C-shaped arm visual positioning system based on dual-camera real-time video stitching technology
By using dual camera real-time video stitching technology in C-arm X-ray fluoroscopy, the reference coordinate system and laser coordinate system are integrated, the problems of inaccurate positioning and radiation risks are solved, precise positioning and field of view are achieved, and the surgery and Diagnostic accuracy and efficiency.
Patent Information
- Application Number
- CN202411117018.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-01
AI Technical Summary
The lack of advanced positioning system of C-arm X-ray flioscopes leads to inaccurate positioning and prolonged surgical time, which increases the risk of X-ray radiation for medical staff and patients, and is also expensive to maintain.
The C-arm visual positioning system based on dual camera real-time video stitching technology can achieve precise positioning through the integration of the reference coordinate system and the laser coordinate system. Combined with the imaging system and the screen display system, structure images are acquired and segmented and feature point recognition are performed. Stitching with video to improve positioning accuracy and field of view.
Accurate positioning of the surgical site is achieved, the number of invalid exposures of X-rays is reduced, the risk of radiation is reduced, the field of view of the surgical or diagnostic areas is expanded, and the accuracy and efficiency of diagnosis and surgery are improved.
Smart Images

Figure CN118887294A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of medical devices, and in particular to a C-arm visual positioning system based on dual-camera real-time video splicing technology. Background Art
[0002] At present, the C-arm X-ray fluoroscopy machine lacks an advanced positioning system, which makes it difficult to achieve accurate spatial positioning during use. In actual operation, the precise positioning of the human body parts under the C-arm is almost entirely dependent on the experience and judgment of the imaging technician. Even experienced and skilled imaging technicians often find it difficult to ensure 100% accuracy of fluoroscopic positioning when faced with complex and changing surgical environments. Due to inaccurate positioning, doctors may need to adjust the angle and position of the C-arm several times and perform repeated fluoroscopic examinations to confirm the exact location of the surgical site or lesion area. In this process, not only is the operation time greatly extended, but medical staff and patients also have to endure more X-ray radiation, increasing potential health risks.
[0003] In addition, a series of other problems may arise during the use of the C-arm X-ray fluoroscopy machine, such as image quality fluctuations due to various factors and high equipment maintenance costs. Summary of the invention
[0004] The present application provides a C-arm visual positioning system based on dual-camera real-time video stitching technology, which enables the positioning system to perform more precise positioning through the fusion of a reference coordinate system and a laser coordinate system.
[0005] The present application provides a C-arm visual positioning system based on dual-camera real-time video stitching technology, the system comprising an imaging system, a positioning system and a screen display system, the imaging system is used to obtain a structural image containing a target structure and transmit it to the positioning system, the imaging system comprises a C-arm, the C-arm is used to scan a patient to obtain a structural image, and the positioning system is specifically used to:
[0006] S110, segmenting the acquired structural image into a plurality of sub-image blocks, each of which contains clear anatomical features;
[0007] S120, identifying and extracting feature points in each sub-image, establishing a reference coordinate system for each sub-image block according to the selected feature points, and selecting one feature point as the origin of the coordinate system;
[0008] S130, setting the coordinate system of the laser system, wherein the coordinate origin is set at the center of the laser emitter, the direction of the X-axis is consistent with the horizontal direction of the operating table, the direction of the Y-axis is consistent with the longitudinal direction of the operating table, the Z-axis is perpendicular to the plane where the X-axis and the Y-axis are located, and the direction of the Z-axis points to the direction of the surgical instrument;
[0009] S140, integrating the reference coordinate system and the laser system coordinate system, and calculating the corresponding coordinates of the coordinates in the reference coordinate system in the laser system coordinate system through the coordinate transformation matrix. The coordinate transformation formula is: laser =R×P base +T;
[0010] S150, identifying a target image from the structural image according to the fused reference coordinate system and the laser system coordinate system.
[0011] Preferably, the angle between the X-axis and Y-axis of the reference coordinate system and the X-axis and Y-axis of the laser system coordinate system is measured, and the measured angle is substituted into the formula The calculated R is substituted into step S140.
[0012] Preferably, the translation vector T=P ly -P by , substitute the calculated T into step S140 to calculate the position of the coordinates in the reference coordinate system in the laser coordinate system.
[0013] Preferably, the specific steps of dividing the structural image into a plurality of sub-image blocks are as follows:
[0014] S121, identifying the structure image, identifying the structure in the structure image, comparing the structure of the structure image with the structure information parameters pre-stored in the C-arm, and identifying the specific structure to be segmented;
[0015] S122, selecting a plurality of pixel points inside the specific structure as initial seed points;
[0016] S123, setting a gray value threshold, comparing the gray value of the structure image with the set gray value, and when the gray value of the structure image is less than the gray value threshold, adding the pixels of the structure image less than the gray value threshold to the specific structure;
[0017] S124, storing the pixel points in the specific structure into a pixel set, where all pixels in the pixel set are pixels in the specific structure to be segmented;
[0018] S125, for each seed point in the pixel set, check all the pixels around each seed point, compare all the pixels around the seed point with the grayscale value preset in step S123, and store the pixels whose grayscale value of the structural image is less than the grayscale value threshold in the pixel set;
[0019] S126: When no pixel point is stored in the pixel point set, the region growing process stops.
[0020] Preferably, the specific steps of the imaging system acquiring the structural image are as follows:
[0021] S210, selecting a plurality of cameras, and symmetrically installing the cameras on the intensifier end of the C-shaped arm;
[0022] S220, transmitting the signal collected by the camera to a screen display on the C-arm operating table, the screen display being installed with video stitching software and image processing software, the video stitching software synthesizing the video collected by the camera into a wide-angle video;
[0023] S230, extracting color features according to the image processing software in step S220, and dividing the image into a lesion area and a background area;
[0024] S240, converting the images of the lesion area and the background area into signals and transmitting them to the screen display, and fusing the detected multiple lesion areas.
[0025] Preferably, the camera is directed downward and covers the surgical area, and the camera can focus automatically. At the same time, the camera has an angle degree mark and can adjust the angle.
[0026] Preferably, the screen display receives the video signal transmitted by the camera, marks the received video through the screen display, and can change the display position by clicking the screen display.
[0027] Preferably, clicking the screen display transmits the display position signal to the camera, and the display position is changed by zooming the camera.
[0028] Preferably, multiple lesion areas are fused in the following steps:
[0029] S310, detecting the contour of the lesion area by using an edge detection algorithm;
[0030] S320, selecting at least four boundary points on the contour of the lesion area according to the contour shape and size of the lesion area, the at least four boundary points are sequentially connected to form a closed boundary area, and the boundary area covers the lesion area;
[0031] S330, repeating steps S310 and S320 for each lesion area, obtaining a boundary area of each lesion area, detecting the geometric center of the boundary area, measuring the geometric centers of adjacent areas, obtaining a distance value, presetting a distance threshold, comparing the distance value with the distance threshold, merging two boundary areas with a distance value less than the distance threshold, and overlapping two boundary areas with a distance value greater than the distance threshold;
[0032] S340: of the two overlapping boundary regions, select a boundary region with a larger area, and the boundary region with the larger area can cover the other boundary region.
[0033] Preferably, when two regions are merged, the merged blank region is filled, and when two regions overlap, the overlapping region is extracted, and if there is an overlapping portion, the overlapping portion is eliminated.
[0034] One or more technical solutions provided in the present application have at least the following technical effects or advantages: by integrating the reference coordinate system with the laser coordinate system, accurate positioning of the surgical site is achieved, the number of ineffective X-ray exposures is reduced, and the time medical staff and patients are exposed to X-rays is reduced, thereby reducing the potential risks caused by radiation;
[0035] The video stitching software combines the videos taken by two cameras into a wide-angle and distortion-free video, expanding the field of view of the surgical or diagnostic area and reducing the blind spots that may be caused by viewing angle limitations, allowing doctors to have a more comprehensive understanding of the situation in the surgical or diagnostic area. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is a schematic diagram of the process of the C-arm visual positioning system based on the dual-camera real-time video stitching technology of the present invention;
[0037] Figure 2 A schematic diagram of a process of dividing a structural image into sub-image blocks according to an embodiment of the present invention;
[0038] Figure 3 A flowchart of specific steps of acquiring a structural image according to a C-arm visual positioning system according to an embodiment of the present invention;
[0039] Figure 4 It is a schematic diagram of the process of fusing multiple lesion areas according to an embodiment of the present invention;
[0040] Figure 5 This is a structural diagram of the camera's field of view. DETAILED DESCRIPTION
[0041] To facilitate the understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.
[0042] It should be noted that the terms “vertical”, “horizontal”, “up”, “down”, “left”, “right” and similar expressions used in this document are only for illustrative purposes and do not represent the only implementation method.
[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.
[0044] Embodiment 1: Figure 1 1 is a flow chart of a C-arm visual positioning system based on dual-camera real-time video stitching technology according to an embodiment of the present invention. The system includes an imaging system, a positioning system and a screen display system. The imaging system is used to obtain a structural image containing a target structure and transmit it to the positioning system. The imaging system includes a C-arm, and the C-arm is used to scan a patient to obtain a structural image. The positioning system is specifically used to:
[0045] S110, segmenting the acquired structural image into a plurality of sub-image blocks, each of which contains clear anatomical features;
[0046] Among them, clear anatomical features include at least bones, blood vessels and organs.
[0047] like Figure 2 As shown, the specific steps of segmenting the structural image into multiple sub-image blocks are as follows:
[0048] S121, identifying the structure image, identifying the structure in the structure image, comparing the structure of the structure image with the structure information parameters pre-stored in the C-arm, and matching the specific structure to be segmented;
[0049] S122, selecting a plurality of pixel points inside the specific structure as initial seed points, where the initial seed points are pixel points selected as starting points during the image segmentation process;
[0050] Specifically, the selected pixels are located in the core area of the target structure and can represent the typical features of the structure. At the same time, the selected pixels are clear to avoid selecting blurred pixels that affect the accuracy. In addition, avoid selecting pixels on the boundary of the structure. The pixel values on the boundary vary greatly, which will cause premature stopping or mistaken expansion to adjacent structures in the process of segmenting sub-image blocks.
[0051] S123, setting a gray value threshold, comparing the gray value of the structure image with the set gray value, and when the gray value of the structure image is less than the gray value threshold, adding the pixels of the structure image less than the gray value threshold to the specific structure;
[0052] S124, storing the pixel points in the specific structure into a pixel set, where all pixels in the pixel set are pixels in the specific structure to be segmented;
[0053] S125, for each seed point in the pixel set, check all the pixels around each seed point, compare all the pixels around the seed point with the grayscale value preset in step S123, and store the pixels whose grayscale value of the structural image is less than the grayscale value threshold in the pixel set. If there are pixels stored in the pixel set, mark the pixels stored in the pixel set to avoid repeated processing of the pixels;
[0054] S126, when no pixel point is stored in the pixel point set, the region growing process stops;
[0055] The boundaries of the segmented sub-image blocks are smoothed to reduce the jagged effect or burr phenomenon. If there are holes in the segmentation results due to noise, they can be filled using morphological closing operations.
[0056] Specifically, orthopedic X-rays are identified to identify the bone structure in the image, and the identified bone structure is compared with the femur information parameters pre-stored in the C-arm to confirm that the specific structure to be segmented is the femur. Multiple pixels are selected in the core area of the femur as initial seed points. According to the grayscale characteristics of the femur on the X-ray, a suitable grayscale value threshold is set, and each pixel of the X-ray is traversed to compare its grayscale value with the set threshold. If the grayscale value of the pixel is less than the threshold, it is considered that the pixel belongs to a part of the femur. All pixels determined to be part of the femur are stored in a pixel set. For each seed point in the pixel set, all pixels around it are checked. If the grayscale value of the surrounding pixels is also less than the threshold, these pixels are also added to the pixel set and marked as processed to avoid duplication. This process is repeated until no new pixels are added to the set. When no more pixels meet the conditions to be added to the set, the region growing process stops, and the set contains a complete femur image.
[0057] S120, identifying and extracting feature points in each sub-image, the feature points including bone intersections, blood vessel branching points, and organ inflection points; establishing a reference coordinate system for each sub-image block according to the selected feature points, and selecting a feature point as the origin of the coordinate system.
[0058] Among them, the origin of the coordinate system is located at the center of the structure, which can reflect the overall characteristics of the structure. In orthopedic surgery, the direction of the main axis of the bone is the X-axis, and the direction perpendicular to the main axis of the bone is the Y-axis.
[0059] S130, set the coordinate system of the laser system, the coordinate origin is set at the center of the laser emitter, the direction of the X-axis is consistent with the horizontal direction of the operating table, the direction of the Y-axis is consistent with the longitudinal direction of the operating table, the Z-axis is perpendicular to the plane where the X-axis and the Y-axis are located, and the direction of the Z-axis points to the direction of the surgical instrument.
[0060] S 140, integrate the reference coordinate system and the laser system coordinate system, and calculate the corresponding coordinates of the reference coordinate system in the laser system coordinate system through the coordinate transformation matrix. The coordinate transformation formula is: laser =R×P base +T
[0061] Among them, P base is the point coordinate in the reference coordinate system (assumed to be a column vector);
[0062] P laser is the corresponding coordinate of the point in the laser system coordinate system;
[0063] R is the rotation matrix, which is used to describe the rotation relationship between two coordinate systems;
[0064] T is the translation vector, which represents the position of the origin of the reference coordinate system in the laser system coordinate system.
[0065] Specifically, measure the angle between the X-axis and Y-axis of the reference coordinate system and the X-axis and Y-axis of the laser system coordinate system, and substitute the measured angle into the formula Translation vector T = P ly -P by , the calculated R and T are substituted into step S140 to calculate the position of the coordinates in the reference coordinate system in the laser coordinate system, and the laser system can accurately locate and navigate according to the converted coordinates;
[0066] Among them, P ly is the origin of the laser system coordinate system; P by is the origin of the reference coordinate system.
[0067] S150, identifying a target image from the structural image according to the fused reference coordinate system and the laser system coordinate system.
[0068] Specifically, features related to the lesion, such as shape, size, texture, grayscale value, etc., are extracted from the preprocessed structural image. After the lesion target image is identified, in order to more accurately understand the position and range of the lesion in the patient's body, it is necessary to match it with the fused reference coordinate system and the laser system coordinate system to obtain the specific position information of the target image and accurately locate the position and range of the lesion in three-dimensional space.
[0069] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0070] By segmenting the image, key feature points such as the intersection of bones, branch points of blood vessels and inflection points of organs can be identified and extracted. These feature points help to establish a more accurate reference coordinate system and provide richer navigation information for surgery. At the same time, the fusion of the reference coordinate system and the laser coordinate system can achieve more accurate positioning and reduce the number of invalid exposures, thereby reducing the exposure time of medical staff and patients to X-rays and reducing the radiation received.
[0071] Embodiment 2: Based on the fusion of the reference coordinate system and the laser system coordinate system of embodiment 1, a precise coordinate system is provided. By introducing a camera and a screen display, the C-arm positioning system is made a visual positioning system. During medical surgery X-ray imaging, unnecessary radiation exposure of medical staff and patients is reduced, thereby reducing radiation risks.
[0072] like Figure 3 and Figure 4 As shown, the specific steps for the imaging system to obtain the structural image are as follows:
[0073] For S210, select a high-resolution camera and install the camera symmetrically on the intensifier end of the C-arm.
[0074] The camera is directed downward and covers key parts of the surgical or diagnostic area. The camera supports autofocus. The camera adjusts the angle through angle degree markings, which makes it easy to adjust the two cameras to the same angle and make the initial fields of view of the two cameras consistent, so that the two cameras can capture the same area and reach the same angle.
[0075] S220, transmitting the signal collected by the camera to a screen display on the C-arm operating table, where video splicing software and image processing software are installed;
[0076] Among them, the video stitching software in the screen display system combines the videos collected by the two cameras into a wide-angle video. The image can show the area directly below the image intensifier completely and without distortion. Since the two cameras are symmetrically positioned and at the same angle, the midpoint of the image is the midpoint of the image intensifier, which expands the field of view of the surgical area and enables doctors to observe the surgical site more comprehensively, thereby improving the accuracy and safety of the surgery. The screen display can be touch-screen. The screen display receives the video signal transmitted by the camera and marks the received video through the screen display. The display area can be changed by clicking on the screen display.
[0077] S230, extracting color features according to the image processing software in step S220, and dividing the image into a lesion area and a background area;
[0078] Specifically, by clustering colors, the colors in the image are divided into different categories, the color features are extracted, and the threshold is set according to the color features to segment the image into the lesion area and the background area.
[0079] S240, converting the images of the lesion area and the background area into signals and transmitting them to the screen display, and fusing the detected multiple lesion areas.
[0080] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0081] By symmetrically installing dual cameras, the video stitching software combines the videos taken by the cameras into a wide-angle and distortion-free video, which not only expands the field of view of the surgical or diagnostic area, but also reduces the blind spots that may be caused by viewing angle limitations, allowing doctors to have a more comprehensive understanding of the situation in the surgical or diagnostic area.
[0082] Embodiment 3: In embodiment 2, multiple lesion regions are detected, and similar or related lesion regions are merged to improve the efficiency of doctors' diagnosis.
[0083] like Figure 5 As shown in the figure, the specific steps of fusion of multiple lesion areas are as follows:
[0084] S310, detecting the contour of the lesion area by using an edge detection algorithm;
[0085] S320, selecting at least four boundary points on the contour of the lesion area according to the contour shape and size of the lesion area, the boundary points are evenly distributed on the contour, and the at least four boundary points are connected in sequence to form a closed boundary area, and the boundary area covers the lesion area.
[0086] S330, repeat steps S310 and S320 for each lesion area, obtain the boundary area of each lesion area, detect the geometric center of the boundary area, measure the geometric center of the adjacent area, obtain a distance value, preset a distance threshold, compare the distance value with the distance threshold, merge two boundary areas with a distance value less than the distance threshold, and overlap two boundary areas with a distance value greater than the distance threshold.
[0087] S340: of the two overlapping boundary regions, select a boundary region with a larger area, and the boundary region with the larger area can cover the other boundary region.
[0088] When two regions are merged, the blank area after the merger is filled, and when two regions overlap, the overlapping area is extracted. If there is still an overlapping part, the overlapping part is eliminated to reduce the impact on the accuracy and completeness of the fusion result.
[0089] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:
[0090] By fusing multiple lesion areas, doctors can obtain a more complete and comprehensive view of the lesion, which helps to more accurately assess the extent, shape and severity of the lesion, thereby improving the accuracy of diagnosis; the fused image is usually clearer and more intuitive than the image of a single lesion area, allowing doctors to more easily understand the distribution and characteristics of the lesion and make diagnostic decisions more quickly.
[0091] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A C-arm visual positioning system based on dual-camera real-time video stitching technology, characterized in that: The system includes an imaging system, a positioning system and a screen display system. The imaging system is used to obtain a structural image and transmit it to the positioning system. The imaging system includes a C-shaped arm, which is used to scan a patient to obtain a structural image. The positioning system is specifically used to: S110, segmenting the acquired structural image into a plurality of sub-image blocks, each of which contains clear anatomical features; S120, identifying and extracting feature points in each sub-image, establishing a reference coordinate system for each sub-image block according to the selected feature points, and selecting one feature point as the origin of the coordinate system; S130, setting the coordinate system of the laser system, wherein the coordinate origin is set at the center of the laser emitter, the direction of the X-axis is consistent with the horizontal direction of the operating table, the direction of the Y-axis is consistent with the longitudinal direction of the operating table, the Z-axis is perpendicular to the plane where the X-axis and the Y-axis are located, and the direction of the Z-axis points to the direction of the surgical instrument; S140, integrating the reference coordinate system and the laser system coordinate system, and calculating the corresponding coordinates of the coordinates in the reference coordinate system in the laser system coordinate system through the coordinate transformation matrix. The coordinate transformation formula is: laser =R×P base +T; S150, identifying a target image from the structural image according to the fused reference coordinate system and the laser system coordinate system.
2. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 1, characterized in that: Measure the angle between the X-axis and Y-axis of the reference coordinate system and the X-axis and Y-axis of the laser system coordinate system, and substitute the measured angle into the formula The calculated R is substituted into step S140.
3. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 1, characterized in that: Translation vector T = P ly -P by , the calculated T is brought into step S140 to calculate the position of the coordinates in the reference coordinate system in the laser coordinate system.
4. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 1, characterized in that: The specific steps of segmenting the structural image into multiple sub-image blocks are as follows: S121, identifying the structure image, identifying the structure in the structure image, comparing the structure of the structure image with the structure information parameters pre-stored in the C-arm, and identifying the specific structure to be segmented; S122, selecting a plurality of pixel points inside the specific structure as initial seed points; S123, setting a gray value threshold, comparing the gray value of the structure image with the set gray value, and when the gray value of the structure image is less than the gray value threshold, adding the pixels of the structure image less than the gray value threshold to the specific structure; S124, storing the pixel points in the specific structure into a pixel set, where all pixels in the pixel set are pixels in the specific structure to be segmented; S125, for each seed point in the pixel set, check all the pixels around each seed point, compare all the pixels around the seed point with the grayscale value preset in step S123, and store the pixels whose grayscale value of the structural image is less than the grayscale value threshold in the pixel set; S126: When no pixel point is stored in the pixel point set, the region growing process stops.
5. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 1, characterized in that: The specific steps for the imaging system to obtain structural images are as follows: S210, selecting a plurality of cameras, and symmetrically installing the cameras on the intensifier end of the C-shaped arm; S220, transmitting the signal collected by the camera to a screen display on the C-arm operating table, the screen display being installed with video stitching software and image processing software, the video stitching software synthesizing the video collected by the camera into a wide-angle video; S230, extracting color features according to the image processing software in step S220, and dividing the image into a lesion area and a background area; S240, converting the images of the lesion area and the background area into signals and transmitting them to the screen display, and fusing the detected multiple lesion areas.
6. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 5, characterized in that: The camera is directed downward and covers the surgical area, and the camera can focus automatically. At the same time, the camera has an angle degree mark and can adjust the angle.
7. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 5, characterized in that: The screen display receives the video signal transmitted by the camera, marks the received video through the screen display, and can change the display position by clicking the screen display.
8. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 7, characterized in that: Clicking the screen display transmits the display position signal to the camera, and changes the display position by zooming the camera.
9. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 5, characterized in that: Multiple lesion areas are fused as follows: S310, detecting the contour of the lesion area by using an edge detection algorithm; S320, selecting at least four boundary points on the contour of the lesion area according to the contour shape and size of the lesion area, the at least four boundary points are sequentially connected to form a closed boundary area, and the boundary area covers the lesion area; S330, repeating steps S310 and S320 for each lesion area, obtaining the boundary area of each lesion area, detecting the geometric center of the boundary area, measuring the geometric centers of adjacent areas, obtaining a distance value, presetting a distance threshold, comparing the distance value with the distance threshold, merging two boundary areas with a distance value less than the distance threshold, and overlapping two boundary areas with a distance value greater than the distance threshold; S340: of the two overlapping boundary regions, select a boundary region with a larger area, and the boundary region with the larger area can cover the other boundary region.
10. The C-arm visual positioning system based on dual-camera real-time video stitching technology as claimed in claim 9, characterized in that: When two areas are merged, fill the blank area after the merger. When two areas overlap, extract the overlapping area. If there is still an overlapping part, eliminate the overlapping part.
