Image Navigation Method, Device, Server Device and Storage Medium

Abstract

An embodiment of the present invention discloses an image navigation method, device, server device, and storage medium. The method includes: obtaining at least two current images each including a first feature code pattern and a marker pattern through at least two cameras; determining the position coordinates of each sub-region of the first feature code pattern of at least two current images according to at least three preset feature positions of the contour of the first feature code pattern, and determining the decoding results respectively corresponding to the first feature code patterns of at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region; if the at least two decoding results both conform to the preset verification rules, determining the positional relationship between at least three preset feature positions and the marker pattern respectively; determining the pose of the object to be tracked corresponding to the tracking component according to the positional relationship, and real-time displaying the pose on the target medical image. The problem of being unable to quickly and accurately obtain the pose of the surgical instrument is solved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of image processing, and in particular, to an image navigation method, a server device, and a storage medium. Background Art

[0002] A surgical navigation system accurately registers the image data scanned before the operation of a patient to the surgical position of the patient, so that the movement of the patient causes an adjustment to the digital image. During the operation, the surgical navigation system can accurately track the surgical instrument and update and display the position of the surgical instrument on the patient's image in the form of a virtual probe in real time, helping the doctor to accurately point the surgical instrument to the correct position, angle, and depth, making the surgical operation faster, more accurate, and safer.

[0003] Since it is necessary to track the position of the surgical instrument in real time, it is necessary to quickly obtain the key feature point information for marking the surgical instrument. In the operation process of the navigation system for tracking the key feature point information, calculation accuracy, efficiency, and robustness are all necessary factors to be considered. The inventors of the present application found during the implementation of the embodiments of the present application that the existing image navigation system at least has the problem of being unable to quickly and accurately obtain the pose of the surgical instrument. Summary of the Invention

[0004] Embodiments of the present invention provide an image navigation method, a server device, and a storage medium, which solve the problem that the existing image navigation system at least has the problem of being unable to quickly and accurately obtain the pose of the surgical instrument.

[0005] In a first aspect, an embodiment of the present invention provides an image navigation method, which includes:

[0006] Obtaining at least two current images each including a first feature code pattern and a marking pattern through at least two cameras; the first feature code pattern is disposed on the surface of a tracking component and includes a polygon contour and at least two sub-regions disposed within the contour, the contour includes at least three convex corner points, the at least two sub-regions are set to at least two colors, the shooting perspectives of the at least two cameras are different, and the marking pattern is disposed in the region of interest;

[0007] Determining the position coordinates of each sub-region of the first feature code pattern of the at least two current images according to at least three preset feature positions of the contour, and determining the decoding results respectively corresponding to the first feature code patterns of the at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region;

[0008] If the decoding results of the first feature code patterns of the at least two current images all conform to the preset verification rules, determining the positional relationship between each of the at least three preset feature positions and the marking pattern;

[0009] Determine the pose of the object to be tracked corresponding to the tracking component according to the position relationship, and display the pose in real time on the target medical image, where the target medical image includes the marker information corresponding to the marker pattern.

[0010] In a second aspect, an embodiment of the present invention further provides an image navigation device, including:

[0011] An image acquisition module, configured to acquire at least two current images each including a first feature code pattern and a marker pattern through at least two cameras; the first feature code pattern is disposed on the surface of the tracking component, and includes a polygonal contour and at least two sub-regions disposed within the contour, the contour includes at least three convex corner points, the at least two sub-regions are set to at least two colors, the shooting perspectives of the at least two cameras are different, and the marker pattern is disposed in the region of interest;

[0012] A decoding module, configured to determine the position coordinates of each sub-region of the first feature code pattern of the at least two current images according to at least three preset feature positions of the contour, and determine the decoding results respectively corresponding to the first feature code patterns of the at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region;

[0013] A position relationship determination module, configured to determine the position relationship between each of the at least three preset feature positions and the marker pattern if the decoding results of the first feature code patterns of the at least two current images both conform to a preset verification rule;

[0014] A display module, configured to determine the pose of the object to be tracked corresponding to the tracking component according to the position relationship, and display the pose in real time on the target medical image, where the target medical image includes the marker information corresponding to the marker pattern.

[0015] In a third aspect, an embodiment of the present invention further provides a server device, where the server device includes:

[0016] One or more processors;

[0017] A storage device, configured to store one or more programs;

[0018] When the one or more programs are executed by the one or more processors, the one or more processors implement the image navigation method as described in any embodiment.

[0019] In a fourth aspect, an embodiment of the present invention further provides a storage medium including computer-executable instructions, where the computer-executable instructions are used to execute the image navigation method as described in any embodiment when executed by a computer processor.

[0020] The technical solution of the image navigation method provided by the embodiment of the present invention obtains at least two current images each containing a first feature code pattern and a marker pattern through at least two cameras; determines the position coordinates of each sub-region of the first feature code pattern of at least two current images through at least three preset feature positions, and determines the decoding results respectively corresponding to the first feature code patterns of at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region; if the decoding results of the first feature code patterns of at least two current images all conform to the preset verification rules, determines the positional relationship between at least three preset feature positions and the marker pattern respectively; determines the pose of the tracked object corresponding to the tracking component according to the positional relationship, and displays the pose in real time on the target medical image. When the decoding results of the first feature code patterns of at least two current images all conform to the preset verification rules, it indicates that the coordinates of at least three preset feature positions of the first feature code pattern of each extracted current image are accurate. Therefore, the pose of the first feature code pattern can be determined according to the positional relationship between at least three preset feature positions corresponding to each current image and the marker pattern, and the pose of the tracking component where the first feature code pattern is located can be determined according to the pose of the first feature code pattern, so as to determine the pose of the tracked object corresponding to the tracking component; compared with directly positioning the structure of the tracking component, the structure of the tracking component can be simplified and the accuracy of navigation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0022] Figure 1 is a flowchart of the image navigation method provided by Embodiment 1 of the present invention;

[0023] Figure 2 is a schematic diagram of the first feature code pattern provided by Embodiment 1 of the present invention;

[0024] Figure 3 is another schematic diagram of the first feature code pattern provided by Embodiment 1 of the present invention;

[0025] Figure 4 is a schematic diagram of image navigation provided by Embodiment 1 of the present invention;

[0026] Figure 5 is a schematic diagram of the corner points of the first feature code pattern provided by Embodiment 1 of the present invention;

[0027] Figure 6It is a structural block diagram of the image navigation device provided in the second embodiment of the present invention;

[0028] Figure 7 It is a structural block diagram of the server device provided in the third embodiment of the present invention. Detailed implementation manners

[0029] To make the objectives, technical solutions and advantages of the present invention clearer, the following will refer to the accompanying drawings in the embodiments of the present invention and clearly and completely describe the technical solutions of the present invention through implementation manners. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0030] Embodiment 1

[0031] Figure 1 It is a flowchart of the image navigation method provided in the first embodiment of the present invention. The technical solution of this embodiment is applicable to the situation of surgical instrument navigation. This method can be executed by the image navigation device provided in the embodiment of the present invention. This device can be implemented in software and / or hardware and configured to be applied in the processor of the server device. This method specifically includes the following steps:

[0032] S101. Obtain at least two current images each including a first feature code pattern and a marker pattern through at least two cameras; the first feature code pattern is disposed on the surface of the tracking component and includes a polygon contour and at least two sub-regions disposed within the contour. The contour includes at least three convex corner points. The at least two sub-regions are set to at least two colors. The shooting perspectives of the at least two cameras are different. The marker pattern is disposed in the region of interest.

[0033] Among them, the at least two cameras can be selected as the two cameras of a binocular. It can be understood that the shooting perspectives of the two cameras of the binocular are different, and three-dimensional reconstruction can be performed on the images captured by the two cameras of the binocular.

[0034] Among them, the contour of the first feature code pattern is an arbitrary shape including at least three convex corner points, such as a triangle (see Figure 2 ), a rectangle (see Figure 3 ), a pentagon or a hexagon, etc. It can be understood that the at least three convex corner points are non-collinear.

[0035] Among them, the sub-region can be a rectangle, a circle or a triangle, etc. In one embodiment, the shape of the sub-region is the same as the contour shape of the first feature code pattern. For example, the contour of the first feature code pattern is a triangle (see Figure 2), the shapes of at least two sub-regions set within the triangle are all triangles; the contour of the first feature code pattern is a rectangle, and the shapes of at least two sub-regions set within the rectangle are all rectangles (see Figure 3 ).

[0036] Among them, the at least two sub-regions are set with at least two colors with distinct contrasts, such as black and white, red and yellow.

[0037] Among them, the marking pattern is used to directly or indirectly determine the reference coordinates and is set within the region of interest. The target medical standard image is a pre-taken three-dimensional image containing the region of interest of the patient and the marker, such as a CT (Computed Tomography) image.

[0038] In one embodiment, the marking pattern is the shape of the marker, and the marker is set within the region of interest. The position of the marker in the target medical image is the reference position, such as the origin of the coordinate system. The material of the marker can be selected as metal or metal oxide.

[0039] In one embodiment, as Figure 4 shown, the marking pattern is the second feature code pattern 102. The second feature code pattern is set on the marking component 13. The marking component 13 is fixedly set in the region of interest 15, that is, the oral mandible. The marking component is also provided with a marker 14, and the positional relationship between the second feature code pattern 102 and the marker 14 is known and remains unchanged during the navigation process. Therefore, the position of the marker can be indirectly determined through the position of the second feature code pattern, that is, the reference coordinates can be indirectly determined through the second feature code pattern. In this embodiment, the marking component 13 includes a first structural part 131 and a second structural part 132 connecting the first structural part 131. The first structural part 131 is fixed to the patient's mandible 13, that is, fixed to the teeth on the same side of the surgical site. The second structural part 132 includes a convex surface, and the second feature code pattern 102 is set on the convex surface; the positional relationship between the first structural part 131 and the second structural part 132 remains unchanged during the navigation process.

[0040] In one embodiment, the at least two current images need to all contain the first feature code pattern and the marking pattern. If one or more of the at least two current images do not all contain the first feature code pattern and the marker, then the at least two current images are discarded.

[0041] Among them, as Figure 4As shown, the first feature code pattern 101 is disposed on the surface of the tracking component 11, and the tracking component 11 is disposed at the end of the object 12 to be tracked. The positional relationship between the two remains unchanged during the navigation process. In one embodiment, the object 12 to be tracked is a surgical instrument, such as a dental surgical instrument, and during the surgical process, the positional relationship between the tracking component and the surgical instrument remains unchanged.

[0042] S102. Determine the position coordinates of each sub-region of the first feature code pattern of the at least two current images according to at least three preset feature positions of the contour, and determine the decoding results corresponding to the first feature code patterns of the at least two current images respectively according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region.

[0043] Among them, the preset feature position is a convex corner point or a contour edge. The at least three preset feature positions may be at least three convex corner points, or at least three contour edges, or a combination of two contour edges and one convex corner point, or a combination of one contour edge and two convex corner points. In this embodiment, the technical solution is described by taking the preset feature position as a convex corner point as an example.

[0044] Among them, the sub-region includes the sub-region coordinates and the neighborhood of the sub-region coordinates. The neighborhood range can be set according to actual needs, and is not specifically limited in this embodiment.

[0045] In one embodiment, the corner points of the first feature code pattern are all convex corner points, each sub-region is arranged at equal intervals, and the interval between the convex corner point and the adjacent sub-region is the same as the interval between each sub-region.

[0046] In one embodiment, each first feature code pattern corresponds to a sub-region coordinate combination, and the sub-region coordinate combination includes the relative coordinates of each sub-region with respect to the at least three convex corner points respectively. Determine the coordinates of at least three convex corner points of the first feature code pattern of the at least two current images respectively (see the corner points pointed by the Figure 5 arrow). According to the coordinates of the at least three convex corner points, determine the position coordinates in the pre-stored sub-region coordinate combination in the first feature code pattern, and use the colors corresponding to the position coordinates as the colors of the sub-regions corresponding to each position coordinate. According to the correspondence relationship between the preset colors and the encoded numbers, determine the encoded number of each sub-region, and the decoding result of the first feature code pattern can be determined according to the preset arrangement order of each sub-region. Exemplarily, taking Figure 3 as an example, define the encoding of the black sub-region as 0 and the encoding of the white sub-region as 1, and sort the sub-regions from left to right and from top to bottom. Figure 2The encoding information of the first feature code pattern is 110110000001011101000101000100. It can be understood that before using the image navigation method described in this embodiment, a correspondence relationship between the first feature code pattern and the combination of sub-region coordinates needs to be established.

[0047] In one embodiment, the method for determining the at least three convex corner points includes: performing threshold segmentation on the at least two current images respectively to obtain at least two binary images; extracting contour sets from the at least two binary images respectively; if the number of convex corner point coordinates of the current contour is greater than or equal to three, determining whether the pre-stored combination of sub-region coordinates is located inside the current contour; if so, taking the current contour as the contour of the first feature code pattern, and taking the at least three convex corner point coordinates as the at least three convex corner point coordinates of the first feature code pattern; if not, deleting the current contour, taking the next contour as the current contour, and jumping to the step of determining whether the pre-stored combination of sub-region coordinates is located inside the current contour if the number of convex corner point coordinates of the current contour is greater than or equal to three. In this embodiment, the threshold segmentation method can be optionally a local adaptive threshold. The contour set contains various contours, such as the contour of the first feature code pattern, the contour of the sub-region, and the contour that originally did not exist formed by the ambient light projected onto the region of interest. If each contour in any contour set does not contain the at least three convex corner point coordinates of the first feature code pattern, the at least two current images are directly discarded.

[0048] It can be understood that by determining the sub-region coordinates through the at least three convex corner points of the first feature code pattern, each sub-region coordinate can be located to sub-pixel accuracy, and this point is stable in typical image blurring scenarios, especially in over-illumination, under-illumination, and sensor noise.

[0049] In one embodiment, the at least two current images both include a first feature code pattern and a second feature code pattern. Therefore, it is necessary to determine the decoding results of the first feature code pattern and the second feature code pattern in each of the at least two current images respectively. Among them, the method for determining the decoding result of the second feature code pattern is the same as the method for determining the decoding result of the first feature code pattern. In other words, their encoding methods are the same, but their corresponding decoding results are different. It can be understood that the different decoding results of the first feature code pattern and the second feature code pattern can enable the processor to accurately distinguish between the first feature code pattern and the second feature code pattern.

[0050] S103. If the decoding results of the first feature code patterns of the at least two current images all conform to the preset verification rules, determine the positional relationships between the at least three preset feature positions and the marking pattern respectively.

[0051] In this embodiment, if the decoding results of the first feature code patterns in the at least two current images all conform to the preset verification rules, it is considered that the position coordinates of at least three convex corner points of the first feature code pattern of any of the extracted current images are accurate, the coordinates of the at least three convex corner points are retained, and the positional relationships between the at least three convex corner points and the marking pattern are determined respectively; if the first feature code patterns of one or more of the at least two current images do not conform to the preset verification rules, it is considered that the coordinates of the at least three convex corner points of the one or more current images extracted are incorrect and cannot be used to locate and track the attachment and the tracked object connected to the attachment. Therefore, the at least two current images are directly discarded.

[0052] In one embodiment, if the decoding results of the first feature code patterns in the at least two current images are all the same as the decoding results of the first feature code patterns stored in advance, it is considered that the decoding results of the first feature code patterns in the at least two current images all conform to the preset verification rules.

[0053] It can be understood that this positional relationship is a spatial positional relationship. When the marking pattern is the shape of a marker, the positional relationships between the at least three convex corner points and the marking pattern respectively are the positional relationships between the at least three convex corner points and the marker respectively.

[0054] In one embodiment, if the decoding results of the first feature code patterns corresponding to the at least two current images are consistent with the decoding results of the first feature code patterns stored in advance, and at the same time the decoding results of the second feature code patterns corresponding to the at least two current images are consistent with the decoding results of the second feature code patterns stored in advance, then the positional relationship between the first feature code pattern and the second feature code pattern in the at least two current images is determined; according to this positional relationship and the positional relationship between the second feature code pattern and the marker stored in advance, the positional relationship between the first feature code pattern and the marker in the at least two current images is determined.

[0055] S104. Determine the pose of the tracked object corresponding to the tracking component according to the positional relationship, and display the pose in real time on the target medical image, where the target medical image includes the marking information corresponding to the marking pattern.

[0056] It can be understood that when the relative positional relationships between three non-collinear coordinate points of an object and the coordinate origin are determined respectively, the position and orientation of the object in space, that is, the pose, can be determined.

[0057] In one embodiment, the tracking component includes a convex surface, and the first feature code pattern is attached to the convex surface. At this time, the at least three convex corner points are non-coplanar. It can be understood that through the positional relationships between the at least three non-coplanar convex corner points and the marker respectively, that is, through the positional relationships between the at least three non-coplanar convex corner points and the coordinate origin, the pose of the first feature code pattern can be accurately obtained. According to the pose of the first feature code pattern, the pose of the tracking component can be accurately determined, and thus the pose of the tracked object corresponding to the tracking component can be determined. It can be understood that in this embodiment, when the tracked object is a surgical instrument, the pose of the surgical instrument can be determined according to the pose of the tracking component.

[0058] For the technical solution of the image navigation method provided by the embodiment of the present invention, when the decoding results of the first feature code patterns of at least two current images all conform to the preset verification rules, it indicates that the coordinates of at least three preset feature positions of the first feature code pattern extracted from each current image are accurate. Therefore, the pose of the first feature code pattern can be determined according to the positional relationships between the at least three preset feature positions corresponding to each current image and the marker pattern, and the pose of the tracking component where the first feature code pattern is located can be determined according to the pose of the first feature code pattern, so as to determine the pose of the tracked object corresponding to the tracking component; compared with directly positioning the structure of the tracking component, the structure of the tracking component can be simplified and the accuracy of navigation can be improved.

[0059] Embodiment Two

[0060] Figure 6 is a structural block diagram of the image navigation device provided by the embodiment of the present invention. This device is used to execute the image navigation method provided by any of the above embodiments, and this device can be implemented as software or hardware. This device includes:

[0061] An image acquisition module 21, configured to acquire at least two current images both including a first feature code pattern and a marker pattern through at least two cameras; the first feature code pattern is disposed on the surface of the tracking component, and includes a polygonal contour and at least two sub-regions disposed within the contour. The contour includes at least three convex corner points, the at least two sub-regions are set to at least two colors, the shooting perspectives of the at least two cameras are different, and the marker pattern is disposed in the region of interest;

[0062] A decoding module 22, configured to determine the position coordinates of each sub-region of the first feature code pattern of at least two current images according to at least three preset feature positions of the contour, and determine the decoding results respectively corresponding to the first feature code patterns of at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region;

[0063] A position relationship determination module 23, configured to determine the position relationships between at least three preset feature position points and the marking pattern respectively if the decoding results of the first feature code patterns of at least two current images all conform to a preset verification rule;

[0064] A display module 24, configured to determine the pose of the object to be tracked corresponding to the tracking component according to the position relationship, and display the pose in real time on a target medical image, where the target medical image includes marking information corresponding to the marking pattern.

[0065] Optionally, the at least three preset feature positions include at least three convex corner points.

[0066] Optionally, the decoding module 22 is configured to respectively determine the coordinates of at least three convex corner points of the first feature code patterns of at least two current images; and determine the position coordinates of each sub-region in the at least two current images according to the coordinates of the at least three convex corner points and a pre-stored sub-region coordinate combination, where the sub-region coordinate combination includes the relative coordinates of each sub-region with respect to the at least three convex corner points.

[0067] Optionally, the decoding module 22 is configured to perform threshold segmentation on at least two current images respectively to obtain at least two binary images; extract contour sets from the at least two binary images respectively; if the number of convex corner point coordinates of the current contour is greater than or equal to three, determine whether the pre-stored sub-region coordinate combination is located inside the current contour; if so, use the current contour as the contour of the first feature code pattern, and use the coordinates of the at least three convex corner points as the coordinates of at least three convex corner points of the first feature code pattern; if not, delete the current contour, use the next contour as the current contour, and jump to the step of determining whether the pre-stored sub-region coordinate combination is located inside the current contour if the number of convex corner point coordinates of the current contour is greater than or equal to three.

[0068] Optionally, the marking pattern is in the shape of a marker, the marker is arranged on a marking component, and the marking component is fixedly arranged in the region of interest.

[0069] Optionally, the marking pattern is a second feature code pattern, the second feature code pattern is arranged on a marking component, the marking component is further provided with a marker, the position relationship between the second feature code pattern and the marker is known, and the second feature code is within the imaging ranges of the at least two cameras;

[0070] The decoding module 22 is further configured to determine the colors of the sub-regions of the second feature code pattern in the at least two current images, and determine the decoding result corresponding to the second feature code pattern in the at least two current images according to the colors of the sub-regions and the preset arrangement order of the sub-regions;

[0071] The position relationship determination module 23 is configured to determine the position relationship between the first feature code pattern and the second feature code pattern in at least two current images if the decoding results of the first feature code patterns corresponding to at least two current images and the decoding result of the second feature code pattern all conform to the preset verification rules; and determine the position relationship between the first feature code pattern and the marker in at least two current images according to the position relationship and the pre-stored position relationship between the second feature code pattern and the marker.

[0072] Optionally, the position relationship determination module 23 is configured to determine the position relationship between the first feature code pattern and the second feature code pattern in at least two current images if the decoding results of the first feature code patterns corresponding to at least two current images are consistent with the decoding results of the pre-stored first feature code patterns, and at the same time, the decoding results of the second feature code patterns corresponding to at least two current images are consistent with the decoding results of the pre-stored second feature code patterns.

[0073] In the technical solution of the image navigation device provided by the embodiment of the present invention, when the decoding results of the first feature code patterns of at least two current images all conform to the preset verification rules, it indicates that the coordinates of at least three preset feature positions of the first feature code pattern extracted from each current image are accurate. Therefore, the pose of the first feature code pattern can be determined according to the position relationship between at least three preset feature positions corresponding to each current image and the marker pattern, and the pose of the tracking component where the first feature code pattern is located can be determined according to the pose of the first feature code pattern, so as to determine the pose of the tracked object corresponding to the tracking component; compared with directly positioning the structure of the tracking component, the structure of the tracking component can be simplified and the navigation accuracy can be improved.

[0074] The image navigation device provided by the embodiment of the present invention can execute the image navigation method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0075] Embodiment III

[0076] Figure 7 It is a schematic structural diagram of the server device provided by Embodiment III of the present invention. As Figure 7 shown, the device includes a processor 301, a memory 302, an input device 303, and an output device 304; the number of processors 301 in the device can be one or more, Figure 7 taking one processor 301 as an example; the processor 301, the memory 302, the input device 303, and the output device 304 in the device can be connected through a bus or other means, Figure 7 taking the connection through a bus as an example.

[0077] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the image navigation method in the embodiments of the present invention (for example, the image acquisition module 21, the decoding module 22, the position relationship determination module 23, and the display module 24). The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 302, that is, implements the above-mentioned image navigation method.

[0078] The memory 302 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 302 may further include a memory remotely set relative to the processor 301, and these remote memories can be connected to the device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0079] The input device 303 can be used to receive input digital or character information and generate key signal inputs related to the user settings and function controls of the device.

[0080] The output device 304 may include a display device such as a display screen, for example, the display screen of a user terminal.

[0081] Embodiment 4

[0082] The embodiments of the present invention further provide a storage medium containing computer-executable instructions, and the computer-executable instructions are used to execute an image navigation method when executed by a computer processor. The method includes:

[0083] Obtaining at least two current images each including a first feature code pattern and a marker pattern through at least two cameras; the first feature code pattern is disposed on the surface of the tracking component and includes a polygonal contour and at least two sub-regions disposed within the contour, the contour includes at least three convex corner points, the at least two sub-regions are set to at least two colors, the shooting perspectives of the at least two cameras are different, and the marker pattern is disposed in the region of interest;

[0084] Determining the position coordinates of each sub-region of the first feature code pattern of the at least two current images according to at least three preset feature positions of the contour, and determining the decoding results respectively corresponding to the first feature code patterns of the at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region;

[0085] If the decoding results of the first feature code patterns of the at least two current images all conform to a preset verification rule, determine the positional relationships between the at least three preset feature positions and the marker pattern respectively;

[0086] Determine the pose of the object to be tracked corresponding to the tracking component according to the positional relationships, and display the pose in real time on a target medical image, where the target medical image includes the marker information corresponding to the marker pattern.

[0087] Certainly, for a storage medium containing computer-executable instructions provided by an embodiment of the present invention, the computer-executable instructions are not limited to the method operations described above, and can also execute relevant operations in the image navigation method provided by any embodiment of the present invention.

[0088] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, 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 a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the image navigation method described in various embodiments of the present invention.

[0089] It should be noted that in the embodiments of the above image navigation device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0090] Note that the above is only a preferred embodiment of the present invention and the applied technical principle. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described here, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An image navigation method, characterized in that, Including: Obtaining at least two current images each including a first feature code pattern and a marker pattern through at least two cameras; the first feature code pattern is disposed on the surface of a tracking component, and includes a polygonal contour and at least two sub-regions disposed within the contour, the contour includes at least three convex corner points, the at least two sub-regions are set to at least two colors, the shooting perspectives of the at least two cameras are different, and the marker pattern is disposed in the region of interest; Determining the position coordinates of each sub-region of the first feature code pattern of the at least two current images according to at least three preset feature positions of the contour, and determining the decoding results respectively corresponding to the first feature code patterns of the at least two current images according to the colors corresponding to the position coordinates of each sub-region and the preset arrangement order of each sub-region; If the decoding results of the first feature code patterns of the at least two current images all conform to the preset verification rules, then determining the positional relationships between the at least three preset feature positions and the marker pattern respectively; Determining the pose of the tracked object corresponding to the tracking component according to the positional relationships, and displaying the pose in real time on a target medical image, where the target medical image includes the marker information corresponding to the marker pattern.

2. The method according to claim 1, characterized in that The at least three preset feature positions include at least three convex corner points.

3. The method according to claim 2, wherein The determining the position coordinates of each sub-region of the first feature code pattern of the at least two current images according to at least three preset feature positions of the contour includes: Respectively determining the coordinates of at least three convex corner points of the first feature code pattern of the at least two current images; Determining the position coordinates of each sub-region in the at least two current images according to the coordinates of the at least three convex corner points and the pre-stored sub-region coordinate combinations, where the sub-region coordinate combinations include the relative coordinates of each sub-region with respect to the at least three convex corner points.

4. The method according to claim 3, wherein The respectively determining the coordinates of at least three convex corner points of the first feature code pattern of the at least two current images includes: Performing threshold segmentation on the at least two current images respectively to obtain at least two binary images; Respectively extracting contour sets from the at least two binary images; If the number of convex corner point coordinates of the current contour is greater than or equal to three, then determining whether the pre-stored sub-region coordinate combinations are located inside the current contour; If so, taking the current contour as the contour of the first feature code pattern, and taking the coordinates of the at least three convex corner points as the coordinates of the at least three convex corner points of the first feature code pattern; If not, deleting the current contour, taking the next contour as the current contour, and jumping to the step of determining whether the pre-stored sub-region coordinate combinations are located inside the current contour if the number of convex corner point coordinates of the current contour is greater than or equal to three.

5. The method according to claim 1, characterized in that, The marker pattern is in the shape of a marker, the marker is disposed on a marker component, and the marker component is fixedly disposed in the region of interest.

6. The method according to claim 1, wherein The marked pattern is a second feature code pattern, the second feature code pattern is disposed on a marking component, the marking component is further provided with a marker, the positional relationship between the second feature code pattern and the marker is known, and the second feature code is within the imaging ranges of the at least two cameras; The method further includes: determining the colors of the sub-regions of the second feature code pattern in the at least two current images, and determining the decoding results corresponding to the second feature code pattern in the at least two current images according to the colors of the sub-regions and the preset arrangement order of the sub-regions; If the decoding results of the first feature code patterns of the at least two current images all conform to the preset verification rules, then determining the positional relationships between the at least three convex corner points and the marked pattern respectively, includes: If the decoding results of the first feature code patterns corresponding to the at least two current images and the decoding results of the second feature code patterns all conform to the preset verification rules, then determining the positional relationships between the first feature code patterns and the second feature code patterns in the at least two current images; According to the positional relationships and the pre-stored positional relationship between the second feature code pattern and the marker, determining the positional relationships between the first feature code patterns and the marker in the at least two current images.

7. The method according to claim 6, characterized in that, If the decoding results of the first feature code patterns corresponding to the at least two current images and the decoding results of the second feature code patterns all conform to the preset verification rules, then determining the positional relationships between the first feature code patterns and the second feature code patterns in the at least two current images, includes: If the decoding results of the first feature code patterns corresponding to the at least two current images are consistent with the decoding results of the pre-stored first feature code patterns, and at the same time the decoding results of the second feature code patterns corresponding to the at least two current images are consistent with the decoding results of the pre-stored second feature code patterns, then determining the positional relationships between the first feature code patterns and the second feature code patterns in the at least two current images.

8. An image navigation device, characterized in that, including: an image acquisition module, configured to acquire at least two current images each including a first feature code pattern and a marked pattern through at least two cameras; the first feature code pattern is disposed on the surface of a tracking component, and includes a polygonal contour and at least two sub-regions disposed within the contour, the contour includes at least three convex corner points, the at least two sub-regions are set to at least two colors, the shooting perspectives of the at least two cameras are different, and the marked pattern is disposed in the region of interest; a decoding module, configured to determine the position coordinates of the sub-regions of the first feature code pattern in the at least two current images according to at least three preset feature positions of the contour, and determine the decoding results corresponding to the first feature code pattern in the at least two current images respectively according to the colors corresponding to the position coordinates of the sub-regions and the preset arrangement order of the sub-regions; A position relationship determination module, configured to determine the position relationships between the at least three preset feature positions and the marker pattern respectively if the decoding results of the first feature code patterns of the at least two current images all conform to a preset verification rule; A display module, configured to determine the pose of the object to be tracked corresponding to the tracking component according to the position relationship, and to display the pose in real time on a target medical image, where the target medical image includes marker information corresponding to the marker pattern.

9. A server device, characterized in that, The server device includes: One or more processors; A storage device, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the image navigation method according to any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions are used to execute the image navigation method according to any one of claims 1-7 when executed by a computer processor.

Images