False detection meridian recovery method, device and equipment based on spatial topology and position reasoning

Abstract

The invention relates to a false detection meridian recovery method, device and equipment based on spatial topology and position reasoning, and the method comprises the steps: generating a false detection recovery acupoint coordinate through a known meridian acupoint and a symmetrical meridian acupoint according to a symmetry constraint relation of human meridian acupoints, and generating a false detection recovery acupoint coordinate based on a logic topology constraint relation of the human meridian acupoints. The method comprises the following steps: correcting X-axis coordinates of falsely detected and repaired acupuncture points through inherent trend and naming sequence of human meridians and collaterals, correcting Y-axis coordinates of the falsely detected and repaired acupuncture points according to a spatial topology constraint relation of the human meridians and collaterals and acupuncture points by determining an up-down position relation of the meridians and collaterals under a human body posture and through a relative position relation under a specific scene, and correcting the false detected and repaired acupuncture points according to the spatial topology constraint relation. The positions of the acupuncture points are estimated through the movement distance of the bed body, and the false detection of the acupuncture points is discriminated and recovered. According to the method, the repairing coordinates are generated through the features of the acupuncture points and the symmetric points, cooperative correction of the axis coordinates is achieved through the logical topology and the spatial topology of the meridians and collaterals, and discrimination and recovery of long-section false detection are achieved through the position of the target point.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and in particular to a method, apparatus and device for recovering falsely detected meridians based on spatial topology and positional reasoning. Background Technology

[0002] With the development of computer vision and artificial intelligence technologies, utilizing computer vision to detect and locate the body's meridians, and realizing the digitalization of traditional Chinese medicine treatment, has become a promising research direction. Accurate detection of the body's meridians is crucial for analyzing human physiology and pathology, and for diagnosing and treating diseases. Therefore, the independently developed SY-3 Digital TCM Meridian Therapy System needs to ensure accurate detection of the user's meridians during the treatment process to guarantee the smoothness and integrity of the treatment, providing the user with a pleasant experience.

[0003] Preliminary research revealed that human meridians possess natural left-right symmetry and relatively fixed positions in specific scenarios during image-based detection. Therefore, a method for recovering misdetected meridians based on spatial topology and positional reasoning is proposed. This method utilizes the inherent left-right symmetry of human meridians, the spatial topological relationships and sequence of acupoints on the same meridian, and the relative positional relationships in specific scenarios. First, it identifies misdetected meridian acupoints. Second, for misdetected meridian acupoints, it uses the left-right symmetry of the meridians to recover the misdetected meridians, thereby ensuring the smoothness and integrity of the treatment process.

[0004] The development of human meridian detection based on image processing technology has encountered challenges in the research and development of digital TCM meridian therapy systems. These challenges include the limited number of human meridian samples, robotic arm obstruction, numerous sampling devices, heavy and complex annotation workload, and inconsistent annotation standards. These factors lead to false positives and even "flying points" in human meridian detection, affecting the smoothness and integrity of the therapy process. To address these issues, this invention designs a method for recovering falsely detected meridians based on spatial topology and positional reasoning, thereby enabling the recovery of falsely detected meridians. Summary of the Invention

[0005] This application provides a method for recovering falsely detected meridians based on spatial topology and location reasoning, characterized by comprising: Based on the symmetry constraint relationship of human meridians and acupoints, the coordinates of misdetected and repaired acupoints are generated by using known meridian acupoints and their symmetrical meridian acupoints. Based on the logical topological constraints of human meridians and acupoints, the X-axis coordinates of misdetected and repaired acupoints are corrected by the inherent direction and naming order of human meridians. Based on the spatial topological constraints of human meridians and acupoints, the Y-axis coordinates of misdetected and repaired acupoints are corrected by determining the vertical positional relationship of meridians under human posture. By estimating the location of acupoints based on the relative positional relationships in a specific scenario and the distance the bed moves, the misdetected acupoints can be identified and restored.

[0006] Optionally, the step of generating coordinates of misdetected acupoints for repair based on the symmetry constraints of human meridians and acupoints, using known meridian acupoints and their symmetrical meridian acupoints, includes: Based on the distance symmetry constraint, the distance ratio formulas of the X-axis and Y-axis are obtained by comparing the relative distance ratios between three adjacent acupoints and three acupoints at symmetrical positions. Based on directional symmetry constraints, the equations for connecting acupoints are established by using the directional symmetry relationship between the known endpoints of acupoints and the extension points of two adjacent acupoints. Based on the angular symmetry constraint, the coordinates of the symmetrical extension recovery point are calculated using the angle between the known endpoint and the straight line formed by the extension point. By solving the equations of the acupoints of known meridians and their symmetrical meridians, the coordinates of the acupoints to be repaired are generated.

[0007] Optionally, the logical topological constraint relationship based on human meridian acupoints, through the inherent direction and naming order of human meridians, corrects the X-axis coordinates of misdetected and repaired acupoints, including: Based on the unilateral sequence constraint of meridians, the correctness of the sequence of repairing misdetected acupoints is verified by detecting the increasing state of the X coordinate of meridian acupoints. Based on the left-right symmetry difference constraint, false detection points at symmetrical positions are identified by using the absolute value threshold of the difference in X coordinates between the symmetrical meridian positions on both sides of the human body. Based on the cross-meridian difference constraint, through the right meridian... Point and left meridian The positional relationship of points helps identify misaligned or incorrectly checked points.

[0008] Optionally, the step of correcting the Y-axis coordinates of misdetected and repaired acupoints by determining the vertical positional relationship of the meridians under human posture, based on the spatial topological constraints of human meridians and acupoints, includes: Based on human posture characteristics, the size constraint of the Y-axis coordinate is determined by setting the spatial topological relationship of the right meridian above and the left meridian below; Based on the upper limit of the Y-coordinate of the right meridian, a position threshold is established by statistically labeled data to correct the Y-coordinate of false detection points; Based on the lower limit of the Y-coordinate of the left meridian, false detection points that deviate from the anatomical position are identified through dynamic boundary detection.

[0009] Optionally, the step of estimating acupoint locations based on the relative positional relationship in a specific scenario and the distance the bed moves, thereby identifying and recovering falsely detected acupoints, includes: Using the initial unobstructed recognition results, a reference system for the base position is established by recording the initial acupoint coordinates; Based on the distance the bed moves, the location of acupoints after obstruction is estimated using a displacement formula. Based on a distance threshold, false detections of long meridian segments are identified by comparing the distance between the detection point and the estimated point.

[0010] The displacement formula is: ; Among them, let For the first The coordinates of each acupoint before the bed was moved are then For the first The coordinates of each acupoint after the bed is moved. This represents the distance the bed moves.

[0011] Optionally, the step of obtaining the distance ratio formulas for the X and Y axes based on the distance symmetry constraint and the relative distance ratio between three adjacent acupoints and three acupoints at symmetrical positions includes: By maintaining a consistent relative distance ratio, we obtain the formulas for the X-axis and Y-axis distance ratios. Let 1, 2, and 3 be three adjacent acupoints, and 4, 5, and 6 be three symmetrical acupoints. Then, the formula for the X-axis distance ratio is: ; The formula for the Y-axis distance ratio is: .

[0012] Optionally, the step of estimating the location of acupoints after obstruction using a displacement formula based on the bed's movement distance, and identifying false detections of long meridian segments by comparing the distance between the detection point and the estimated point based on a distance threshold, includes: Based on the detected acupoints The acupoints obtained by estimating through the displacement formula Perform error comparison; If the error is within the threshold range, it is considered to meet the relative position constraint and the recovery effect is considered to be good; otherwise, it is considered not to meet the relative position constraint and the recovery effect is not good.

[0013] This application also provides a false detection meridian recovery device based on spatial topology and location reasoning, characterized in that the device comprises: The symmetry repair module is used to generate the coordinates of misdetected acupoints for repair based on the symmetry constraints of human meridian acupoints and the known meridian acupoints and their symmetrical meridian acupoints. The X-axis logic correction module is used to correct the X-axis coordinates of misdetected acupoints based on the logical topological constraints of human meridian acupoints and the inherent direction and naming order of human meridians. The Y-axis spatial correction module is used to correct the Y-axis coordinates of misdetected acupoints by determining the vertical position relationship of the meridians under the human body posture, based on the spatial topological constraints of the meridians and acupoints. The dynamic scene recovery module is used to estimate the location of acupoints by measuring the distance the bed moves, based on the relative positional relationship in a specific scene, thereby identifying and recovering falsely detected acupoints.

[0014] Optionally, the dynamic scene restoration module further includes: The reference position recording module is used to record the coordinates of acupoints for the first unobstructed recognition. The displacement estimation module is used to estimate the location of acupoints based on the distance the bed moves. The error detection module is used to identify false detection points by using a distance threshold.

[0015] This application also provides an electronic device, characterized in that it is used to implement any of the described methods for recovering false-detection meridians based on spatial topology and location reasoning, comprising: Cameras are used to acquire images of the human body and to label acupoints along the body's meridians. The processor is used to perform all computational tasks and implement a method for recovering false-detection meridians based on spatial topology and location reasoning. Memory is used to store processor-executable instructions and statically stored data.

[0016] The beneficial effects of this application are as follows: By using the symmetry constraint relationship based on the human meridian, the repair coordinates are generated using the distance, direction and angle features of known acupoints and their symmetrical points, achieving high-precision single-point false detection recovery. Furthermore, by using the logical topology and spatial topology dual constraints of the human meridian, combined with the naming order of meridian pathways and posture-related positional relationships, collaborative correction of X / Y axis coordinates is achieved. Moreover, by using dynamic position reasoning in specific scenarios, the target point position is estimated using the first unobstructed reference position and the bed movement displacement model, and real-time identification and recovery of long-segment false detections is achieved based on distance thresholds, significantly improving the robustness of the robotic arm in occlusion scenarios. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings required in the description of the embodiments or the prior art are briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a specific embodiment of the false detection meridian recovery method based on spatial topology and location reasoning of this application is shown. Figure 2 This diagram illustrates a prone, symmetrical human meridian acupoints, representing a specific embodiment of the false detection meridian recovery method based on spatial topology and positional reasoning of this application. Figure 3 This illustration shows a schematic diagram of acupoints based on spatial topology and positional reasoning in a specific embodiment of the false detection meridian recovery method based on spatial topology and positional reasoning of this application; Figure 4 This diagram illustrates the symmetric features of acupoints in a specific embodiment of the false detection meridian recovery method based on spatial topology and positional reasoning according to this application. Figure 5 A flowchart illustrating the human meridian logic topology relationship diagram of a false detection meridian recovery method based on spatial topology and positional reasoning according to a specific embodiment of this application; Figure 6 A diagram illustrating the spatial constraint relationship of human meridians, showing a flowchart of a false detection meridian recovery method based on spatial topology and positional reasoning according to a specific embodiment of this application; Figure 7 This paper illustrates a relative position constraint relationship diagram under a specific scenario for a false detection meridian recovery method based on spatial topology and position reasoning according to a specific embodiment of this application. Figure 8 This diagram illustrates a device block diagram of a false detection meridian recovery method based on spatial topology and location reasoning according to a specific embodiment of this application. Detailed Implementation

[0019] Various exemplary embodiments, features, and aspects of this application will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0021] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0022] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0023] This invention proposes a method for recovering falsely detected meridians based on spatial topology and positional reasoning, to address the problem of false detection of meridian acupoints caused by robotic arm occlusion during acupuncture robot operation, particularly the challenge of recovering falsely detected long meridian segments. This method innovatively integrates the anatomical characteristics of human meridians with dynamic scene modeling: First, based on triple constraints of distance symmetry, direction symmetry, and angle symmetry, the coordinates of unknown repair points are solved using known acupoints; second, utilizing the inherent direction of meridian naming order and the spatial topological relationship related to human posture, X / Y axis correction mechanisms are constructed respectively; finally, a core module for dynamic scene recovery is introduced, establishing a reference system for the baseline position through initial unobstructed recognition, estimating the target position by combining the bed movement displacement model, and achieving three levels of false detection discrimination (single point / local / long segment) based on distance thresholds.

[0024] Example 1 like Figure 1 The diagram shown is a flowchart of a method for restoring falsely detected meridians based on spatial topology and location reasoning according to an embodiment of this application, which specifically includes the following: S100 generates the coordinates of misdetected and repaired acupoints based on the symmetry constraint relationship of human meridians and acupoints, using known meridian acupoints and their symmetrical meridian acupoints.

[0025] Specifically, based on the anatomical symmetry of the human meridian system, a triple constraint model of distance, direction, and angle is established. The distance symmetry constraint requires that the relative positional ratios of known acupoint groups and their symmetrical point groups remain strictly consistent along the X / Y axes, quantifying the geometric relationship through proportional formulas. The direction symmetry constraint defines the vector angle relationship formed by a known endpoint and its adjacent extension point, constructing a straight-line equation to describe the direction symmetry. The angle symmetry constraint ensures that the angle value formed by the endpoint and the extended recovery point is equal on the symmetrical side, thereby deriving the coordinates of the symmetrical extended recovery point. Finally, by solving the intersection points of the equations connecting the acupoints of the known meridian and its symmetrical meridian, the coordinates of the misdetected repair point are generated.

[0026] S200, based on the logical topological constraints of human meridians and acupoints, corrects and repairs the X-axis coordinates of misdetected acupoints by using the inherent direction and naming order of human meridians.

[0027] Specifically, based on the inherent anatomical pathways and naming order of human meridians, a three-layer logical topology verification mechanism is constructed. Unilateral sequence constraints force acupoints along a single meridian to strictly increase in the X-axis direction according to their naming order, eliminating sequence misalignment through coordinate monotonicity verification. Left-right symmetry difference constraints require that the absolute value of the X-coordinate difference between symmetrical acupoints on both sides of the body does not exceed the threshold allowed by the anatomical structure, using difference boundary conditions to identify abnormal offsets. Cross-meridian difference constraints establish the right meridian's... Point and left meridian The spatial relationship of the points is misaligned, and the cross-regional false detection is eliminated by using the relative position inequality.

[0028] S300, based on the spatial topological constraints of human meridians and acupoints, corrects the Y-axis coordinates of misdetected and repaired acupoints by determining the vertical positional relationship of meridians under human posture.

[0029] Specifically, based on the spatial distribution of meridians in a standard human posture, a rigid partial order relationship is established with the right meridian above and the left meridian below. Based on this spatial topological constraint, a dual-boundary control model is established: the Y-coordinate of the right meridian must not exceed the upper limit threshold of the anatomical position, and the Y-coordinate of the left meridian must not be lower than the lower limit threshold of the anatomical position. By dynamically monitoring the Y-coordinate relationship and boundary conformity between the repair point and the symmetrical point, abnormal points deviating from the reasonable anatomical range are automatically identified.

[0030] The S400 estimates the location of acupoints by measuring the distance the bed moves, based on the relative positional relationship in a specific scenario, thereby identifying and restoring falsely detected acupoints.

[0031] Specifically, for scenarios where the robotic arm is occluded, a position reasoning mechanism based on physical displacement is established. The initial unobstructed recognition result forms a reference coordinate system, completely recording the initial spatial distribution of acupoints. When the bed moves horizontally, the estimated target position is calculated based on the displacement model. By comparing the distance between the actual detected coordinates and the estimated coordinates, and determining whether it exceeds the anatomical displacement tolerance threshold, objective identification of long-segment false detections is achieved. The recovery effect evaluation depends entirely on the spatial consistency between the estimated point and the measured point; if the displacement constraint is met, it is considered valid; otherwise, relocalization is triggered.

[0032] In summary, this application breaks through the limitations of traditional local correction and for the first time constructs a triple-constraint repair mechanism based on anatomical symmetry. It quantifies the geometric proportions of a group of points through distance symmetry constraints, establishes the vector angle equation through directional symmetry constraints, derives the coordinates of symmetrical extension points through angle symmetry constraints, and finally solves the intersection points of the acupoint connection equations to generate high-precision repair points. By integrating logical and spatial dual-topology correction systems, it uses unilateral sequence constraints in the X-axis direction to ensure that the naming order matches the coordinate increment, combines left-right symmetry difference constraints to control the offset threshold, and introduces cross-meridian difference constraints to eliminate misalignment errors. The system establishes a dual-boundary dynamic monitoring model based on the rigid body partial order relationship of the right meridian above and the left meridian below in the Y-axis direction. It automatically identifies abnormal points by using upper and lower limit thresholds of anatomical position, and achieves collaborative optimization of X / Y axis coordinates. It also has a unique displacement-driven recovery engine for robotic arm occlusion scenarios. It constructs a benchmark reference system based on the distribution of acupoints without occlusion for the first time. Based on the pure horizontal movement characteristics of the bed, it generates the target position estimate through the physical displacement formula. It uses the anatomical tolerance threshold to compare Euclidean distance to identify long-segment false detections, forming a closed-loop mechanism that takes effect if spatial consistency meets the standard, otherwise relocation.

[0033] As an optional implementation of this application, optionally, in step S100, based on the symmetry constraint relationship of human meridian acupoints, the coordinates of misdetected repair acupoints are generated through known meridian acupoints and their symmetrical meridian acupoints, including: S101. Based on the distance symmetry constraint, the distance ratio formulas of the X-axis and Y-axis are obtained by comparing the relative distance ratios between three adjacent acupoints and three acupoints at symmetrical positions.

[0034] Specifically, such as Figure 2 As shown in the diagram, the relationships between acupoints on the meridians indicate that the left and right meridians are symmetrical, and correspondingly, the acupoints are also symmetrical. Furthermore, the spatial topology formed by several acupoints is mirror-image. Simultaneously, the acupoints on the meridians have a specific order; for example, on the Triple Energizer Meridian in the arm, Triple Energizer Meridian-4 is to the right of Triple Energizer Meridian-3, and Triple Energizer Meridian-5 is to the right of Triple Energizer Meridian-4. Due to the motion-based recognition, based on the initial recognition (where there is no robotic arm obstruction and false positives are rare) and with fixed hand and foot supports, the approximate locations of all recognized acupoints can be estimated based on the distance the bed moves. If individual acupoints do not conform to the above relationships or deviate significantly from the estimated locations, they can be considered false positives, and then the symmetry of the acupoints can be used to restore the original location.

[0035] Among them, such as Figure 4As shown, let points 1, 2, and 3 be known acupoints on the meridians, point 2 be the endpoint of a known acupoint, and points 1 and 3 be extension points of known acupoints. Then, points 4, 5, and 6 are symmetrical acupoints on the meridians, point 5 is the endpoint of a symmetrical acupoint, and points 4 and 6 are extension points of symmetrical acupoints. In this case, the distance ratio of the X-axis and Y-axis of the known lateral points 1, 2, and 3 should be equal to the distance ratio of the X-axis and Y-axis of the known lateral points 4, 5, and 6.

[0036] Furthermore, let's assume , , Given the x-coordinates of three adjacent acupoints along a meridian, , and The coordinates of the three points along the x-axis of the symmetrical meridian acupoint are given. , , Given the y-coordinates of three adjacent acupoints along a meridian, , , Given the coordinates of the three points along the y-axis of its symmetrical meridian acupoints, and keeping the relative distance ratio consistent, obtain the formula for the distance ratio between the X-axis and Y-axis.

[0037] The formula for the X-axis distance ratio is: ; The formula for the Y-axis distance ratio is: .

[0038] S102, based on directional symmetry constraints, establishes the equation for connecting acupoints by using the directional symmetry relationship between the known endpoints of acupoints and the extension points of two adjacent acupoints.

[0039] Specifically, such as Figure 4 As shown, the directions of the two lines BA and BC are symmetrical about point B. Based on the symmetry of the directions and the included angle, the formula for the included angle of vectors can be obtained: ; in, , and These represent the length and angle between two adjacent meridians.

[0040] S103, based on the angular symmetry constraint, calculate the coordinates of the symmetrical extension recovery point by using the angle between the known endpoint and the straight line formed by the extension point.

[0041] Specifically, such as Figure 4As shown, the angle α formed by the known acupoint endpoint B, the known acupoint extension point A, and the extension recovery point C is equal to the angle b formed by the symmetrical acupoint endpoint F, the symmetrical acupoint extension point E, and the symmetrical extension recovery point G.

[0042] S104 generates the coordinates of misdetected acupoints for repair by solving the intersection points of the equations connecting the acupoints of known meridians and their symmetrical meridians.

[0043] Specifically, obtaining the acupoint connection equation involves setting the X-axis coordinate of the extended recovery point to the median of a known meridian acupoint and its symmetrical meridian acupoint, obtaining the Y-axis coordinate of the extended recovery point using the vector angle formula, and generating the acupoint connection equation by calculating the coordinates of the known meridian acupoints adjacent to the extended recovery point. Generating the coordinates of the misdetected repair acupoints involves calculating the intersection of the acupoint connection equations of the known meridian and its symmetrical meridian to obtain the coordinates of the misdetected repair acupoints.

[0044] In this embodiment, as Figure 4 As shown, the X-coordinate of the extended recovery point C is set to the median of the coordinates of points B and F. The Y-coordinate of point C is calculated using the vector angle formula in S104, thus determining the coordinates of point C. Similarly, the X-coordinate of the extended recovery point G is set to the median of the coordinates of points A and E. The Y-coordinate of point G is calculated using the vector angle formula in S140, thus determining the coordinates of point G. The equations connecting the acupoints are the equations of the lines corresponding to points B, C, F, and G, which can be calculated respectively. The intersection point O of the two non-parallel lines BC and FG is the misdiagnosed acupoint repair point.

[0045] As an optional implementation of this application, optionally, in step S200, based on the logical topological constraints of human meridian acupoints, the X-axis coordinates of the misdetected and repaired acupoints are corrected through the inherent direction and naming order of human meridians, including: S201, based on the unilateral sequence constraint of the meridians, verifies the correctness of the sequence of repairing misdetected acupoints by detecting the increasing state of the X coordinate of the meridian acupoints.

[0046] Specifically, the acupoints on one side of the human body are strictly ordered in ascending order along the X-axis. The correctness of the current order can be determined by comparing the X-axis coordinates of adjacent points of the misidentified and repaired acupoints in a fixed order.

[0047] Among them, such as Figure 5 As shown, taking the left meridian as an example, let x4, x5, x6, and x7 represent the X-coordinates of L-pi-4, L-pi-5, L-pi-6, and L-pi-7, respectively, with L-pi-5 being the misdetected acupoint for repair. The X-axis coordinates of the acupoints along the left meridian are compared. When the comparison result is... If the order of the incorrectly detected acupoints is correct, then the order of the corrected acupoints should be corrected; otherwise, the X-axis coordinates of the incorrectly ordered points should be swapped.

[0048] S202, based on the left-right symmetry difference constraint, identifies false detection points at symmetrical positions by using the absolute value threshold of the difference in X coordinates between the symmetrical meridian positions on both sides of the human body.

[0049] Specifically, the method for constraining the X-axis position of the misdetected acupoint at its symmetrical location using the left-right symmetry difference is that the absolute value of the difference between the X-coordinate of the misdetected acupoint and its symmetrical meridian acupoint is less than the left-right symmetry difference. The formula is as follows: ; Among them, such as Figure 5 As shown, the X-axis coordinate of the left meridian is represented as follows: The X-axis coordinate of the right meridian is represented as: The maximum difference at the same location on the left and right meridians is expressed as Then, the formula for left-right symmetrical difference can be formed as follows: .

[0050] S203, based on the cross-meridian difference constraint, through the right meridian... Point and left meridian The positional relationship of points helps identify misaligned or incorrectly checked points.

[0051] Specifically, the X-axis position constraint of the misdetected acupoint at the misaligned location, as described in the cross-meridian difference value detection, is that the X-coordinate of the misdetected acupoint is less than the difference between the X-coordinate of the next acupoint on the opposite meridian and the cross-meridian difference value. The formula is as follows: .

[0052] Among them, such as Figure 5 As shown, let the right meridian be the first The X-coordinate of each acupoint is The first meridian on the left The X-coordinate of each acupoint is The maximum value of the difference across meridians is Then the formula for cross-meridian difference can be formed as follows: .

[0053] As an optional implementation of this application, optionally, in step S300, based on the spatial topological constraints of human meridian acupoints, the Y-axis coordinates of the misdetected acupoints are corrected by determining the vertical positional relationship of the meridians under the human body posture, including: S301, based on human posture characteristics, determines the Y-axis coordinate size constraint by setting the spatial topological relationship of the right meridian above and the left meridian below.

[0054] Specifically, based on the characteristics of the human body, the meridians are divided into left and right parts. Under a certain posture, the left and right parts have a certain size relationship in the Y direction, which is set as the right meridian on top and the left meridian on the bottom.

[0055] S302, based on the upper limit of the Y coordinate of the right meridian, establishes a position threshold through statistical annotation data, corrects the Y coordinate of false detection points, and based on the lower limit of the Y coordinate of the left meridian, identifies false detection points that deviate from the anatomical position through dynamic boundary detection.

[0056] Specifically, such as Figure 6 As shown, under a given posture, the left and right parts have a definite size relationship in the Y direction, with the right meridian above and the left meridian below. and These represent the Y-coordinates of the symmetrical right and left meridians, respectively. This indicates the upper limit of the Y-coordinate of the right meridian. This represents the lower limit of the Y-coordinate of the left meridian. The specific spatial topological structure is as follows: ; ; .

[0057] As an optional implementation of this application, optionally, in step S400, the location of acupoints is estimated by the movement distance of the bed based on the relative positional relationship in a specific scenario, thereby realizing the identification and recovery of falsely detected acupoints, including: S401 utilizes the initial unobstructed recognition results to establish a reference system for the base position by recording the initial acupoint coordinates.

[0058] Specifically, such as Figure 7 As shown, in the initial scenario where the robotic arm is not obstructed, the coordinates of acupoints along the human meridian are collected by sensors, and all initial acupoints are recorded to form a coordinate set: And establish a spatial location reference system, with each acupoint indexed. Store them in the order they appear.

[0059] During storage, it is ensured that the basic topological constraints are met, so that the meridian acupoints are arranged in the order of naming and that the spatial relationship of right on top and left on bottom is maintained.

[0060] S402, based on the distance the bed moves, estimates the location of acupoints after obstruction using a displacement formula, and based on a distance threshold, identifies false detections of long meridian segments by comparing the distance between the detection point and the estimated point.

[0061] Specifically, based on the moving distance of the bed. The estimated coordinates of the acupoint after movement are calculated based on the displacement formula. , forming a distance of movement The estimated coordinate set of all acupoints: Then, the actual detection coordinates of each acupoint are calculated. With estimated coordinates Distance difference between and with the set threshold Compare them.

[0062] Among them, when When the condition is met, it is determined that the relative position constraint is satisfied, indicating a good recovery effect; while when... If the condition is not met, it is determined that the recovery effect is poor and repositioning is required.

[0063] And, the displacement formula is: ; Among them, let For the first The coordinates of each acupoint before the bed was moved are then For the first The coordinates of each acupoint after the bed is moved. This represents the distance the bed moves.

[0064] Example 2 Based on the same principles as the aforementioned methods, a method for recovering falsely detected meridians based on spatial topology and location reasoning is also proposed. See [link to relevant documentation]. Figure 8 A false detection meridian recovery device 100 based on spatial topology and location reasoning according to an embodiment of this disclosure includes: The symmetry repair module 110 is used to generate the coordinates of misdetected repair acupoints based on the symmetry constraint relationship of human meridian acupoints and through known meridian acupoints and their symmetrical meridian acupoints. The X-axis logic correction module 120 is used to correct the X-axis coordinates of misdetected acupoints based on the logical topological constraints of human meridian acupoints and the inherent direction and naming order of human meridians. Y-axis spatial correction module 130 is used to correct the Y-axis coordinates of misdetected acupoints by determining the vertical position relationship of the meridians under the human body posture, based on the spatial topological constraint relationship of the meridians and acupoints. The dynamic scene recovery module 140 is used to estimate the location of acupoints by measuring the distance the bed moves based on the relative positional relationship in a specific scene, thereby identifying and recovering falsely detected acupoints.

[0065] As an optional implementation of this application, the dynamic scene restoration module 140 may further include: The reference position recording module 141 is used to record the coordinates of the acupoints for the first unobstructed recognition. Displacement estimation module 142 is used to estimate the location of acupoints based on the distance the bed moves. Error detection module 143 is used to identify false detection points by using a distance threshold.

[0066] Obviously, those skilled in the art should understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the control methods described above. The modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps into a single integrated circuit module. Thus, the present invention is not limited to any specific hardware and software combination.

[0067] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the control methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0068] Example 3 Furthermore, this application proposes an electronic device characterized in that, for implementing any of the aforementioned methods for recovering false-detection meridians based on spatial topology and location reasoning, it comprises: Cameras are used to acquire images of the human body and to label acupoints along the body's meridians. The processor is used to perform all computational tasks and implement a method for recovering false-detection meridians based on spatial topology and location reasoning. Memory is used to store processor-executable instructions and statically stored data.

[0069] The electronic device of this disclosure includes a processor and a memory for storing processor-executable instructions. The processor is configured to implement any of the aforementioned false-detection meridian recovery methods based on spatial topology and location reasoning when executing the executable instructions.

[0070] It should be noted that the number of processors can be one or more. Furthermore, the electronic device in this embodiment may also include input devices and output devices. The processor, memory, input devices, and output devices can be connected via a bus or other means, without specific limitations herein.

[0071] The memory, serving as a computer-readable storage medium for the false detection meridian recovery method based on spatial topology and location reasoning, can be used to store software programs, computer-executable programs, and various modules, such as the program or module corresponding to the false detection meridian recovery method based on spatial topology and location reasoning in this disclosure. The processor executes various functional applications and data processing of the electronic device by running the software program or module stored in the memory.

[0072] Input devices can be used to receive input digital numbers or signals. These signals can be key signals related to user settings and function control of the device / terminal / server. Output devices can include display devices such as screens.

[0073] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for recovering falsely detected meridians based on spatial topology and location reasoning, characterized in that, include: Based on the symmetry constraint relationship of human meridians and acupoints, the coordinates of misdetected and repaired acupoints are generated by using known meridian acupoints and their symmetrical meridian acupoints. Based on the logical topological constraints of human meridians and acupoints, the X-axis coordinates of misdetected and repaired acupoints are corrected by the inherent direction and naming order of human meridians. Based on the spatial topological constraints of human meridians and acupoints, the Y-axis coordinates of misdetected and repaired acupoints are corrected by determining the vertical positional relationship of meridians under human posture. By estimating the location of acupoints based on the relative positional relationships in a specific scenario and the distance the bed moves, the misdetected acupoints can be identified and restored.

2. The method for recovering falsely detected meridians based on spatial topology and location reasoning as described in claim 1, characterized in that, The process of generating coordinates for misdetected and repaired acupoints based on the symmetry constraints of human meridians and acupoints, using known meridian acupoints and their symmetrical meridian acupoints, includes: Based on the distance symmetry constraint, the distance ratio formulas of the X-axis and Y-axis are obtained by comparing the relative distance ratios between three adjacent acupoints and three acupoints at symmetrical positions. Based on directional symmetry constraints, the equations for connecting acupoints are established by using the directional symmetry relationship between the known endpoints of acupoints and the extension points of two adjacent acupoints. Based on the angular symmetry constraint, the coordinates of the symmetrical extension recovery point are calculated using the angle between the known endpoint and the straight line formed by the extension point. By solving the equations of the acupoints of known meridians and their symmetrical meridians, the coordinates of the acupoints to be repaired are generated.

3. The method for recovering falsely detected meridians based on spatial topology and location reasoning as described in claim 1, characterized in that, The logical topological constraint relationship based on human meridians and acupoints corrects the X-axis coordinates of misdetected and repaired acupoints by utilizing the inherent direction and naming order of human meridians, including: Based on the unilateral sequence constraint of meridians, the correctness of the sequence of repairing misdetected acupoints is verified by detecting the increasing state of the X coordinate of meridian acupoints. Based on the left-right symmetry difference constraint, false detection points at symmetrical positions are identified by using the absolute value threshold of the difference in X coordinates between the symmetrical meridian positions on both sides of the human body. Based on the cross-meridian difference constraint, through the right meridian... Point and left meridian The positional relationship of points helps identify misaligned or incorrectly checked points.

4. The method for recovering falsely detected meridians based on spatial topology and location reasoning as described in claim 1, characterized in that, The method of correcting and repairing the Y-axis coordinates of misdetected acupoints by determining the vertical positional relationship of the meridians under human posture, based on the spatial topological constraints of human meridians and acupoints, includes: Based on human posture characteristics, the size constraint of the Y-axis coordinate is determined by setting the spatial topological relationship of the right meridian above and the left meridian below; Based on the upper limit of the Y-coordinate of the right meridian, a position threshold is established by statistically labeled data to correct the Y-coordinate of false detection points; Based on the lower limit of the Y-coordinate of the left meridian, false detection points that deviate from the anatomical position are identified through dynamic boundary detection.

5. The method for recovering falsely detected meridians based on spatial topology and location reasoning as described in claim 1, characterized in that, The method of estimating acupoint locations based on relative positional relationships in specific scenarios and the distance the bed moves, thereby identifying and recovering falsely detected acupoints, includes: Using the initial unobstructed recognition results, a reference system for the base position is established by recording the initial acupoint coordinates; Based on the distance the bed moves, the location of acupoints after obstruction is estimated using a displacement formula. Based on a distance threshold, false detections of long meridian segments are identified by comparing the distance between the detection point and the estimated point. The displacement formula is: ； Among them, let For the first The coordinates of each acupoint before the bed was moved are then For the first The coordinates of each acupoint after the bed is moved. This represents the distance the bed moves.

6. The method for recovering falsely detected meridians based on spatial topology and location reasoning as described in claim 2, characterized in that, The method, based on distance symmetry constraints, obtains the distance ratio formulas for the X and Y axes by using the relative distance ratios between three adjacent acupoints and three acupoints at symmetrical positions, including: By maintaining a consistent relative distance ratio, we obtain the formulas for the X-axis and Y-axis distance ratios. Let 1, 2, and 3 be three adjacent acupoints, and 4, 5, and 6 be three symmetrical acupoints. Then, the formula for the X-axis distance ratio is: ； The formula for the Y-axis distance ratio is: 。 7. The method for recovering falsely detected meridians based on spatial topology and location reasoning as described in claim 5, characterized in that, The process of estimating the location of acupoints after obstruction using a displacement formula based on the bed's movement distance, and identifying false detections of long meridian segments by comparing the distance between the detection point and the estimated point based on a distance threshold, includes: Based on the detected acupoints The acupoints obtained by estimating through the displacement formula Perform error comparison; If the error is within the threshold range, it is considered to meet the relative position constraint and the recovery effect is considered to be good; otherwise, it is considered not to meet the relative position constraint and the recovery effect is not good.

8. A device for restoring meridian function after false positives based on spatial topology and location reasoning, characterized in that, The device includes: The symmetry repair module is used to generate the coordinates of misdetected acupoints for repair based on the symmetry constraints of human meridian acupoints and the known meridian acupoints and their symmetrical meridian acupoints. The X-axis logic correction module is used to correct the X-axis coordinates of misdetected acupoints based on the logical topological constraints of human meridian acupoints and the inherent direction and naming order of human meridians. The Y-axis spatial correction module is used to correct the Y-axis coordinates of misdetected acupoints by determining the vertical position relationship of the meridians under the human body posture, based on the spatial topological constraints of the meridians and acupoints. The dynamic scene recovery module is used to estimate the location of acupoints by measuring the distance the bed moves, based on the relative positional relationship in a specific scene, thereby identifying and recovering falsely detected acupoints.

9. The false detection meridian recovery device based on spatial topology and location reasoning according to claim 8, characterized in that, The dynamic scene recovery module also includes: The reference position recording module is used to record the coordinates of acupoints for the first unobstructed recognition. The displacement estimation module is used to estimate the location of acupoints based on the distance the bed moves. The error detection module is used to identify false detection points by using a distance threshold.

10. An electronic device, characterized in that, The method for implementing the false detection meridian recovery method based on spatial topology and location reasoning as described in any one of claims 1 to 7 includes: Cameras are used to acquire images of the human body and to label acupoints along the body's meridians. The processor is used to perform all computational tasks and implement a method for recovering false-detection meridians based on spatial topology and location reasoning. Memory is used to store processor-executable instructions and statically stored data.

Images