memory to implement the above-described method for positioning a venous puncture target point based on a depth camera and a near-infrared camera.

[0039] To achieve the above object, the present invention also provides a computer-readable storage medium storing a computer program, which is loaded and executed by a processor to implement the above-described method for positioning a venous puncture target point based on a depth camera and a near-infrared camera.

[0040] The method for positioning a venous puncture target point based on a depth camera and a near-infrared camera provided by the present invention has the following beneficial effects compared with the prior art:

[0041] By aligning the near-infrared camera with the depth camera, the depth information of the puncture target point has the same accuracy as the depth camera, and combined with an expert model to recommend target points based on the aligned near-infrared image, the best puncture target point can be quickly located and the spatial position information of the puncture target point can be obtained, thereby improving the accuracy of target point recognition and having high positioning efficiency.

[0042] Other features and advantages of the present invention will be described in the subsequent specification, and will, in part, be obvious from the specification, or will be understood by practicing the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, but do not constitute a limitation to the present invention. In the drawings:

[0044] Figure 1 is a flowchart of a vein puncture target positioning method based on a depth camera and a near-infrared camera according to an embodiment of the present invention;

[0045] Figure 2 is an exemplary algorithm flowchart according to an embodiment of the present invention;

[0046] Figure 3 is an enhanced effect diagram of a hand image according to an embodiment of the present invention;

[0047] Figure 4 is a schematic diagram of the blood vessel segmentation result of a hand image according to an embodiment of the present invention;

[0048] Figure 5 is a schematic diagram of the blood vessel centerline extraction result according to an embodiment of the present invention;

[0049] Figure 6 is a schematic diagram of the blood vessel centerline segmentation result according to an embodiment of the present invention;

[0050] Figure 7 is a schematic diagram of a puncture target according to an embodiment of the present invention;

[0051] Figure 8 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0053] The embodiments of the present invention will be described in more detail below with reference to the drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0054] It should be understood that concepts such as "first" and "second" that may be mentioned in the present invention are only used to distinguish different data or units, and are not used to limit the order or interdependence of the functions performed by these data or units. These terms are only used to distinguish one feature from another. For example, without departing from the scope of the exemplary embodiments, the first feature may be referred to as the second feature, and similarly the second feature may be referred to as the first feature.

[0055] It should be noted that the modifications of "one" and "multiple" that may be mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more". "Multiple" should be understood as two or more.

[0056] Embodiment 1

[0057] In an embodiment of the present invention, a venous puncture target positioning method based on a depth camera and a near-infrared camera is provided, including the following steps: 1) Obtain a depth image and a color image of the hand through the depth camera, and obtain a near-infrared image of the hand through the near-infrared camera; 2) Extract feature points from the grayscale image of the color image and the near-infrared image respectively and perform feature point matching, calculate the homography transformation matrix according to the matching result, and obtain the near-infrared image after homography transformation; 3) Use an image enhancement algorithm to enhance the near-infrared image after homography transformation; 4) Perform vascular segmentation on the enhanced near-infrared image to obtain a vascular region; 5) Extract the vascular centerline from the vascular region; 6) Divide the vascular centerline into multiple segments, and use each segmentation point as a candidate target; 7) Use an expert model to screen out the target puncture target from the candidate targets; 8) Calculate the spatial coordinates of the target puncture target.

[0058] Figure 1 For the flowchart of the venous puncture target positioning method based on a depth camera and a near-infrared camera according to an embodiment of the present invention, the method of the present invention will be further described in detail below Figure 1 in combination with

[0059] First, in step 101, obtain hand images through a depth camera and a near-infrared camera respectively: use the depth camera to obtain a depth image and a color image of the hand (such as the back of the hand, forearm, elbow, etc.), and use the near-infrared camera to obtain a near-infrared image of the hand.

[0060] In an embodiment of the present invention, since the sizes of the respective images are inconsistent, it is necessary to perform soft alignment on the depth image and the color image (while keeping the image content unchanged, adjust the position and angle of the image in a smooth transition manner to reduce obvious splicing traces and visual abruptness).

[0061] In step 102, a homography transformation is performed on the color image and the near-infrared image to obtain the near-infrared image after homography transformation. In this step, the first feature points are extracted from the color image, the second feature points are extracted from the near-infrared image, the first feature points and the second feature points are feature-matched to obtain the matched feature point pairs. According to the matched feature point pairs, Homograph (homography transformation) is applied to obtain the near-infrared image after homography transformation.

[0062] Homograph (homography transformation) is a projective transformation from plane to plane, which maps the points on one plane to another plane through a 3×3 matrix. This transformation preserves collinearity, that is, a straight line remains a straight line after transformation. Homography transformation is widely used in computer vision and image processing, especially in image registration, stitching, and camera pose estimation.

[0063] In the embodiments of the present invention, the specific steps of the homography transformation are as follows:

[0064] 21) Feature points are extracted from the image by using a feature point extraction algorithm (such as SIFT, ORB, SURF algorithm, etc.);

[0065] 22) Descriptors corresponding to each feature point are extracted;

[0066] 23) The descriptors of the feature points are matched by a matching algorithm (such as the KNN nearest neighbor algorithm) to find the matched feature point pairs in the two images;

[0067] 24) The RANSAC algorithm is used to eliminate the wrong matched feature point pairs to improve the accuracy and robustness of the matching;

[0068] 25) Solve the system of equations to calculate the Homograph (homography transformation) matrix: Solve the linear system of equations through at least 4 pairs of matched feature point pairs to calculate the homography transformation matrix;

[0069] 26) Perform a homography transformation on the image.

[0070] Through the above steps, the near-infrared camera is aligned with the depth camera in the way of feature matching, and the position of the puncture target point is mapped to the coordinate system of the depth camera, so as to obtain the depth information of the puncture target point, and this depth information has the same accuracy as the depth camera (ignoring the matching error and camera calibration error).

[0071] In step 103, the near-infrared image after homography transformation is enhanced. An image enhancement algorithm is used to highlight the blood vessel features in the hand image.

[0072] In the embodiments of the present invention, the restricted contrast adaptive histogram equalization method is used to enhance the near-infrared image after the homography transformation, improving the contrast of the blood vessel region in the image to facilitate better blood vessel segmentation. The specific steps are as follows:

[0073] 31) Divide the entire image into multiple small image blocks (such as 8×8 image blocks). This step is to independently process the local regions of the image to better adapt to the local characteristics of the image;

[0074] 32) For each image block, calculate its histogram, that is, count the number of pixels at each gray level;

[0075] 33) Calculate the cumulative distribution. When calculating the cumulative distribution, restrict the contrast to prevent the histogram from being particularly steep. For example, form a set B of the values in the histogram that are higher than a certain threshold a, then each element b in B is changed to a, the sum of the parts higher than a is obtained as c, c is divided by 256 (this 256 refers to the gray level, that is, the gray level ranges from 0 to 255) to obtain d, and d is added to each gray level;

[0076] 34) Perform equalization processing on the trimmed histogram, that is, calculate the equalized gray value according to the cumulative distribution probability of each gray level;

[0077] 35) Traverse the image blocks and perform bilinear interpolation between blocks to smoothly transition the contrast change between different blocks;

[0078] 36) Mix the image after the smooth transition processing with the original image to obtain the final enhanced image. This step is to retain some details and features of the original image while increasing the contrast and clarity of the image. Through the above steps, the restricted contrast adaptive histogram equalization method can suppress noise while enhancing the image contrast, and is particularly suitable for application scenarios such as medical images that require high contrast.

[0079] In step 104, perform blood vessel segmentation on the enhanced hand image to obtain the blood vessel region.

[0080] In medical image processing, blood vessel segmentation is an important part of many clinical diagnoses and treatments. Since blood vessels usually appear as slender and low-contrast structures in images, blood vessel segmentation is one of the key steps in puncture target recommendation. A supervised image segmentation method based on deep learning can be adopted to perform blood vessel segmentation to obtain the blood vessel region from the hand image.

[0081] In step 105, extract the blood vessel centerline from the blood vessel region. In the embodiments of the present invention, blood vessel centerline extraction algorithms such as those based on weak texture enhancement algorithms, curvature algorithms, or topological relationships of blood vessel branches can be used to extract the blood vessel centerline from the blood vessel region.

[0082] In step 106, the blood vessel centerline is segmented to obtain multiple blood vessel segments.

[0083] In step 107, a puncture target is screened from each blood vessel segment by using an expert model. According to the experience of senior puncture workers, the blood vessel puncture rules suitable for puncture are summarized, and finally the nature of the puncture target is obtained. The selection of puncture target characteristics is ranked from high to low in importance as blood vessel filling, high blood vessel straightness, large blood vessel diameter, and large blood vessel puncturable length. According to the blood vessel puncture rules, a linear regression model is established, the feature weights of the candidate targets are calculated, and the scores of each potential target are obtained through weighted summation, and the target with the highest score is selected for recommendation.

[0084] The algorithm steps for screening the puncture target by the expert model are as follows:

[0085] 71) Collect candidate target data, including the straightness, diameter, and puncturable length of the blood vessels where the candidate targets are located, and score them by senior puncture workers;

[0086] 72) Establish a regression model, with the input of the straightness, diameter, and puncturable length of the blood vessels where each candidate target is located, and the output of the model is the target score;

[0087] 73) Use the collected candidate target data to train the regression model to obtain the weight values of the straightness, diameter, and puncturable length of the blood vessels where the candidate targets are located;

[0088] 74) For multiple candidate targets in an image, perform regression analysis according to the weights calculated in step 73, and calculate the scores of each candidate target;

[0089] 75) Sort the candidate targets according to the scores;

[0090] 76) Recommend the candidate target with the highest score as the final target puncture target, and obtain its puncture direction and puncture length. The puncture direction is determined according to the angle between the blood vessel segment and the horizontal direction.

[0091] In order to further improve the accuracy of target recognition, a line segment recognition method based on deep learning can be used to extract the trend characteristics of blood vessels.

[0092] In step 108, calculate the spatial coordinates of the puncture target.

[0093] In the embodiment of the present invention, according to the pixel coordinates of the target puncture target, the depth value of the corresponding depth image is obtained; by using the depth value and the internal parameters of the depth camera, the three-dimensional spatial coordinates of the target puncture target are obtained. This step converts the image coordinates of the puncture target into spatial coordinates (X C , Y C , ZC ), the specific calculation steps are as follows:

[0094] 81) Obtain the internal parameter f of the depth camera x , f y , u0, v0; where f x , f y is the calibration parameter of the focal length; u0, v0 are the coordinates of the reference point on the image, usually taking the center of the image as the reference point.

[0095] 82) Obtain the two-dimensional coordinates of the puncture target on the near-infrared image, index it to the depth image, and thus obtain the depth information Z C , Z C is the depth of the puncture target in space;

[0096] 83) Calculate the spatial coordinate X of the puncture target C , and the calculation formula is: X C = (u - u0) * Z C / f x ; where u is the x coordinate of the puncture target on the near-infrared image, and Z C is the depth of the puncture target in space;

[0097] 84) Calculate the spatial coordinate Y of the puncture target C , and the calculation formula is: Y C = (v - v0) * Z C / f y ; where v is the y coordinate of the puncture target on the near-infrared image, and Z C is the depth of the puncture target in space.

[0098] The venous puncture target positioning method based on a depth camera and a near-infrared camera provided by the present invention is used for image processing of the patient's hand area image. The near-infrared camera and the depth camera are aligned by feature matching, so that the depth information of the puncture target has the same accuracy as the depth camera. Combining image processing and an expert model for target recommendation, it has a relatively fast speed and can quickly obtain the puncture target in three-dimensional space that meets the automatic puncture rules of auxiliary puncture equipment (such as an automatic puncture robot), which can improve the puncture success rate and accuracy of the auxiliary puncture equipment, shorten the operation time; reduce the possibility of secondary puncture, improve the puncture success rate while also improving the work efficiency of medical staff, and also reduce the possibility of local infection, systemic infection, hematoma, blood vessel rupture, nerve injury, etc. for patients due to puncture, thereby improving the medical quality.

[0099] Figure 2 is an exemplary algorithm flowchart according to an embodiment of the present invention, Figures 3 to 7 is a schematic diagram of the hand image processing result according to an example of the present invention. The following will be combined withFigures 2 to 7 Describe the technical effects of the present invention.

[0100] As Figure 2 shown, first, depth images and color images are obtained by a depth camera respectively, and a near-infrared image is obtained by a near-infrared camera. The depth image is used to obtain the spatial coordinates of the target point subsequently, and the color image is used for feature matching with the near-infrared image. The feature matching process includes: performing grayscale processing on the color image to obtain a grayscale image and extracting feature points of the grayscale image based on the SIFT algorithm; similarly, extracting feature points of the near-infrared image based on the SIFT algorithm; using the KNN algorithm to perform feature point matching on the two parts of feature points, and then calculating to obtain a homography matrix and obtaining the near-infrared image after homography transformation through the homography matrix.

[0101] The near-infrared image after homography transformation is enhanced for the hand image through an image enhancement algorithm, highlighting the blood vessel features (as Figure 3 shown). The enhanced hand image is segmented for blood vessels, and it is judged whether there is a blood vessel area. If there is no blood vessel area, the processing of the current near-infrared image ends; if there is a blood vessel area (as Figure 4 the right side in is the segmented blood vessel area), then the blood vessel centerline is extracted from the blood vessel area through a blood vessel centerline extraction algorithm (as Figure 5 shown), and after being segmented by a blood vessel centerline segmentation algorithm (as Figure 6 shown), the trained expert model is used to screen out the best puncture target point, its puncture direction and puncture length (as Figure 7 shown). Finally, the depth information of the puncture target point is obtained based on the depth image, the puncture target point coordinates are converted into spatial coordinates, the algorithm ends, and the positioning of the puncture target point is completed.

[0102] In an embodiment of the present invention, an electronic device is further provided. Figure 8 For the structural schematic diagram of the electronic device according to the embodiment of the present invention, as Figure 8 shown, the electronic device of the present invention includes a processor 801, a memory 802, and a computer program stored in the memory 802 and executable on the processor 801. Among them, when the computer program is read and executed by the processor 801, the steps in the above-mentioned venous puncture target point positioning method based on a depth camera and a near-infrared camera are implemented.

[0103] In an embodiment of the present invention, a computer-readable storage medium is further provided. A computer program is stored in the computer-readable storage medium. Among them, the computer program is set to execute the steps in the above-mentioned venous puncture target point positioning method based on a depth camera and a near-infrared camera when running.

[0104] In this embodiment, the computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, read-only memory (ROM for short), random access memory (RAM for short), external hard drives, magnetic disks, or optical discs that can store computer programs.

[0105] Those of ordinary skill in the art can understand that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A venous puncture target location method based on a depth camera and a near-infrared camera, characterized in that, Including the following steps: 1) Obtain the depth image and color image of the hand through a depth camera, and obtain the near-infrared image of the hand through a near-infrared camera; 2) Calculate the transformation matrix between the color image and the near-infrared image, and obtain the transformed near-infrared image; 3) Use the transformed near-infrared image to obtain the target puncture target; 4) Calculate the spatial coordinates of the target puncture target.

2. The method for venous puncture target location based on a depth camera and a near-infrared camera according to claim 1, characterized in that: The step 2) further includes: 21) Extract feature points from the grayscale image of the color image and the near-infrared image respectively; Extract the descriptor corresponding to each feature point; 22) Match the descriptors of the feature points through a matching algorithm to find the matching feature point pairs in the two images; 23) Calculate the homography transformation matrix according to the matching result; 24) Use the homography transformation matrix to obtain the homography-transformed near-infrared image.

3. The venous puncture target positioning method based on a depth camera and a near-infrared camera according to claim 1, wherein The step 3) further includes: 31) Enhance the homography-transformed near-infrared image by using an image enhancement algorithm; 32) Perform vascular segmentation on the enhanced near-infrared image to obtain the vascular region; 33) Extract the vascular centerline from the vascular region; 34) Divide the vascular centerline into multiple segments, and use each segmentation point as a candidate target; 35) Use an expert model to screen out the target puncture target from the candidate targets.

4. The method for positioning a vein puncture target point based on a depth camera and a near-infrared camera according to claim 3, wherein The step 31) further includes: Divide the image into multiple image blocks; For each image block, calculate its histogram to obtain the number of pixels at each gray level; Calculate the cumulative distribution; when calculating the cumulative distribution, limit the contrast; Perform equalization processing on the trimmed histogram, and calculate the equalized gray value according to the cumulative distribution probability of each gray level; Traverse the image blocks and perform bilinear interpolation between blocks to smoothly transition the contrast change between different blocks; Mix the processed image with the original image to obtain the final enhanced image.

5. The vein puncture target positioning method based on a depth camera and a near-infrared camera according to claim 3, wherein, The step 35) further includes: 51) Collect target data; the target data includes: the straightness, diameter, and puncturable length of the blood vessel where the target is located, and it is scored by senior puncture workers; 52) Establish a regression model, with the straightness, diameter, and puncturable length of the blood vessel where the target is located as the model input, and the target score as the model output; 53) Use the collected target data to train the regression model to obtain the weight values of the straightness, diameter, and puncturable length of the blood vessel where the target is located; 54) Perform regression analysis on multiple candidate targets in the same image according to the weights calculated in step 53) to obtain the score of each candidate target; 55) Sort the candidate targets according to the scores; 56) Recommend the candidate target with the highest score as the target puncture target.

6. The vein puncture target positioning method based on a depth camera and a near-infrared camera according to claim 1, wherein, The step 4) further includes: 61) According to the pixel coordinates of the target puncture target, obtain the depth value of the corresponding depth image; 62) Use the depth value and the internal parameters of the depth camera to obtain the three-dimensional spatial coordinates of the target puncture target.

7. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor is used to execute the computer program stored in the memory to implement the steps of the method for locating a venous puncture target based on a depth camera and a near-infrared camera according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which is loaded and executed by a processor to implement the steps of the venous puncture target positioning method based on a depth camera and a near-infrared camera as described in any one of claims 1 to 6.

Images