Neck acupoint recognition method and device, massage robot and digital human

Abstract

The invention provides a neck acupoint recognition method and device, a massage robot and a digital human, and belongs to the technical field of acupoint recognition, and the method comprises the steps: determining key points, related to transverse and straight cun, of a neck image to be recognized and feature points related to meridians, and determining unit straight cun and unit transverse cun of the neck image to be recognized based on the key points, based on the feature points, the Ren vessel and the Du vessel of the neck image to be identified are determined; the key points comprise the impression hole; determining a laryngeal knot of the neck image to be identified; determining the position relation between the throat knot, the Yintang acupoint, the Ren meridian and the governor meridian and the first type of neck acupoints, and determining the first type of neck acupoints based on the throat knot, the Yintang acupoint, the Ren meridian, the governor meridian, the position relation, the unit straight cun and the unit transverse cun; and determining an association relationship between the first type of neck acupuncture points and the second type of neck acupuncture points, and determining the second type of neck acupuncture points based on the association relationship and the first type of neck acupuncture points. The method does not need to calibrate the neck acupoints in advance, and improves the recognition accuracy and efficiency of the neck acupoints.

Description

Technical Field

[0001] The present invention relates to the technical field of acupoint recognition, and in particular to a method and device for recognizing neck acupoints, a massage robot and a digital human. Background Art

[0002] With the extensive use of mobile phones, tablets and other electronic products, the cervical spine has been immobile for a long time, which seriously threatens the health of the cervical spine. Chinese medicine massage can solve 95% of cervical problems. Massage, kneading, pressing, pressing and rubbing the acupoints can effectively eliminate the fatigue of the neck muscles, dredge the meridians, promote blood circulation, improve the blood circulation of the head and neck, and effectively relieve the discomfort caused by cervical spondylosis. Acupoint massage is convenient and easy to operate, and is particularly suitable for daily health massage. At present, acupoint positioning is mostly manually positioned by professional doctors, and requires a lot of professional training, which is not conducive to the daily health care of non-professionals performing acupoint massage, nor is it conducive to the automation of massage medical equipment.

[0003] The existing patent CN111598949A discloses an automatic positioning method for acupuncture points on the head and neck of the human body, which requires training a model based on an image set with acupuncture points marked, so as to directly obtain the neck acupuncture points through the trained model. That is, in the prior art, a model is trained whose input is an image to be identified and whose output is a neck acupuncture point, and the training process of the model depends on the accurate marking of the neck acupuncture points. It has the following technical problems: manual marking is required to obtain a second image set in order to realize the recognition of neck acupuncture points, which depends on the accuracy of manual marking, and the recognition accuracy is low. In addition, the labeling process is complicated and time-consuming, resulting in low recognition efficiency of neck acupuncture points.

[0004] Therefore, there is an urgent need to provide a neck acupoint recognition method, device, massage robot and digital human to improve the recognition accuracy and efficiency of neck acupoints. Summary of the invention

[0005] In view of this, it is necessary to provide a neck acupoint recognition method, device, massage robot and digital human to solve the technical problem existing in the prior art that the recognition accuracy and efficiency of neck acupoints are low due to reliance on manual labeling.

[0006] In a first aspect, the present invention provides a method for identifying neck acupoints, comprising: Determine key points related to the horizontal and vertical inches and feature points related to the meridians of the neck image to be identified, and determine the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determine the Ren meridian and Du meridian of the neck image to be identified based on the feature points; the key points include Yintang acupoint; Determining the Adam's apple of the neck image to be identified; Determine the positional relationship between the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, and the first type of neck acupoints, and determine the first type of neck acupoints based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit straight inch, and the unit horizontal inch; Determine the association relationship between the first category of neck acupoints and the second category of neck acupoints, and determine the second category of neck acupoints based on the association relationship and the first category of neck acupoints.

[0007] In some possible implementations, the key points also include a left forehead hair corner point and a right forehead hair corner point related to the horizontal inch and a front hairline related to the vertical inch; the feature points include a left earlobe point, a right earlobe point, a left acromion point and a right acromion point; then determining the key points related to the horizontal and vertical inches and the feature points related to the meridians of the neck image to be identified includes: Detecting the neck image to be identified to obtain a plurality of key points to be selected, and determining the left forehead hair corner point, the right forehead hair corner point, the first target point and the second target point related to the Yintang acupoint, and the left earlobe point, the right earlobe point, the left acromion point, and the right acromion point among the plurality of key points to be selected based on a mapping relationship between the key point numbers to be selected and the key points to be selected; Determine the midpoint between the first target point and the second target point as the Yintang acupoint; A face rectangular frame of the neck image to be identified is determined, and a frame line close to the top of the head in the face rectangular frame is used as the front hairline.

[0008] In some possible implementations, determining the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determining the Ren meridian and the Du meridian of the neck image to be identified based on the feature points includes: Determine the longitudinal distance and the longitudinal bone cun between the Yintang acupoint and the front hairline, and the transverse distance and the transverse bone cun between the left frontal hair corner point and the right frontal hair corner point; Determine the unit vertical inch based on the longitudinal distance and the longitudinal bone inch, and determine the unit horizontal inch based on the horizontal distance and the horizontal bone inch; Determine a first connecting line and a first midpoint of the left earlobe point and the right earlobe point, and use a first straight line on the front of the human body that is perpendicular to the first connecting line and passes through the first midpoint as the Ren meridian, and determine a second connecting line and a second midpoint of the left acromion point and the right acromion point, and use a second straight line on the back of the human body that is perpendicular to the second connecting line and passes through the second midpoint as the Du meridian.

[0009] In some possible implementations, determining the Adam's apple of the neck image to be identified includes: Determine a plurality of candidate reference points and a plurality of candidate reference point numbers of the neck image to be identified; The Adam's apple is determined based on the Adam's apple number of the Adam's apple and a pre-constructed association relationship between the candidate reference point numbers and the candidate reference point positions.

[0010] In some possible implementations, the positional relationship is a bone positional relationship; determining the first type of cervical acupoints based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit vertical inch and the unit horizontal inch includes: Determine the bone position of the first type of cervical acupuncture points based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Du meridian and the position relationship; The bone position is converted into an image position based on the unit vertical inch and the unit horizontal inch, and the image position is used as the position of the first type of cervical acupuncture points.

[0011] In some possible implementations, the first type of neck acupoints includes Renying, Futu, Tiantu, and Tianchuang located on the front neck, and Yamen and Dazhui located on the back neck; the positional relationships include: The Renying point is 1.5 horizontal inches away from the Adam's apple; The Futu point is 3 horizontal inches away from the Adam's apple; The Tiantu point is located on the Ren meridian, below the Adam's apple and 2 inches away from the Adam's apple; The Tianchuang point is 3.5 horizontal inches away from the Adam's apple; The Yamen acupoint is located on the Governor Vessel, 14.5 straight inches away from the Yintang acupoint; The Dazhui point is located on the Du meridian, 18 straight inches away from the Yintang point.

[0012] In some possible implementations, the second type of neck acupoints include Lianquan, Qishe, Shuitu, and Quepen located on the front neck, and Fengfu, Fengchi, Jingbailao, and Tianzhu located on the back neck; the association relationship is: The Lianquan acupoint is located at the midpoint of the line connecting the chin and the Adam's apple; the chin is the lower frame line of the rectangular frame of the human face; The Qishe point is 1.5 horizontal inches away from the Tiantu point; The Shuitu point is located on the Ren meridian and at the midpoint of the line connecting the Qishe point and the Renying point; The Quepen point is the intersection of the extended line of the line connecting the Tiantu point and the Qishe point and the target line segment, and the target line segment is a line segment perpendicular to the line connecting the left nipple and the right nipple and passing through the left nipple or the right nipple; The Tianding point is located at the midpoint of the line connecting the Futu point and the Quepen point; The Fengfu point is located above the Yamen point, 0.5 straight inches away from the Yamen point; The Fengchi point is 1.3 horizontal inches away from the Fengfu point; The Jing Bailao point is located above the Dazhui point, 2 vertical inches and 1 horizontal inch away from the Dazhui point; The Tianzhu point is located below the Yamen point, 0.3 vertical inches and 1.3 horizontal inches away from the Yamen point.

[0013] On the other hand, the present invention also provides a neck acupoint identification device, comprising: a reference information determination unit, used to determine key points related to the horizontal and vertical inches of the neck image to be identified and feature points related to the meridians, and determine the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determine the Ren meridian and Du meridian of the neck image to be identified based on the feature points; the key points include Yintang acupoint; an Adam's apple determining unit, used to determine the Adam's apple of the neck image to be identified; A first-category neck acupoint determination unit is used to determine the positional relationship between the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, and the first-category neck acupoint, and determine the first-category neck acupoint based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit vertical inch, and the unit horizontal inch; The second-category neck acupoint determination unit is configured to determine the association between the first-category neck acupoints and the second-category neck acupoints, and determine the second-category neck acupoints based on the association and the first-category neck acupoints.

[0014] On the other hand, the present invention also provides a massage robot, comprising an acupoint recognition subsystem for determining neck acupoints and a massage subsystem for performing massage based on the neck acupoints, wherein the acupoint recognition subsystem comprises a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the neck acupoint identification method in any one of the possible implementations described above.

[0015] On the other hand, the present invention also provides a digital human, including a virtual neck model and neck acupoints marked in the virtual neck model, wherein the neck acupoints are determined based on a neck acupoint recognition method, and the neck acupoint recognition method is the neck acupoint recognition method described in any one of the possible implementation methods mentioned above.

[0016] The beneficial effect of adopting the above embodiment is that the neck acupoint recognition method provided by the present invention, by determining the positional relationship between the Adam's apple, Yintang acupoint, Renmai, Dumai and the first type of neck acupoints, realizes that only the Adam's apple, Yintang acupoint, Renmai, Dumai can be determined to realize the recognition of the first type of neck acupoints based on this positional relationship, and then the second type of neck acupoints can be determined based on the association relationship. At this point, all neck acupoints are obtained. Compared with the annotation of neck acupoints, the Adam's apple is a more obvious feature of the human body, and the key points and feature points of the Yintang acupoint, Renmai and Dumai are also more obvious features. The calibration process is simpler, and there are multiple algorithms in the prior art that can directly determine the Adam's apple, key points and feature points without sample annotation and training process, that is, the recognition process of neck acupoints does not rely on manual annotation, ensuring the recognition accuracy and recognition efficiency of neck acupoints. In addition, the present invention constructs unit straight inch and unit horizontal inch through the determined key points, eliminates the influence of individual differences on neck acupoints through unit straight inch and unit horizontal inch, and further ensures the recognition accuracy of neck acupoints. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of an embodiment of the method for identifying acupuncture points on the neck provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of determining unit vertical inch and unit horizontal inch provided by the present invention; Figure 3 For the present invention Figure 1 A schematic flow chart of an embodiment of step S102; Figure 4 A schematic diagram of an embodiment of the detection result of the second detection algorithm; Figure 5 For the present invention Figure 1 A schematic diagram of an embodiment of determining neck acupuncture points in step S103; Figure 6 A schematic diagram of the structure of an embodiment of the cervical acupuncture point recognition device provided by the present invention; Figure 7 This is a schematic structural diagram of an embodiment of the massage robot provided by the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] It should be understood that the schematic drawings are not drawn to scale. The flowchart used in the present invention shows the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present invention, can add one or more other operations to the flowchart, and can also remove one or more operations from the flowchart. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0021] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0022] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The present invention provides a neck acupuncture point recognition method, device, massage robot and digital human, which are respectively described below.

[0024] Figure 1 FIG. 1 is a flow chart of an embodiment of a method for identifying acupuncture points on the neck according to an embodiment of the present invention. Figure 1 As shown, the neck acupoint identification method includes: S101, determining key points related to the horizontal and vertical inches and feature points related to the meridians of the neck image to be identified, and determining the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determining the Ren and Du meridians of the neck image to be identified based on the feature points; the key points include the Yintang acupoint.

[0025] The method for obtaining the neck image to be identified is: collecting three-dimensional point cloud data of the human head and neck based on a depth camera, and using the three-dimensional point cloud data as the neck image to be identified.

[0026] In a specific embodiment of the present invention, the key points related to the horizontal and vertical dimensions and the feature points related to the veins of the neck image to be identified are determined based on the first detection algorithm. The first detection algorithm is a mature algorithm in the prior art. Specifically, the first detection algorithm is an open source algorithm that can be used directly without training. Through this setting, the recognition efficiency of the neck acupuncture points can be further improved.

[0027] Among them, the unit vertical inch refers to the conversion relationship between the image size and the bone size along the first direction, the first direction refers to the direction from head to toe, and the unit horizontal inch refers to the conversion relationship between the image size and the bone size along the second direction, and the second direction is perpendicular to the first direction.

[0028] It should be noted that the "inch" in the embodiment of the present invention is not a commonly used unit of measurement in life, but an equal division unit on the body. For different people, the length of the equal division unit is different.

[0029] It should also be noted that the selection of key points must be based on the bone measurement method. For example, the bone measurement method stipulates the bone distance between the front hairline and the back hairline, so the key points must be the front hairline and the back hairline. In other words, the key points refer to the points corresponding to the bone measurement in the bone measurement method.

[0030] S102: Determine the Adam's apple of the neck image to be identified.

[0031] Specifically, the Adam's apple of the neck image to be identified is determined based on the second detection algorithm, wherein the second detection algorithm is also a mature algorithm in the prior art, and specifically, the second detection algorithm is an open source algorithm, which can be used directly without training. Through this setting, the recognition efficiency of the neck acupuncture points can be further improved.

[0032] S103, determining the positional relationship between the Adam's apple, Yintang acupoint, the Ren meridian, the Governor meridian and the first category of cervical acupoints, and determining the first category of cervical acupoints based on the Adam's apple, Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit vertical inch and the unit horizontal inch.

[0033] Among them, the first type of neck acupoints refers to the neck acupoints directly related to the Adam's apple, Yintang point, Ren meridian and Du meridian.

[0034] S104, determining the association relationship between the first category of neck acupoints and the second category of neck acupoints, and determining the second category of neck acupoints based on the association relationship and the first category of neck acupoints.

[0035] Among them, the second type of neck acupoints refers to the neck acupoints that are not directly related to the Adam's apple, Yintang points, Ren meridian and Du meridian, and have a geometric positional relationship with the first type of neck acupoints.

[0036] It should be understood that the neck acupoint recognition method in the embodiment of the present invention can be implemented in any device based on neck acupoint recognition, such as an acupuncture robot, a massage robot, etc. Specifically, the neck acupoint recognition method is stored in the above-mentioned device in the form of a compiled program, and when the device is started, the program is called and the neck acupoint recognition method is implemented.

[0037] Compared with the prior art, the neck acupoint recognition method provided by the embodiment of the present invention, by determining the positional relationship between the Adam's apple, Yintang acupoint, Renmai, Dumai and the first type of neck acupoints, realizes that only the Adam's apple, Yintang acupoint, Renmai, Dumai can be determined to realize the recognition of the first type of neck acupoints based on this positional relationship, and then the second type of neck acupoints can be determined based on the association relationship. At this point, all neck acupoints are obtained. Compared with the annotation of neck acupoints, the Adam's apple is a more obvious feature of the human body. The key points and feature points of the Yintang acupoint, Renmai and Dumai are also more obvious features. The calibration process is simpler, and there are multiple algorithms in the prior art that can directly determine the Adam's apple, key points and feature points without sample annotation and training process, that is: the recognition process of neck acupoints does not rely on manual annotation, ensuring the recognition accuracy and recognition efficiency of neck acupoints. In addition, the embodiment of the present invention constructs unit straight inch and unit horizontal inch through the determined key points, and eliminates the influence of individual differences on neck acupoints through unit straight inch and unit horizontal inch, further ensuring the recognition accuracy of neck acupoints.

[0038] In some embodiments of the present invention, the bone measurement selected in the bone measurement method is that the horizontal bone measurement between the left frontal hair corner point and the right frontal hair corner point is 9 inches, and the vertical bone measurement between the front hairline and the Yintang acupoint is 3 inches. Correspondingly, the key points include the left frontal hair corner point and the right frontal hair corner point related to the horizontal inch, and the front hairline related to the vertical inch.

[0039] It should be understood that the bone measurement is not limited to the above specific embodiments. For example, the vertical bone measurement can also be the bone measurement between the front hairline and the back hairline, which will not be described in detail here.

[0040] The Ren Meridian and the Du Meridian are the midlines of the front and back of the human body respectively, and the human body is a symmetrical structure. Therefore, in some embodiments of the present invention, the characteristic points should be symmetrical points. Specifically, the characteristic points include the left earlobe point, the right earlobe point, the left acromion point and the right acromion point.

[0041] Based on the above key points and feature points, in some embodiments of the present invention, the first detection algorithm includes a key point detection algorithm for determining the left forehead hair corner point, the right forehead hair corner point, the left earlobe point, the right earlobe point, the left acromion point, the right acromion point and the Yintang acupoint, and a face detection algorithm for determining the front hairline; then the step S101 of determining the key points related to the horizontal and vertical inches of the neck image to be identified and the feature points related to the meridians includes: Detecting the neck image to be identified to obtain multiple key points to be selected, and determining the left forehead hair corner point, the right forehead hair corner point, the first target point and the second target point related to the Yintang acupoint, and the left earlobe point, the right earlobe point, the left acromion point, and the right acromion point among the multiple key points to be selected based on the mapping relationship between the key point numbers to be selected and the key points to be selected; The midpoint between the first target point and the second target point is determined as the Yintang acupoint; A face rectangular frame of the neck image to be identified is determined, and a frame line close to the top of the head in the face rectangular frame is used as the front hairline.

[0042] The neck image to be identified can be detected based on a key point detection algorithm, and a face rectangular frame of the neck image to be identified can be determined based on a face detection algorithm.

[0043] It should be noted that the detection results of the key point detection algorithm include the numbers of the key points to be selected, that is, when determining the left forehead hair corner point, the right forehead hair corner point, the left earlobe point, the right earlobe point, the left acromion point, the right acromion point, the first target point and the second target point, it is only necessary to quickly determine the left forehead hair corner point, the right forehead hair corner point, the left earlobe point, the right earlobe point, the left acromion point, the right acromion point, the first target point and the second target point according to the numbers of the previously determined left forehead hair corner point, the right forehead hair corner point, the left earlobe point, the right earlobe point, the left acromion point, the right acromion point, the first target point and the second target point from multiple key points to be selected, thereby further improving the efficiency of neck acupuncture point recognition.

[0044] In a specific embodiment of the present invention, the key point detection algorithm is Mediapipe or Dlib.

[0045] Mediapipe can extract 478 key points of the face, among which key points 8 and 9 are the first target point and the second target point, the midpoint of the first target point and the second target point is the Yintang acupoint, and key points 103 and 332 are the left forehead hair corner point and the right forehead hair corner point.

[0046] Dlib can extract 68 facial key points, including eyes, eyebrows, nose, mouth and other facial features. Key points 21 and 22 are the first target point and the second target point. The midpoint of the first target point and the second target point is the Yintang acupoint. Key points 18 and 25 are the left and right forehead hair corner points.

[0047] The specific numbers of the left earlobe point, right earlobe point, left acromion point, and right acromion point are not described here.

[0048] In a specific embodiment of the present invention, the face detection algorithm is a RetinaFace algorithm or a MogFace algorithm. The detection results of the RetinaFace algorithm and the MogFace algorithm both include a detection frame, the upper frame line of the detection frame is flush with the front hairline, and the lower frame line is flush with the chin.

[0049] The embodiment of the present invention can quickly determine the front hairline by using the face rectangular frame obtained by the face detection algorithm, thereby further improving the recognition efficiency of the neck acupuncture points.

[0050] In a specific embodiment of the present invention, Figure 2 As shown, the step S101 of determining the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determining the Ren channel and Du channel of the neck image to be identified based on the feature points, includes: S201, determining the longitudinal distance and longitudinal bone cun between the Yintang point and the front hairline, and the transverse distance and transverse bone cun between the left frontal hair corner point and the right frontal hair corner point.

[0051] The longitudinal distance and the transverse distance refer to the distance in the image coordinate system where the neck image to be identified is located, and the transverse bone inch and the longitudinal bone inch refer to the distance in the bone measurement method.

[0052] S202: Determine a unit vertical inch based on the longitudinal distance and the longitudinal bone inch, and determine a unit horizontal inch based on the horizontal distance and the horizontal bone inch.

[0053] Specifically, the unit vertical inch is the ratio of the longitudinal bone inch to the longitudinal distance, and the unit horizontal inch is the ratio of the horizontal bone inch to the horizontal distance.

[0054] S203. Determine a first connecting line and a first midpoint between the left earlobe and the right earlobe, and take a first straight line on the front of the human body that is perpendicular to the first connecting line and passes through the first midpoint as the Ren meridian, and determine a second connecting line and a second midpoint between the left acromion point and the right acromion point, and take a second straight line on the back of the human body that is perpendicular to the second connecting line and passes through the second midpoint as the Du meridian.

[0055] The embodiment of the present invention determines the unit horizontal inch and the unit vertical inch, thereby eliminating the adverse effect on the acupoint recognition result caused by the differences in horizontal distance and vertical distance due to the shooting angle of the neck image to be identified, individual differences, etc., and recognizes the neck acupoints with normalized size, further improving the recognition accuracy.

[0056] In some embodiments of the present invention, Figure 3 As shown, step S102 includes: S301: Determine a plurality of candidate reference points of a neck image to be identified.

[0057] Among them, candidate reference points include the Adam's apple.

[0058] It should be noted that: since the Adam's apple is crucial as a reference point for the accuracy of subsequent neck acupuncture point identification, in order to ensure the accuracy of Adam's apple identification, before step S301, it is necessary to apply the Poisson reconstruction method or KinectFusion or DynamicFusion technology to perform three-dimensional reconstruction of the three-dimensional point cloud data of the head and neck obtained by the depth camera.

[0059] S302: Determine the Adam's apple based on the Adam's apple number of the Adam's apple and the pre-constructed association relationship between the candidate reference point numbers and the candidate reference point positions.

[0060] The embodiment of the present invention determines the Adam's apple based on the association between the pre-constructed candidate reference point numbers and the candidate reference point positions. There is no need to locate the Adam's apple through parameters such as coordinates. The Adam's apple can be located based on the candidate reference point numbers only, which reduces the complexity of Adam's apple positioning and can further improve the positioning efficiency of the neck acupuncture points.

[0061] In a specific embodiment of the present invention, since accurate identification of the Adam's apple is crucial to accurate identification of the neck acupuncture points, in a specific embodiment of the present invention, multiple candidate reference points of the neck image to be identified are determined based on HRNet (High-Resolution Network), and HRNet generates reliable high-resolution representation by connecting sub-networks of different resolutions in parallel and performing multi-scale fusion between these sub-networks. The design of HRNet enables it to have high accuracy and efficiency in key point detection tasks.

[0062] Specifically, when the second detection algorithm is HRNet, its detection result is as follows: Figure 4 As shown by Figure 4 It can be seen that the candidate reference point numbered 1 is the Adam's apple.

[0063] In a specific embodiment of the present invention, the positional relationship is a bone positional relationship, that is, the positional relationship refers to the horizontal and vertical inch relationship between each neck acupoint and the Adam's apple or neck acupoint.

[0064] The neck acupuncture point recognition refers to the position in the actual neck image to be recognized. Therefore, in some embodiments of the present invention, Figure 5 As shown, the first type of cervical acupoints are determined based on the Adam's apple, Yintang acupoints, Ren channel, Du channel, position relationship, unit vertical inch and unit horizontal inch in step S103, including: S501. Determine the bone position of the first type of cervical acupoints based on the Adam's apple, Yintang acupoints, Ren meridian, Du meridian and their position relationship.

[0065] Among them, the bone position refers to the position measured in horizontal inches and vertical inches.

[0066] S502: Convert the bone position into an image position based on the unit vertical inch and the unit horizontal inch, and use the image position as the position of the first type of cervical acupuncture point.

[0067] After determining the bone position, the embodiment of the present invention converts the bone position into an image position based on the unit vertical inch and the unit horizontal inch, which can improve the compatibility of the neck acupoints and the neck image to be identified, and facilitate subsequent post-processing operations on the identified neck acupoints.

[0068] It should be noted that the second type of neck acupoints are also bone positions. After the second type of neck acupoints are determined, they should also be converted into image positions based on the unit vertical inch and unit horizontal inch.

[0069] In some embodiments of the present invention, the first type of cervical acupoints include Renying, Futu, Tiantu, and Tianchuang located on the front of the neck, and Yamen and Dazhui located on the back of the neck; the position relationship includes: Renying acupoint is 1.5 horizontal inches away from Adam's apple; Futu point is 3 horizontal inches away from Adam's apple; Tiantu acupoint is located on the Ren channel, below the Adam's apple and 2 inches away from the Adam's apple; Tianchuang acupoint is 3.5 horizontal inches away from Adam's apple; Yamen acupoint is located on the Du channel, 14.5 straight inches away from Yintang acupoint; The Dazhui point is located on the Du meridian, 18 straight inches away from the Yintang point.

[0070] In some embodiments of the present invention, the second type of neck acupoints include Lianquan, Qishe, Shuitu, Quepen located on the front neck, and Fengfu, Fengchi, Jingbailao, and Tianzhu located on the back neck; the association relationship is: Lianquan acupoint is located at the midpoint of the line connecting the chin and Adam's apple; the chin is the lower frame line of the rectangular frame of the human face; Qishe point is 1.5 horizontal inches away from Tiantu point; Shuitu acupoint is located on the Ren meridian and at the midpoint of the line connecting Qishe acupoint and Renying acupoint; The Quepen point is the intersection of the extended line of the connection between the Tiantu point and the Qishe point and the target line segment. The target line segment is a line segment that is perpendicular to the line connecting the left nipple and the right nipple and passes through the left nipple or the right nipple. Among them, the left nipple and the right nipple can be determined based on open source models such as Faster-CNN, SSD and YOLO.

[0071] Tianding acupoint is located at the midpoint of the line connecting Futu acupoint and Quepen acupoint; Fengfu acupoint is located above Yamen acupoint, 0.5 cun away from Yamen acupoint; Fengchi point is 1.3 horizontal inches away from Fengfu point; The Bailao point on the neck is located above the Dazhui point, 2 vertical inches and 1 horizontal inch away from the Dazhui point; Tianzhu point is located below Yamen point, 0.3 vertical inches and 1.3 horizontal inches away from Yamen point.

[0072] It should be noted that the position of Tianzhu acupoint was determined by taking into account the positional relationship between the cervical vertebrae. Specifically, assuming that each cervical vertebrae is the same size, there are 6 cervical vertebrae between Yamen acupoint and Dazhui acupoint. From the above positional relationship, it can be seen that the distance between Yamen acupoint and Dazhui acupoint is 3.5 straight inches, so each cervical vertebra = 3.5 straight inches / 6 = 0.6 straight inches. Tianzhu acupoint and Yamen acupoint are separated by half a cervical vertebra, so the distance between Tianzhu acupoint and Yamen acupoint is 0.3 straight inches.

[0073] In the process of determining the positional relationship, the embodiment of the present invention refers to the position of the human cervical spine, thereby further ensuring the accuracy of the positional relationship.

[0074] Since the bone measurement used in the above embodiments is the bone measurement between the Yintang acupoint and the front hairline as a reference for identifying the neck acupoints, and the bone measurement can also be the bone measurement between the front hairline and the back hairline, therefore, in order to further verify the accuracy of the identified neck acupoints, in some embodiments of the present invention, the neck acupoint identification method further includes: Determine the back hairline based on the front hairline, and the back hairline is 12 inches away from the front hairline; Verify whether the positional relationship is accurate based on the posterior hairline and the Yamen, Dazhui and Fengfu points.

[0075] Specifically, the Yamen acupoint, Dazhui acupoint and Fengfu acupoint are determined based on the verified positional relationship between the posterior hairline and the Yamen acupoint, Dazhui acupoint and Fengfu acupoint, and a judge is made as to whether they coincide / are consistent with the Yamen acupoint, Dazhui acupoint and Fengfu acupoint determined based on the Yintang acupoint. If they coincide / are consistent, the positional relationship is determined to be accurate; otherwise, it is inaccurate.

[0076] In a specific embodiment of the present invention, the Yamen acupoint is located above the posterior hairline, 0.5 straight inches away from the posterior hairline, the Dazhui acupoint is located below the posterior hairline, 3 straight inches away from the posterior hairline, and the Fengfu acupoint is located below the posterior hairline, 1 straight inch away from the posterior hairline.

[0077] In summary, the embodiment of the present invention further verifies the accuracy of the neck acupoints through the posterior hairline.

[0078] In order to better implement the neck acupoint recognition method in the embodiment of the present invention, based on the neck acupoint recognition method, the embodiment of the present invention also provides a neck acupoint recognition device, such as Figure 6 As shown, the neck acupoint recognition device 600 includes: The reference information determination unit 601 is used to determine the key points related to the horizontal and vertical inches of the neck image to be identified and the feature points related to the meridians, and determine the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determine the Ren and Du meridians of the neck image to be identified based on the feature points; the key points include the Yintang acupoint; The Adam's apple determining unit 602 is used to determine the Adam's apple of the neck image to be identified; The first type of neck acupoint determination unit 603 is used to determine the positional relationship between the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian and the first type of neck acupoint, and determine the first type of neck acupoint based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit vertical inch and the unit horizontal inch; The second-category neck acupoint determining unit 604 is used to determine the association relationship between the first-category neck acupoints and the second-category neck acupoints, and determine the second-category neck acupoints based on the association relationship and the first-category neck acupoints.

[0079] The neck acupoint identification device 600 provided in the above embodiment can implement the technical solution described in the above neck acupoint identification method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above neck acupoint identification method embodiment, which will not be repeated here.

[0080] like Figure 7 As shown, the present invention also provides a massage robot 700. The massage robot 700 includes an acupoint identification subsystem 710 for determining neck acupoints and a massage subsystem 720 for performing massage based on neck acupoints. The acupoint identification subsystem 710 includes a processor 711, a memory 712 and a display 713. Figure 7 Only some of the components of the massage robot 700 are shown, but it should be understood that it is not required to implement all of the shown components, and more or fewer components may be implemented instead.

[0081] In some embodiments, the memory 712 may be an internal storage unit of the acupoint identification subsystem 710, such as a hard disk or memory of the acupoint identification subsystem 710. In other embodiments, the memory 712 may also be an external storage device of the acupoint identification subsystem 710, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the acupoint identification subsystem 710.

[0082] Furthermore, the memory 712 may include both an internal storage unit of the acupoint identification subsystem 710 and an external storage device. The memory 712 is used to store application software installed in the acupoint identification subsystem 710 and various data.

[0083] In some embodiments, the processor 711 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 712, such as the neck acupoint recognition method of the present invention.

[0084] In some embodiments, the display 713 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 713 is used to display information of the acupoint identification subsystem 710 and to display a visual user interface. The components 711-713 of the acupoint identification subsystem 710 communicate with each other through a system bus.

[0085] In some embodiments of the present invention, when the processor 711 executes the neck acupoint recognition program in the memory 712, the following steps may be implemented: Determine the key points related to the horizontal and vertical inches and the feature points related to the meridians of the neck image to be identified, and determine the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determine the Ren and Du meridians of the neck image to be identified based on the feature points; the key points include the Yintang acupoint; Determine the Adam's apple of the neck image to be identified; Determine the positional relationship between the Adam's apple, Yintang acupoint, the Ren and Governor vessels and the first type of neck acupoints, and determine the first type of neck acupoints based on the Adam's apple, Yintang acupoint, the Ren and Governor vessels, the positional relationship, the unit vertical inch and the unit horizontal inch; The association relationship between the first type of neck acupoints and the second type of neck acupoints is determined, and the second type of neck acupoints is determined based on the association relationship and the first type of neck acupoints.

[0086] It should be understood that: when the processor 711 executes the neck acupoint recognition program in the memory 712, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the previous related method embodiments.

[0087] Among them, Figure 7 As shown, the massage subsystem 720 includes a path planning unit 721 and a massage unit 722. The path planning unit 721 is used to perform path planning according to the moxibustion needle positions and acupoint coordinates in the massage unit 722 to generate a planned path. The massage unit 722 moves the moxibustion needles to the locations of the acupoints according to the planned path.

[0088] The embodiment of the present invention can replace doctors to complete long-term massage treatment work by providing a massage robot 700, thereby alleviating the burden on doctors and reducing medical expenses.

[0089] On the other hand, an embodiment of the present invention further provides a digital human, including a virtual neck model and neck acupoints marked in the virtual neck model, wherein the neck acupoints are determined based on a neck acupoint recognition method, and the neck acupoint recognition method is the neck acupoint recognition method in any one of the above embodiments.

[0090] The embodiment of the present invention can achieve training objectives through the provision of a digital human, such as training on the recognition of neck acupuncture points.

[0091] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0092] The above is a detailed introduction to the neck acupoint recognition method, device, massage robot and digital human provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for identifying neck acupoints, characterized in that: include: Determine key points related to the horizontal and vertical inches and feature points related to the meridians of the neck image to be identified, and determine the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determine the Ren meridian and Du meridian of the neck image to be identified based on the feature points; the key points include Yintang acupoint; Determining the Adam's apple of the neck image to be identified; Determine the positional relationship between the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, and the first type of neck acupoints, and determine the first type of neck acupoints based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit straight inch, and the unit horizontal inch; Determine the association relationship between the first category of neck acupoints and the second category of neck acupoints, and determine the second category of neck acupoints based on the association relationship and the first category of neck acupoints.

2. The method for identifying neck acupoints according to claim 1, characterized in that: The key points also include the left forehead hair corner point and the right forehead hair corner point related to the horizontal inch and the front hairline related to the vertical inch; the feature points include the left earlobe point, the right earlobe point, the left acromion point and the right acromion point; then the key points related to the horizontal and vertical inch and the feature points related to the meridians of the neck image to be identified are determined, including: Detecting the neck image to be identified to obtain a plurality of key points to be selected, and determining the left forehead hair corner point, the right forehead hair corner point, the first target point and the second target point related to the Yintang acupoint, and the left earlobe point, the right earlobe point, the left acromion point, and the right acromion point among the plurality of key points to be selected based on a mapping relationship between the key point numbers to be selected and the key points to be selected; Determine the midpoint between the first target point and the second target point as the Yintang acupoint; A face rectangular frame of the neck image to be identified is determined, and a frame line close to the top of the head in the face rectangular frame is used as the front hairline.

3. The method for identifying neck acupoints according to claim 2, characterized in that: Determining the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determining the Ren meridian and the Du meridian of the neck image to be identified based on the feature points, including: Determine the longitudinal distance and the longitudinal bone cun between the Yintang acupoint and the front hairline, and the transverse distance and the transverse bone cun between the left frontal hair corner point and the right frontal hair corner point; Determine the unit vertical inch based on the longitudinal distance and the longitudinal bone inch, and determine the unit horizontal inch based on the horizontal distance and the horizontal bone inch; Determine a first connecting line and a first midpoint of the left earlobe point and the right earlobe point, and use a first straight line on the front of the human body that is perpendicular to the first connecting line and passes through the first midpoint as the Ren meridian, and determine a second connecting line and a second midpoint of the left acromion point and the right acromion point, and use a second straight line on the back of the human body that is perpendicular to the second connecting line and passes through the second midpoint as the Du meridian.

4. The method for identifying neck acupuncture points according to claim 1, characterized in that: The determining of the Adam's apple of the neck image to be identified includes: Determine a plurality of candidate reference points and a plurality of candidate reference point numbers of the neck image to be identified; The Adam's apple is determined based on the Adam's apple number of the Adam's apple and a pre-constructed association relationship between the candidate reference point numbers and the candidate reference point positions.

5. The method for identifying neck acupoints according to claim 1, characterized in that: The positional relationship is a bone positional relationship; the first type of cervical acupoints are determined based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit vertical inch and the unit horizontal inch, including: Determine the bone position of the first type of cervical acupuncture points based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Du meridian and the position relationship; The bone position is converted into an image position based on the unit vertical inch and the unit horizontal inch, and the image position is used as the position of the first type of cervical acupuncture points.

6. The method for identifying neck acupoints according to claim 2, characterized in that: The first type of neck acupoints include Renying, Futu, Tiantu and Tianchuang located on the front neck and Yamen and Dazhui located on the back neck; the position relationship includes: The Renying point is 1.5 horizontal inches away from the Adam's apple; The Futu point is 3 horizontal inches away from the Adam's apple; The Tiantu point is located on the Ren meridian, below the Adam's apple and 2 inches away from the Adam's apple; The Tianchuang point is 3.5 horizontal inches away from the Adam's apple; The Yamen acupoint is located on the Governor Vessel, 14.5 straight inches away from the Yintang acupoint; The Dazhui point is located on the Du meridian, 18 straight inches away from the Yintang point.

7. The method for identifying neck acupuncture points according to claim 6, characterized in that: The second type of neck acupoints include Lianquan, Qishe, Shuitu and Quepen located on the front neck, and Fengfu, Fengchi, Jingbailao and Tianzhu located on the back neck; the association relationship is: The Lianquan acupoint is located at the midpoint of the line connecting the chin and the Adam's apple; the chin is the lower frame line of the rectangular frame of the human face; The Qishe point is 1.5 horizontal inches away from the Tiantu point; The Shuitu point is located on the Ren meridian and at the midpoint of the line connecting the Qishe point and the Renying point; The Quepen point is the intersection of the extended line of the line connecting the Tiantu point and the Qishe point and the target line segment, and the target line segment is a line segment perpendicular to the line connecting the left nipple and the right nipple and passing through the left nipple or the right nipple; The Tianding point is located at the midpoint of the line connecting the Futu point and the Quepen point; The Fengfu point is located above the Yamen point, 0.5 straight inches away from the Yamen point; The Fengchi point is 1.3 horizontal inches away from the Fengfu point; The Jing Bailao point is located above the Dazhui point, 2 vertical inches and 1 horizontal inch away from the Dazhui point; The Tianzhu point is located below the Yamen point, 0.3 vertical inches and 1.3 horizontal inches away from the Yamen point.

8. A device for identifying acupuncture points on the neck, characterized in that: include: a reference information determination unit, used to determine key points related to the horizontal and vertical inches of the neck image to be identified and feature points related to the meridians, and determine the unit vertical inch and unit horizontal inch of the neck image to be identified based on the key points, and determine the Ren meridian and Du meridian of the neck image to be identified based on the feature points; the key points include Yintang acupoint; an Adam's apple determining unit, used to determine the Adam's apple of the neck image to be identified; A first-category neck acupoint determination unit is used to determine the positional relationship between the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, and the first-category neck acupoint, and determine the first-category neck acupoint based on the Adam's apple, the Yintang acupoint, the Ren meridian, the Governor meridian, the positional relationship, the unit vertical inch, and the unit horizontal inch; The second-category neck acupoint determination unit is configured to determine the association between the first-category neck acupoints and the second-category neck acupoints, and determine the second-category neck acupoints based on the association and the first-category neck acupoints.

9. A massage robot, characterized in that: The invention comprises an acupoint identification subsystem for determining neck acupoints and a massage subsystem for performing massage based on the neck acupoints, wherein the acupoint identification subsystem comprises a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the neck acupoint identification method described in any one of claims 1 to 7.

10. A digital human, characterized in that: It includes a virtual neck model and neck acupoints marked in the virtual neck model, wherein the neck acupoints are determined based on a neck acupoint recognition method, and the neck acupoint recognition method is the neck acupoint recognition method described in any one of claims 1 to 7 above.

Images