A catheter length measurement method for digital production

Through computer vision processing algorithms and image processing technology, non-contact and batch online measurement of catheter length is realized, solving the problems of high labor costs and low automation in the prior art, and improving the efficiency and quality of catheter production.

CN115704669BActive Publication Date: 2025-08-26SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110937550.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-16
Publication Date
2025-08-26
Estimated Expiration
2041-08-16

AI Technical Summary

Technical Problem

The existing catheter length measurement methods are high in the aerospace field, low in labor costs, and high error detection rates, which cannot meet the needs of digital production.

Method used

Using computer vision processing algorithms, the catheter edge profile is obtained by taking images at both ends of the catheter and performing image processing, and non-contact catheter length measurement is achieved using industrial cameras and photoelectric sensors, and the actual length is calculated based on system calibration.

Benefits of technology

It realizes non-contact, batch online measurement of catheter length, improves measurement efficiency and stability, is suitable for any specification catheter, and improves the degree of automation and manufacturing quality of catheter production.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115704669B_ABST
    Figure CN115704669B_ABST
Patent Text Reader

Abstract

This invention discloses a catheter length measurement method for digital production. The method comprises the following steps: a photoelectric sensor synchronously triggers two industrial cameras to capture images of the catheter end. The true catheter edge is obtained through methods such as region of interest extraction, catheter edge recognition, discontinuous edge completion, backlight edge removal, and ambient noise removal. Elliptical edge coarse and fine extraction are then performed to obtain the correct catheter elliptical edge contour. Roundness is analyzed and the catheter end face center is located. Finally, catheter inclination correction is performed based on the slope of the straight segment contour. Combined with system calibration parameters, the catheter length data is calculated. This method can achieve catheter length measurement during digital catheter production, with high measurement speed, high automation, good versatility, and good stability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of computer vision and discloses a catheter length measurement method oriented to digital production. Background Art

[0002] Conduits are widely used in aerospace, aviation, automotive, and other manufacturing industries to transport working media such as gases and liquids, and are a crucial component of engine systems. To accommodate the confined space within the engine and meet the demands of miniaturization, conduits must be bent from straight tubes into complex, three-dimensional curved tubes, allowing them to be assembled within the engine without interference. The manufacturing accuracy of curved tubes is a crucial factor affecting engine performance, and the quality of straight tube production directly determines their precision. Therefore, high-quality straight tube production is fundamental to engine performance. Length measurement is a crucial step in straight tube production, impacting engine production efficiency and quality.

[0003] Currently, in the aerospace industry, the method for measuring catheter length still relies on traditional contact measurement, primarily the gauge method and the three-coordinate method. The gauge method uses a dedicated measuring tool, such as a vernier caliper, to obtain length information by clamping it on the end of the catheter. This method is significantly influenced by the operator's subjective judgment, has a high probability of false detection, and different catheter specifications require different types of dedicated gauges. The three-coordinate method uses a three-dimensional coordinate measuring machine to obtain the three-dimensional coordinates of key points on the surface of the pipe and calculate its length through fitting analysis. This method is complex to operate, requires high technical skills from the operator, and has a limited measurement range. Therefore, existing catheter length measurement methods have high labor costs, low automation levels, and high error rates. They cannot meet the needs of today's digital production and fundamentally hinder the development of manufacturing technology in the aerospace industry. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the technical problem to be solved by the present invention is to provide a catheter length measurement method for digital production. This method uses computer vision processing algorithms to achieve non-contact, batch online catheter length measurement, which can effectively improve the level of digital production of catheters.

[0005] The technical solution adopted by the present invention to achieve the above-mentioned purpose is: a catheter length measurement method for digital production, comprising the following steps:

[0006] A catheter length measurement method for digital production is proposed. The method captures images of both ends of the catheter to be inspected and processes the images to obtain the catheter edge contour. The actual catheter length is calculated based on the catheter pixel distance. The method specifically includes the following steps:

[0007] S1 station detection and movement steps: When the catheter to be inspected is placed on the inspection station, the photoelectric sensor installed on the inspection station outputs a signal to control the industrial camera on the slide to move to the top of the two ends of the catheter to be inspected, and the backlight source on the slide moves to the bottom of the two ends of the catheter to be inspected;

[0008] S2 trigger shooting step: synchronously trigger the industrial camera to collect images of the left and right ends of the catheter respectively;

[0009] S3 image processing step: perform the following image processing on the left and right end original images respectively to obtain the pixel distance of the catheter length within the camera field of view;

[0010] i. Extract and preprocess the catheter edge image to remove ambient noise and obtain the catheter sub-pixel edge;

[0011] ii. Analyze the catheter edge image and extract the center point of the catheter end face;

[0012] iii. Correct the catheter inclination and calculate the pixel distance of the catheter length within the camera's field of view;

[0013] S4 catheter length calculation steps: Based on the catheter length pixel distance within the field of view of the left and right cameras, combined with the camera distance and camera pixel size parameters obtained by system calibration, the actual catheter length is calculated.

[0014] The extracting and preprocessing of the catheter edge image includes:

[0015] S3.1: In the image, a rectangular area is intercepted based on the fixed position of the catheter end surface under the camera's view as the region of interest;

[0016] S3.2: Use the Canny operator to perform sub-pixel edge extraction on the region of interest and complete adjacent and discontinuous edges;

[0017] S3.3: Set the difference threshold between the maximum and minimum values ​​of the sub-pixel edge row coordinates to remove the edge contour of the backlight source;

[0018] S3.4: Retain the sub-pixel edge with the largest contour length as the catheter edge and remove other environmental noise.

[0019] Analyzing the catheter edge image and extracting the catheter end face center point includes:

[0020] S3.5: Segment the edge contour of the catheter into several straight line segments and elliptical arc segments, and merge the elliptical edge contours with adjacent and discontinuous endpoints into a single elliptical edge contour;

[0021] S3.6: If the number of merged ellipse contours is greater than one, select the ellipse contour with the smallest mean pixel column coordinate value as the catheter left end face ellipse for the left image, and select the ellipse contour with the largest mean pixel column coordinate value as the catheter right end face ellipse for the right image. The image coordinate systems from the perspectives of the left and right cameras are both based on the lower left corner of the image as the coordinate origin.

[0022] S3.7: Calculate the roundness of the elliptical edge contour. If the roundness is greater than 0.008, fit it to an ellipse using least squares fitting, and select the center of the ellipse as the center of the catheter end face. Otherwise, calculate the centroid of the elliptical edge contour and use it as the center of the catheter end face.

[0023] Correcting the catheter inclination and calculating the catheter pixel distance within the camera field of view include:

[0024] S3.8: Select the two longest straight line segments, fit them and calculate the mean of their slopes. The slopes of the straight line segments of the catheter from the left camera’s perspective are k and k respectively. l , the slope of the straight line segment of the catheter from the right camera perspective is k r ;

[0025] S3.9: Let the actual inclination angle of the catheter within the left camera’s field of view be θ l , the column pixel coordinate of the end face center point is y l , the camera's column pixel resolution is y, and the distance of the left side of the catheter is d l Calculated as:

[0026] k l =tanθ l

[0027] d l =(yy l ) / cosθ l

[0028] Assume that the actual inclination angle of the catheter in the right camera's field of view is θ r , the column pixel coordinate of the center point of the catheter end surface is y r , the mean slope of the fitted straight line is k r , the pixel distance d to the right of the catheter r Calculated as:

[0029] k r =tanθ r

[0030] d r =y r / cosθ r

[0031] The calculation of the catheter length includes:

[0032] According to the distance d between the two camera pixels in the field of view of the catheterl and d r , the camera distance Δl and camera pixel size δ obtained by system calibration, the actual length l of the catheter can be calculated as:

[0033] l=(d l +d r )·δ+Δl

[0034] The camera distance Δl and the camera pixel size δ are obtained by pre-calibration.

[0035] A catheter length measurement device for digital production includes: a device body and a host computer; the host computer outputs instructions to capture images of the two ends of the catheter to be tested, performs image processing, obtains the catheter edge contour, and calculates the actual catheter length based on the catheter pixel distance;

[0036] The device body includes a metal frame, four electric guide rails, a catheter station support frame, two backlight support frames, two backlight sources, a photoelectric sensor, two vertical electric slides, and two industrial cameras;

[0037] The host computer includes a processor and a memory, wherein the memory stores a workstation detection and movement program module, a trigger shooting program module, an image processing program module, and a catheter length calculation program module; the processor loads the above program modules to execute the above-mentioned method steps to realize catheter length measurement in digital production.

[0038] A catheter station support frame is provided on the bottom crossbeam of the metal frame, and an electric guide rail is provided on each side of the catheter station support frame. The two ends of the electric guide rail are fixedly connected to the bottom crossbeam of the metal frame, and the backlight source support is slidably connected to the two electric guide rails through sliders. A backlight source is provided on the top of the backlight source support frame, and a photoelectric sensor is provided on the top of the catheter station support frame. When the catheter to be detected is placed on the catheter station support frame, the two ends of the catheter to be detected are suspended on the backlight source, and the photoelectric sensor is used to sense whether the catheter to be detected is placed on the catheter station support frame; the two electric guide rails and the photoelectric sensor on the bottom crossbeam of the metal frame are respectively connected to the host computer to receive instructions from the host computer;

[0039] Two electric guide rails are provided on the top crossbeam of the metal frame, and the two ends of the electric guide rails are fixedly connected to the top crossbeam of the metal frame. The two vertical electric slides are respectively slidably connected to the two electric guide rails through sliders, and two industrial cameras are fixedly installed at the bottom of the vertical electric slides; the two electric guide rails, the vertical electric slides and the industrial cameras on the top crossbeam of the metal frame are respectively connected to the upper computer to receive instructions from the upper computer.

[0040] The program steps of the station detection and movement program module specifically include:

[0041] When the catheter to be inspected is placed on the catheter work station support frame, the photoelectric sensor outputs a sensing signal to the host computer. The host computer controls the bottom beam of the metal frame, the four electric guide rails on the top beam to slide horizontally, and the vertical electric slide to slide vertically, thereby driving the backlight source to move below the two ends of the catheter to be inspected and driving the industrial camera to move above the two ends of the catheter to be inspected. At the same time, two industrial cameras are triggered to capture the left and right images of the two ends of the catheter respectively and send them to the host computer.

[0042] During the movement, the distance between the two industrial cameras remains unchanged; when the vertical electric slide moves the industrial camera, the distance from the industrial camera to the axis of the catheter must be ensured to remain unchanged.

[0043] The present invention has the following beneficial effects and advantages:

[0044] 1. The method of the present invention provides a new length measurement method for digital production of catheters, which has the advantages of non-contact, high efficiency and good robustness, and is conducive to promoting the improvement of manufacturing level in my country's aerospace field.

[0045] 2. The present invention accurately extracts the center of the catheter end face through two ellipse edge extractions and ellipse fitting, thereby improving the stability of the catheter measurement method, having strong versatility, and being applicable to catheters of any specifications.

[0046] 3. The method of the present invention has a short measurement time and a high degree of automation, and can complete continuous online measurement of catheters. It can be used as a unit in a digital catheter production system to significantly improve the production efficiency and manufacturing quality of catheters. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of the catheter length measuring device in the method of the present invention;

[0048] Figure 2 Schematic diagram of the internal modules of the host computer in the method of the present invention;

[0049] Figure 3 is a flow chart of the method of the present invention;

[0050] Figure 4 is a flow chart of the image processing algorithm in the method of the present invention;

[0051] Figure 5 (a) is an image of the region of interest at the catheter end captured by the left camera in the method of the present invention;

[0052] Figure 5 (b) is the edge image of the region of interest image of the catheter end portion captured by the left camera in the method of the present invention after sub-pixel extraction and completion;

[0053] Figure 5(c) is the edge image extracted after preprocessing of the original image of the catheter end under the left camera in the method of the present invention;

[0054] Figure 6 (a) is the edge image of the catheter captured by the left camera in the method of the present invention after being segmented by straight line segments and elliptical arc segments;

[0055] Figure 6 (b) is the edge image of the catheter edge image captured by the left camera in the method of the present invention after the ellipse edge is roughly extracted;

[0056] Figure 6 (c) is the image of the center point of the end face after the catheter edge image captured by the left camera is elliptical fitted in the method of the present invention;

[0057] Figure 7 (a) is a schematic diagram of the catheter inclination correction principle under the left camera in the method of the present invention;

[0058] Figure 7 (b) is a schematic diagram of the catheter inclination correction principle under the right camera in the method of the present invention;

[0059] Figure 8 (a) is the image of the center point of the catheter end surface obtained by the final processing under the left camera in the method of the present invention;

[0060] Figure 8 (b) is the image of the center point of the catheter end surface obtained by the final processing under the right camera in the method of the present invention;

[0061] Among them, 1 is the device body, 101 is the metal frame, 102 is the electric guide rail, 103 is the catheter station support frame, 104 is the backlight support frame, 105 is the backlight source, 106 is the photoelectric sensor, 107 is the vertical electric slide, 108 is the industrial camera, 2 is the host computer, 201 is the processor, 202 is the memory, 2021 is the station detection and movement program module, 2022 is the trigger shooting program module, 2023 is the image processing program module, and 2024 is the catheter length calculation program module. DETAILED DESCRIPTION

[0062] To make the above-mentioned objects, features, and advantages of the present invention more readily apparent, the specific implementation methods of the present invention are described in detail below with reference to the accompanying drawings. The following description sets forth many specific details to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways than those described herein, and those skilled in the art may make similar modifications without departing from the scope of the invention. Therefore, the present invention is not limited to the specific implementation methods disclosed below.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art of the art to which the present invention pertains. The terms used in the specification of the invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention.

[0064] like Figure 1-2 As shown, the hardware device for measuring catheter length includes a device body 1 and a host computer 2. Device body 1 comprises a steel frame 101, four electric guide rails 102, a catheter workstation support frame 103, two backlight support frames 104, two backlight sources 105, a photoelectric sensor 106, two vertical electric slides 107, and two industrial cameras 108. Host computer 2 includes a processor 201 and memory 202. Memory 202 stores a workstation detection and movement program module 2021, a triggering and shooting program module 2022, an image processing program module 2023, and a catheter length calculation program module 2024. Processor 201 loads these program modules and executes the program detection method steps to achieve catheter length measurement in digital production.

[0065] A catheter station support frame 103 is mounted on the bottom crossbeam of the steel frame 101. A motorized guide rail 102 is mounted on either side of the support frame 103. Both ends of the motorized guide rail 102 are fixedly connected to the bottom crossbeam of the steel frame 101. A backlight support 104 is slidably connected to each of the two motorized guide rails 102 via sliders. A backlight source 105, an LED backlight panel, is mounted on top of the backlight support 104. A photoelectric sensor 106 is mounted on top of the catheter station support frame 103. When a catheter to be inspected is placed on the support frame 103, both ends of the catheter hang over the backlight source 105. The photoelectric sensor 106 senses whether the catheter to be inspected is placed on the support frame 103. The two motorized guide rails 102 and the photoelectric sensor 106 on the bottom crossbeam of the steel frame 101 are connected to a host computer to receive commands from the host computer.

[0066] Two electric guide rails 102 are installed on the top crossbeam of the steel frame 101. The ends of the electric guide rails 102 are fixedly connected to the top crossbeam of the steel frame 101. A vertical electric slide 107 is slidably connected to the two electric guide rails 102 via sliders. An industrial camera 108 is fixedly mounted on the bottom of the vertical slide 107. The two electric guide rails 102 on the top crossbeam of the steel frame 101, the vertical electric slide 107, and the industrial camera 108 are each connected to a host computer to receive commands from the host computer.

[0067] The working principle of the device when moving the workstation: When the catheter to be inspected is placed on the catheter workstation support frame 103, the photoelectric sensor 106 outputs a sensing signal to the host computer. The host computer controls the bottom crossbeam of the steel frame 101, the four electric guide rails 102 on the top crossbeam slide horizontally, and the vertical electric slide 107 slide vertically, thereby driving the backlight source 105 to move below the two ends of the catheter to be inspected and the industrial camera 108 to move above the two ends of the catheter to be inspected. At the same time, the two industrial cameras 108 are triggered to respectively capture the left and right images of the two ends of the catheter and send them to the host computer. During the movement, the distance between the two industrial cameras 108 remains unchanged; the vertical electric slide 107 moves the industrial camera 108 to ensure that the distance between the industrial camera 108 and the catheter axis remains unchanged.

[0068] like Figure 3-Figure 4 As shown, the present invention provides a catheter length measurement method for digital production, comprising the following steps:

[0069] Step 1: During the digital production of the catheter, the finished catheter is fed into the length measuring unit and placed on the support frame 103;

[0070] Step 2: The photoelectric sensor 106 below the catheter synchronously triggers two industrial cameras 108 to capture an image of the end of the catheter;

[0071] Step 3: Process the image captured by the left camera as follows: Step 4.1 to Step 4.9 to obtain the pixel distance of the catheter within the camera's field of view;

[0072] i. Extract the catheter edge image and preprocess it (steps 3.1-3.4):

[0073] Step 3.1: Cut a fixed rectangular area in the original image as the region of interest, and remove the inherent invalid background area in the image to obtain Figure 5 Each time, the catheter end is placed at a fixed position within the viewing angle of the industrial camera so as to capture the fixed area as the catheter end region of interest.

[0074] Step 3.2: Use the Canny operator to perform sub-pixel edge extraction on the region of interest, fill in the edges with adjacent and discontinuous endpoints, and ensure the continuity of the catheter edge, such as Figure 5 As shown in (b), the results of sub-pixel edge extraction include: the edge of the backlight source in the image, the true edge of the catheter, and some environmental noise points and small edges;

[0075] Step 3.3: For each object on the sub-pixel edge, calculate the maximum and minimum values ​​of its pixel row coordinates, then calculate the difference between the maximum and minimum values. Remove edge objects whose difference is less than a threshold, thus removing the edge contour of the backlight source. In the experiment, the threshold was set to 1075.

[0076] Step 3.4: Compare the contour lengths of all edges obtained in step 3.3. Since the contour lengths of the noise edges are all smaller than the contour lengths of the catheter edges, select the edge with the largest contour length, which is the true edge of the catheter. This can eliminate some environmental noise points and small edges, such as Figure 5 (c)

[0077] ii. Analyze the catheter edge image and extract the catheter end face center point (steps 3.5-3.7):

[0078] Step 3.5: If Figure 6 As shown in (a), the catheter edge contour is segmented into several straight line segments and elliptical arc segments by using the straight line segment progressive approximation contour method. The straight line contours in the subsequent steps are combined together for slope fitting in step 4.8. The elliptical arc segments are combined together, and the elliptical edge contours with adjacent and discontinuous endpoints are merged. The straight line segment contours are filtered out to complete the coarse extraction of the elliptical edge.

[0079] Step 3.6: If Figure 6 As shown in (b), if the number of elliptical edge contours obtained by coarse extraction is greater than 1, it means that there are arc-shaped burrs on the straight line contour. The elliptical edge contour objects obtained by coarse extraction are traversed, and the contour with the smallest pixel column coordinate mean is retained (the image coordinate systems under the left and right camera perspectives both use the lower left corner of the image as the coordinate origin) (if the image is captured by the right camera, the contour with the largest pixel column coordinate mean is retained). The arc-shaped burrs can be removed, and the fine extraction is completed to obtain an elliptical edge contour; otherwise, proceed directly to the next step.

[0080] Step 3.7: Calculate the roundness of the ellipse edge contour. If the roundness is greater than 0.008, such as Figure 6 As shown in (c), the least squares method is used to fit the ellipse, and the center point of the ellipse is taken as the center point of the catheter end face; otherwise, the centroid of the ellipse edge contour is calculated and taken as the center point of the catheter end face;

[0081] iii. Correct the catheter inclination and calculate the pixel distance of the catheter length within the camera's field of view (steps 3.8-3.9):

[0082] Step 3.8: Sort the straight line profiles obtained in step 4.5 by length from largest to smallest, take the first two straight line profiles, and calculate the mean of the slopes of the two straight lines by straight line fitting, and set it as k l ;

[0083] Step 3.9: If Figure 7 As shown in (a), let the actual inclination angle of the catheter in the left camera field of view be θ l , the column pixel coordinate of the end face center point is y l , the camera's column pixel resolution is y, and the corrected catheter length pixel distance is d lIt can be calculated as:

[0084] k l =tanθ l (1)

[0085] d l =(yy l ) / cosθ l (2)

[0086] Step 4: If Figure 7 As shown in (b), the image captured by the right camera is processed from step 3.1 to step 3.8, and the actual inclination angle of the catheter in the left camera field of view is θ r , the column pixel coordinate of the end face center point is y r , the mean slope of the fitted straight line is k r , the corrected catheter length pixel distance d r It can be calculated as:

[0087] k r =tanθ r (3)

[0088] d r =y r / cosθ r (4)

[0089] Step 5: Calculate the distance d between the two cameras based on the length of the catheter in pixels. l and d r , the camera distance Δl and camera pixel size δ obtained by system calibration, the actual length l of the catheter can be calculated as:

[0090] l=(d l +d r )·δ+Δl (5)

[0091] The camera distance and pixel size are calibrated by the system before the measurement unit is initialized. The method is as follows:

[0092] Prepare two stainless steel bars with good axial straightness, good end flatness, and a small difference in length to serve as standard tubes. Use a coordinate measuring machine to measure the lengths of the two standard tubes, assuming they are l1 and l2. Use the method of the present invention to measure the two standard tubes separately. Ensure that all industrial cameras and backlight sources remain stationary during both measurements, and that the left and right ends of the two standard tubes are within the field of view of both cameras.

[0093] Assume that after measuring the standard tube with a length of l1, the pixel distance within the field of view of the left and right cameras is d l1 and d r1 ; After measuring the standard tube with a length of l2, the pixel distance within the field of view of the left and right cameras is d l2 and dr2 , the camera distance Δl and pixel size δ have the following relationship:

[0094] l1=(d l1 +d r1 )·δ+Δl (4)

[0095] l2=(d l2 +d r2 )·δ+Δl (5)

[0096] After the calculation and solution, the system parameter calibration is completed.

[0097] Step 6: After the current catheter length measurement is completed, wait for the next processed catheter to be sent to the length measurement unit.

[0098] like Figure 8 (a) is the image of the center point of the catheter end surface obtained by the final processing under the left camera in the method of the present invention, as shown in FIG. Figure 8 (b) is the image of the center point of the catheter end face obtained by the final processing under the right camera in the method of the present invention. The diameter of the catheter is 10 mm, the measured length is 814.961 mm, and the single measurement time is 1.5 s.

[0099] In summary, the method of the present invention provides a catheter length measurement method for digital production, which has a fast measurement speed, a high degree of automation, and strong stability, and greatly improves the production efficiency and manufacturing quality of catheters.

[0100] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A catheter length measurement method for digital production, characterized in that: By capturing images of both ends of the catheter to be inspected and performing image processing, the catheter edge contour is obtained, and the actual catheter length is calculated based on the catheter pixel distance. Specifically, the following steps are included: S1 station detection and movement step: when the catheter to be detected is placed on the detection station, the photoelectric sensor (106) provided on the detection station outputs a signal to control the industrial camera (108) on the slide rail to move to the top of the two ends of the catheter to be detected, and the backlight source (105) on the slide rail to move to the bottom of the two ends of the catheter to be detected; S2 triggers the shooting step: synchronously triggering the industrial camera (108) to respectively capture images of the left and right ends of the catheter; S3 image processing step: perform the following image processing on the left and right end original images respectively to obtain the pixel distance of the catheter length within the camera field of view; i. Extract and preprocess the catheter edge image to remove ambient noise and obtain the catheter sub-pixel edge; ii. Analyze the catheter edge image and extract the center point of the catheter end face; including: S3.5: Segment the edge contour of the catheter into several straight line segments and elliptical arc segments, and merge the elliptical edge contours with adjacent and discontinuous endpoints into a single elliptical edge contour; S3.6: If the number of merged ellipse contours is greater than one, select the ellipse contour with the smallest mean pixel column coordinate value as the catheter left end face ellipse for the left image, and select the ellipse contour with the largest mean pixel column coordinate value as the catheter right end face ellipse for the right image. The image coordinate systems from the perspectives of the left and right cameras are both based on the lower left corner of the image as the coordinate origin. S3.7: Calculate the roundness of the elliptical contour. If the roundness is greater than 0.008, fit the contour to an ellipse using least squares fitting, and select the center of the ellipse as the center of the catheter end face. Otherwise, calculate the centroid of the elliptical contour and use that as the center of the catheter end face. iii. Correct the catheter inclination and calculate the pixel distance of the catheter length within the camera's field of view; including: S3.8: Select the two longest straight line segments, fit them and calculate the mean of their slopes. The slopes of the straight line segments of the catheter from the left camera’s perspective are k and k respectively. l , the slope of the straight line segment of the catheter from the right camera perspective is k r ; S3.9: Let the actual inclination angle of the catheter within the left camera’s field of view be θ l , the column pixel coordinate of the end face center point is y l , the camera's column pixel resolution is y, and the distance of the left side of the catheter is d l Calculated as: k l =tanθ l d l =(y-y l ) / cosθ l Assume that the actual inclination angle of the catheter in the right camera's field of view is θ r , the column pixel coordinate of the center point of the catheter end surface is y r , the mean slope of the fitted straight line is k r , the pixel distance d to the right of the catheter r Calculated as: k r =tanθ r d r =y r / cosθ r S4 catheter length calculation steps: Based on the catheter length pixel distance within the field of view of the left and right cameras, combined with the camera distance and camera pixel size parameters obtained by system calibration, the actual catheter length is calculated, including: According to the distance d between the tube pixels in the field of view of the two cameras l and d r , the camera distance Δl and camera pixel size δ obtained by system calibration, the actual length l of the catheter can be calculated as: l=(d l +d r )·δ+Δl The camera distance Δl and the camera pixel size δ are obtained by pre-calibration.

2. The catheter length measurement method for digital production according to claim 1, characterized in that: The extracting and preprocessing of the catheter edge image includes: S3.1: In the image, a rectangular area is intercepted based on the fixed position of the catheter end surface under the camera's view as the region of interest; S3.2: Use the Canny operator to perform sub-pixel edge extraction on the region of interest and complete adjacent and discontinuous edges; S3.3: Set the difference threshold between the maximum and minimum values ​​of the sub-pixel edge row coordinates to remove the edge contour of the backlight source; S3.4: Retain the sub-pixel edge with the largest contour length as the catheter edge and remove other environmental noise.

3. A catheter length measuring device for digital production, characterized in that: include: The device body (1) and the host computer (2); the host computer (2) outputs instructions to capture images of both ends of the catheter to be detected, performs image processing, obtains the edge contour of the catheter, and calculates the actual catheter length based on the catheter pixel distance; The device body (1) comprises a metal frame (101), four electric guide rails (102), a catheter station support frame (103), two backlight support frames (104), two backlight sources (105), a photoelectric sensor (106), two vertical electric slides (107), and two industrial cameras (108); The host computer (2) comprises a processor (201) and a memory (202), wherein the memory (202) stores a workstation detection and movement program module (2021), a trigger shooting program module (2022), an image processing program module (2023), and a catheter length calculation program module (2024); the processor (201) loads the above-mentioned program modules to execute the method steps according to any one of claims 1 to 2, thereby realizing catheter length measurement in digital production.

4. The catheter length measuring device for digital production according to claim 3, characterized in that: A catheter station support frame (103) is provided on the bottom crossbeam of the metal frame (101), and an electric guide rail (102) is provided on both sides of the catheter station support frame (103). The two ends of the electric guide rail (102) are fixedly connected to the bottom crossbeam of the metal frame (101). The backlight support frame (104) is slidably connected to the two electric guide rails (102) through sliders. A backlight source (105) is provided on the top of the backlight support frame (104). A photoelectric sensor (106) is provided on the top of the catheter station support frame (103). When the catheter to be detected is placed on the catheter station support frame (103), the two ends of the catheter to be detected are suspended on the backlight source (105). The photoelectric sensor (106) is used to sense whether the catheter to be detected is placed on the catheter station support frame (103); the two electric guide rails (102) and the photoelectric sensor (106) on the bottom crossbeam of the metal frame (101) are respectively connected to the host computer (2) to receive commands from the host computer; Two electric guide rails (102) are provided on the top crossbeam of the metal frame (101), the two ends of the electric guide rails (102) are fixedly connected to the top crossbeam of the metal frame (101), two vertical electric slides (107) are respectively slidably connected to the two electric guide rails (102) through sliders, and two industrial cameras (108) are respectively fixedly installed on the lower part of the vertical electric slide (107); the two electric guide rails (102) on the top crossbeam of the metal frame (101), the vertical electric slide (107), and the industrial camera (108) are respectively connected to the host computer (2) to receive commands from the host computer.

5. The catheter length measuring device for digital production according to claim 4, characterized in that: The program steps of the workstation detection and movement program module (2021) specifically include: When the catheter to be inspected is placed on the catheter station support frame (103), the photoelectric sensor (106) outputs a sensing signal to the host computer (2), and the host computer (2) controls the bottom crossbeam of the metal frame (101) and the four electric guide rails (102) on the top crossbeam to slide horizontally and the vertical electric slide (107) to slide vertically, thereby driving the backlight source (105) to move below the two ends of the catheter to be inspected and driving the industrial camera (108) to move above the two ends of the catheter to be inspected. At the same time, the two industrial cameras (108) are triggered to respectively capture the left and right images of the two ends of the catheter and send them to the host computer (2).

6. The catheter length measuring device for digital production according to claim 5, characterized in that: During the movement, the distance between the two industrial cameras (108) remains unchanged; when the vertical electric slide (107) moves the industrial camera (108), it is necessary to ensure that the distance between the industrial camera (108) and the axis of the catheter remains unchanged.

Citation Information

Patent Citations

  • Pipeline measurement method based on multi-view vision

    CN110766669A

  • Automatic flange elbow welding method based on binocular vision

    CN111047702A