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

Abstract

The application provides a head acupoint positioning method and device, electronic equipment and storage medium, and relates to the technical field of medical treatment, wherein the method comprises the following steps: constructing an initial three-dimensional head parameterized model based on a target image comprising a target object head; controlling each tactile sensor in a collection device worn on the target object head to move towards 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 value, and then optimizing the initial three-dimensional head parameterized model based on the current position of each tactile sensor; and performing head acupoint 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 greater 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 is more in line with the target object, and the accuracy of head acupoint positioning is improved.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a method, device, electronic device, and storage medium for locating acupoints on the head. Background Technology

[0002] Acupoints on the head hold a very important position in Traditional Chinese Medicine (TCM). According to TCM theory, the head is the meeting point of all Yang meridians and a convergence point of many important meridians in the body. Therefore, acupoints on the head have a wide-ranging impact on health and function. However, there are significant individual differences in the head; factors such as head size, shape, and hair density can all affect the accuracy of acupoint location.

[0003] In related technologies, a three-dimensional parametric model of the target object's head is usually generated based on the target object's head image, and then the head acupoints are located in the three-dimensional parametric model.

[0004] However, the aforementioned technologies that generate a three-dimensional parametric head model based solely on head images are affected by factors such as hair density and hair occlusion of the head, which reduces the accuracy of the constructed three-dimensional parametric head model and further reduces the accuracy of head acupoint localization. Summary of the Invention

[0005] This invention provides a method, device, electronic device, and storage medium for locating acupoints on the head, in order to overcome the shortcomings of existing technologies that reduce the accuracy of acupoint location on the head.

[0006] This invention provides a method for locating acupoints on the head, comprising the following steps.

[0007] Based on the target image including the head of the target object, an initial three-dimensional head parametric model of the target object is constructed.

[0008] The tactile sensors in the acquisition device worn on the head of the target object are controlled to move towards 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 then the current position of each tactile sensor is obtained.

[0009] Based on the current position of each of the tactile sensors, the initial three-dimensional head parameterization model is optimized to obtain an optimized three-dimensional head parameterization model.

[0010] The head acupoints are located in the optimized three-dimensional head parametric model.

[0011] According to a head acupoint positioning method provided by the present invention, the acquisition device includes a plurality of tactile sensors distributed at different locations, each tactile sensor being connected to a corresponding driving device, and each tactile sensor having a force sensing module at the position in contact with the head;

[0012] The control involves moving each tactile sensor in the acquisition device worn on the target object's head toward the head to apply pressure to the head, until the pressure applied to the head by each tactile sensor exceeds a corresponding pressure threshold, and then acquiring the current position of each tactile sensor, including:

[0013] For each of the aforementioned tactile sensors, the driving device corresponding to the tactile sensor controls the tactile sensor to move towards the head to apply pressure to the head, and the force sensing module corresponding to the tactile sensor collects the current pressure.

[0014] When the current pressure is greater than or equal to the pressure threshold corresponding to the tactile sensor, the tactile sensor is controlled by the drive device corresponding to the tactile sensor to stop moving towards the head;

[0015] With all the tactile sensors having stopped moving toward the head, the current position of each of the tactile sensors is obtained.

[0016] According to the 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.

[0017] According to the present invention, a method for locating acupoints on the head includes locating acupoints on the head within the optimized three-dimensional parametric head model, comprising:

[0018] Obtain a standard three-dimensional parametric head model, which includes multiple labeled acupoints on the head;

[0019] In the optimized 3D head parameterized model, find the target vertices that correspond one-to-one with each of the head acupoints in the standard 3D head parameterized model;

[0020] The name of the acupoint on the head corresponding to the target vertex in the standard three-dimensional head parameterized model is determined as the acupoint name of the target vertex.

[0021] According to a head acupoint localization method provided by the present invention, the step of optimizing the initial three-dimensional head parametric model based on the current position of each of the tactile sensors to obtain an optimized three-dimensional head parametric model includes:

[0022] The current position of each of the tactile sensors is mapped to the three-dimensional coordinate system corresponding to the initial three-dimensional head parameterization model to obtain the three-dimensional coordinates of the head position corresponding to each of the tactile sensors;

[0023] A three-dimensional point cloud of the head surface is constructed based on the aforementioned three-dimensional coordinates;

[0024] Based on the three-dimensional point cloud of the head surface, the initial three-dimensional head parametric model is optimized to obtain the optimized three-dimensional head parametric model.

[0025] According to the present invention, a method for locating acupoints on the head includes optimizing an initial three-dimensional head parametric model based on a three-dimensional point cloud on the head surface to obtain an optimized three-dimensional head parametric model, comprising:

[0026] Perform initial alignment between each vertex in the initial 3D head parameterized model and the 3D point cloud of the head surface;

[0027] An objective function is constructed based on the distance between each vertex and the distance between the three-dimensional point clouds aligned with each vertex in the three-dimensional point cloud of the head surface;

[0028] The initial 3D head parameterized model is optimized based on the objective function until the objective function is minimized, thus obtaining the optimized 3D head parameterized model.

[0029] The present invention also provides a head acupoint positioning device, comprising:

[0030] A construction unit is used 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;

[0031] The control unit is used to 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 the pressure applied to the head by each tactile sensor is greater than the corresponding pressure threshold, and then to obtain the current position of each tactile sensor.

[0032] An optimization unit is used to optimize the initial three-dimensional head parameterization model based on the current position of each of the tactile sensors to obtain an optimized three-dimensional head parameterization model.

[0033] A positioning unit is used to locate acupoints on the head in the optimized three-dimensional head parameterized model.

[0034] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the head acupoint positioning methods described above.

[0035] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the head acupoint positioning method as described above.

[0036] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the head acupoint positioning method as described above.

[0037] The present invention provides a method, apparatus, electronic device, and storage medium for locating acupoints on the head. Based on a target image including the head of a target object, an initial three-dimensional parametric model of the target object's head is constructed. Each tactile sensor in a data acquisition device worn on the target object's head is controlled to move towards the head to apply pressure until the pressure applied by each tactile sensor to the head exceeds a corresponding pressure threshold. The current position of each tactile sensor is then acquired. Based on the current positions of each tactile sensor, the initial three-dimensional parametric model of the head is optimized to obtain an optimized three-dimensional parametric model of the head. Finally, acupoints on the head are located within this optimized three-dimensional 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 exceeds a corresponding pressure threshold. Then, based on the current positions of each tactile sensor, an optimized three-dimensional parametric model of the head is obtained. By applying pressure to the head, the tactile sensors can better conform to the scalp of the target object, thereby making the obtained optimized three-dimensional parametric model of the head more consistent with the target object, improving the accuracy of the optimized three-dimensional parametric model, and further improving the accuracy of acupoint location. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is one of the flowcharts illustrating the head acupoint location method provided in this embodiment of the invention.

[0040] Figure 2 This is a schematic diagram of the initial three-dimensional head parameterized model provided by the present invention.

[0041] Figure 3 This is a side view of the target object wearing the acquisition device provided in an embodiment of the present invention.

[0042] Figure 4This is a top view of the target object wearing the acquisition device provided in an embodiment of the present invention.

[0043] Figure 5 This is a schematic diagram of the tactile sensor applying pressure according to an embodiment of the present invention.

[0044] Figure 6 This is the second flowchart illustrating the head acupoint location method provided in this embodiment of the invention.

[0045] Figure 7 This is the third flowchart of the head acupoint location method provided in the embodiments of the present invention.

[0046] Figure 8 This is a front view of the standard three-dimensional parametric head model with acupoints annotated, provided in an embodiment of the present invention.

[0047] Figure 9 This is a rear view of the standard three-dimensional parametric head model with acupoints annotated, as provided in this embodiment of the invention.

[0048] Figure 10 This is a side view of a standard three-dimensional parametric head model with labeled acupoints provided in an embodiment of the present invention.

[0049] Figure 11 This is a schematic diagram of the standard three-dimensional head parametric model and the optimized three-dimensional head parametric model provided in the embodiments of the present invention.

[0050] Figure 12 This is one of the schematic diagrams provided in the embodiments of the present invention for optimizing the initial three-dimensional head parameterized model.

[0051] Figure 13 This is the second schematic diagram of optimizing the initial three-dimensional head parameterized model provided in the embodiment of the present invention.

[0052] Figure 14 This is a schematic diagram of the head acupoint positioning device provided in an embodiment of the present invention.

[0053] Figure 15 This is a schematic diagram of the physical structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0055] The following is combined Figures 1-13 This invention describes a method for locating acupoints on the head. The subject executing this method can be an electronic device such as a computer, medical device, or robotic arm capable of controlling the acquisition equipment, or it can be a head acupoint positioning device installed in the electronic device. This head acupoint positioning device can be implemented through software, hardware, or a combination of both.

[0056] Figure 1 This is one of the flowcharts illustrating the head acupoint location method provided in this embodiment of the invention, such as... Figure 1 As shown, this method for locating acupoints on the head includes the following steps:

[0057] Step 101: Based on the target image including the head of the target object, construct an initial three-dimensional head parametric model of the target object.

[0058] For example, the target object can be any person who needs head acupoint localization. The electronic device acquires a target image including the target object's head via a camera. Specifically, the target image can be an RGB image showing the frontal view of the target object's face. Face detection and facial key point localization are performed on this RGB image. Based on the detected face information and each facial key point, a correlation method is used to predict and obtain an initial 3D head parameterized model of the target object. The constructed initial 3D head parameterized model is as follows: Figure 2 As shown. The relevant methods can include Towards Metrical Reconstruction of Human Faces (MICA), Detailed Expression Capture and Animation (DECA), Emotion-Driven Monocular Face Capture and Animation (EMOCA), etc. The initial 3D head parameterization model can be the FLAME (Faces Learned with an Articulated Model and Expressions) model; this invention does not limit this to a specific model.

[0059] Step 102: 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 the pressure applied to the head by each tactile sensor is greater than the corresponding pressure threshold, and then obtain the current position of each tactile sensor.

[0060] For example, a head-worn data acquisition device is pre-designed. This device can be strip-shaped, band-shaped, or a headband-like device. The device is worn on the target's head. The hairline can be used as a reference line as the starting layout line, and the tactile sensors on the edge of the acquisition device are distributed along the hairline. Of course, other parts can also be used as references. Ultimately, all the tactile sensors distributed on the acquisition device are distributed as evenly as possible in different positions on the head to more accurately perceive scalp shape information over a wider range. Figure 3 This is a side view of the target object wearing the acquisition device provided in an embodiment of the present invention, such as... Figure 3 As shown, the data acquisition device is worn with the hairline as the reference line. The red circles represent the marking points on the head surface. The data acquisition device is worn correctly by following the marking points on the head surface. Figure 4 This is a top view of the target object wearing the acquisition device provided in an embodiment of the present invention, such as... Figure 4 As shown, multiple tactile sensors are distributed on the data acquisition device. Figure 4 The tactile sensors are represented by red dots.

[0061] When constructing the initial 3D parametric model of the target object's head, each tactile sensor is controlled to move towards the head, specifically towards the normal direction of the scalp, so that each tactile sensor applies pressure to the corresponding position on the head. Figure 5 This is a schematic diagram of the tactile sensor applying pressure according to an embodiment of the present invention, as shown below. Figure 5 As shown, the red ellipse represents the tactile sensor, which applies pressure in the normal direction to the scalp. The system continuously monitors the pressure applied by each tactile sensor to its corresponding position on the head. When the pressure applied by a tactile sensor exceeds a corresponding pressure threshold, the sensor stops moving towards the head. This process continues until all tactile sensors have stopped moving towards the head, indicating that each sensor is fully in contact with the scalp. At this point, the current position of each tactile sensor is recorded. Specifically, a positioning module can be incorporated into each tactile sensor to determine its current position based on the positions acquired by that module. Alternatively, an Inertial Measurement Unit (IMU) can be included in each tactile sensor. When the device is first worn on the head, it is initialized and held stationary for a preset time, recording the initial position of each tactile sensor. The control acquisition device is started, and when all tactile sensors are fully in contact with the scalp, the motion trajectory measured by each IMU is acquired. This motion trajectory is determined based on the acceleration and angular velocity data measured by the IMU. By integrating the acceleration and angular velocity data, the displacement of the tactile sensor from the initial position to the scalp is calculated, and the current position of the tactile sensor is calculated by combining the initial position and the displacement.

[0062] Step 103: Based on the current position of each of the tactile sensors, optimize the initial three-dimensional head parameterization model to obtain the optimized three-dimensional head parameterization model.

[0063] For example, when the current position of each tactile sensor is obtained, since each tactile sensor is attached to the scalp, the current position of each tactile sensor can represent the corresponding scalp position, which is equivalent to obtaining multiple scalp positions. Then, the initial three-dimensional head parametric model can be optimized based on multiple scalp positions, so that the optimized three-dimensional head parametric model is more in line with the overall head shape of the target object.

[0064] Step 104: Locate acupoints on the head in the optimized three-dimensional head parameterized model.

[0065] For example, when the optimized 3D head parametric model of the target object is obtained, the optimized 3D head parametric model is matched with the standard 3D head parametric model so that the names of each acupoint marked in the standard 3D head parametric model are mapped to the optimized 3D head parametric model, thereby realizing the localization of head acupoints in the optimized 3D head parametric model.

[0066] The head acupoint localization method provided by this invention constructs an initial three-dimensional head parametric model of the target object based on a target image including the target object's head. It controls the movement of each tactile sensor in a data acquisition device worn on the target object's head towards the head to apply pressure until the pressure applied by each tactile sensor to the head exceeds a corresponding pressure threshold. Then, it acquires the current position of each tactile sensor. Based on the current positions of each tactile sensor, it optimizes the initial three-dimensional head parametric model to obtain an optimized three-dimensional head parametric model. Finally, it performs head acupoint localization within the optimized three-dimensional head parametric model. This invention controls multiple tactile sensors to apply pressure to the head until the pressure applied by each tactile sensor exceeds a corresponding pressure threshold, and then obtains the optimized three-dimensional head parametric model based on the current positions of each tactile sensor. By applying pressure to the head, the tactile sensors can better conform to the scalp of the target object, making the obtained optimized three-dimensional head parametric model more consistent with the target object, improving the accuracy of the optimized three-dimensional head parametric model, and further improving the accuracy of head acupoint localization.

[0067] In one embodiment, the data acquisition device includes multiple tactile sensors distributed at different locations. Each tactile sensor is connected to a corresponding driving device, and each tactile sensor has a force sensing module at the position where it contacts the head. That is, one tactile sensor is connected to one driving device, and each tactile sensor has a force sensing module. The driving device can be a motor, and each driving device is connected to a processor of an electronic device, which controls the operation of each driving device. Furthermore, it should be noted that the tactile sensors should be densely distributed on the data acquisition device, specifically at preset intervals. The preset values ​​can be set based on requirements, for example, 0.5 cm or smaller; this invention does not limit this.

[0068] Figure 6 This is a second schematic flowchart of the head acupoint location method provided in this embodiment of the invention, as shown below. Figure 6 As shown, step 102 above controls each tactile sensor in the acquisition device worn on the target object's head to move towards 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 then obtains the current position of each tactile sensor. This can be achieved through the following steps:

[0069] Step 601: For each of the tactile sensors, control the tactile sensor to move towards the head 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.

[0070] For example, after the acquisition device is started, the processor of the electronic device sends a start command to the driving device corresponding to each tactile sensor, so that after the driving device is started, it controls the connected tactile sensor to move towards the head 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 of the tactile sensor in contact with the head collects the current pressure in real time and sends the current pressure to the processor of the electronic device.

[0071] Step 602: When the current pressure is greater than or equal to the pressure threshold corresponding to the tactile sensor, the tactile sensor is controlled to stop moving towards the head by the drive device corresponding to the tactile sensor.

[0072] For example, the electronic device pre-stores a correspondence between tactile sensor identifiers and pressure thresholds. When the processor of the electronic device receives the current pressure sent by the force sensing module corresponding to the tactile sensor, it looks up the pressure threshold corresponding to the tactile sensor identifier in the correspondence and compares the current pressure with the found pressure threshold. If the current pressure is less than the found pressure threshold, the processor continues to control the tactile sensor to apply pressure towards the head via the drive device. If the current pressure is greater than or equal to the found pressure threshold, it indicates that the tactile sensor is fully in contact with the scalp. At this point, the processor controls the tactile sensor to stop moving towards the head, thus ceasing to apply pressure to the head. Similarly, other tactile sensors are controlled to move towards the head until the current pressure collected by the force sensing module corresponding to the other tactile sensor is greater than or equal to the pressure threshold corresponding to that other tactile sensor, at which point the other tactile sensors also stop moving towards the head.

[0073] Step 603: When all the tactile sensors have stopped moving toward the head, obtain the current position of each of the tactile sensors.

[0074] For example, when all tactile sensors stop moving towards the head, it means that all tactile sensors have been in contact with the scalp of the target object. At this time, the current position of each tactile sensor is obtained, and the current position of each tactile sensor represents the position of each scalp of the target object.

[0075] In this embodiment, the current pressure is collected by the force sensing module set on each tactile sensor. By comparing the current pressure with the corresponding pressure threshold, the time when the tactile sensor stops moving towards the head is determined. When all tactile sensors stop moving towards the head, it means that all tactile sensors have been in contact with the scalp of the target object. At this time, the current position of each tactile sensor is obtained, which improves the accuracy of obtaining the current position.

[0076] In one embodiment, the pressure threshold corresponding to the tactile sensor is determined based on the head position corresponding to the tactile sensor.

[0077] For example, since the head is curved and the hardness of different areas of the head varies, the pressure threshold of each tactile sensor is also different. Specifically, it can be determined based on the hardness of the head position corresponding to each tactile sensor. That is, the pressure threshold of the tactile sensor corresponding to a harder position is larger, and the pressure threshold of the tactile sensor corresponding to a softer position is smaller.

[0078] In this embodiment, the pressure threshold corresponding to the tactile sensor is determined based on the head position corresponding to the tactile sensor, which improves the accuracy of determining each pressure threshold and further improves the accuracy of controlling the corresponding tactile sensor based on each pressure threshold.

[0079] In one embodiment, Figure 7 This is the third flowchart illustrating the head acupoint location method provided in this embodiment of the invention, as shown below. Figure 7 As shown, step 104 above involves locating acupoints on the head in the optimized 3D head parametric model, which can be achieved through the following steps:

[0080] Step 1041: Obtain a standard three-dimensional parametric head model, which includes multiple labeled acupoints on the head.

[0081] For example, we obtain the FLAME model. The FLAME model is a parameterized head geometry model containing three sets of parameters: basic shape, expression vector, and head pose. The FLAME model can learn individual facial features using a small amount of keypoint tracking data and can be represented using low-dimensional latent vectors, thus achieving both universal and personalized expression for different faces. Furthermore, the FLAME model has a fixed data structure; FLAME models with different parameters share the same data structure, meaning there is a one-to-one correspondence between points and between the lines connecting them. Using a general model where all basic shape, expression, and head pose parameters of the FLAME model are 0.00 as the standard 3D head parameterized model, based on the definitions and rules of acupoints on the head, all head acupoints are labeled on the standard FLAME model. That is, the corresponding vertex in the standard 3D head parameterized model is labeled with the name of the head acupoint, and this vertex serves as the head acupoint location. For example, the 100th vertex of the standard 3D head parameterized model is the Yintang acupoint, and the 1500th vertex is the Baihui acupoint, etc. Figure 8 This is a front view of a standard three-dimensional parametric head model with labeled acupoints provided in an embodiment of the present invention. Figure 9 This is a rear view of the standard three-dimensional parametric head model with acupoint annotations provided in this embodiment of the invention. Figure 10 This is a side view of a standard three-dimensional parametric head model with labeled acupoints provided in this embodiment of the invention, such as... Figures 8 to 10 As shown, each red dot represents a vertex labeled with the name of an acupoint.

[0082] Step 1042: In the optimized three-dimensional head parameterized model, find the target vertices that correspond one-to-one with each of the head acupoints in the standard three-dimensional head parameterized model.

[0083] For example, after obtaining a standard 3D parametric head model labeled with multiple acupoints, since both the standard and optimized 3D parametric head models are FLAME models, they have the same data structure. The identifiers of each vertex in the standard 3D parametric head model are then matched with those in the optimized 3D parametric head model. For instance, both the standard and optimized 3D parametric head models contain 5023 vertices, and each vertex is identified by a number from 1 to 5023. Vertices with the same number correspond one-to-one. Therefore, the target vertex corresponding to the acupoints labeled in the standard 3D parametric head model can be found in the vertices of the optimized 3D parametric head model; this is the target object's acupoint. Figure 11 These are schematic diagrams of the standard 3D head parametric model and the optimized 3D head parametric model provided in embodiments of the present invention, as shown below. Figure 11 As shown, the left image represents the standard 3D parametric head model, and the right image represents the optimized 3D parametric head model. The red dots on the back of the head in both images are acupoints, and they correspond one-to-one with the same numerical labels, which are the identifiers of the vertices.

[0084] Step 1043: Determine the name of the acupoint on the head corresponding to the target vertex in the standard three-dimensional head parameterized model as the acupoint name of the target vertex.

[0085] For example, after identifying the target vertices in the optimized 3D head parametric model that correspond one-to-one with the acupoints marked in the standard 3D head parametric model, the names of the acupoints corresponding to the target vertices in the standard 3D head parametric model are determined as the acupoint names of the target vertices. For instance, if the 1000th vertex in the standard 3D head parametric model is marked as a head acupoint with the name "Yintang acupoint," then the 1000th vertex in the optimized 3D head parametric model is also a head acupoint with the name "Yintang acupoint." After determining the acupoint names for each vertex, the location of each acupoint can be determined based on the position of each vertex, thus obtaining a personalized set of head acupoints for the target object. This personalized set of head acupoints includes the correspondence between the locations and names of each acupoint on the target object.

[0086] In this embodiment, based on the pre-annotated standard 3D head parametric model, the acupoints of the head in the optimized 3D head parametric model are located. This eliminates the dependence on massive head acupoint annotation data. Only one head acupoint annotation is required on the standard 3D head parametric model, which can be used an unlimited number of times. It is also unaffected by factors such as light and environment, thus avoiding the tediousness of annotation and improving the accuracy of head acupoint location.

[0087] In one embodiment, step 103 above optimizes the initial three-dimensional head parameterization model based on the current position of each of the tactile sensors to obtain an optimized three-dimensional head parameterization model, which can be implemented in the following way:

[0088] The current position of each tactile sensor is mapped to the three-dimensional coordinate system corresponding to the initial three-dimensional head parameterization model to obtain the three-dimensional coordinates of the head position corresponding to each tactile sensor; a three-dimensional point cloud of the head surface is constructed based on each three-dimensional coordinate; the initial three-dimensional head parameterization model is optimized based on the three-dimensional point cloud of the head surface to obtain the optimized three-dimensional head parameterization model.

[0089] For example, when the current position of each tactile sensor is obtained, based on the relationship between the world coordinate system and the model's three-dimensional coordinate system, the current position of each tactile sensor is mapped to the three-dimensional coordinate system corresponding to the initial three-dimensional head parameterized model to obtain the three-dimensional coordinates of each tactile sensor. Since each tactile sensor is now in contact with the scalp, the three-dimensional coordinates of each tactile sensor are equivalent to the three-dimensional coordinates of the head position corresponding to each tactile sensor. The set of three-dimensional coordinates of the head position corresponding to each tactile sensor forms a three-dimensional point cloud of the head surface. Then, based on the three-dimensional point cloud of the head surface, the initial three-dimensional head parameterized model of the target object is optimized to obtain the optimized three-dimensional head parameterized model of the target object.

[0090] In this embodiment, the current position of each tactile sensor is mapped to the three-dimensional coordinate system corresponding to the initial three-dimensional head parameterization model to obtain the three-dimensional coordinates of the head position corresponding to each tactile sensor. Based on the three-dimensional point cloud of the head surface constructed from each three-dimensional coordinate, the initial three-dimensional head parameterization model is optimized to obtain the optimized three-dimensional head parameterization 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 consistent with the head shape of the target object, improving the accuracy of the three-dimensional point cloud construction of the head surface, and further improving the accuracy of the optimized three-dimensional head parameterization model.

[0091] In one embodiment, the initial three-dimensional head parametric model is optimized based on the three-dimensional point cloud of the head surface to obtain the optimized three-dimensional head parametric model. This can be achieved in the following way:

[0092] The vertices in the initial 3D head parameterized model are initially aligned with the 3D point cloud of the head surface; an objective function is constructed based on the distance between each vertex and the 3D point cloud of the head surface aligned with each vertex; the initial 3D head parameterized model is optimized based on the objective function until the objective function is minimized, thus obtaining the optimized 3D head parameterized model.

[0093] For example, an optimization method based on registration can be used. Specifically, each vertex in the initial 3D head parametric model is initially registered with the 3D point cloud on the head surface to achieve initial alignment. Based on the distance between each vertex and the 3D point cloud on the head surface that is aligned with each vertex, an objective function is constructed. The minimum point distance is used as the objective function for registration optimization. Based on this objective function, the shape and pose parameters of the initial 3D head parametric model are continuously optimized so that the shape of the optimized 3D head parametric model can achieve optimal registration with the 3D point cloud on the head surface, and finally, the optimized 3D head parametric model is obtained.

[0094] For example, an optimization method based on projection can be used to better match the scalp of the initial 3D head parametric model with the 3D point cloud of the head surface. This can be achieved by synchronously projecting the initial 3D head parametric model and the 3D point cloud of the head surface into 2D from different perspectives. Based on the distance between the projection points of each vertex and the projection points of the 3D point cloud of the head surface that are aligned with each vertex, an objective function is constructed. The objective function is to minimize the distance deviation between the projection points. Based on this objective function, the shape and pose parameters of the initial 3D head parametric model are continuously optimized so that the shape of the optimized 3D head parametric model can achieve optimal registration with the 3D point cloud of the head surface, ultimately resulting in the optimized 3D head parametric model. Figure 12 This is one of the schematic diagrams provided in the embodiments of the present invention for optimizing the initial three-dimensional head parameterized model, such as... Figure 12 As shown, the blue dots represent the 3D point cloud of the head surface, and the red arrows indicate the target directions for optimization of the scalp in the initial 3D parametric head model. Figure 12 In the process, the initial 3D head parameterized model needs to be optimized in the direction indicated by the red arrow. Figure 13 This is the second schematic diagram of optimizing the initial three-dimensional head parameterized model provided in this embodiment of the invention, as shown below. Figure 13 As shown, the blue dots represent the 3D point cloud of the head surface, and the red arrows indicate the target directions for optimization of the scalp in the initial 3D parametric head model. Figure 13 In the process, the initial 3D head parametric model needs to be optimized in the direction indicated by the red arrow, with the aim of making the shape of the optimized 3D head parametric model fit and align with the 3D point cloud on the head surface as closely as possible.

[0095] It should be noted that the above two methods are only two embodiments of the present invention. Other optimization functions can also be designed to optimize the initial three-dimensional head parameterized model, and the present invention does not limit this.

[0096] In this embodiment, the initial three-dimensional head parametric model is optimized based on the three-dimensional point cloud of the head surface, so that the optimized three-dimensional head parametric model is more consistent with the head of the target object, thereby improving the accuracy of the optimized three-dimensional head parametric model and further improving the accuracy of locating acupoints on the head of the target object based on the optimized three-dimensional head parametric model.

[0097] The head acupoint positioning device provided by the present invention is described below. The head acupoint positioning device described below can be referred to in correspondence with the head acupoint positioning method described above.

[0098] Figure 14 This is a schematic diagram of the head acupoint positioning device provided in an embodiment of the present invention, as shown below. Figure 14 As 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; wherein:

[0099] Construction unit 1401 is used 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;

[0100] Control unit 1402 is used to 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 the pressure applied to the head by each tactile sensor is greater than the corresponding pressure threshold, and to obtain the current position of each tactile sensor.

[0101] The optimization unit 1403 is used to optimize the initial three-dimensional head parameterization model based on the current position of each of the tactile sensors to obtain an optimized three-dimensional head parameterization model.

[0102] The positioning unit 1404 is used to locate acupoints on the head in the optimized three-dimensional head parameterized model.

[0103] The head acupoint positioning device provided by this invention constructs an initial three-dimensional head parametric model of the target object based on a target image including the target object's head. It controls the movement of each tactile sensor in a data acquisition device worn on the target object's head towards the head to apply pressure until the pressure applied by each tactile sensor to the head exceeds a corresponding pressure threshold. Then, it acquires the current position of each tactile sensor. Based on the current positions of each tactile sensor, it optimizes the initial three-dimensional head parametric model to obtain an optimized three-dimensional head parametric model. Finally, it performs head acupoint positioning within the optimized three-dimensional head parametric model. This invention controls multiple tactile sensors to apply pressure to the head until the pressure applied by each tactile sensor exceeds a corresponding pressure threshold, and then obtains the optimized three-dimensional head parametric model based on the current positions of each tactile sensor. By applying pressure to the head, the tactile sensors can better conform to the scalp of the target object, making the obtained optimized three-dimensional head parametric model more consistent with the target object, improving the accuracy of the optimized three-dimensional head parametric model, and further improving the accuracy of head acupoint positioning.

[0104] Based on any of the above embodiments, the acquisition device includes a plurality of tactile sensors distributed at different locations, each tactile sensor being connected to a corresponding driving device, and each tactile sensor having a force sensing module at the position in contact with the head;

[0105] The control unit 1402 is specifically used for:

[0106] For each of the aforementioned tactile sensors, the driving device corresponding to the tactile sensor controls the tactile sensor to move towards the head to apply pressure to the head, and the force sensing module corresponding to the tactile sensor collects the current pressure.

[0107] When the current pressure is greater than or equal to the pressure threshold corresponding to the tactile sensor, the tactile sensor is controlled by the drive device corresponding to the tactile sensor to stop moving towards the head;

[0108] With all the tactile sensors having stopped moving toward the head, the current position of each of the tactile sensors is obtained.

[0109] 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.

[0110] Based on any of the above embodiments, the positioning unit 1404 is specifically used for:

[0111] Obtain a standard three-dimensional parametric head model, which includes multiple labeled acupoints on the head;

[0112] In the optimized 3D head parameterized model, find the target vertices that correspond one-to-one with each of the head acupoints in the standard 3D head parameterized model;

[0113] The name of the acupoint on the head corresponding to the target vertex in the standard three-dimensional head parameterized model is determined as the acupoint name of the target vertex.

[0114] Based on any of the above embodiments, the optimization unit 1403 is specifically used for:

[0115] The current position of each of the tactile sensors is mapped to the three-dimensional coordinate system corresponding to the initial three-dimensional head parameterization model to obtain the three-dimensional coordinates of the head position corresponding to each of the tactile sensors;

[0116] A three-dimensional point cloud of the head surface is constructed based on the aforementioned three-dimensional coordinates;

[0117] Based on the three-dimensional point cloud of the head surface, the initial three-dimensional head parametric model is optimized to obtain the optimized three-dimensional head parametric model.

[0118] Based on any of the above embodiments, the optimization unit 1403 is further specifically used for:

[0119] Perform initial alignment between each vertex in the initial 3D head parameterized model and the 3D point cloud of the head surface;

[0120] An objective function is constructed based on the distance between each vertex and the distance between the three-dimensional point clouds aligned with each vertex in the three-dimensional point cloud of the head surface;

[0121] The initial 3D head parameterized model is optimized based on the objective function until the objective function is minimized, thus obtaining the optimized 3D head parameterized model.

[0122] Figure 15 This is a schematic diagram of the physical structure of the electronic device provided in the embodiments of the present invention, such as... Figure 15 As shown, the electronic device may include a processor 1510, a communications interface 1520, a memory 1530, and a communication bus 1540, wherein the processor 1510, the communications interface 1520, and the memory 1530 communicate with each other through the communication bus 1540. The processor 1510 can call logical instructions in the memory 1530 to execute a head acupoint localization method, which 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;

[0123] The tactile sensors in the acquisition device worn on the head of the target object are controlled to move towards 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 then the current position of each tactile sensor is obtained.

[0124] Based on the current position of each of the tactile sensors, the initial three-dimensional head parameterization model is optimized to obtain an optimized three-dimensional head parameterization model.

[0125] The head acupoints are located in the optimized three-dimensional head parametric model.

[0126] Furthermore, the logical instructions in the aforementioned memory 1530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0127] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, the computer program being executed by a processor, the computer being able to execute the head acupoint localization method provided by the above methods, the method including: constructing an initial three-dimensional head parametric model of the target object based on a target image including the head of the target object;

[0128] The tactile sensors in the acquisition device worn on the head of the target object are controlled to move towards 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 then the current position of each tactile sensor is obtained.

[0129] Based on the current position of each of the tactile sensors, the initial three-dimensional head parameterization model is optimized to obtain an optimized three-dimensional head parameterization model.

[0130] The head acupoints are located in the optimized three-dimensional head parametric model.

[0131] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the head acupoint localization method provided by the above methods, the method comprising: constructing an initial three-dimensional head parametric model of the target object based on a target image including the head of the target object;

[0132] The tactile sensors in the acquisition device worn on the head of the target object are controlled to move towards 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 then the current position of each tactile sensor is obtained.

[0133] Based on the current position of each of the tactile sensors, the initial three-dimensional head parameterization model is optimized to obtain an optimized three-dimensional head parameterization model.

[0134] The head acupoints are located in the optimized three-dimensional head parametric model.

[0135] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0136] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A head acupoint positioning method, characterized in that, The method comprises: constructing an initial three-dimensional head parameterized model of the target object based on a target image comprising a head of the target object; controlling each haptic sensor in a collection device worn on the head of the target object to move towards the head to apply pressure to the head until the pressure applied to the head by each haptic sensor is greater than a corresponding pressure threshold, and then obtaining the current position of each haptic sensor; optimizing the initial three-dimensional head parameterized model based on the current position of each haptic sensor to obtain an optimized three-dimensional head parameterized model; performing head acupoint positioning in the optimized three-dimensional head parameterized model; the method of optimizing the initial three-dimensional head parameterized model based on the current position of each haptic sensor to obtain an optimized three-dimensional head parameterized model comprises: mapping the current position of each haptic sensor to a three-dimensional coordinate system corresponding to the initial three-dimensional head parameterized model to obtain the three-dimensional coordinates of the corresponding head position of each haptic sensor; constructing a three-dimensional point cloud of the head surface based on each three-dimensional coordinate; 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 vertex and the three-dimensional point cloud of the head surface that aligns with each vertex; 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.

2. The head acupoint positioning method according to claim 1, characterized in that, The collection device comprises a plurality of haptic sensors distributed at different positions, each haptic sensor is connected to a corresponding driving device, and the position of each haptic sensor that contacts the head is provided with a force perception module; the method of controlling each haptic sensor in a collection device worn on the head of the target object to move towards the head to apply pressure to the head until the pressure applied to the head by each haptic sensor is greater than a corresponding pressure threshold, and then obtaining the current position of each haptic sensor, comprises: for each haptic sensor, controlling the haptic sensor to move towards the head to apply pressure to the head through the corresponding driving device of the haptic sensor, and collecting the current pressure through the corresponding force perception module of the haptic sensor; when the current pressure is greater than or equal to the corresponding pressure threshold of the haptic sensor, controlling the haptic sensor to stop moving towards the head through the corresponding driving device of the haptic sensor; when all haptic sensors stop moving towards the head, obtaining the current position of each haptic sensor.

3. The head acupoint positioning method according to claim 1, characterized in that, The corresponding pressure threshold of the haptic sensor is determined based on the corresponding head position of the haptic sensor.

4. The head acupoint positioning method according to claim 1, characterized in that, The method of performing head acupoint positioning in the optimized three-dimensional head parameterized model comprises: obtaining a standard three-dimensional head parameterized model, the standard three-dimensional head parameterized model comprising a plurality of labeled head acupoint points; finding target vertices in the optimized three-dimensional head parameterized model that correspond one-to-one to each head acupoint point in the standard three-dimensional head parameterized 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.

5. A head acupoint positioning device, characterized in that, The method comprises the following steps: A construction unit is configured to construct an initial three-dimensional head parametric model of a target object based on a target image comprising a head of the target object. A control unit is configured to control each tactile sensor in a collection device worn on the head of the target object to move towards the head to apply pressure to the head until the pressure applied to the head by each tactile sensor is greater than a corresponding pressure threshold value, and then obtain the current position of each tactile sensor. An optimization unit is configured to optimize 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. A positioning unit is configured to position acupoints on the head in the optimized three-dimensional head parametric model. The optimization unit is specifically configured to: Map the current position of each tactile sensor to a three-dimensional coordinate system corresponding to the initial three-dimensional head parametric model to obtain three-dimensional coordinates of the head position corresponding to each tactile sensor. Construct a three-dimensional point cloud of the head surface based on each three-dimensional coordinate. Initially align each vertex in the initial three-dimensional head parametric model with the three-dimensional point cloud of the head surface. Construct an objective function based on the distance between each vertex and the three-dimensional point cloud of the head surface 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.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The processor executes the computer program to implement the head acupoint positioning method of any one of claims 1-4.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the head acupoint positioning method of any one of claims 1-4.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the head acupoint positioning method of any one of claims 1-4.

Images