Uterine laparoscope tracking control method and system based on image processing

Abstract

The invention discloses a laparoscope tracking control method and system based on image processing, relates to the technical field of laparoscopes, and solves the problems that a brand new control mode is not adopted, the shooting posture of a lens is adjusted in real time, and the angles of pictures shot by the lens are all in a consistent state. According to the method, related processing is carried out on the spatial positioning points of the shooting equipment and the generated shooting picture, related spatial signs of the corresponding shooting equipment during shooting of the first picture are determined, the related feature contours are identified, the feature points are selected from the corresponding feature contours, the feature vectors are locked, and the positioning accuracy of the shooting equipment is improved. When associated shooting is carried out on shot pictures at other positions subsequently, according to the determined feature vectors, the postures of the equipment at other positions are adjusted in real time, so that the pictures at other positions are consistent with the original shot picture in the shooting angle, medical staff can carry out diagnosis conveniently, and the diagnosis efficiency is improved. Corresponding medical workers do not need to adjust the angle.

Description

Technical Field

[0001] The present invention relates to the technical field of hysteroscopy and laparoscopy, and in particular to a hysteroscopy and laparoscopy tracking control method and system based on image processing. Background Art

[0002] Hysteroscopy and laparoscopy is a commonly used minimally invasive surgical technique. Several small holes are made in the abdomen, and a laparoscope and surgical instruments are inserted. The intra-abdominal situation is observed on the monitor with the help of a high-definition camera system, and the surgical operation is performed. Hysteroscopy and laparoscopy can be used to diagnose and treat a variety of gynecological diseases, such as endometriosis, uterine fibroids, ovarian cysts, infertility, etc.

[0003] The application with publication number CN101862216A discloses a laparoscopic self-help uterine manipulator, and the technical problem to be solved is to facilitate the use of doctors, and the operation is simple, and the work efficiency is improved. The present invention adopts the following technical scheme: a laparoscopic self-help uterine manipulator, including a base and a uterine manipulator, the uterine manipulator is connected to the base, the uterine manipulator is composed of a vertical rod, a main screw and a uterine manipulator screw, one end of the vertical rod is connected to the base, and the other end is connected to the main screw, the front end of the main screw is connected to the uterine manipulator screw through a universal shaft, and a cervical plug or a cervical cup is sleeved on the uterine manipulator screw. Compared with the prior art, the uterine manipulator is fixed on the patient's uterus by using the base and the first and second screws, and the uterus is moved by adjusting the fixed sleeve or the direction adjustment rod to expose the field of view, which is conducive to the operation of pelvic, uterine or accessory surgery, and is operated by the laparoscopic surgeon to control the position of the uterus, which is simple to operate and does not require special personnel to control, can save manpower and operation time, and improve work efficiency.

[0004] In the actual operation and control process of the hysteroscope and laparoscope, the relevant personnel generally make real-time adjustments to the lens based on the actual detection image of the corresponding hysteroscope and laparoscope to determine the corresponding detection position and whether the detection image is comprehensive enough. However, the original control processing method has a large adjustment range and the angles of the images taken before and after are inconsistent. In the actual observation and evaluation process, there is a certain degree of difficulty. A new control method is not adopted to adjust the shooting posture of the lens in real time so that the angles of the images taken by the lens are in a consistent state to ensure the overall correlation effect of the shooting. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a hysteroscopic and laparoscopic tracking control method and system based on image processing, which solves the problem of not adopting a new control method to adjust the shooting posture of the lens in real time so that the angles of the images taken by the lens are in a consistent state.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a hysteroscopic laparoscopic tracking control method based on image processing, comprising the following steps:

[0007] Step 1: After the micro-photographing device enters the uterine and abdominal cavity, based on the micro-positioning sensor inside the device, after each movement of the device for a certain distance, the device performs associated photography to determine the photographed image, and the photographing posture of the device for subsequent photographing images is adjusted in real time based on the photographing posture of the first group of photographed images;

[0008] Step 2: Sort the pictures according to the relationship before and after shooting for the several groups of pictures taken, and then integrate and splice the adjacent pictures according to the different spatial characteristics of the shooting equipment, determine the spliced ​​picture and display it.

[0009] A hystero-laparoscopic tracking control system based on image processing, comprising:

[0010] A micro-photographing device is used to take high-definition pictures of the interior of the hysteroscope and generate photographic images;

[0011] A micro positioning sensor is arranged in the micro photographing device and is used to locate the position information of the micro photographing device in real time so as to generate positioning information;

[0012] The posture adjustment end, based on its internal micro-positioning sensor, performs associated shooting to determine the shooting image after each travel of the device, and uses the shooting posture of the first group of shooting images to adjust the shooting posture of the device in the subsequent shooting images in real time;

[0013] At the image stitching end, for the several groups of pictures taken, the pictures are sorted according to the correlation before and after the shooting, and then the adjacent pictures are integrated and stitched according to the different spatial characteristics of the shooting equipment, and the stitched picture is determined and displayed.

[0014] Among them, in step one, its micro-positioning sensor sends positioning information to the control end in real time, and identifies the travel distance of its micro-shooting device based on the real-time positioning information. When the travel distance reaches Y1, where Y1 is a preset value, the shooting instruction is executed and the first set of captured images is generated.

[0015] Furthermore, in step 1, the specific sub-steps of adjusting the shooting posture in real time are:

[0016] S11, performing image optimization on the first group of captured images, wherein the image optimization includes: denoising, image quality enhancement and grayscale processing, identifying internal contours from the captured images after image optimization, and if there is only one group of internal contours, calibrating the internal contours as characteristic contours; if there are multiple groups of internal contours, selecting a group of internal contours with the largest area as characteristic contours;

[0017] Identify the spatial positioning point from the positioning information, determine a group of associated points on the feature contour that are farthest from the spatial positioning point, mark the associated points as feature points, and determine a group of spatial feature vectors XL1 from the spatial positioning point to the feature point;

[0018] S12, based on the micro positioning sensor inside the micro shooting device, when the micro shooting device travels a distance of Y1 again, executes the second set of shooting instructions, and marks the spatial positioning point determined at the current moment as D k At this moment, k=2, representing the spatial positioning point corresponding to the second set of shooting instructions. Based on the trajectory and direction of its micro-shooting device in this stage, the characteristic contour determined by the first set of shooting images is translated in the same trajectory and direction to lock the translation contour and identify its spatial positioning point D 2 Connect with the marked feature points in the translation contour to determine the spatial feature vector XL2, and identify whether XL1 and XL2 are consistent:

[0019] If they are consistent, the shooting is directly performed to determine the second group of shooting images;

[0020] If they are not consistent, XL2 is adjusted, and the corresponding micro-photographing device is also adjusted during the adjustment process. After XL2 and XL1 are consistent, the shooting command is executed to determine the second set of captured images.

[0021] If after multiple adjustments, XL1 and XL2 are still not in the same state, adjust the angles of XL2 and XL1 to the same state, then execute the shooting command and determine the second set of shooting images;

[0022] S13, in the subsequent shooting process of each group of different shot images, the posture of the micro-shooting device is adjusted in real time according to the same processing method as the above step S13, and after the adjustment is completed, the shot image is determined.

[0023] Furthermore, in step 2, the specific sub-steps of integrating and stitching adjacent captured images include:

[0024] S21, sorting the plurality of groups of photographed pictures based on the shooting order, performing association processing on the first group of photographed pictures and the second group of photographed pictures in adjacent pictures, and identifying and locking their splicing contours:

[0025] Based on the path of the first group of shooting pictures and the second group of shooting pictures, the moving trajectory of the spatial positioning point is determined, the end point of the moving trajectory is the spatial positioning point of the second group of shooting pictures, and the initial point of the moving trajectory is the spatial positioning point of the first group of shooting pictures. The previous group of points of the moving trajectory is locked, and this point is calibrated as a standard point. The horizontal base plane of this standard point is constructed. The horizontal base plane is perpendicular to the moving trajectory, and its vertical point is the standard point. The horizontal base plane is determined, and a number of intersections between this horizontal base plane and the first group of shooting pictures are identified. Based on the several intersections, the first group of splicing contours are determined, and this vertical point belongs to the spatial positioning point of the first group of splicing contours. Then, a horizontal base plane perpendicular to the end point of the moving trajectory is constructed, and based on the several intersections between this horizontal base plane and the second group of shooting pictures, the second group of splicing contours are determined, and this end point belongs to the spatial positioning point of the second group of splicing contours.

[0026] S22, based on the spatial positioning points corresponding to the two groups of splicing contours, the two groups of spatial positioning points are overlapped, and the overlap stage is analyzed to see whether the associated splicing contours overlap:

[0027] If they overlap, the first set of pictures and the second set of pictures are directly integrated and spliced ​​based on the positions of their splicing outlines;

[0028] If they do not overlap, the spatial positioning points of the two spliced ​​contours are overlapped, the correlation difference between the two spliced ​​contours on the two-dimensional plane is identified, and the related area generated between the two spliced ​​contours is marked as the area to be adjusted;

[0029] Based on the two side lines of the area to be adjusted, the center line inside the area to be adjusted is locked, wherein the center line divides the area to be adjusted into two left and right areas, and the areas of the left and right areas are equal, and the two end points of the center line are the intersection points generated between the two splicing contours, based on the determined center line, the two side lines of the area to be adjusted are decomposed into a plurality of decomposition points, and vertical lines passing through the decomposition points and perpendicular to the center line are constructed, and based on the constructed plurality of vertical lines, two groups of decomposition points associated with the same vertical point are marked as alignment decomposition points;

[0030] Move the alignment decomposition points to the positions of the associated vertical points, so that the two splicing contours gradually overlap and complete the overall splicing of adjacent shooting images;

[0031] S23, for other adjacent pictures, the same method as steps S21-S22 is used to sequentially process them to obtain a stitched picture belonging to the whole of several groups of shooting pictures.

[0032] The present invention provides a hysteroscopic laparoscopic tracking control method and system based on image processing. Compared with the prior art, it has the following beneficial effects:

[0033] The present invention performs relevant processing on the spatial positioning point of the shooting device and the generated shooting picture, determines the relevant spatial signs of the corresponding shooting device when shooting the first picture, and identifies the associated characteristic contour based on the specific shooting picture, selects the characteristic point from the corresponding characteristic contour, and locks the characteristic vector based on the spatial positioning point and the characteristic point. When the shooting pictures at other positions are subsequently shot in association, the posture of the equipment at other positions is adjusted in real time according to the determined characteristic vector, so that the pictures at other positions are consistent with the original pictures in shooting angles, which is convenient for medical staff to make diagnosis, and there is no need for the corresponding medical staff to adjust the angle.

[0034] For the several groups of shooting pictures generated, in the adjacent shooting pictures, the spatial features between the adjacent shooting pictures and the corresponding stitching contours are locked, and based on the stitching overlap between the corresponding stitching contours, it is identified whether there are stitching anomalies between the stitching contours. For the related contours with unfinished stitching, the corresponding center line is locked by determining the area to be adjusted generated between the related contours, and then the contour is adjusted through the corresponding center line, so that multiple adjacent shooting pictures are associated and stitched, so as to achieve a better display effect, so as to facilitate the overall diagnosis of relevant medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the process of the present invention;

[0036] Figure 2 It is a schematic diagram for determining the area to be adjusted in the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Example 1

[0039] See also Figure 1 The present application provides a hystero-laparoscopic tracking control method based on image processing. For the relevant acquisition process of the skin and flesh tissue images associated with the hystero-laparoscopic system, relevant professional instruments need to be used for exploration and acquisition. The instrument includes a corresponding micro-positioning sensor and a micro-shooting device. The micro-shooting device transmits the acquired tissue images to an external terminal, including the following steps:

[0040] Step 1, after the micro-photographing device enters the uterine and abdominal cavity, based on the micro-positioning sensor inside the device, after each travel of a certain distance, the device performs associated shooting to determine the photographed image, and uses the shooting posture of the first group of photographed images to adjust the shooting posture of the device for subsequent photographed images in real time, to ensure that the photographed images are in a state of consistent shooting angles, to facilitate subsequent associated analysis, and the posture can be controlled automatically, and a corresponding rotating mechanism is provided in the micro-device to facilitate posture adjustment. Because the artificial posture adjustment range is too large, it is difficult to ensure that the shooting posture of the corresponding photographing device is relatively consistent with the shooting posture of the previous group of images, resulting in the inability to integrate and splice the photographed images of different areas in the later stage, resulting in the need to compare the images before and after one by one when performing associated analysis on such photographed images in the later stage, which is not conducive to the relevant medical care work of the corresponding medical staff;

[0041] The specific sub-steps for real-time adjustment are:

[0042] S11, its micro positioning sensor sends positioning information to the control end in real time, and based on the real-time positioning information, identifies the travel distance of its micro shooting device. When the travel distance reaches Y1, where Y1 is a preset value, the specific value is determined by the relevant operator based on experience, and is generally very small, executes the shooting instruction, and generates the first set of shooting images;

[0043] S12, the first group of captured images are optimized, and the image optimization includes: denoising, image quality enhancement and grayscale processing. Since the related processing methods associated with image optimization are relatively common in the prior art, they are not described in detail here. The image is denoised by median filtering. For each pixel in the image, the median of the pixel values ​​in its neighborhood is taken as the new pixel value of the point. Median filtering has a good removal effect on salt and pepper noise. For example, for a 3x3 neighborhood, 9 pixel values ​​are sorted from small to large, and the middle value is taken as the new value of the central pixel. The image quality enhancement and grayscale processing include: adjusting the grayscale histogram of the image to make the grayscale distribution of the image more uniform. This can enhance the contrast of the image and make the details in the image more obvious. For example, for a grayscale image, the distribution of its grayscale values ​​is counted, and then the grayscale values ​​are remapped so that the probability of each grayscale level appearing in the image is roughly equal, and the clarity of the image is improved by enhancing the edge and detail information of the image. Common sharpening methods include Laplace operator, Sobel operator, etc. These operators detect edges by calculating the gradient of the image, and then enhance the edges, and enhance the color effect of the image by adjusting parameters such as the color saturation and hue of the image. For example, the color saturation can be increased to make the color of the image more vivid, or the hue can be adjusted to make the color of the image more in line with human visual perception. The internal contour (that is, the edge contour line generated by the corresponding image, each group of edge contour lines forms a closed loop and is the corresponding internal contour) is identified from the captured image after image optimization. If there is only one group of internal contours, this internal contour is calibrated as the feature contour. If there are multiple groups of internal contours, a group of internal contours with the largest area is selected as the feature contour;

[0044] Identify its spatial positioning point from the positioning information, determine a group of associated points on this feature contour that are farthest from the spatial positioning point, mark the associated points as feature points, and determine a group of spatial feature vectors XL1 from the spatial positioning point to the feature point (the vector has an angle and a length, and the angle reference can be determined based on the set horizontal plane or based on horizontal planes in other directions, so no association limitation is made here, and it can be understood as a group of feature vectors in space);

[0045] S13, based on the micro positioning sensor inside the micro shooting device, when the micro shooting device travels a distance of Y1 again, executes the second set of shooting instructions, and marks the spatial positioning point determined at the current moment as D kAt this moment, k=2, representing the spatial positioning point corresponding to the second set of shooting instructions. Based on the trajectory and direction of the micro-shooting device in this stage, the characteristic contour determined by the first set of shooting images is translated in the same trajectory and direction to lock the translation contour (the trajectory and direction here do not include the rotation direction, because the positioning sensor cannot identify whether a rotation has occurred, and can only identify its spatial moving point and the corresponding moving direction. When the contour is translated, according to the corresponding spatial direction, its posture in space will also change. For example, when it moves in an arc, its corresponding contour will also change from the side view direction to the top view direction, etc. This is just an example and is not specific to this case), and its spatial positioning point D is identified. 2 Connect with the marked feature points in the translation contour to determine the spatial feature vector XL2, and identify whether XL1 and XL2 are consistent:

[0046] If they are consistent, the shooting is directly performed to determine the second group of shooting images;

[0047] If they are not consistent, XL2 is adjusted, and the corresponding micro-photographing device is also adjusted during the adjustment process. After XL2 and XL1 are consistent, the shooting command is executed to determine the second set of captured images.

[0048] There is also a situation: if after multiple adjustments, the state is still not consistent (it means that when the corresponding micro device moves, there are specific obstacles, which makes the length of its vector inconsistent, then it is only necessary to make the angle consistent to execute the corresponding image shooting), after adjusting the angles of XL2 and XL1 to the consistent state, the shooting command can be executed to determine the second group of shooting images;

[0049] S14, in the subsequent shooting process of each group of different shot images, the posture of the micro-shooting device is adjusted in real time according to the same processing method as the above step S13, and after the adjustment is completed, the shot image is determined;

[0050] Specifically, for the shooting images at different distances of each movement, in order to facilitate the high-intensity consideration of the corresponding shooting equipment when shooting the images, first of all, the shooting angle of the corresponding shooting equipment should be as consistent as possible, so there is no need for external medical staff to adjust the shooting angle in real time. When the medical staff makes adjustments, the adjustment range will be too large, then the adjustment range will not only have a large deviation, but also cause discomfort to the detected person. Therefore, based on the corresponding movement trajectory and direction, the generated characteristic contour is adjusted in real time to lock the corresponding characteristic vector, and real-time adjustment and posture control are performed based on the corresponding characteristic vector to ensure that the image is relatively consistent during shooting. Most of the uterine and abdominal cavity is a channel-type structure. If the angle is inconsistent, it is not conducive to the specific diagnosis of the corresponding medical staff.

[0051] Step 2: for the groups of pictures taken, the pictures are sorted according to the correlation relationship before and after shooting, and then the adjacent pictures are integrated and spliced ​​according to the different spatial characteristics of the shooting equipment, and the spliced ​​pictures are determined and displayed. Specifically, the spliced ​​pictures can better display the correlation of internal tissue characteristics, so as to facilitate better diagnosis by medical staff;

[0052] Among them, the specific sub-steps of integration and splicing include:

[0053] S21, sorting the plurality of groups of photographed pictures based on the shooting order, performing association processing on the first group of photographed pictures and the second group of photographed pictures in adjacent pictures, and identifying and locking their splicing contours:

[0054] Based on the route of the first group of shooting pictures and the second group of shooting pictures, the moving trajectory of its spatial positioning point is determined (its spatial positioning point is the real-time positioning route of the corresponding micro-positioning sensor, and its real-time positioning route is the route from the first group of shooting pictures to the second group of shooting pictures), the end point of its moving trajectory is the spatial positioning point of the second group of shooting pictures, and the initial point of its moving trajectory is the spatial positioning point of the first group of shooting pictures. The previous group of points on the moving trajectory is locked, and this point is calibrated as a standard point (the unit length between adjacent points is a preset value, which is formulated by relevant operators based on experience, and can also be considered as the interval frequency value of the corresponding positioning sensor. For example, if this end point is the point sent at the corresponding time point, then the previous group of points is the point sent at the previous time point of the corresponding time point, and the time interval between the two is the corresponding interval The interval frequency, the distance length between two adjacent spatial points can be basically ignored), construct the horizontal base plane of this standard point, the horizontal base plane is perpendicular to the moving trajectory, and the vertical point is the standard point, determine the horizontal base plane, and identify several intersection points where the horizontal base plane intersects with the first group of shooting pictures, and determine the first group of splicing contours based on several intersection points. This vertical point belongs to the spatial positioning point of the first group of splicing contours (the shooting picture can be understood as the associated picture of the channel, and the horizontal base plane can be understood as the horizontal plane perpendicular to the channel, then there will be intersection points, and the contour line generated by the intersection point is the associated contour), and then construct the horizontal base plane perpendicular to the end point of the moving trajectory, and determine the second group of splicing contours based on several intersection points between the horizontal base plane and the second group of shooting pictures. This end point belongs to the spatial positioning point of the second group of splicing contours;

[0055] S22, based on the spatial positioning points corresponding to the two groups of splicing contours, the two groups of spatial positioning points are overlapped, and the overlap stage is analyzed to see whether the associated splicing contours overlap:

[0056] If they overlap, the first set of pictures and the second set of pictures are directly integrated and spliced ​​based on the positions of their splicing outlines;

[0057] If they do not overlap (the reason for the non-overlap is that when the corresponding detection device moves, the muscle tissue in the corresponding abdominal cavity channel will change or move due to squeezing, resulting in a correlation change in the corresponding captured image, which will cause the images corresponding to the front and rear nodes to be different, which can be understood as inconsistent cross-sectional spans), after the spatial positioning points of the two spliced ​​contours are overlapped, the correlation difference between the two spliced ​​contours on the two-dimensional plane is identified, and the related area generated between the two spliced ​​contours is marked as the area to be adjusted (that is, the area where the two spliced ​​contours do not cross and overlap, such as Figure 2 The filled area in , the filled related area is the corresponding area to be adjusted);

[0058] Based on the two side lines of the area to be adjusted, the center line inside the area to be adjusted is locked, where the center line divides the area to be adjusted into two left and right areas, and the areas of the left and right areas are equal (because the method of determining the center line is more common, it will not be described in detail here, and the triangle method is generally used to determine the two left and right areas of equal area), and the two end points of the center line are the intersection points generated between the two spliced ​​contours, based on the determined center line, the two side lines of the area to be adjusted are decomposed into several decomposition points, and vertical lines passing through the decomposition points and perpendicular to the center line are constructed, and based on the constructed several groups of vertical lines, two groups of decomposition points associated with the same vertical point are marked as alignment decomposition points;

[0059] Move the alignment decomposition points to the associated vertical point positions, so that the two splicing contours are gradually overlapped to complete the overall splicing of adjacent shooting images. Specifically, the image splicing process here does not need to consider the image texture or stretching problems related to the images after splicing. First, the area to be adjusted between the two contours is very small, because the distance between the two determined spatial positioning points is negligible, so even if there are related changes in the organizational structure, the specific contour difference of the change is small, so by performing related adjustments on the edge of the image, the impact on the captured image can be ignored, so there is no need to consider the impact of the splicing process on the captured image;

[0060] S23, for other adjacent pictures, the same method as steps S21-S22 is used to sequentially process them to obtain a stitched picture belonging to the whole of several groups of shooting pictures;

[0061] Step 3: For the completed stitched image, keep the stitching traces at the stitching points and display them. The reason for keeping the traces for associated display is to facilitate external medical staff to view. Stitching is performed here. If you need to view the original associated captured images, you can directly select and view them from the several transmitted captured images.

[0062] Example 2

[0063] A hystero-laparoscopic tracking control system based on image processing, comprising:

[0064] A micro-photographing device is used to take high-definition pictures of the interior of the hysteroscope and generate photographic images;

[0065] A micro positioning sensor is arranged in the micro photographing device and is used to locate the position information of the micro photographing device in real time so as to generate positioning information;

[0066] The posture adjustment end, based on its internal micro-positioning sensor, performs associated shooting to determine the shooting image after each travel of the device, and uses the shooting posture of the first group of shooting images to adjust the shooting posture of the device in the subsequent shooting images in real time;

[0067] At the image stitching end, for the several groups of pictures taken, the pictures are sorted according to the correlation before and after the shooting, and then the adjacent pictures are integrated and stitched according to the different spatial characteristics of the shooting equipment, and the stitched picture is determined and displayed.

[0068] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0069] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A hysteroscopic laparoscopic tracking control method based on image processing, characterized in that: The following steps are involved: Step 1: After the micro-photographing device enters the uterine and abdominal cavity, based on the micro-positioning sensor inside the device, after each movement of the device for a certain distance, the device performs associated photography to determine the photographed image, and the photographing posture of the device for subsequent photographing images is adjusted in real time based on the photographing posture of the first group of photographed images; Step 2: Sort the pictures according to the relationship before and after shooting for the several groups of pictures taken, and then integrate and splice the adjacent pictures according to the different spatial characteristics of the shooting equipment, determine the spliced ​​picture and display it.

2. The hystero-laparoscopic tracking control method based on image processing according to claim 1, characterized in that: In step one, the micro-positioning sensor sends positioning information to the control end in real time, and identifies the travel distance of the micro-shooting device based on the real-time positioning information. When the travel distance reaches Y1, where Y1 is a preset value, the shooting instruction is executed and the first set of captured images is generated.

3. The hystero-laparoscopic tracking control method based on image processing according to claim 2, characterized in that: In step 1, the specific sub-steps of adjusting the shooting posture in real time are: S11, performing image optimization on the first group of captured images, wherein the image optimization includes: denoising, image quality enhancement and grayscale processing, identifying internal contours from the captured images after image optimization, and if there is only one group of internal contours, calibrating the internal contours as characteristic contours; if there are multiple groups of internal contours, selecting a group of internal contours with the largest area as characteristic contours; Identify the spatial positioning point from the positioning information, determine a group of associated points on the feature contour that are farthest from the spatial positioning point, mark the associated points as feature points, and determine a group of spatial feature vectors XL1 from the spatial positioning point to the feature point; S12, based on the micro positioning sensor inside the micro shooting device, when the micro shooting device travels a distance of Y1 again, executes the second set of shooting instructions, and marks the spatial positioning point determined at the current moment as D k At this moment, k=2, representing the spatial positioning point corresponding to the second set of shooting instructions. Based on the trajectory and direction of the micro-shooting device in this stage, the feature contour determined by the first set of shooting images is translated in the same trajectory and direction to lock the translation contour, and its spatial positioning point D2 is identified and connected with the feature point marked in the translation contour to determine the spatial feature vector XL2 of this time, and whether XL1 and XL2 are consistent is identified: If they are consistent, the shooting is directly performed to determine the second group of shooting images; If they are not consistent, XL2 is adjusted, and the corresponding micro-photographing device is also adjusted during the adjustment process. After XL2 and XL1 are consistent, the shooting command is executed to determine the second set of captured images. S13, in the subsequent shooting process of each group of different shot images, the posture of the micro-shooting device is adjusted in real time according to the same processing method as the above step S13, and after the adjustment is completed, the shot image is determined.

4. The hystero-laparoscopic tracking control method based on image processing according to claim 3 is characterized in that: The step S12 also includes: If after multiple adjustments, XL1 and XL2 are still not in a consistent state, the shooting command can be executed to determine the second set of shooting images after adjusting the angles of XL2 and XL1 to a consistent state.

5. The hystero-laparoscopic tracking control method based on image processing according to claim 1, characterized in that: In the step 2, the specific sub-steps of integrating and splicing adjacent captured images include: S21, sorting the plurality of groups of photographed pictures based on the shooting order, performing association processing on the first group of photographed pictures and the second group of photographed pictures in adjacent pictures, and identifying and locking their splicing contours: Based on the path of the first group of shooting pictures and the second group of shooting pictures, the moving trajectory of the spatial positioning point is determined, the end point of the moving trajectory is the spatial positioning point of the second group of shooting pictures, and the initial point of the moving trajectory is the spatial positioning point of the first group of shooting pictures. The previous group of points of the moving trajectory is locked, and this point is calibrated as a standard point. The horizontal base plane of this standard point is constructed. The horizontal base plane is perpendicular to the moving trajectory, and its vertical point is the standard point. The horizontal base plane is determined, and a number of intersections between this horizontal base plane and the first group of shooting pictures are identified. Based on the several intersections, the first group of splicing contours are determined, and this vertical point belongs to the spatial positioning point of the first group of splicing contours. Then, a horizontal base plane perpendicular to the end point of the moving trajectory is constructed, and based on the several intersections between this horizontal base plane and the second group of shooting pictures, the second group of splicing contours are determined, and this end point belongs to the spatial positioning point of the second group of splicing contours. S22, based on the spatial positioning points corresponding to the two groups of splicing contours, the two groups of spatial positioning points are overlapped, and the overlap stage is analyzed to see whether the associated splicing contours overlap: If they overlap, the first set of pictures and the second set of pictures are directly integrated and spliced ​​based on the positions of their splicing outlines; If they do not overlap, the spatial positioning points of the two spliced ​​contours are overlapped, the correlation difference between the two spliced ​​contours on the two-dimensional plane is identified, and the related area generated between the two spliced ​​contours is marked as the area to be adjusted; Based on the two side lines of the area to be adjusted, the center line inside the area to be adjusted is locked, wherein the center line divides the area to be adjusted into two left and right areas, and the areas of the left and right areas are equal, and the two end points of the center line are the intersection points generated between the two splicing contours, based on the determined center line, the two side lines of the area to be adjusted are decomposed into a plurality of decomposition points, and vertical lines passing through the decomposition points and perpendicular to the center line are constructed, and based on the constructed plurality of vertical lines, two groups of decomposition points associated with the same vertical point are marked as alignment decomposition points; The alignment decomposition points are moved to the positions of the associated vertical points, so that the two splicing contours are gradually overlapped, completing the overall splicing between adjacent shooting images.

6. The hystero-laparoscopic tracking control method based on image processing according to claim 5, characterized in that: In the step 2, the method of determining the overall stitching picture of the plurality of groups of shooting pictures is: S23, for other adjacent pictures, the same method as steps S21-S22 is used to sequentially process them to obtain a stitched picture belonging to the whole of several groups of shooting pictures.

7. A hystero-laparoscopic tracking control system based on image processing, the control system operates according to the hystero-laparoscopic tracking control method based on image processing according to claims 1-6, characterized in that: include: A micro-photographing device is used to take high-definition pictures of the interior of the hysteroscope and generate photographic images; A micro positioning sensor is arranged in the micro photographing device and is used to locate the position information of the micro photographing device in real time so as to generate positioning information; The posture adjustment end, based on its internal micro-positioning sensor, performs associated shooting to determine the shooting image after each distance traveled by the device, and uses the shooting posture of the first group of shooting images to adjust the shooting posture of the device in the subsequent shooting images in real time; At the image stitching end, for the several groups of pictures taken, the pictures are sorted according to the correlation before and after the shooting, and then the adjacent pictures are integrated and stitched according to the different spatial characteristics of the shooting equipment, and the stitched picture is determined and displayed.

Images