Auxiliary positioning equipment and method for traditional Chinese medicine fire needle

Abstract

The invention discloses an auxiliary positioning device and method for a traditional Chinese medicine fire needle, and belongs to the technical field of traditional Chinese medicine fire acupuncture and moxibustion and data recognizing.The method comprises the steps that after a human body to be subjected to acupuncture and moxibustion is fixed on an acupuncture and moxibustion bed, an image of the human body to be positioned on the acupuncture and moxibustion bed is collected; performing correction processing on the to-be-positioned human body image by adopting a deep learning algorithm so as to convert the to-be-positioned human body image into a standard image, and obtaining a corrected to-be-positioned human body image; the target acupuncture point of the to-be-positioned human body image is determined on the basis of the corrected to-be-positioned human body image, and then infrared marking positioning is adopted on the basis of the target acupuncture point, so that auxiliary positioning of the traditional Chinese medicine fire needle can be realized, and the problem that the accurate position of fire acupuncture diagnosis and treatment is difficult to determine due to insufficient traditional Chinese medicine experience in the prior art is solved.

Description

Technical Field

[0001] The present invention belongs to the field of traditional Chinese medicine fire acupuncture technology and data recognition technology, and specifically relates to an auxiliary positioning device and method for traditional Chinese medicine fire needles. Background Art

[0002] Fire needle therapy is a traditional Chinese medicine treatment method that uses special needles that are heated to red and then inserted into the acupoints or affected areas of the human body to treat various diseases. According to Chinese medicine theory, fire needle therapy can relieve and treat functional loss with the help of external yang energy, such as replenishing yang deficiency and promoting the excretion of internal evil. The operation method of fire acupuncture is mainly divided into the following steps: according to the patient's condition, choose the appropriate acupoints for acupuncture; before acupuncture, the acupuncture site needs to be disinfected to avoid infection; according to the selected acupoints, acupuncture is performed; using the energy of fire, warm stimulation is performed on the acupuncture site; when the patient feels comfortable, the warm stimulation is stopped. During acupuncture, the patient's reaction should be closely observed so that the treatment plan can be adjusted in time; fire acupuncture can be combined with Chinese medicine, massage and other therapies to achieve better treatment results. During the operation, attention should be paid to the accuracy of acupoint selection, the degree of redness of the needle, and the depth and speed of acupuncture.

[0003] In actual practice, acupuncture positions are often determined by traditional Chinese medicine practitioners themselves, but a large number of traditional Chinese medicine practitioners lack experience and find it difficult to determine the exact position of fire acupuncture treatment. Summary of the invention

[0004] The present invention provides an auxiliary positioning device and method for fire needles in traditional Chinese medicine, which are used to solve the problem in the prior art that it is difficult to determine the exact position of fire acupuncture diagnosis and treatment due to insufficient experience in traditional Chinese medicine.

[0005] In one aspect, the present invention provides an auxiliary positioning device for traditional Chinese medicine fire needles, comprising: an image data acquisition module, an image data correction module, a key point recognition module and an auxiliary positioning module; The image data acquisition module is used to acquire the image of the human body to be located on the acupuncture bed, and transmit the image of the human body to be located to the image data correction module; The image data correction module is used to use a deep learning algorithm to perform correction processing on the human body image to be located, so as to transform the human body image to be located into a standard image, thereby obtaining a corrected human body image to be located; The key point recognition module is used to determine the target acupuncture points of the human body image to be located based on the corrected human body image to be located; The auxiliary positioning module is used to mark the human body on the acupuncture bed using an infrared marking method to generate a first marking point, and adjust the first marking point through a machine vision recognition algorithm until the first marking point coincides with the target acupuncture point of the human body image to be located, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

[0006] Further, the image data acquisition module includes an image acquisition unit and a data transmission unit; The image acquisition unit is used to acquire the picture taken by the fixed camera located above the acupuncture bed, so as to acquire the image of the human body to be located on the acupuncture bed; wherein the lens axis of the fixed camera is perpendicular to the acupuncture bed, and the picture taken by the fixed camera includes the entire acupuncture bed; The data transmission unit is used to transmit the image of the human body to be located acquired by the image acquisition unit to the image data correction module.

[0007] Further, the image data correction module includes an image matching unit, a joint point determination unit and a correction unit; The image matching unit is used to obtain a standard human acupoint map pre-stored in different postures, and use a deep learning algorithm to match the human body image to be located with the standard human body acupoint map, determine the standard human body acupoint map corresponding to the human body image to be located, and obtain a target standard human body acupoint map; The joint point determination unit is used to determine each joint point in the human body image to be located and each joint point in the target standard human body acupuncture point map; The correction unit is used to scale the human body image to be located so that the human body image to be located coincides with the same joint point in the target standard human acupuncture point map, thereby obtaining the corrected human body image to be located; When the human body image to be located is scaled, the scaling operation and the scaling operation sequence are recorded.

[0008] Furthermore, a deep learning algorithm is used to match the human body image to be located with the standard human body acupoint map, and the standard human body acupoint map corresponding to the human body image to be located is determined to obtain the target standard human body acupoint map, including: A deep learning algorithm is used to identify the human body posture in the human body image to be located and determine the predicted posture type; Determine a standard human acupoint map with the same posture type as the predicted posture type, and obtain a target standard human acupoint map; Among them, each standard human acupuncture point map is preset with its own corresponding posture type.

[0009] Further, the key point identification module includes an original point construction unit, a coordinate determination unit and a key point determination unit; The origin point construction unit is used to determine a first origin point corresponding to the target standard human acupuncture point map and a second origin point corresponding to the corrected human body image to be located by taking any joint point as the origin point; The coordinate determination unit is used to determine the first target coordinates corresponding to each acupuncture point in the target standard human acupuncture point map based on the first original point; The key point determination unit is used to determine the second target coordinates in the corrected image of the human body to be located based on the second original point and the target coordinates; wherein the second target coordinates corresponding to the same joint point are the same as the first target coordinates; The key point determination unit is further used to determine the target acupuncture point based on the second target coordinates.

[0010] Further, determining the target acupuncture point based on the second target coordinates includes: Marking the corrected image of the human body to be located according to the second target coordinates to obtain a second marking point; After reversing the order of the scaling operations, the scaling operations are then reversed to obtain a reverse scaling operation sequence; Scaling the image of the human body to be located with the second marking point according to the reverse scaling operation sequence to obtain the original image of the human body to be located; Based on the second original point, the third target coordinates of each second marking point in the original human body image to be located are determined to obtain the target acupuncture point.

[0011] Furthermore, the auxiliary positioning module includes an infrared adjustment unit and an image recognition unit; The infrared adjustment unit is used to mark the human body on the acupuncture bed using an infrared marking method to generate a first marking point; The image recognition unit is used to implement the scheduling image data acquisition module to obtain real-time images, and use a machine vision recognition algorithm to recognize the first marking points in the real-time image to determine the target marking position corresponding to each first marking point; The infrared adjustment unit is also used to adjust the direction of the infrared until each target acupuncture point coincides with a target marking position, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

[0012] Further, a machine vision recognition algorithm is used to recognize the first marking points in the real-time image to determine the target marking position corresponding to each first marking point, including: The YOLO algorithm is used to identify the real-time image to determine the first marking point in the real-time image; The position corresponding to the second original point in the real-time image is used as the third original point, and the target marking position corresponding to each first marking point is determined according to the third original point and the identified first marking point.

[0013] Furthermore, the auxiliary positioning module further includes: a positioning completion notification unit; The positioning completion notification unit is used to generate and display notification information of auxiliary positioning completion after each target acupuncture point coincides with a target mark position.

[0014] In another aspect, the present invention provides an auxiliary positioning method for traditional Chinese medicine fire needles, characterized by comprising: Collecting images of the human body to be positioned on the acupuncture bed; A deep learning algorithm is used to correct the image of the human body to be located, so as to transform the image of the human body to be located into a standard image, thereby obtaining a corrected image of the human body to be located; Determine the target acupuncture point of the human body image to be located based on the corrected human body image to be located; The human body on the acupuncture bed is marked by an infrared marking method to generate a first marking point, and the first marking point is adjusted by a machine vision recognition algorithm until the first marking point coincides with the target acupuncture point of the human body image to be located, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

[0015] The present invention provides an auxiliary positioning device and method for traditional Chinese medicine fire needles. After the person to be acupunctured is fixed on the acupuncture bed, an image of the person to be positioned on the acupuncture bed is collected; a deep learning algorithm is used to correct the image of the person to be positioned, so as to transform the image of the person to be positioned into a standard image, and obtain a corrected image of the person to be positioned; based on the corrected image of the person to be positioned, the target acupoints of the image of the person to be positioned are determined, and then infrared marking is used for positioning based on the target acupoints, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles, and solving the problem in the prior art that it is difficult to determine the accurate position of fire acupuncture diagnosis and treatment due to insufficient experience in traditional Chinese medicine. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] Figure 1 The present invention provides a structural schematic diagram of an auxiliary positioning device for traditional Chinese medicine fire needles.

[0018] Figure 2 The present invention provides a flow chart of an auxiliary positioning method for traditional Chinese medicine fire needles.

[0019] Among them, 101-image data acquisition module, 102-image data correction module, 103-key point recognition module, 104-auxiliary positioning module.

[0020] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0021] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0022] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] Fire needle therapy is a traditional Chinese medicine treatment method that uses special needles that are heated to red and then inserted into acupuncture points or affected areas of the human body to treat various diseases. In actual practice, acupuncture positions are often determined by traditional Chinese medicine practitioners, but a large number of traditional Chinese medicine practitioners lack experience and find it difficult to determine the exact position of fire acupuncture treatment. Therefore, an embodiment of the present invention provides an auxiliary positioning device and method for traditional Chinese medicine fire needles, which uses image analysis for positioning and can effectively assist traditional Chinese medicine practitioners in finding acupuncture points.

[0024] like Figure 1 As shown, the present invention provides an auxiliary positioning device for traditional Chinese medicine fire needles, comprising: an image data acquisition module 101, an image data correction module 102, a key point recognition module 103 and an auxiliary positioning module 104; The image data acquisition module 101 is used to acquire the image of the human body to be located on the acupuncture bed, and transmit the image of the human body to be located to the image data correction module 102; For example, a camera may be fixed above the acupuncture bed in advance, so that the image of the human body to be located on the acupuncture bed can be collected by the image data acquisition module 101. Traditional Chinese medicine acupuncture generally adopts a fixed posture, and the distribution of acupoints on each person's body is the same. Therefore, the location of different acupoints can be determined by analyzing the position of the joints.

[0025] The image data correction module 102 is used to use a deep learning algorithm to correct the image of the human body to be located, so as to transform the image of the human body to be located into a standard image, thereby obtaining a corrected image of the human body to be located; Generally, the standard human acupoint map has corresponding joint positions and different acupoints. Therefore, the image of the human body to be located can be matched with the standard human body acupoint map of the corresponding posture, so that the image of the human body to be located can be converted into an image that can identify acupoints.

[0026] The key point recognition module 103 is used to determine the target acupuncture points of the human body image to be located based on the corrected human body image to be located; The relative positions of joints in the corrected human body image to be located are the same as those in the standard human body acupoint map. In principle, the acupoint positions between joints are also the same. Therefore, the target acupoints of the human body image to be located can be determined based on this.

[0027] The auxiliary positioning module 104 is used to mark the human body on the acupuncture bed using an infrared marking method to generate a first marking point, and adjust the first marking point through a machine vision recognition algorithm until the first marking point coincides with the target acupuncture point of the human body image to be located, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

[0028] The infrared marking method may refer to setting up multiple infrared transmitters that can rotate in multiple directions on the acupuncture bed, and carrying infrared rays on a device similar to a pan-tilt head, so as to achieve multi-directional rotation, thereby changing the landing point of the infrared rays, and finally marking by the landing point of the infrared rays to assist in the positioning of traditional Chinese medicine fire needles.

[0029] In the embodiment of the present invention, the image data acquisition module 101 includes an image acquisition unit and a data transmission unit; The image acquisition unit is used to acquire the picture taken by the fixed camera located above the acupuncture bed, so as to acquire the image of the human body to be located on the acupuncture bed; wherein the lens axis of the fixed camera is perpendicular to the acupuncture bed, and the picture taken by the fixed camera includes the entire acupuncture bed; When the camera is fixed, the picture it captures is also fixed. That is to say, even if different images are captured, the pixels that change are only the position of the human body to be acupunctured. Therefore, when the human body posture is fixed, acupoint recognition and positioning can be performed.

[0030] The data transmission unit is used to transmit the image of the human body to be located acquired by the image acquisition unit to the image data correction module 102.

[0031] In the embodiment of the present invention, the image data correction module 102 includes an image matching unit, a joint point determination unit and a correction unit; The image matching unit is used to obtain a standard human acupoint map pre-stored in different postures, and use a deep learning algorithm to match the human body image to be located with the standard human body acupoint map, determine the standard human body acupoint map corresponding to the human body image to be located, and obtain a target standard human body acupoint map; The joint point determination unit is used to determine each joint point in the human body image to be located and each joint point in the target standard human body acupuncture point map; The correction unit is used to scale the human body image to be located so that the human body image to be located coincides with the same joint point in the target standard human acupuncture point map, thereby obtaining the corrected human body image to be located; When the human body image to be located is scaled, the scaling operation and the scaling operation sequence are recorded.

[0032] For example, the zoom operation can be performed by zooming in and out, zooming in and out, zooming in and out, and zooming in and out, thereby changing the image ratio so that two human bodies in the same posture can overlap, that is, the human body in the human body image to be located overlaps with the human body in the target standard human body acupoint map, and finally determining the target acupoint.

[0033] In an embodiment of the present invention, a deep learning algorithm is used to match the human body image to be located with the standard human body acupoint map, determine the standard human body acupoint map corresponding to the human body image to be located, and obtain the target standard human body acupoint map, including: A deep learning algorithm is used to identify the human body posture in the human body image to be located and determine the predicted posture type; Determine a standard human acupoint map with the same posture type as the predicted posture type, and obtain a target standard human acupoint map; Among them, each standard human acupuncture point map is preset with its own corresponding posture type.

[0034] Optionally, the deep learning algorithm may be a convolutional neural network algorithm, which may be trained using a pre-determined human posture diagram and corresponding posture types, so that the convolutional neural network algorithm has classification capabilities and can predict posture types of human body images to be located.

[0035] It is worth mentioning that other posture types can also be set, so as to automatically determine whether the human body posture on the acupuncture bed is correct, and perform positioning after the posture is correct.

[0036] In the embodiment of the present invention, the key point identification module 103 includes an original point construction unit, a coordinate determination unit and a key point determination unit; The origin point construction unit is used to determine a first origin point corresponding to the target standard human acupuncture point map and a second origin point corresponding to the corrected human body image to be located by taking any joint point as the origin point; The coordinate determination unit is used to determine the first target coordinates corresponding to each acupuncture point in the target standard human acupuncture point map based on the first original point; The key point determination unit is used to determine the second target coordinates in the corrected image of the human body to be located based on the second original point and the target coordinates; wherein the second target coordinates corresponding to the same joint point are the same as the first target coordinates; The key point determination unit is further used to determine the target acupuncture point based on the second target coordinates.

[0037] After determining the original point, the pixel coordinates of each other pixel can be determined in units of pixels to achieve positioning.

[0038] In an embodiment of the present invention, determining the target acupuncture point based on the second target coordinates includes: Marking the corrected image of the human body to be located according to the second target coordinates to obtain a second marking point; After reversing the order of the scaling operations, the scaling operations are then reversed to obtain a reverse scaling operation sequence; Scaling the image of the human body to be located with the second marking point according to the reverse scaling operation sequence to obtain the original image of the human body to be located; Based on the second original point, the third target coordinates of each second marking point in the original human body image to be located are determined to obtain the target acupuncture point.

[0039] In the embodiment of the present invention, the auxiliary positioning module 104 includes an infrared adjustment unit and an image recognition unit; The infrared adjustment unit is used to mark the human body on the acupuncture bed using an infrared marking method to generate a first marking point; The image recognition unit is used to implement the scheduling image data acquisition module 101 to obtain real-time images, and use a machine vision recognition algorithm to recognize the first marking points in the real-time image to determine the target marking position corresponding to each first marking point; The infrared adjustment unit is also used to adjust the direction of the infrared until each target acupuncture point coincides with a target marking position, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

[0040] In an embodiment of the present invention, a machine vision recognition algorithm is used to recognize first marking points in a real-time image, and a target marking position corresponding to each first marking point is determined, including: The YOLO algorithm is used to identify the real-time image to determine the first marking point in the real-time image; The position corresponding to the second original point in the real-time image is used as the third original point, and the target marking position corresponding to each first marking point is determined according to the third original point and the identified first marking point.

[0041] Optionally, the YOLO algorithm may be pre-trained, and the training steps include: Initialize the model parameters of the YOLO algorithm; A training sample image and an expected output image are obtained, wherein the expected output image is used to characterize the training sample image including a true value label, and the true value label is used to characterize the manually calibrated actual frame; in an embodiment of the present invention, the manually calibrated actual frame actually refers to the actual frame corresponding to the infrared landing point, and the size of the prediction frame can be adjusted to improve the accuracy.

[0042] Input the training sample image into the YOLO algorithm, obtain the actual output image, and obtain the loss function value corresponding to the YOLO algorithm based on the expected output image and the actual output image; Determine whether the loss function value is less than the preset threshold. If so, use the current model parameters as the final parameters of the YOLO algorithm. Otherwise, update the model parameters of the YOLO algorithm and enter the next training until the loss function value is less than the preset threshold to obtain the final parameters of the YOLO algorithm.

[0043] The loss function value is obtained through the loss function, and the loss function is:

[0044] in, represents the loss function, represents the weight of positioning loss, S represents the number of grids in the feature map, and B represents the number of prediction boxes for each grid in the feature map. represents the positioning loss; represents the first coefficient, represents the second coefficient; for the first i The first j When the IoU value between the predicted box and the corresponding actual box in the expected output image is greater than a given threshold, the predicted box with the largest IoU value is taken as a positive sample, and its corresponding first coefficient is 1, the second coefficient is 0, the first coefficient corresponding to other prediction boxes and the second coefficient are all 0; when the IoU value between all predicted boxes and the corresponding actual boxes in the expected output image is less than a given threshold, the first coefficients corresponding to all predicted boxes are and the second coefficient All are 0; Indicates the prediction confidence corresponding to the prediction box, Indicates the actual confidence corresponding to the actual box, represents the first penalty coefficient, represents the second penalty coefficient, classes represents the category set, Indicates the feature map i The first j The predicted boxes output belong to the category c The probability of Represents the probability that the image actually belongs to category c.

[0045] It is worth noting that the coordinates in the embodiment of the present invention may refer to the average coordinates of multiple pixels. For example, a joint point may include multiple pixels, so the average coordinates of the pixels may be used to represent the position of the key point.

[0046] In the embodiment of the present invention, the auxiliary positioning module 104 further includes: a positioning completion notification unit; The positioning completion notification unit is used to generate and display notification information of auxiliary positioning completion after each target acupuncture point coincides with a target mark position.

[0047] The present invention provides an auxiliary positioning device for traditional Chinese medicine fire needles. After the person to be acupunctured is fixed on the acupuncture bed, an image of the person to be positioned is collected on the acupuncture bed; a deep learning algorithm is used to correct the image of the person to be positioned, so as to transform the image of the person to be positioned into a standard image, so as to obtain a corrected image of the person to be positioned; based on the corrected image of the person to be positioned, target acupuncture points of the image of the person to be positioned are determined, and then infrared marking is used for positioning based on the target acupuncture points, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles, and solving the problem in the prior art that it is difficult to determine the accurate position of fire acupuncture diagnosis and treatment due to insufficient experience in traditional Chinese medicine.

[0048] like Figure 2 As shown, an embodiment of the present invention provides an auxiliary positioning method for traditional Chinese medicine fire needles, characterized by comprising: S201, collecting an image of a human body to be positioned on the acupuncture bed; S202, using a deep learning algorithm to perform correction processing on the image of the human body to be located, so as to transform the image of the human body to be located into a standard image, and obtain a corrected image of the human body to be located; S203, determining the target acupuncture points of the human body image to be located based on the corrected human body image to be located; S204, using an infrared marking method to mark the human body on the acupuncture bed to generate a first marking point, and adjusting the first marking point through a machine vision recognition algorithm until the first marking point coincides with the target acupuncture point of the human body image to be located, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

[0049] An auxiliary positioning method for traditional Chinese medicine fire needles provided in an embodiment of the present invention can be executed by the above-mentioned device, and its principles and beneficial effects are similar, which will not be described in detail here.

[0050] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present invention is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable device. The computer program or instruction may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instruction may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it may also be an optical medium, such as a digital video disc (DVD); it may also be a semiconductor medium, such as a solid state drive (SSD).

[0051] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An auxiliary positioning device for traditional Chinese medicine fire needles, characterized in that: include: Image data acquisition module, image data correction module, key point recognition module and auxiliary positioning module; The image data acquisition module is used to acquire the image of the human body to be located on the acupuncture bed, and transmit the image of the human body to be located to the image data correction module; The image data correction module is used to use a deep learning algorithm to perform correction processing on the human body image to be located, so as to transform the human body image to be located into a standard image, thereby obtaining a corrected human body image to be located; The key point recognition module is used to determine the target acupuncture points of the human body image to be located based on the corrected human body image to be located; The auxiliary positioning module is used to mark the human body on the acupuncture bed using an infrared marking method to generate a first marking point, and adjust the first marking point through a machine vision recognition algorithm until the first marking point coincides with the target acupuncture point of the human body image to be located, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

2. The auxiliary positioning device for traditional Chinese medicine fire needle according to claim 1, characterized in that: The image data acquisition module includes an image acquisition unit and a data transmission unit; The image acquisition unit is used to acquire the picture taken by the fixed camera located above the acupuncture bed, so as to acquire the image of the human body to be located on the acupuncture bed; wherein the lens axis of the fixed camera is perpendicular to the acupuncture bed, and the picture taken by the fixed camera includes the entire acupuncture bed; The data transmission unit is used to transmit the image of the human body to be located acquired by the image acquisition unit to the image data correction module.

3. The auxiliary positioning device for traditional Chinese medicine fire needle according to claim 1, characterized in that: The image data correction module includes an image matching unit, a joint point determination unit and a correction unit; The image matching unit is used to obtain a standard human acupoint map pre-stored in different postures, and use a deep learning algorithm to match the human body image to be located with the standard human body acupoint map, determine the standard human body acupoint map corresponding to the human body image to be located, and obtain a target standard human body acupoint map; The joint point determination unit is used to determine each joint point in the human body image to be located and each joint point in the target standard human body acupuncture point map; The correction unit is used to scale the human body image to be located so that the human body image to be located coincides with the same joint point in the target standard human acupuncture point map, thereby obtaining the corrected human body image to be located; When the human body image to be located is scaled, the scaling operation and the scaling operation sequence are recorded.

4. The auxiliary positioning device for traditional Chinese medicine fire needles according to claim 3, characterized in that: A deep learning algorithm is used to match the human body image to be located with the standard human body acupoint map, determine the standard human body acupoint map corresponding to the human body image to be located, and obtain the target standard human body acupoint map, including: A deep learning algorithm is used to identify the human body posture in the human body image to be located and determine the predicted posture type; Determine a standard human acupoint map with the same posture type as the predicted posture type, and obtain a target standard human acupoint map; Among them, each standard human acupuncture point map is preset with its own corresponding posture type.

5. The auxiliary positioning device for traditional Chinese medicine fire needle according to claim 3, characterized in that: The key point identification module includes an original point construction unit, a coordinate determination unit and a key point determination unit; The origin point construction unit is used to determine a first origin point corresponding to the target standard human acupuncture point map and a second origin point corresponding to the corrected human body image to be located by taking any joint point as the origin point; The coordinate determination unit is used to determine the first target coordinates corresponding to each acupuncture point in the target standard human acupuncture point map based on the first original point; The key point determination unit is used to determine the second target coordinates in the corrected image of the human body to be located based on the second original point and the target coordinates; wherein the second target coordinates corresponding to the same joint point are the same as the first target coordinates; The key point determination unit is further used to determine the target acupuncture point based on the second target coordinates.

6. The auxiliary positioning device for traditional Chinese medicine fire needles according to claim 5, characterized in that: Determining the target acupuncture point based on the second target coordinates includes: Marking the corrected image of the human body to be located according to the second target coordinates to obtain a second marking point; After reversing the order of the scaling operations, the scaling operations are then reversed to obtain a reverse scaling operation sequence; Scaling the image of the human body to be located with the second marking point according to the reverse scaling operation sequence to obtain the original image of the human body to be located; Based on the second original point, the third target coordinates of each second marking point in the original human body image to be located are determined to obtain the target acupuncture point.

7. The auxiliary positioning device for traditional Chinese medicine fire needles according to claim 6, characterized in that: The auxiliary positioning module includes an infrared adjustment unit and an image recognition unit; The infrared adjustment unit is used to mark the human body on the acupuncture bed using an infrared marking method to generate a first marking point; The image recognition unit is used to implement the scheduling image data acquisition module to obtain real-time images, and use a machine vision recognition algorithm to recognize the first marking points in the real-time image to determine the target marking position corresponding to each first marking point; The infrared adjustment unit is also used to adjust the direction of the infrared until each target acupuncture point coincides with a target marking position, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

8. The auxiliary positioning device for traditional Chinese medicine fire needles according to claim 7, characterized in that: Using a machine vision recognition algorithm to recognize the first marking points in the real-time image, and determining the target marking position corresponding to each first marking point, including: The YOLO algorithm is used to identify the real-time image to determine the first marking point in the real-time image; The position corresponding to the second original point in the real-time image is used as the third original point, and the target marking position corresponding to each first marking point is determined according to the third original point and the identified first marking point.

9. The auxiliary positioning device for traditional Chinese medicine fire needles according to claim 7, characterized in that: The auxiliary positioning module also includes: a positioning completion notification unit; The positioning completion notification unit is used to generate and display notification information of auxiliary positioning completion after each target acupuncture point coincides with a target mark position.

10. A method for auxiliary positioning of fire needles in traditional Chinese medicine, characterized in that: include: Collecting images of the human body to be positioned on the acupuncture bed; A deep learning algorithm is used to correct the image of the human body to be located, so as to transform the image of the human body to be located into a standard image, thereby obtaining a corrected image of the human body to be located; Determine the target acupuncture point of the human body image to be located based on the corrected human body image to be located; The human body on the acupuncture bed is marked by an infrared marking method to generate a first marking point, and the first marking point is adjusted by a machine vision recognition algorithm until the first marking point coincides with the target acupuncture point of the human body image to be located, thereby realizing auxiliary positioning of traditional Chinese medicine fire needles.

Images