Teaching surgery video acquisition method, device and medium

Abstract

The application discloses a kind of surgical video acquisition methods, equipment and medium for teaching, it is related to image processing technical field.The method comprises: the spatial coordinates of multiple camera devices relative to operating table, perspective direction and video image are acquired in real time;According to the spatial coordinates and perspective direction of the camera device, construct splicing surface, match the video frame of the video image corresponding to adjacent camera device on the splicing surface, carry out image splicing to adjacent video frame, obtain splicing surface frame;Superimpose splicing surface frame, generate teaching video image.It solves the problem that the efficiency is low and the attention of physician is affected in the prior art that students are organized to observe and learn in operating room;When using fixed position to record the operation process, the view angle is single, the field of view and the depth of field of special part are not enough, and multiple view angle images cannot be obtained.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, device and medium for acquiring surgical videos for teaching purposes. Background Technology

[0002] Traditional surgical teaching typically involves organizing students to observe and learn in the operating room, or using pre-recorded surgical procedures for teaching purposes. Organizing students to observe in the operating room is inefficient due to space limitations, resulting in a limited number of visitors. Furthermore, the chaotic environment can lead to air pollution and even distract the surgeon. Using pre-recorded surgical procedures is problematic because the personnel recording the procedure are unfamiliar with the key surgical sites that researchers or students need to focus on, resulting in insufficient field of vision and depth for specific areas. Additionally, to prevent interference with the surgery, the camera position is usually fixed, making it impossible to capture multi-view images of the surgical process.

[0003] Therefore, it is necessary to propose more reasonable technical solutions to address the problems existing in the current technology. Summary of the Invention

[0004] To address the issues that current surgical teaching methods typically involve organizing students to observe and learn in the operating room, which is inefficient and affects the surgeon's concentration; and that using fixed camera positions to record the surgical process results in a single perspective, insufficient field of view and depth of vision for special areas, and an inability to obtain multi-view images.

[0005] In a first aspect, embodiments of the present invention provide a method for acquiring surgical videos for educational purposes, applied to a server that is communicatively connected to multiple camera devices, the method comprising:

[0006] Real-time acquisition of the spatial coordinates, viewing angle, and video images of multiple camera devices relative to the operating table;

[0007] A splicing surface is constructed based on the spatial coordinates and viewing direction of the camera device. Video frames of the corresponding video images of adjacent camera devices on the splicing surface are matched, and the adjacent video frames are spliced ​​to obtain the splicing surface frame.

[0008] Superimpose and stitch together the surface frames to generate teaching video footage.

[0009] The step of constructing the stitching surface based on the spatial coordinates and viewing angle of the camera device includes:

[0010] Obtain the focal length set corresponding to the viewing angle of multiple camera devices, and select the area with the most camera devices in the focal length set as the shooting area;

[0011] The shooting distance is set according to the spatial coordinates of the camera device corresponding to the convergence area and the distance to the shooting area;

[0012] A spherical surface is constructed with the center point of the shooting area as the center and the shooting distance as the radius to form a splicing surface.

[0013] The step of matching video frames of corresponding video images of adjacent camera devices on the splicing surface includes:

[0014] Obtain the projection points of the corresponding camera devices in the intersection area on the splicing surface, and obtain the adjacent camera devices based on the adjacency relationship of the projection points;

[0015] The images corresponding to the adjacent camera devices are scaled according to the shooting distance to obtain the video frames of the corresponding video images.

[0016] The feature is that the step of stitching images together adjacent video frames includes:

[0017] Feature points are extracted from adjacent video frames to generate a feature point set;

[0018] Match the feature point sets of adjacent video frames to obtain a set of feature point pairs;

[0019] Calculate the affine transformation between adjacent video frames using a set of feature point pairs;

[0020] Based on the affine transformation, image fusion is performed on adjacent video frames.

[0021] Secondly, embodiments of the present invention provide a surgical video acquisition device for teaching, applied to a server that is communicatively connected to multiple camera devices, including:

[0022] The camera acquisition module is used to acquire the spatial coordinates, viewing angle and video images of multiple camera devices relative to the operating table in real time;

[0023] The stitching module is used to construct a stitching surface based on the spatial coordinates and viewing direction of the camera device, match the video frames of the corresponding video images of adjacent camera devices on the stitching surface, and stitch the adjacent video frames to obtain the stitching surface frame.

[0024] The video module is used to overlay and stitch together frames to generate instructional video footage.

[0025] The splicing module is characterized by comprising:

[0026] The area confirmation unit is used to obtain the focal length set corresponding to the viewing angle of multiple camera devices, and select the intersection area with the most camera devices in the focal length set as the shooting area.

[0027] The distance setting unit is used to set the shooting distance based on the spatial coordinates of the camera device corresponding to the convergence area and the distance between the shooting area and the shooting area;

[0028] The splicing surface unit is used to construct a splicing surface with the center point of the shooting area as the center and the shooting distance as the radius of the sphere.

[0029] The splicing module is characterized by further comprising:

[0030] The projection unit is used to obtain the projection points of the corresponding camera devices in the intersection area on the splicing surface, and to obtain the adjacent camera devices according to the adjacency relationship of the projection points;

[0031] The scaling unit is used to scale the images corresponding to the adjacent camera devices according to the shooting distance to obtain video frames of the corresponding video images.

[0032] The splicing module is characterized by further comprising:

[0033] The feature extraction unit is used to extract feature points from adjacent video frames and generate a feature point set.

[0034] The feature matching unit is used to match the feature point sets of adjacent video frames to obtain a set of feature point pairs;

[0035] The affine transformation unit is used to calculate the affine transformation between adjacent video frames using a set of feature point pairs.

[0036] An image fusion unit is used to perform image fusion on adjacent video frames according to the affine transformation.

[0037] Thirdly, embodiments of the present invention provide a computer device including a memory and a processor that are communicatively connected, wherein the memory is used to store a computer program, and the processor is used to read the computer program and execute the teaching surgical video acquisition method as proposed in the above embodiments.

[0038] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing instructions that, when executed on a computer, perform the surgical video acquisition method for teaching purposes as described in the above embodiments.

[0039] Beneficial effects:

[0040] In this embodiment, the area focused by the camera device can be obtained through the spatial coordinates and viewing direction of the camera device. The camera device is worn on the heads of different surgeons, and the viewing direction corresponds to the camera's shooting direction during surgery. Because different surgeons have different angles relative to the key surgical sites, multi-dimensional imaging of these sites is possible. Finally, images from different angles captured by different camera devices are fused to generate a teaching video. During teaching, the focal point of the surgery can be obtained from the shooting angles of different camera devices, while the viewing angles of camera devices that do not capture the focal point are discarded. Furthermore, the focal point is usually a relatively important part of the surgeon's work, resulting in better imaging of special surgical sites. This solves the problems of existing technologies where organizing students to observe and learn in the operating room is inefficient and affects the surgeon's attention; and when using fixed camera positions to record the surgical process, the viewing angle is singular, and the field of view and depth of special sites are insufficient, making it impossible to obtain multi-view images. Attached Figure Description

[0041] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0042] Figure 1 This is a flowchart of the surgical video acquisition method for teaching purposes proposed in the first embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the structure of the surgical video acquisition device for teaching proposed in the second embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of a preferred configuration of the surgical video acquisition device for teaching according to the second embodiment of the present invention;

[0045] Figure 4 This is a surgical video acquisition device for teaching purposes proposed in the third embodiment of the present invention. Detailed Implementation

[0046] To more clearly illustrate the technical solutions in the embodiments of the invention or the prior art, the invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the invention, but does not constitute a limitation on the invention.

[0047] For the first aspect, please refer to... Figure 1 This invention proposes a method for acquiring surgical videos for teaching purposes. The method is applied to a server that is communicatively connected to multiple camera devices. The server can be, but is not limited to, a computer device with sufficient computing resources, such as a personal computer (PC), smartphone, personal digital assistant (PAD), or platform server. The method is used to acquire in real-time the spatial coordinates, viewing angles, and video images of multiple camera devices relative to the operating table. A stitching surface is constructed based on the spatial coordinates and viewing angles of the camera devices. Video frames corresponding to the video images of adjacent camera devices on the stitching surface are matched, and adjacent video frames are stitched together to obtain a stitched surface frame. The stitched surface frame is then superimposed to generate a teaching video image. This method solves the problems of inefficiency and reduced physician focus when organizing students to observe and learn in the operating room, and the limited field of view and depth of special areas when recording the surgical process using fixed camera positions, making it impossible to acquire multi-view images.

[0048] It is understood that the aforementioned execution entity does not constitute a limitation on the embodiments of this application. Accordingly, the operation steps of this method may be, but are not limited to, the steps S11 to S13 below:

[0049] Step S11: Real-time acquisition of the spatial coordinates, viewing angles, and video images of multiple camera devices relative to the operating table;

[0050] Specifically, the camera device can be a head-mounted camera, such as glasses with video recording capabilities or a surgical cap equipped with a camera, for the physician to wear during surgery. Preferably, the camera device has wireless transmission capabilities and is equipped with an angle sensor. The server can obtain the spatial coordinates of the camera device in real time through data interaction with the camera device. These spatial coordinates are the three-dimensional coordinates of the camera device relative to the operating table, or they can be a set reference coordinate. Simultaneously, it can obtain the viewing angle of the camera device; for example, by obtaining the viewing angle of the camera device through an angle sensor, or by matching the viewing angle of the corresponding video image of the camera device with respect to a reference point; and it can also obtain the video images captured by the camera device.

[0051] Step S12: Construct a splicing surface based on the spatial coordinates and viewing direction of the camera device, match the video frames of the corresponding video images of adjacent camera devices on the splicing surface, and perform image splicing on the adjacent video frames to obtain the splicing surface frame.

[0052] In practice, the spatial coordinates of the camera devices can be used to obtain their three-dimensional spatial position relative to the operating table. Simultaneously, the viewing angle corresponding to the shooting angle of each camera device can be obtained to determine which cameras are in shooting mode, and whether they are shooting critical surgical areas or procedures. The camera devices in shooting mode are then identified and arranged spatially to form a stitching surface. Video frames corresponding to adjacent camera devices are used; for example, adjacent camera devices in shooting mode are connected close together, and this connected network serves as the stitching surface. The video frames captured by adjacent camera devices on this stitching surface are then stitched together to obtain the stitched surface frame.

[0053] Step S13: Overlay and stitch together the surface frames to generate the teaching video image.

[0054] The obtained spliced ​​frames are superimposed and combined to create an instructional video.

[0055] In this embodiment, the area focused by the camera device can be obtained through the spatial coordinates and viewing direction of the camera device. The camera device is worn on the heads of different surgeons, and the viewing direction corresponds to the camera's shooting direction during surgery. Because different surgeons have different angles relative to the key surgical sites, multi-dimensional imaging of these sites is possible. Finally, images from different angles captured by different camera devices are fused to generate a teaching video. During teaching, the focal point of the surgery can be obtained from the shooting angles of different camera devices, while the viewing angles of camera devices that do not capture the focal point are discarded. Furthermore, the focal point is usually a relatively important part of the surgeon's work, resulting in better imaging of special surgical sites. This solves the problems of existing technologies where organizing students to observe and learn in the operating room is inefficient and affects the surgeon's attention; and when using fixed camera positions to record the surgical process, the viewing angle is singular, and the field of view and depth of special sites are insufficient, making it impossible to obtain multi-view images.

[0056] Preferably, the step of constructing the stitching surface based on the spatial coordinates and viewing angle of the camera device includes:

[0057] Obtain the focal length set corresponding to multiple camera devices in the viewing direction, and select the area with the most camera devices in the focal length set as the shooting area;

[0058] Specifically, when doctors are performing surgery and need to record instructional videos, a large number of people are involved, and each person involved in the surgery is wearing a camera device. During the surgery, participants usually focus on the key surgical areas, but some participants may be positioned at other perspectives; therefore, it is necessary to remove the video footage of participants from other perspectives. In this embodiment, by acquiring the focal length set corresponding to the viewing directions of multiple camera devices, such as the set corresponding to the intersection of the viewing directions of the camera devices, the most common intersection area corresponding to the camera devices in the focal length set is selected as the shooting area. The main shooting area, i.e., the surgical area, is then identified and judged to locate the key surgical sites.

[0059] The shooting distance is set according to the spatial coordinates of the camera device corresponding to the intersection area and the distance to the shooting area;

[0060] It is possible to obtain and set a display distance for the learning video based on the spatial coordinates of the camera device corresponding to the intersection area and the distance between the shooting area and the shooting area; it is clear that this display distance can be determined by the shooting distance.

[0061] The splicing surface is constructed using a sphere with the center point of the shooting area as the center and the shooting distance as the radius.

[0062] To facilitate the display of surgical video images from different angles, a sphere with the center point of the shooting area as the center and the shooting distance as the radius can be set as the stitching surface. This allows the teaching video to be taught from different observation points on the stitching surface, with different angles corresponding to the stitching surface.

[0063] Preferably, the step of matching video frames of corresponding video images from adjacent camera devices on the splicing surface includes:

[0064] Obtain the projection points of the corresponding camera devices on the splicing surface in the intersection area, and obtain the adjacent camera devices based on the adjacency relationship of the projection points;

[0065] In this embodiment, in order to ensure the continuity of images in the teaching video during teaching, the projection points of the corresponding camera devices on the splicing surface can be obtained in the intersection area. The adjacency relationship of the projection points can be used to obtain the adjacent camera devices, which can improve the speed of splicing the video frames corresponding to the video images obtained by the adjacent camera devices in the current view.

[0066] The images corresponding to adjacent camera devices are scaled according to the shooting distance to obtain the video frames of the corresponding video images.

[0067] The images corresponding to adjacent camera devices are scaled according to the shooting distance to enlarge or reduce the video image; the video image is adjusted to the screen size corresponding to the distance between the stitching surface and the shooting distance, and then video frames are obtained from the enlarged and reduced video image.

[0068] Preferably, the step of stitching images together adjacent video frames includes:

[0069] Feature points are extracted from adjacent video frames to generate a feature point set;

[0070] Specifically, feature points are extracted from adjacent video frames that need to be stitched together, such as using the SIFT algorithm to extract feature points from adjacent video frames. The main steps of the SIFT algorithm include scale space extremum detection, feature point localization, feature point orientation determination, and feature point description.

[0071] Match the feature point sets of adjacent video frames to obtain a set of feature point pairs;

[0072] Specifically, matching the SIFT feature point sets of adjacent video frames involves finding the nearest and second nearest neighbor feature points in the reference feature points of the adjacent feature point sets, using the RANSAC algorithm to remove false matches, and obtaining a set of feature point pairs of adjacent video frames.

[0073] Calculate the affine transformation between adjacent video frames using a set of feature point pairs;

[0074] Image fusion is performed on adjacent video frames based on affine transformation.

[0075] After obtaining the affine transformation between adjacent video frames, image fusion can be performed using a weighted average method.

[0076] For the second aspect, please refer to... Figure 2 and Figure 3 This invention provides a surgical video acquisition device 100 for teaching purposes, applied to a server that is communicatively connected to multiple camera devices, comprising:

[0077] The camera acquisition module 110 is used to acquire the spatial coordinates, viewing angle, and video images of multiple camera devices relative to the operating table in real time.

[0078] Specifically, the camera device can be a head-mounted camera, such as glasses with video recording capabilities or a surgical cap equipped with a camera, for the physician to wear during surgery. Preferably, the camera device has wireless transmission capabilities and is equipped with an angle sensor. The server can obtain the spatial coordinates of the camera device in real time through data interaction with the camera device. These spatial coordinates are the three-dimensional coordinates of the camera device relative to the operating table, or they can be a set reference coordinate. Simultaneously, it can obtain the viewing angle of the camera device; for example, by obtaining the viewing angle of the camera device through an angle sensor, or by matching the viewing angle of the corresponding video image of the camera device with respect to a reference point; and it can also obtain the video images captured by the camera device.

[0079] The splicing module 120 is used to construct a splicing surface based on the spatial coordinates and viewing direction of the camera device, match the video frames of the corresponding video images of adjacent camera devices on the splicing surface, and perform image splicing on the adjacent video frames to obtain the splicing surface frame.

[0080] In practice, the spatial coordinates of the camera devices can be used to obtain their three-dimensional spatial position relative to the operating table. Simultaneously, the viewing angle corresponding to the shooting angle of each camera device can be obtained to determine which cameras are in shooting mode, and whether they are shooting critical surgical areas or procedures. The camera devices in shooting mode are then arranged spatially to form a stitching surface; for example, adjacent camera devices in shooting mode are connected close together, and the resulting network serves as the stitching surface. Video frames captured by adjacent camera devices on this stitching surface are then stitched together to obtain the stitched surface frame.

[0081] Video module 130 is used to overlay and stitch together surface frames to generate teaching video images.

[0082] The obtained spliced ​​frames are superimposed and combined to create an instructional video.

[0083] In this embodiment, the area focused by the camera device can be obtained through the spatial coordinates and viewing direction of the camera device. The camera device is worn on the heads of different surgeons, and the viewing direction corresponds to the camera's shooting direction during surgery. Because different surgeons have different angles relative to the key surgical sites, multi-dimensional imaging of these sites is possible. Finally, images from different angles captured by different camera devices are fused to generate a teaching video. During teaching, the focal point of the surgery can be obtained from the shooting angles of different camera devices, while the viewing angles of camera devices that do not capture the focal point are discarded. Furthermore, the focal point is usually a relatively important part of the surgeon's work, resulting in better imaging of special surgical sites. This solves the problems of existing technologies where organizing students to observe and learn in the operating room is inefficient and affects the surgeon's attention; and when using fixed camera positions to record the surgical process, the viewing angle is singular, and the field of view and depth of special sites are insufficient, making it impossible to obtain multi-view images.

[0084] Preferably, the splicing module 120 includes:

[0085] The area confirmation unit 121 is used to obtain the focal length set corresponding to multiple camera devices in the viewing direction, and select the intersection area with the most corresponding camera devices in the focal length set as the shooting area.

[0086] Specifically, when doctors are performing surgery and need to record instructional videos, a large number of people are involved, and each person involved in the surgery is wearing a camera device. During the surgery, participants usually focus on the key surgical areas, but some participants may be positioned at other perspectives; therefore, it is necessary to remove the video footage of participants at other perspectives. In this embodiment, by acquiring the focal length set corresponding to the viewing directions of multiple camera devices, such as the set corresponding to the intersection of the viewing directions of the camera devices, the most frequent intersection area corresponding to the camera devices in the focal length set is selected as the shooting area. The main shooting area, i.e., the surgical area, is then identified and judged to locate the key surgical sites.

[0087] The distance setting unit 122 is used to set the shooting distance based on the spatial coordinates of the camera device corresponding to the intersection area and the distance between the shooting area and the shooting area;

[0088] It is possible to obtain and set a display distance for the learning video based on the spatial coordinates of the camera device corresponding to the intersection area and the distance between the shooting area and the shooting area; it is clear that this display distance can be determined by the shooting distance.

[0089] The splicing surface unit 123 is used to construct a splicing surface with the center point of the shooting area as the center and the shooting distance as the radius of the sphere.

[0090] To facilitate the display of surgical video images from different angles, a sphere with the center point of the shooting area as the center and the shooting distance as the radius can be set as the stitching surface. This allows the teaching video to be taught from different observation points on the stitching surface, with different angles corresponding to the stitching surface.

[0091] Preferably, the splicing module 120 further includes:

[0092] Projection unit 124 is used to obtain the projection points of the corresponding camera devices in the intersection area on the splicing surface, and to obtain the adjacent camera devices according to the adjacency relationship of the projection points;

[0093] In this embodiment, in order to ensure the continuity of images in the teaching video during teaching, the projection points of the corresponding camera devices on the splicing surface can be obtained in the intersection area. The adjacency relationship of the projection points can be used to obtain the adjacent camera devices, which can improve the speed of splicing the video frames corresponding to the video images obtained by the adjacent camera devices in the current view.

[0094] The scaling unit 125 is used to scale the images corresponding to adjacent camera devices according to the shooting distance to obtain the video frames of the corresponding video images.

[0095] The images corresponding to adjacent camera devices are scaled according to the shooting distance to enlarge or reduce the video image; the video image is adjusted to the screen size corresponding to the distance between the stitching surface and the shooting distance, and then video frames are obtained from the enlarged and reduced video image.

[0096] Preferably, the splicing module 120 further includes:

[0097] Feature extraction unit 126 is used to extract feature points from adjacent video frames respectively and generate feature point sets;

[0098] Specifically, feature points are extracted from adjacent video frames that need to be stitched together, such as using the SIFT algorithm to extract feature points from adjacent video frames. The main steps of the SIFT algorithm include scale space extremum detection, feature point localization, feature point orientation determination, and feature point description.

[0099] The feature matching unit 127 is used to match the feature point sets of adjacent video frames to obtain a set of feature point pairs;

[0100] Specifically, matching the SIFT feature point sets of adjacent video frames involves finding the nearest and second nearest neighbor feature points in the reference feature points of the adjacent feature point sets, using the RANSAC algorithm to remove false matches, and obtaining a set of feature point pairs of adjacent video frames.

[0101] The affine transformation unit 128 is used to calculate the affine transformation between adjacent video frames using a set of feature point pairs.

[0102] The image fusion unit 129 is used to perform image fusion on adjacent video frames according to affine transformation.

[0103] After obtaining the affine transformation between adjacent video frames, image fusion can be performed using a weighted average method.

[0104] Please see Figure 4 The third embodiment of the present invention provides a surgical video acquisition device for teaching purposes, which, at the hardware level, includes:

[0105] The data interface is used to establish data communication between the processor and the camera device;

[0106] Memory, used to store instructions;

[0107] The processor is used to read instructions stored in the memory and execute the teaching surgical video acquisition method in Example 1 according to the instructions: Step S11, real-time acquisition of the spatial coordinates, viewing angle and video images of multiple camera devices relative to the operating table; Step S12, construction of a splicing surface according to the spatial coordinates and viewing angle of the camera devices, matching the video frames of the corresponding video images of adjacent camera devices on the splicing surface, and performing image splicing on adjacent video frames to obtain a splicing surface frame; Step S13, superimposing the splicing surface frame to generate a teaching video image.

[0108] Optionally, the device also includes an internal bus. The processor, memory, and data interface can be interconnected via the internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc.

[0109] The memory may include, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Flash Memory, First Input First Output (FIFO), and / or First In Last Out (FILO). The processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0110] The working process, working details and technical effects of the device provided in this third embodiment can be found in the first embodiment, and will not be repeated here.

[0111] This fourth embodiment provides a computer-readable storage medium storing instructions containing the teaching surgical video acquisition method of the first embodiment. That is, the computer-readable storage medium stores instructions that, when executed on a computer, perform the teaching surgical video acquisition method as described in the first aspect. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0112] The working process, working details, and technical effects of the computer-readable storage medium provided in this fourth embodiment can be found in the first embodiment, and will not be repeated here.

[0113] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the teaching surgical video acquisition method as described in the first embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0114] The embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and apply this without any creative effort.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a repository code merging device to execute the methods of various embodiments or some parts of the embodiments.

[0116] Finally, it should be noted that the above are merely preferred embodiments of the invention and are not intended to limit the scope of protection of the invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the scope of protection of the invention.

Claims

1. A method for acquiring surgical videos for teaching purposes, characterized in that, Applied to a server that communicates with multiple camera devices, the method includes: Real-time acquisition of the spatial coordinates, viewing angle, and video images of multiple camera devices relative to the operating table; A splicing surface is constructed based on the spatial coordinates and viewing direction of the camera device. Video frames of the corresponding video images of adjacent camera devices on the splicing surface are matched, and the adjacent video frames are spliced ​​to obtain the splicing surface frame. Superimpose and stitch together surface frames to generate teaching video footage; The step of constructing the stitching surface based on the spatial coordinates and viewing angle of the camera device includes: Obtain the focal length set corresponding to the viewing angle of multiple camera devices, and select the area with the most camera devices in the focal length set as the shooting area; The shooting distance is set according to the spatial coordinates of the camera device corresponding to the convergence area and the distance to the shooting area; A spherical surface is constructed with the center point of the shooting area as the center and the shooting distance as the radius to form a splicing surface; The step of matching video frames of corresponding video images of adjacent camera devices on the splicing surface includes: Obtain the projection points of the corresponding camera devices in the intersection area on the splicing surface, and obtain the adjacent camera devices based on the adjacency relationship of the projection points; The images corresponding to the adjacent camera devices are scaled according to the shooting distance to obtain the video frames of the corresponding video images.

2. The method for acquiring surgical videos for teaching purposes according to claim 1, characterized in that, The steps for stitching images together adjacent video frames include: Feature points are extracted from adjacent video frames to generate a feature point set; Match the feature point sets of adjacent video frames to obtain a set of feature point pairs; Calculate the affine transformation between adjacent video frames using a set of feature point pairs; Based on the affine transformation, image fusion is performed on adjacent video frames.

3. A surgical video acquisition device for teaching purposes, characterized in that, A server-side application that communicates with multiple camera devices, including: The camera acquisition module is used to acquire the spatial coordinates, viewing angle and video images of multiple camera devices relative to the operating table in real time; The stitching module is used to construct a stitching surface based on the spatial coordinates and viewing direction of the camera device, match the video frames of the corresponding video images of adjacent camera devices on the stitching surface, and stitch the adjacent video frames to obtain the stitching surface frame. The video module is used to overlay and stitch together frames to generate instructional video footage; The splicing module includes: The area confirmation unit is used to obtain the focal length set corresponding to the viewing angle of multiple camera devices, and select the intersection area with the most camera devices in the focal length set as the shooting area. The distance setting unit is used to set the shooting distance based on the spatial coordinates of the camera device corresponding to the convergence area and the distance between the shooting area and the shooting area; The splicing surface unit is used to construct a splicing surface with the center point of the shooting area as the center and the shooting distance as the radius of the sphere; The projection unit is used to obtain the projection points of the corresponding camera devices in the intersection area on the splicing surface, and to obtain the adjacent camera devices according to the adjacency relationship of the projection points; The scaling unit is used to scale the images corresponding to the adjacent camera devices according to the shooting distance to obtain video frames of the corresponding video images.

4. The surgical video acquisition device for teaching purposes according to claim 3, characterized in that, The splicing module also includes: The feature extraction unit is used to extract feature points from adjacent video frames and generate a feature point set. The feature matching unit is used to match the feature point sets of adjacent video frames to obtain a set of feature point pairs; The affine transformation unit is used to calculate the affine transformation between adjacent video frames using a set of feature point pairs. An image fusion unit is used to perform image fusion on adjacent video frames according to the affine transformation.

5. A computer device, characterized in that, The device includes a memory and a processor that are communicatively connected, wherein the memory is used to store a computer program, and the processor is used to read the computer program and execute the surgical video acquisition method for teaching purposes as described in any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, perform the surgical video acquisition method for teaching purposes as described in any one of claims 1 to 2.

Images