Head acupoint positioning method and device, electronic equipment and storage medium

Abstract

The invention provides a head acupuncture point positioning method and device, electronic equipment and a storage medium, and relates to the technical field of medical treatment, and the method comprises the steps: constructing an initial three-dimensional head parameterized model based on a target image comprising the head of a target object; controlling each tactile sensor in an acquisition device worn on the head of the target object to move towards the head direction to apply pressure to the head until the pressure applied to the head by each tactile sensor is greater than a corresponding pressure threshold, and optimizing the initial three-dimensional head parameterized model based on the current position of each tactile sensor; and performing head acupuncture point positioning in the optimized three-dimensional head parameterized model. It can be known that when the pressure applied to the head by each tactile sensor is larger than the corresponding pressure threshold value, the three-dimensional head parameterized model is optimized based on the current position of each tactile sensor, so that the optimized three-dimensional head parameterized model better conforms to the target object, and the accuracy of head acupuncture point positioning is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular, to a method, device, electronic device, and storage medium for head acupoint positioning. Background Art

[0002] Head acupoints play a very important role in traditional Chinese medicine. According to traditional Chinese medicine theory, the head is the meeting point of all yang meridians and is the intersection point of multiple important meridians in the human body. Therefore, the acupoints on the head have a wide range of effects on the health and functions of the human body. However, there are significant individual differences in the head, such as the size, shape, and hair density of the head, which will have some impacts on the accuracy of head acupoint positioning.

[0003] In related technologies, generally, a three-dimensional head parametric model of a target object is generated based on the head image of the target object, and then head acupoint positioning is performed in the three-dimensional head parametric model.

[0004] However, in the above-mentioned related technologies, generating a three-dimensional head parametric model only based on the head image is affected by factors such as hair density and hair occlusion of the head, resulting in a decrease in the accuracy of the constructed three-dimensional head parametric model, and further reducing the accuracy of head acupoint positioning. Summary of the Invention

[0005] The present invention provides a method, device, electronic device, and storage medium for head acupoint positioning to solve the defect of reducing the accuracy of head acupoint positioning in the prior art.

[0006] The present invention provides a method for head acupoint positioning, including the following steps.

[0007] Based on a target image including the head of a target object, construct an initial three-dimensional head parametric model of the target object; Control each tactile sensor in the acquisition device worn on the head of the target object to move towards the head to apply pressure to the head until, when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, obtain the current positions of each tactile sensor; Based on the current positions of each tactile sensor, optimize the initial three-dimensional head parametric model to obtain an optimized three-dimensional head parametric model; Perform head acupoint positioning in the optimized three-dimensional head parametric model.

[0008] According to the method for head acupoint positioning provided by the present invention, the acquisition device includes a plurality of the tactile sensors distributed at different positions, each of the tactile sensors is respectively connected to a corresponding driving device, and a force sensing module is provided at the position where each tactile sensor contacts the head; Controlling each tactile sensor worn on the head of the target object to move towards the head to apply pressure to the head until, when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, obtaining the current positions of each tactile sensor, includes: For each tactile sensor, controlling the tactile sensor to move towards the head through the driving device corresponding to the tactile sensor to apply pressure to the head, and collecting the current pressure through the force sensing module corresponding to the tactile sensor; When the current pressure is greater than or equal to the pressure threshold corresponding to the tactile sensor, controlling the tactile sensor to stop moving towards the head through the driving device corresponding to the tactile sensor; When all the tactile sensors stop moving towards the head, obtaining the current positions of each tactile sensor.

[0009] According to a head acupoint positioning method provided by the present invention, the pressure threshold corresponding to the tactile sensor is determined based on the head position corresponding to the tactile sensor.

[0010] According to a head acupoint positioning method provided by the present invention, the head acupoint positioning in the optimized three-dimensional head parametric model includes: Obtaining a standard three-dimensional head parametric model, which includes a plurality of marked head acupoint points; Searching for target vertices corresponding to each of the head acupoint points in the standard three-dimensional head parametric model in the optimized three-dimensional head parametric model; Determining the name of the head acupoint corresponding to the target vertex in the standard three-dimensional head parametric model as the acupoint name of the target vertex.

[0011] According to a head acupoint positioning method provided by the present invention, the optimizing the initial three-dimensional head parametric model based on the current positions of each tactile sensor to obtain an optimized three-dimensional head parametric model includes: Mapping the current positions of each tactile sensor into the three-dimensional coordinate system corresponding to the initial three-dimensional head parametric model to obtain the three-dimensional coordinates of the head positions corresponding to each tactile sensor; Constructing a three-dimensional point cloud of the head surface based on each of the three-dimensional coordinates; Based on the three-dimensional point cloud of the head surface, optimizing the initial three-dimensional head parametric model to obtain the optimized three-dimensional head parametric model.

[0012] A method for head acupoint positioning provided by the present invention, based on the three-dimensional point cloud of the head surface, optimizing the initial three-dimensional head parameterized model to obtain the optimized three-dimensional head parameterized model, includes: Initial alignment of each vertex in the initial three-dimensional head parameterized model and the three-dimensional point cloud of the head surface; Constructing an objective function based on the distance between each vertex and the three-dimensional point cloud aligned with each vertex in the three-dimensional point cloud of the head surface; Optimizing the initial three-dimensional head parameterized model based on the objective function until the objective function is minimized to obtain the optimized three-dimensional head parameterized model.

[0013] The present invention also provides a head acupoint positioning device, including: A construction unit for constructing an initial three-dimensional head parameterized model of the target object based on a target image including the head of the target object; A control unit for controlling each tactile sensor in the acquisition device worn on the head of the target object to move towards the head to apply pressure to the head until the current positions of each tactile sensor are obtained when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold; An optimization unit for optimizing the initial three-dimensional head parameterized model based on the current positions of each tactile sensor to obtain an optimized three-dimensional head parameterized model; A positioning unit for performing head acupoint positioning in the optimized three-dimensional head parameterized model.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, it implements the head acupoint positioning method as described in any one of the above.

[0015] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the head acupoint positioning method as described in any one of the above.

[0016] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the head acupoint positioning method as described in any one of the above.

[0017] The head acupoint positioning method, device, electronic device, and storage medium provided by the present invention are based on a target image including the head of a target object, construct an initial three-dimensional head parametric model of the target object, control each tactile sensor in the acquisition device worn on the head of the target object to move in the direction of the head to apply pressure to the head until, when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, obtain the current positions of the tactile sensors, and optimize the initial three-dimensional head parametric model based on the current positions of the tactile sensors to obtain an optimized three-dimensional head parametric model, and finally perform head acupoint positioning in the optimized three-dimensional head parametric model. It can be seen that the present invention controls a plurality of tactile sensors to apply pressure to the head until, when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, and then obtains an optimized three-dimensional head parametric model based on the current positions of the tactile sensors. By applying pressure to the head, each tactile sensor can better fit the scalp of the target object, so that the obtained optimized three-dimensional head parametric model is more in line with the target object, improving the accuracy of the optimized three-dimensional head parametric model and further improving the accuracy of head acupoint positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 is one of the flow diagrams of the head acupoint positioning method provided by an embodiment of the present invention.

[0020] Figure 2 is a schematic diagram of the initial three-dimensional head parametric model provided by the present invention.

[0021] Figure 3 is a side view of a target object wearing an acquisition device provided by an embodiment of the present invention.

[0022] Figure 4 is a top view of a target object wearing an acquisition device provided by an embodiment of the present invention.

[0023] Figure 5 is a schematic diagram of a tactile sensor applying pressure provided by an embodiment of the present invention.

[0024] Figure 6 is another flow diagram of the head acupoint positioning method provided by an embodiment of the present invention.

[0025] Figure 7It is the third schematic flowchart of the head acupoint positioning method provided by the embodiments of the present invention.

[0026] Figure 8 It is the front view of the standard three-dimensional head parametric model after head acupoint marking provided by the embodiments of the present invention.

[0027] Figure 9 It is the rear view of the standard three-dimensional head parametric model after head acupoint marking provided by the embodiments of the present invention.

[0028] Figure 10 It is the side view of the standard three-dimensional head parametric model after head acupoint marking provided by the embodiments of the present invention.

[0029] Figure 11 It is the schematic diagram of the standard three-dimensional head parametric model and the optimized three-dimensional head parametric model provided by the embodiments of the present invention.

[0030] Figure 12 It is one of the schematic diagrams of optimizing the initial three-dimensional head parametric model provided by the embodiments of the present invention.

[0031] Figure 13 It is the second schematic diagram of optimizing the initial three-dimensional head parametric model provided by the embodiments of the present invention.

[0032] Figure 14 It is the structural schematic diagram of the head acupoint positioning device provided by the embodiments of the present invention.

[0033] Figure 15 It is the physical structure schematic diagram of the electronic device provided by the embodiments of the present invention. Detailed implementation manners

[0034] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without any creative efforts shall fall within the protection scope of the present invention.

[0035] The following combines Figures 1 - 13 to describe the head acupoint positioning method of the present invention. The execution subject of the head acupoint positioning method can be an electronic device such as a computer, a medical device, or a robotic arm that can control the operation of the acquisition device, or a head acupoint positioning device provided in the electronic device, and the head acupoint positioning device can be implemented by software, hardware, or a combination of both.

[0036] Figure 1is one of the schematic flowcharts of the head acupoint positioning method provided by the embodiments of the present invention. As Figure 1 shown, the head acupoint positioning method includes the following steps: Step 101: Based on a target image including the head of a target object, construct an initial three-dimensional head parametric model of the target object.

[0037] Exemplarily, the target object can be any person with a need for head acupoint positioning. The electronic device collects a target image including the head of the target object through a camera device. Specifically, the target image can be an RGB image including the front face of the target object. Perform face detection and facial key point positioning on the RGB image. Based on the detected face information and each facial key point, use relevant methods to predict the initial three-dimensional head parametric model of the target object. The constructed initial three-dimensional head parametric model is as Figure 2 shown. Among them, the relevant methods can be metric reconstruction of monocular faces (Towards Metrical Reconstruction of Human Faces, MICA), detailed expression capture and animation (Detailed Expression Capture and Animation, DECA), emotion-driven monocular face capture and animation (Emotion Driven Monocular Face Capture and Animation, EMOCA), etc. The initial three-dimensional head parametric model can be a FLAME (Faces Learned with an Articulated Model and Expressions) model. The present invention does not limit this.

[0038] Step 102: Control each tactile sensor in the collection device worn on the head of the target object to move towards the head direction to apply pressure to the head until the current positions of each tactile sensor are obtained when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold.

[0039] Exemplarily, a collection device that can be worn on the head is pre-designed. The collection device can be in the shape of a strip, a band, or a headgear, etc. Wear the collection device on the head of the target object. The hairline can be used as a reference line as the starting layout line, and the tactile sensors at the edge of the collection device are distributed on the hairline. Of course, other parts can also be used as a reference. Finally, all the tactile sensors distributed on the collection device are evenly dispersed at different positions on the head as much as possible to accurately sense the scalp shape information in a larger range. Figure 3 is a side view of the target object wearing the collection device provided by the embodiments of the present invention. As Figure 3As shown, the acquisition device is worn with the hairline as the reference line. The red circles all represent the head surface marking points, and the acquisition device is correctly worn through the head surface marking points. Figure 4 is a top view of the target object wearing the acquisition device provided by an embodiment of the present invention. As Figure 4 shown, a plurality of tactile sensors are distributed on the acquisition device. Figure 4 In [the figure], red dots are used to represent each tactile sensor.

[0040] When the initial three-dimensional head parametric model of the target object is constructed, control each tactile sensor to move towards the head direction. Specifically, it can move in the normal direction of the scalp, so that each tactile sensor applies pressure to the corresponding position on the head. Figure 5 is a schematic diagram of the tactile sensor applying pressure provided by an embodiment of the present invention. As Figure 5 shown, the red ellipse represents the tactile sensor, and the tactile sensor applies pressure in the normal direction of the scalp. And the magnitude of the pressure applied by each tactile sensor to the corresponding position on the head is collected in real time. When the pressure applied by the tactile sensor to the head is greater than the corresponding pressure threshold, control the tactile sensor to stop moving towards the head direction. Until all tactile sensors stop moving towards the head direction, it means that each tactile sensor has completely adhered to the scalp. At this time, obtain the current position of each tactile sensor. Specifically, a positioning module can be set in each tactile sensor, and the positions collected by each positioning module are determined as the current positions of each tactile sensor; an Inertial Measurement Unit (IMU) can also be set in each tactile sensor. When the acquisition device is just worn on the head, initialize the acquisition device, keep the acquisition device stationary for a preset duration, and record the initial positions of each tactile sensor. Control the acquisition device to start. When each tactile sensor has completely adhered to the scalp, obtain the motion trajectories measured by each IMU. The motion trajectories are determined based on the acceleration data and angular velocity data measured by the IMU. By integrating the acceleration data and angular velocity data, calculate the displacement of the tactile sensor from the initial position to the adhered scalp, and calculate the current position of the tactile sensor in combination with the initial position and the displacement.

[0041] Step 103: Optimize the initial three-dimensional head parametric model based on the current positions of the tactile sensors to obtain an optimized three-dimensional head parametric model.

[0042] Exemplarily, when the current positions of each tactile sensor are obtained, since each tactile sensor has adhered to the scalp, the current positions of each tactile sensor can represent the corresponding scalp positions, which is equivalent to obtaining multiple scalp positions. Furthermore, the initial three-dimensional head parametric model can be optimized based on the multiple scalp positions, so that the optimized three-dimensional head parametric model better conforms to the entire head shape of the target object.

[0043] Step 104: Locate the acupoints on the optimized three-dimensional head parametric model.

[0044] Exemplarily, when obtaining the optimized three-dimensional head parametric model of the target object, the optimized three-dimensional head parametric model is matched with the standard three-dimensional head parametric model, so that each acupoint name marked in the standard three-dimensional head parametric model is mapped on the optimized three-dimensional head parametric model, thereby realizing the location of the acupoints on the optimized three-dimensional head parametric model.

[0045] The acupoint location method provided by the present invention constructs an initial three-dimensional head parametric model of a target object based on a target image including the head of the target object, controls each tactile sensor in the acquisition device worn on the head of the target object to move towards the head to apply pressure to the head until the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, obtains the current position of each tactile sensor, optimizes the initial three-dimensional head parametric model based on the current position of each tactile sensor to obtain an optimized three-dimensional head parametric model, and finally locates the acupoints on the optimized three-dimensional head parametric model. It can be seen that the present invention controls multiple tactile sensors to apply pressure to the head until the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, and then obtains the optimized three-dimensional head parametric model based on the current position of each tactile sensor. By applying pressure to the head, each tactile sensor can better fit the scalp of the target object, so that the obtained optimized three-dimensional head parametric model is more in line with the target object, improving the accuracy of the optimized three-dimensional head parametric model and further improving the accuracy of acupoint location.

[0046] In one embodiment, the acquisition device includes a plurality of the tactile sensors distributed at different positions. Each tactile sensor is respectively connected to a corresponding driving device, and a force sensing module is provided at the position where each tactile sensor contacts the head; that is, one tactile sensor is connected to one driving device, and one force sensing module is provided on one tactile sensor. The driving device can be a motor, and each driving device is connected to the processor of the electronic device, and the processor of the electronic device controls the operation of each driving device. In addition, it should be noted that the tactile sensors should be densely distributed on the acquisition device, and can be specifically distributed at intervals of a preset value, and the preset value can be set based on requirements. For example, the preset value is 0.5 cm or a smaller value, and the present invention does not limit this.

[0047] Figure 6 It is the second flowchart of the acupoint location method for the head provided by the embodiment of the present invention. As Figure 6As shown, the above step 102 controls each tactile sensor in the acquisition device worn on the head of the target object to move towards the head direction to apply pressure to the head, and when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, the current position of each tactile sensor is obtained. Specifically, it can be achieved through the following steps: Step 601: For each tactile sensor, control the tactile sensor to move towards the head direction through the driving device corresponding to the tactile sensor to apply pressure to the head, and collect the current pressure through the force sensing module corresponding to the tactile sensor.

[0048] Exemplarily, after the acquisition device is started, for each tactile sensor, the processor of the electronic device sends a start command to the driving device corresponding to the tactile sensor, so that after the driving device is started, it controls the connected tactile sensor to move towards the head direction to apply pressure to the head. During the process of the tactile sensor applying pressure to the head, the force sensing module set at the position where the tactile sensor contacts the head collects the current pressure in real time and sends the current pressure to the processor of the electronic device.

[0049] Step 602: When the current pressure is greater than or equal to the pressure threshold corresponding to the tactile sensor, control the tactile sensor to stop moving towards the head direction through the driving device corresponding to the tactile sensor.

[0050] Exemplarily, the electronic device prestores the corresponding relationship between the identifier of the tactile sensor and the pressure threshold. When the processor of the electronic device receives the current pressure sent by the force sensing module corresponding to the tactile sensor, it searches for the pressure threshold corresponding to the identifier of the tactile sensor in the corresponding relationship, and compares the current pressure with the found pressure threshold. When the current pressure is less than the found pressure threshold, continue to control the tactile sensor to apply pressure towards the head direction through the driving device; when the current pressure is greater than or equal to the found pressure threshold, it indicates that the tactile sensor has completely adhered to the scalp. At this time, control the tactile sensor to stop moving towards the head direction through the driving device, so that the tactile sensor stops applying pressure to the head. According to the same method, control other tactile sensors to move towards the head direction until the current pressure collected by the force sensing modules corresponding to other tactile sensors is greater than or equal to the pressure thresholds corresponding to other tactile sensors, and then control other tactile sensors to also stop moving towards the head direction.

[0051] Step 603: When all the tactile sensors stop moving towards the head direction, obtain the current positions of each tactile sensor.

[0052] Exemplarily, when all the tactile sensors stop moving towards the head direction, it indicates that all the tactile sensors have adhered to the scalp of the target object. At this time, the current positions of the respective tactile sensors are obtained, and the respective scalp positions of the target object are characterized by the current positions of the respective tactile sensors.

[0053] In this embodiment, the current pressure is collected by the force sensing modules provided on the respective tactile sensors. By comparing the current pressure with the corresponding pressure thresholds, the time when the tactile sensors stop moving towards the head direction is determined. When all the tactile sensors stop moving towards the head direction, it indicates that all the tactile sensors have adhered to the scalp of the target object. At this time, the current positions of the respective tactile sensors are obtained, improving the accuracy of obtaining the respective current positions.

[0054] In one embodiment, the pressure threshold corresponding to the tactile sensor is determined based on the head position corresponding to the tactile sensor.

[0055] Exemplarily, since the head is curved and the softness and hardness of different regions of the head are different, the pressure thresholds corresponding to the respective tactile sensors are also different. Specifically, they can be determined based on the softness and hardness of the head positions corresponding to the respective tactile sensors, that is, the pressure threshold of the tactile sensor corresponding to the harder position is larger, and the pressure threshold of the tactile sensor corresponding to the softer position is smaller.

[0056] In this embodiment, the pressure threshold corresponding to the tactile sensor is determined based on the head position corresponding to the tactile sensor, improving the accuracy of determining the respective pressure thresholds and further improving the accuracy of controlling the corresponding tactile sensors based on the respective pressure thresholds.

[0057] In one embodiment, Figure 7 is the third flow schematic diagram of the head acupoint positioning method provided by the embodiment of the present invention. As Figure 7 shown, the above step 104 performs head acupoint positioning in the optimized three-dimensional head parametric model, and can be specifically implemented through the following steps: Step 1041: Obtain a standard three-dimensional head parametric model, which includes a plurality of marked head acupoint points.

[0058] Exemplarily, obtain the FLAME model, which is a parametric head geometry model that includes three sets of parameters: the base shape, the expression vector, and the head pose. The FLAME model can learn individual facial features through a small amount of key-point tracking data and can be represented by a low-dimensional latent vector, thereby achieving general and personalized expressions of different human faces. Moreover, the FLAME model has a fixed data structure, and FLAME models with different parameters have the same data structure, that is, point-to-point correspondence and line-to-line correspondence between points. Taking the general model with all the base shape parameters, expression parameters, and head pose parameters of the FLAME model being 0.00 as the standard three-dimensional head parametric model, based on the definitions and rules of each acupoint on the head, all the head acupoints are marked on the standard FLAME model, that is, the corresponding head acupoint names are marked on the corresponding vertices in the standard three-dimensional head parametric model, and this vertex serves as the head acupoint. For example, the 100th vertex of the standard three-dimensional head parametric model is the Yintang acupoint, the 1500th vertex is the Baihui acupoint, etc. Figure 8 is the front view of the standard three-dimensional head parametric model after head acupoint marking provided by the embodiment of the present invention. Figure 9 is the rear view of the standard three-dimensional head parametric model after head acupoint marking provided by the embodiment of the present invention. Figure 10 is the side view of the standard three-dimensional head parametric model after head acupoint marking provided by the embodiment of the present invention, as Figures 8 - 10 shown, each red point represents a vertex marked with an acupoint name.

[0059] Step 1042: Search for target vertices in the optimized three-dimensional head parametric model that correspond one-to-one to each of the head acupoint points in the standard three-dimensional head parametric model.

[0060] Exemplarily, after obtaining the standard three-dimensional head parametric model marked with multiple head acupoint points, since both the standard three-dimensional head parametric model and the optimized three-dimensional head parametric model are FLAME models, the standard three-dimensional head parametric model and the optimized three-dimensional head parametric model have the same data structure. Then, match the identifiers of each vertex in the standard three-dimensional head parametric model with the identifiers of each vertex in the optimized three-dimensional head parametric model. For example, both the standard three-dimensional head parametric model and the optimized three-dimensional head parametric model include 5023 vertices, and the identifiers of each vertex are numbers from 1 to 5023. Then, the vertices with the same number correspond one-to-one. Therefore, the target vertices corresponding to the head acupoint points marked on the standard three-dimensional head parametric model can be searched among the vertices of the optimized three-dimensional head parametric model, which are the head acupoint points of the target object. Figure 11It is a schematic diagram of the standard 3D head parametric model and the optimized 3D head parametric model provided by the embodiments of the present invention. As Figure 11 shown, the left figure represents the standard 3D head parametric model, and the right figure represents the optimized 3D head parametric model. The red dots on the back of the heads of both are head acupoint points, and they correspond one by one and have the same numerical labels, and the numerical labels are the identifiers of the vertices.

[0061] Step 1043: Determine the name of the head acupoint point corresponding to the target vertex in the standard 3D head parametric model as the acupoint name of the target vertex.

[0062] Exemplarily, after finding the target vertices corresponding one by one to the head acupoint points marked in the standard 3D head parametric model among all the vertices of the optimized 3D head parametric model, determine the name of the head acupoint point corresponding to the target vertex in the standard 3D head parametric model as the acupoint name of the target vertex. For example, the 1000th vertex in the standard 3D head parametric model is marked as a head acupoint point, and the acupoint name is Yintang acupoint, then the 1000th point in the optimized 3D head parametric model is also a head acupoint point, and its acupoint name is Yintang acupoint. After the acupoint name of each vertex is determined, the position of each acupoint can also be known based on the position of each vertex, so as to obtain the personalized head acupoint set of the target object. The personalized head acupoint set includes the corresponding relationship between the positions and acupoint names of the various acupoints of the target object.

[0063] In this embodiment, based on the pre - marked standard 3D head parametric model, the positioning of each head acupoint in the optimized 3D head parametric model is carried out, getting rid of the dependence on a large amount of head acupoint annotation data. It only needs to perform head acupoint annotation on the standard 3D head parametric model once and can be used infinitely, and is not affected by factors such as light and environment, thus avoiding the cumbersome annotation and at the same time improving the accuracy of head acupoint positioning.

[0064] In one embodiment, the above - mentioned step 103 optimizes the initial 3D head parametric model based on the current positions of the respective tactile sensors to obtain the optimized 3D head parametric model, which can be specifically implemented in the following manner: Map the current positions of the respective tactile sensors to the 3D coordinate system corresponding to the initial 3D head parametric model to obtain the 3D coordinates of the head positions corresponding to the respective tactile sensors; construct a 3D point cloud on the head surface based on the respective 3D coordinates; optimize the initial 3D head parametric model based on the 3D point cloud on the head surface to obtain the optimized 3D head parametric model.

[0065] Exemplarily, when the current positions of the respective tactile sensors are obtained, based on the relationship between the world coordinate system and the three-dimensional coordinate system of the model, the current positions of the respective tactile sensors are mapped into the three-dimensional coordinate system corresponding to the initial three-dimensional head parametric model to obtain the three-dimensional coordinates of the respective tactile sensors. Since the respective tactile sensors are all in contact with the scalp at this time, the three-dimensional coordinates of the respective tactile sensors are equivalent to the three-dimensional coordinates of the head positions corresponding to the respective tactile sensors. Then, the set of the three-dimensional coordinates of the head positions corresponding to the respective tactile sensors forms a three-dimensional point cloud of the head surface. Furthermore, based on the three-dimensional point cloud of the head surface, the initial three-dimensional head parametric model of the target object is optimized to obtain an optimized three-dimensional head parametric model of the target object.

[0066] In this embodiment, the current positions of the respective tactile sensors are mapped into the three-dimensional coordinate system corresponding to the initial three-dimensional head parametric model to obtain the three-dimensional coordinates of the head positions corresponding to the respective tactile sensors. Based on the three-dimensional point cloud of the head surface constructed from the respective three-dimensional coordinates, the initial three-dimensional head parametric model is optimized to obtain an optimized three-dimensional head parametric model. Since the three-dimensional point cloud of the head surface can represent different scalp positions of the target object's head, the constructed three-dimensional point cloud of the head surface is more in line with the head shape of the target object, improving the accuracy of the construction of the three-dimensional point cloud of the head surface and further improving the accuracy of the optimized three-dimensional head parametric model.

[0067] In one embodiment, the above-mentioned optimization of the initial three-dimensional head parametric model based on the three-dimensional point cloud of the head surface to obtain the optimized three-dimensional head parametric model can be specifically implemented by the following method: Perform initial alignment of the respective vertices in the initial three-dimensional head parametric model and the three-dimensional point cloud of the head surface; construct an objective function based on the distances between the respective vertices and the three-dimensional point cloud in the three-dimensional point cloud of the head surface that is aligned with each vertex; optimize the initial three-dimensional head parametric model based on the objective function until the objective function is minimized to obtain the optimized three-dimensional head parametric model.

[0068] Exemplarily, an optimization method based on registration can be used. Specifically, the respective vertices in the initial three-dimensional head parametric model and the three-dimensional point cloud of the head surface are initially registered to achieve initial alignment, and an objective function is constructed based on the distances between the respective vertices and the three-dimensional point cloud in the three-dimensional point cloud of the head surface that is aligned with each vertex. The minimum of the point distances is used as the objective function for registration optimization. Based on this objective function, the shape parameters and pose parameters of the initial three-dimensional head parametric model are continuously optimized so that the shape of the optimized three-dimensional head parametric model can achieve the optimal registration with the three-dimensional point cloud of the head surface, and finally the optimized three-dimensional head parametric model is obtained.

[0069] Exemplarily, based on the projection optimization method, in order to better match the scalp of the initial three-dimensional head parameterized model with the three-dimensional point cloud of the head surface, 2D projections of different perspectives of the initial three-dimensional head parameterized model and the three-dimensional point cloud of the head surface can be synchronized. Based on the distance between the projection points of each vertex and the projection points of the three-dimensional point cloud of the head surface aligned with each vertex, an objective function is constructed. Taking the minimum distance deviation between the projection points as the optimized objective function, the shape parameters and pose parameters of the initial three-dimensional head parameterized model are continuously optimized based on this objective function, so that the shape of the optimized three-dimensional head parameterized model can achieve the optimal registration with the three-dimensional point cloud of the head surface, and finally the optimized three-dimensional head parameterized model is obtained. Figure 12 is one of the schematic diagrams provided by the embodiments of the present invention for optimizing the initial three-dimensional head parameterized model. As Figure 12 shown, the blue points represent the three-dimensional point cloud of the head surface, and the red arrow is the target direction for optimizing the scalp of the initial three-dimensional head parameterized model. In Figure 12 , the initial three-dimensional head parameterized model needs to be optimized in the direction indicated by the red arrow. Figure 13 is the second schematic diagram provided by the embodiments of the present invention for optimizing the initial three-dimensional head parameterized model. As Figure 13 shown, the blue points represent the three-dimensional point cloud of the head surface, and the red arrow is the target direction for optimizing the scalp of the initial three-dimensional head parameterized model. In Figure 13 , the initial three-dimensional head parameterized model needs to be optimized in the direction indicated by the red arrow, aiming to make the shape of the optimized three-dimensional head parameterized model fit and align with the three-dimensional point cloud of the head surface as much as possible.

[0070] It should be noted that the above two methods are only two embodiments of the present invention, and other optimization functions can also be designed to achieve the optimization of the initial three-dimensional head parameterized model, and the present invention does not limit this.

[0071] In this embodiment, the initial three-dimensional head parameterized model is optimized based on the three-dimensional point cloud of the head surface, so that the obtained optimized three-dimensional head parameterized model is more in line with the head of the target object, thereby improving the accuracy of the optimized three-dimensional head parameterized model and further improving the accuracy of the head acupoint positioning of the target object based on the optimized three-dimensional head parameterized model.

[0072] Next, the head acupoint positioning device provided by the present invention will be described. The head acupoint positioning device described below can be correspondingly referred to the head acupoint positioning method described above.

[0073] Figure 14 is the structural schematic diagram of the head acupoint positioning device provided by the embodiments of the present invention. As Figure 14As shown, the head acupoint positioning device 1400 includes a construction unit 1401, a control unit 1402, an optimization unit 1403, and a positioning unit 1404; where: The construction unit 1401 is configured to construct an initial three-dimensional head parametric model of the target object based on a target image including the head of the target object; The control unit 1402 is configured to control each tactile sensor in the acquisition device worn on the head of the target object to move in the direction of the head to apply pressure to the head until the current positions of each tactile sensor are obtained when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold; The optimization unit 1403 is configured to optimize the initial three-dimensional head parametric model based on the current positions of each tactile sensor to obtain an optimized three-dimensional head parametric model; The positioning unit 1404 is configured to perform head acupoint positioning in the optimized three-dimensional head parametric model.

[0074] The head acupoint positioning device provided by the present invention constructs an initial three-dimensional head parametric model of the target object based on a target image including the head of the target object, controls each tactile sensor in the acquisition device worn on the head of the target object to move in the direction of the head to apply pressure to the head until the current positions of each tactile sensor are obtained when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, optimizes the initial three-dimensional head parametric model based on the current positions of each tactile sensor to obtain an optimized three-dimensional head parametric model, and finally performs head acupoint positioning in the optimized three-dimensional head parametric model. It can be seen that the present invention controls multiple tactile sensors to apply pressure to the head until the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, and then obtains an optimized three-dimensional head parametric model based on the current positions of each tactile sensor. By applying pressure to the head, each tactile sensor can better fit the scalp of the target object, so that the obtained optimized three-dimensional head parametric model is more in line with the target object, improving the accuracy of the optimized three-dimensional head parametric model and further improving the accuracy of head acupoint positioning.

[0075] Based on any of the above embodiments, the acquisition device includes a plurality of the tactile sensors distributed at different positions, each of the tactile sensors is respectively connected to a corresponding driving device, and a force sensing module is provided at a position where each tactile sensor contacts the head; The control unit 1402 is specifically configured to: For each of the tactile sensors, control the tactile sensor to move in the direction of the head to apply pressure to the head through the driving device corresponding to the tactile sensor, and collect the current pressure through the force sensing module corresponding to the tactile sensor; When the current pressure is greater than or equal to the pressure threshold corresponding to the tactile sensor, the driving device corresponding to the tactile sensor is used to control the tactile sensor to stop moving towards the head direction; When all the tactile sensors stop moving towards the head direction, obtain the current positions of the tactile sensors.

[0076] Based on any of the above embodiments, the pressure threshold corresponding to the tactile sensor is determined based on the head position corresponding to the tactile sensor.

[0077] Based on any of the above embodiments, the positioning unit 1404 is specifically configured to: Obtain a standard three-dimensional head parametric model, which includes a plurality of labeled head acupoint points; In the optimized three-dimensional head parametric model, find target vertices corresponding one by one to each of the head acupoint points in the standard three-dimensional head parametric model; Determine the name of the acupoint corresponding to the target vertex in the standard three-dimensional head parametric model as the acupoint name of the target vertex.

[0078] Based on any of the above embodiments, the optimization unit 1403 is specifically configured to: Map the current positions of the tactile sensors to the three-dimensional coordinate system corresponding to the initial three-dimensional head parametric model to obtain the three-dimensional coordinates of the head positions corresponding to the tactile sensors; Construct a three-dimensional point cloud of the head surface based on the three-dimensional coordinates; Based on the three-dimensional point cloud of the head surface, optimize the initial three-dimensional head parametric model to obtain the optimized three-dimensional head parametric model.

[0079] Based on any of the above embodiments, the optimization unit 1403 is further specifically configured to: Perform an initial alignment between each vertex in the initial three-dimensional head parametric model and the three-dimensional point cloud of the head surface; Construct an objective function based on the distances between each vertex and the three-dimensional point cloud aligned with each vertex in the three-dimensional point cloud of the head surface; Optimize the initial three-dimensional head parametric model based on the objective function until the objective function is minimized to obtain the optimized three-dimensional head parametric model.

[0080] Figure 15 It is a schematic diagram of the physical structure of the electronic device provided by the embodiments of the present invention, as Figure 15As shown in the figure, the electronic device may include: a processor 1510, a communications interface 1520, a memory 1530, and a communication bus 1540. Among them, the processor 1510, the communications interface 1520, and the memory 1530 communicate with each other through the communication bus 1540. The processor 1510 may call the logical instructions in the memory 1530 to execute the head acupoint positioning method, which includes: based on a target image including the head of a target object, constructing an initial three-dimensional head parametric model of the target object; Controlling each tactile sensor in the acquisition device worn on the head of the target object to move towards the head to apply pressure to the head until, when the pressure applied by each tactile sensor to the head is greater than the corresponding pressure threshold, obtaining the current positions of each tactile sensor; Based on the current positions of each tactile sensor, optimizing the initial three-dimensional head parametric model to obtain an optimized three-dimensional head parametric model; Performing head acupoint positioning in the optimized three-dimensional head parametric model.

[0081] In addition, when the logical instructions in the above-mentioned memory 1530 are implemented in the form of software functional units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0082] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the head acupoint positioning method provided by the above-mentioned various methods. The method includes: based on a target image including the head of a target object, constructing an initial three-dimensional head parametric model of the target object; Control the movement of each tactile sensor in the acquisition device worn on the head of the target object towards the head to apply pressure to the head until the current positions of each tactile sensor are obtained when the pressures applied by each tactile sensor to the head are all greater than the corresponding pressure thresholds; Optimize the initial three-dimensional head parametric model based on the current positions of each tactile sensor to obtain an optimized three-dimensional head parametric model; Perform head acupoint positioning in the optimized three-dimensional head parametric model.

[0083] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the head acupoint positioning method provided by the above methods. The method includes: constructing an initial three-dimensional head parametric model of the target object based on a target image including the head of the target object; Control the movement of each tactile sensor in the acquisition device worn on the head of the target object towards the head to apply pressure to the head until the current positions of each tactile sensor are obtained when the pressures applied by each tactile sensor to the head are all greater than the corresponding pressure thresholds; Optimize the initial three-dimensional head parametric model based on the current positions of each tactile sensor to obtain an optimized three-dimensional head parametric model; Perform head acupoint positioning in the optimized three-dimensional head parametric model.

[0084] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0085] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solutions, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for locating acupuncture points on the head, characterized in that: include: Based on the target image including the head of the target object, construct an initial three-dimensional head parameterized model of the target object; Controlling each tactile sensor in the acquisition device worn on the head of the target object to move toward the head to apply pressure to the head, until the pressure applied to the head by each tactile sensor is greater than the corresponding pressure threshold, and obtaining the current position of each tactile sensor; Based on the current position of each of the tactile sensors, the initial three-dimensional head parameterized model is optimized to obtain an optimized three-dimensional head parameterized model; The head acupuncture points are located in the optimized three-dimensional head parameterized model.

2. The head acupuncture point positioning method according to claim 1, characterized in that: The acquisition device comprises a plurality of tactile sensors distributed at different positions, each of the tactile sensors is connected to a corresponding driving device, and a force sensing module is provided at a position of each tactile sensor in contact with the head; The controlling each tactile sensor in the acquisition device worn on the head of the target object to move toward the head to apply pressure to the head until the pressure applied to the head by each tactile sensor is greater than the corresponding pressure threshold, and obtaining the current position of each tactile sensor includes: For each of the tactile sensors, a driving device corresponding to the tactile sensor is used to control the tactile sensor to move toward the head so as to apply pressure to the head, and a force sensing module corresponding to the tactile sensor is used to collect the current pressure; When the current pressure is greater than or equal to a pressure threshold corresponding to the tactile sensor, controlling the tactile sensor to stop moving toward the head through a driving device corresponding to the tactile sensor; When all the tactile sensors stop moving toward the head, the current position of each tactile sensor is obtained.

3. The head acupuncture point positioning method according to claim 1, characterized in that: The pressure threshold corresponding to the tactile sensor is determined based on a head position corresponding to the tactile sensor.

4. The head acupuncture point positioning method according to claim 1, characterized in that: The positioning of head acupuncture points in the optimized three-dimensional head parameterized model includes: Acquire a standard three-dimensional parametric model of the head, wherein the standard three-dimensional parametric model of the head includes a plurality of marked head acupuncture points; Searching for target vertices in the optimized three-dimensional head parameterized model that correspond one-to-one to each of the head acupuncture points in the standard three-dimensional head parameterized model; The name of the head acupuncture point corresponding to the target vertex in the standard three-dimensional head parameterized model is determined as the acupuncture point name of the target vertex.

5. The head acupuncture point locating method according to claim 1, characterized in that: The step of optimizing the initial three-dimensional head parameterized model based on the current position of each of the tactile sensors to obtain an optimized three-dimensional head parameterized model includes: Mapping the current position of each of the tactile sensors to the three-dimensional coordinate system corresponding to the initial three-dimensional head parameterized model to obtain the three-dimensional coordinates of the head position corresponding to each of the tactile sensors; Constructing a three-dimensional point cloud of the head surface based on the three-dimensional coordinates; Based on the three-dimensional point cloud of the head surface, the initial three-dimensional head parameterized model is optimized to obtain the optimized three-dimensional head parameterized model.

6. The head acupuncture point positioning method according to claim 5, characterized in that: The step of optimizing the initial three-dimensional head parameterized model based on the three-dimensional point cloud of the head surface to obtain the optimized three-dimensional head parameterized model comprises: Initially aligning each vertex in the initial three-dimensional head parameterized model with the three-dimensional point cloud of the head surface; constructing an objective function based on the distance between each of the vertices and the three-dimensional point cloud aligned with each of the vertices in the three-dimensional point cloud of the head surface; The initial three-dimensional head parameterized model is optimized based on the objective function until the objective function is minimized, thereby obtaining the optimized three-dimensional head parameterized model.

7. A head acupuncture point positioning device, characterized in that: include: A construction unit, configured to construct an initial three-dimensional head parameterized model of the target object based on a target image including the head of the target object; A control unit, used for controlling each tactile sensor in the acquisition device worn on the head of the target object to move toward the head to apply pressure to the head, until the pressure applied to the head by each tactile sensor is greater than the corresponding pressure threshold, and obtaining the current position of each tactile sensor; an optimization unit, configured to optimize the initial three-dimensional head parameterized model based on the current position of each of the tactile sensors to obtain an optimized three-dimensional head parameterized model; A positioning unit is used to locate head acupuncture points in the optimized three-dimensional head parameterized model.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the head acupuncture point locating method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the head acupuncture point locating method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the head acupuncture point locating method according to any one of claims 1 to 6 is implemented.

Images