AR glasses cursor control method and system based on head posture induction

Abstract

The invention relates to the technical field of AR interaction control, in particular to an AR glasses cursor control method and system based on head posture induction, and the method comprises the steps of data acquisition, mapping establishment, displacement accumulation and cursor control. Through the AR glasses equipment body, the natural rotation posture of the head of the user is collected and used as an input instruction, and a reverse mapping normal form is constructed, so that the physical direction of cursor movement is opposite to the physical direction of user head rotation, and a non-intuitive chasing relation between the cursor and a target is avoided; intuitive mapping between natural rotation of the head of the user and cursor control of the AR glasses is achieved, accurate control over the cursor can be achieved without additional auxiliary actions or a controller, and convenience and privacy are high.

Description

Technical Field

[0001] This invention relates to the field of AR interactive control technology, and in particular to a method and system for cursor control of AR glasses based on head posture sensing. Background Technology

[0002] AR glasses (Augmented Reality Glasses) are smart wearable devices that combine the real world and the virtual world by using technologies such as augmented reality, audio-visual fusion, and waveguide lenses to collect data from real-world scenes through cameras and sensors. Their working principle involves projecting computer-generated images, videos, or other virtual information directly onto the user's eyes through a built-in micro-projector or transparent display screen, merging it with the vision of the real world. This allows the wearer to overlay virtual scenes on top of the real world and achieve virtual-real fusion and interaction through sensing and computing.

[0003] The main methods for cursor operation in existing AR glasses typically include: External handheld controller: Users need to hold a physical controller (such as a controller or mobile phone) and control the cursor through thumb remote or touch screen. However, this method forces the hand to not do other work, which greatly reduces the human-computer interaction of AR glasses and is inconvenient to carry.

[0004] Physical control of glasses: Users need to control the movement of the cursor by using the roller or button on the glasses. This method requires users to continuously bend their arms to control the roller. Although it is convenient to carry, it can easily lead to arm fatigue after a long period of operation.

[0005] Gesture recognition: The cursor is controlled by capturing hand movements through the front-facing camera of the AR glasses. This method requires the user to continuously raise their arm to make specific gestures, which can easily lead to muscle fatigue after prolonged use. Furthermore, the recognition rate decreases in poor lighting or complex background environments, and it lacks privacy and comfort when used in public places.

[0006] Therefore, there is an urgent need for a convenient, accurate, and privacy-preserving method for cursor operation on AR glasses.

[0007] It should be noted that the information disclosed in this background section is intended only to enhance the understanding of the overall background of the present invention, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0008] To address the shortcomings of existing AR glasses cursor control methods in terms of convenience, efficiency, and accuracy, this invention provides an AR glasses cursor control method based on head posture sensing. This method uses the AR glasses device itself to collect and utilize the user's natural head rotation posture as input commands, achieving an intuitive mapping between the user's natural head rotation and AR glasses cursor control. The method includes the following steps: Data acquisition: The first angular velocity of the user's head rotating around the first spatial axis and the second angular velocity of the user's head rotating around the second spatial axis are acquired by the gyroscope; Establish mapping: Using the collected first and second angular velocities as inputs, establish a reverse mapping paradigm between the user's head rotation posture and cursor control, and output the cursor movement speed signal after smoothing compensation; Displacement accumulation: Apply a displacement accumulation mechanism to the output cursor movement speed signal to convert the continuous cursor movement speed signal into an accumulated displacement amount; Cursor control: The output displacement is synchronized with the interactive confirmation signal in time and encapsulated into a standard HID data packet to drive the cursor to update its position and perform operations, thus achieving convenient, efficient and high-precision cursor control for AR glasses.

[0009] Furthermore, the first spatial axis is a vertical axis, the second spatial axis is a horizontal axis, the first angular velocity is the angular velocity of the user's head rotating around the vertical axis along the X-axis, and the second angular velocity is the angular velocity of the user's head pitching around the horizontal axis along the Y-axis.

[0010] Furthermore, the core of the reverse mapping paradigm is that the physical direction of cursor movement is opposite to the physical direction of user head rotation, expressed as:

[0011]

[0012] in, , These represent the angular velocities of the cursor's movement along the X and Y axes, respectively, in radians. The sensitivity factor for cursor movement defined by the user. , These are the first angular velocity and the second angular velocity, respectively.

[0013] Furthermore, the smoothness compensation involves collecting acceleration data of the user's head rotating around the first spatial axis / second spatial axis, converting it into acceleration values ​​and using it as a feedforward quantity. This data is then directly and linearly superimposed with the angular velocity of the cursor movement to output a cursor movement speed signal, thereby compensating for the phase lag of the gyroscope, improving the smoothness of cursor movement, and reducing latency.

[0014] Furthermore, the smoothness compensation is expressed as:

[0015]

[0016] in, , These are the acceleration values ​​of the user's head rotating around the first spatial axis and the second spatial axis, respectively. This is a compensation factor.

[0017] Furthermore, the acceleration of the user's head rotating around the first and second spatial axes is collected by the accelerometer of the inertial measurement unit and obtained through the following formula conversion:

[0018]

[0019] in, , These are the raw rotation data of the user's head around the vertical axis and the raw rotation data of the user's head around the horizontal axis, respectively. This is the sensitivity coefficient of the accelerometer.

[0020] Furthermore, the smoothness compensation also includes dead-zone filtering, comprising the following steps: Set a dead zone threshold. When the absolute value of the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is 0. When the cursor movement speed signal is greater than the dead zone threshold, the output speed is the difference between the original cursor movement speed signal and the dead zone threshold. When the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is the sum of the original cursor movement speed signal and the dead zone threshold.

[0021] Furthermore, the displacement accumulation mechanism is implemented through discrete recursive accumulation, and includes the following steps: Fixed sampling period Calculate the displacement increment in each sampling period The displacement increment is continuously accumulated to the displacement accumulator. When the accumulated displacement in the accumulator is ≥ 1 pixel, the integer part of the accumulated value is output as the displacement. At the same time, the integer part of the output value is subtracted from the accumulator, and a margin of less than 1 pixel is retained for accumulation calculation in subsequent sampling periods. The displacement increment is then calculated. Expressed as:

[0022]

[0023] The accumulator operation value is then expressed as:

[0024]

[0025] in, , These represent the displacement increments of the cursor along the X-axis and the Y-axis, respectively.

[0026] Furthermore, the interactive confirmation signal comes from at least one of the physical buttons, touchpad, gesture recognition module, or voice command module integrated into the temple of the AR glasses.

[0027] On the other hand, the present invention also provides an AR glasses cursor control system based on head posture sensing, for implementing the AR glasses cursor control method based on head posture sensing as described above.

[0028] Based on the above, the AR glasses cursor control method and system based on head posture sensing provided by the present invention, compared with the prior art, collects and utilizes the user's natural head rotation posture as input command through the AR glasses device itself, and constructs a reverse mapping paradigm so that the physical direction of cursor movement is opposite to the physical direction of user head rotation, avoiding the non-intuitive "chasing" relationship between the cursor and the target, realizing an intuitive mapping between the user's natural head rotation and AR glasses cursor control, achieving precise cursor control without additional auxiliary actions or controllers, and offering high convenience and privacy. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Unless otherwise specified, the positional relationships in the drawings described below are based on the direction in which the components are drawn in the figures.

[0030] Figure 1 A schematic diagram of the logic framework of an AR glasses cursor control method based on head posture sensing provided in an embodiment of the present invention; Detailed Implementation To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] In the description of this invention, it should be noted that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, 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 indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more. Additionally, the term "comprising" and any variations thereof mean "at least comprising."

[0032] AR glasses (Augmented Reality Glasses) work by projecting computer-generated images, videos, or other virtual information directly onto the user's eyes through a built-in miniature projector or transparent display screen. This merges the images with the real world's visuals, allowing the wearer to overlay virtual scenes onto the real world and achieve virtual-real fusion and interaction through sensing and computing.

[0033] However, the existing cursor control methods for AR glasses have obvious flaws: For example, using an external handheld controller to control the cursor via thumb remote sensing or a touchscreen takes up hand space and is inconvenient to carry.

[0034] For example, the physical control of glasses requires continuous bending of the arm to control the movement of the cursor through the rollers or buttons on the glasses, which can easily cause fatigue.

[0035] For example, gesture recognition relies on arm raising movements and is affected by ambient light and background complexity, resulting in poor privacy and comfort.

[0036] The applicant's research found that the most natural head rotation of the user is very consistent with the core needs and logic of AR glasses cursor control. Therefore, an AR glasses cursor control method based on head posture sensing is provided to solve the technical problems of existing AR glasses cursor control methods being inconvenient, inefficient and inaccurate.

[0037] Please see Figure 1 , Figure 1 This is a schematic diagram of the logic framework of an AR glasses cursor control method based on head posture sensing, provided in an embodiment of the present invention.

[0038] By collecting and utilizing the user's natural head rotation posture as input commands through the AR glasses device itself, an intuitive mapping is achieved between the user's natural head rotation and the cursor control of the AR glasses. This method includes the following steps: Data acquisition: The first angular velocity of the user's head rotating around the first spatial axis and the second angular velocity of the user's head rotating around the second spatial axis are acquired by the gyroscope; Establish mapping: Using the collected first and second angular velocities as inputs, establish a reverse mapping paradigm between the user's head rotation posture and cursor control, and output the cursor movement speed signal after smoothing compensation; Displacement accumulation: Apply a displacement accumulation mechanism to the output cursor movement speed signal to convert the continuous cursor movement speed signal into an accumulated displacement amount; Cursor control: The output displacement is synchronized with the interactive confirmation signal in time and encapsulated into a standard HID data packet to drive the cursor to update its position and perform operations, thus achieving convenient, efficient and high-precision cursor control for AR glasses.

[0039] Furthermore, the first spatial axis is the vertical axis, the second spatial axis is the horizontal axis, the first angular velocity is the angular velocity of the user's head rotating around the vertical axis along the X-axis, and the second angular velocity is the angular velocity of the user's head pitching around the horizontal axis along the Y-axis.

[0040] Furthermore, the core of the reverse mapping paradigm is that the physical direction of cursor movement is opposite to the physical direction of the user's head rotation, expressed as:

[0041]

[0042] in, , These represent the angular velocities of the cursor's movement along the X and Y axes, respectively, in radians. The sensitivity factor for cursor movement defined by the user. , These are the first angular velocity and the second angular velocity, respectively.

[0043] Furthermore, smoothness compensation is achieved by collecting acceleration data of the user's head rotating around the first spatial axis / second spatial axis, converting it into acceleration values ​​and using it as a feedforward quantity. This is then directly and linearly superimposed with the angular velocity of the cursor movement to output a cursor movement speed signal, thereby compensating for the phase lag of the gyroscope, improving the smoothness of cursor movement, and reducing latency.

[0044] Furthermore, the smoothness compensation is expressed as:

[0045]

[0046] in, , These are the acceleration values ​​of the user's head rotating around the first spatial axis and the second spatial axis, respectively. This is a compensation factor.

[0047] Furthermore, the acceleration of the user's head rotating around the first and second spatial axes is collected by the accelerometer of the inertial measurement unit and obtained through the following formula:

[0048]

[0049] in, , These are the raw rotation data of the user's head around the vertical axis and the raw rotation data of the user's head around the horizontal axis, respectively. This is the sensitivity coefficient of the accelerometer.

[0050] Furthermore, smoothness compensation also includes dead-zone filtering, which comprises the following steps: Set a dead zone threshold. When the absolute value of the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is 0. When the cursor movement speed signal is greater than the dead zone threshold, the output speed is the difference between the original cursor movement speed signal and the dead zone threshold. When the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is the sum of the original cursor movement speed signal and the dead zone threshold.

[0051] Furthermore, the displacement accumulation mechanism is implemented through discrete recursive accumulation, including the following steps: Fixed sampling period Calculate the displacement increment in each sampling period The displacement increment is continuously accumulated to the displacement accumulator. When the accumulated displacement in the accumulator is ≥ 1 pixel, the integer part of the accumulated value is output as the displacement. At the same time, the integer part of the output value is subtracted from the accumulator, and a margin of less than 1 pixel is retained for accumulation calculation in subsequent sampling periods. The displacement increment is then calculated. Expressed as:

[0052]

[0053] The accumulator operation value is then expressed as:

[0054]

[0055] in, , These represent the displacement increments of the cursor along the X-axis and the Y-axis, respectively.

[0056] Furthermore, the interactive confirmation signal comes from at least one of the physical buttons, touchpads, gesture recognition modules, or voice command modules integrated into the temples of the AR glasses.

[0057] The technical solution of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application and through various specific implementation methods.

[0058] Example 1 This embodiment provides a cursor control method for AR glasses based on head posture sensing. This method is compatible with consumer-grade AR glasses and integrates a high-precision inertial measurement unit (IMU) for real-time monitoring of the user's head rotation posture, as well as an interactive confirmation module for user confirmation. As shown in the figure, the method includes the following steps: Data acquisition: The first angular velocity of the user's head rotating around the first spatial axis and the second angular velocity of the user's head rotating around the second spatial axis are acquired by the gyroscope.

[0059] In practice, when a user wears AR glasses on their head to watch virtual videos or play games, the system reads raw rotation data of the user's head around the first spatial axis and the raw rotation data of the user's head around the second spatial axis from the IMU via the SPI bus.

[0060] In this embodiment, the first spatial axis is the vertical axis and the second spatial axis is the horizontal axis. The first angular velocity is the angular velocity of the user's head rotating around the vertical axis along the X-axis, and the second angular velocity is the angular velocity of the user's head pitching around the horizontal axis along the Y-axis.

[0061] Based on the gyroscope's sensitivity coefficient, the raw rotation data of the user's head around the vertical axis (X-axis) and the raw pitch data around the horizontal axis (Y-axis) are converted into angular velocity values ​​in degrees (°) (unit: degrees / second). One degree equals... In radians, this is further converted into an angular velocity value (rad / s) in radians.

[0062] By standardizing raw sensor data into internationally recognized standard units with clear physical meaning that can be directly used by the control system, it provides a unified and standardized input basis for subsequent precise cursor control algorithms.

[0063] By utilizing the sensor's sensitivity parameters, the unitless raw digital readings are converted into angular velocity values ​​with intuitive physical meaning (degrees per second). Then, using basic conversion relationships between angular units, commonly used degrees are converted into more mathematically and engineeringly standardized radians, providing a data foundation for the subsequent inverse mapping paradigm.

[0064] In this embodiment, a gyroscope with a range of ±500 dps and a sensitivity of 65.5 LSB / ° / s is preferred. The first angular velocity... Expressed as:

[0065] Second angular velocity Expressed as:

[0066] in, , These are the raw rotation data of the user's head around the vertical axis (X-axis) and the raw rotation data of the head around the horizontal axis (Y-axis), collected by the gyroscope. This is the sensitivity coefficient of the gyroscope.

[0067] Establish mapping: Using the collected first and second angular velocities as inputs, establish a reverse mapping paradigm between the user's head rotation posture and cursor control, and output the cursor movement speed signal after smoothing compensation; The applicant's research found that, due to the inherent characteristic that the UI interface of AR glasses moves with the AR glasses themselves, when a user wears the AR on their head and rotates it, the UI interface will rotate synchronously, creating a non-intuitive "chasing" relationship between the cursor and the target. This makes the user feel that they are not controlling a cursor, but chasing a dynamic target. This counterintuitive experience forces the user to make frequent and large-scale head corrections, which directly leads to low operating efficiency and accelerated physical fatigue.

[0068] To address this issue, this embodiment provides a reverse mapping paradigm. The core of this reverse mapping paradigm is that the physical direction of cursor movement is opposite to the physical direction of the user's head rotation. By simply reversing the direction, the control superposition and logical conflict that exist in the traditional forward cursor in the moving coordinate system are fundamentally resolved. Moreover, cursor movement of the entire UI interface can be achieved by rotating the head posture within a small range, thus achieving a perfect unity between control logic and visual perception.

[0069] For example, when a user turns their head horizontally to the right, the system moves the cursor to the left, and the same applies to other directions. From the user's perspective, this effect is equivalent to the entire UI interface, along with the target on it, moving to the right, while the cursor remains stationary as a fixed aiming point. Through the reverse-moving cursor, the user perceives their own perspective shift within the virtual space, resolving the interaction logic conflicts inherent in AR's dynamic coordinate system. This aligns with the instinctive first-person perspective, creating unparalleled immersion and intuitive operation.

[0070] In practice, the collected first and second angular velocities are used as inputs and multiplied by a configurable sensitivity coefficient, respectively, to map the cursor's movement speed along the X-axis (horizontal direction) and Y-axis (vertical direction) in the UI interface, opposite to the physical direction of the user's head rotation. The configurable sensitivity coefficient can be a system preset or a user-defined sensitivity coefficient.

[0071] The angular velocity of the cursor moving along the X-axis Expressed as:

[0072] angular velocity of cursor movement along the Y-axis Expressed as:

[0073] in, The sensitivity factor for cursor movement defined by the user. , These are the first angular velocity and the second angular velocity, respectively. By mathematically inverting these values, the physical positive angular velocity (+...) This is directly converted into a negative movement on the interaction (- This is achieved by implementing core control logic that ensures the physical direction of cursor movement is opposite to the physical direction of the user's head rotation, thus resolving interaction logic conflicts in the AR dynamic coordinate system.

[0074] Based on the above, smoothness compensation is achieved by collecting the acceleration data of the user's head rotating around the first spatial axis / second spatial axis, converting it into an acceleration value and using it as a feedforward quantity. This value is then directly and linearly superimposed with the angular velocity of the cursor movement to output a cursor movement speed signal, thereby compensating for the phase lag of the gyroscope, improving the smoothness of cursor movement, and reducing latency.

[0075] Accelerometers are often used to correct angular drift after gyroscope integration; this is a feedback correction process. However, in this embodiment, the acceleration value is directly superimposed on the base velocity calculated from the angular velocity, which is equivalent to feedforward control.

[0076] When the head begins to rotate (accelerate) or stops rotating (decelerate), the accelerometer can immediately sense this trend and "tell" the system in advance to increase or decrease the cursor speed, thereby compensating for the phase lag of the gyroscope. Furthermore, because it uses simple linear superposition, compared to typical methods (which involve complex sensor fusion algorithms with high computational costs), this method has extremely low computational overhead, ensuring high-frequency execution in the main loop and meeting the stringent low-latency requirements of cursor control.

[0077] In practice, the raw rotational data of the user's head around the vertical axis (X-axis) and the raw rotational data of the user's head around the horizontal axis (Y-axis) collected by the accelerometer are also read in batches from the IMU via the SPI bus. The acceleration value of the user's head around the vertical axis (X-axis) is then calculated based on the accelerometer's sensitivity and gravitational acceleration. And the acceleration value of the user's head pitching around the horizontal axis along the Y-axis The acceleration value of the user's head rotating around the vertical axis along the X-axis. Expressed as:

[0078] The acceleration value of the user's head pitching around the horizontal axis along the Y-axis Expressed as:

[0079] in, , These are the raw rotation data of the user's head around the vertical axis (X-axis) and the raw rotation data of the user's head around the horizontal axis (Y-axis). This is the sensitivity coefficient of the accelerometer.

[0080] The converted acceleration value is multiplied by a compensation factor much smaller than 1 and then added to the velocity to achieve cursor speed control that follows the head rotation speed. This is equivalent to adding a proactive control loop to the system, allowing the cursor to start moving faster and stop moving more promptly, significantly reducing the user-perceived operation delay. The smoothness compensation is then expressed as:

[0081]

[0082] in, , These are the acceleration values ​​of the user's head rotating around the first spatial axis and the second spatial axis, respectively. The compensation factor is set to a preset value less than 1.

[0083] Of course, it is understandable that, in order to ensure that the angular velocity and acceleration data used for fusion are strictly synchronized in time, the sensitivity-adjusted angular velocity data and the weighted acceleration data can be linearly superimposed to output the final optimized cursor velocity value for subsequent processing.

[0084] Furthermore, smoothness compensation also includes dead-zone filtering, which comprises the following steps: Set a dead zone threshold. When the absolute value of the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is 0. When the cursor movement speed signal is greater than the dead zone threshold, the output speed is the difference between the original cursor movement speed signal and the dead zone threshold. When the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is the sum of the original cursor movement speed signal and the dead zone threshold.

[0085] Dead-zone filtering is a typical nonlinear filtering method. Its core principle is based on threshold detection, dividing the input signal into two regions: "effective signal" and "ineffective noise." In practice, the cursor velocity value Vin (containing both X and Y axes) is read after mapping and compensation. The absolute value of the cursor velocity value Vin is compared with a predefined dead-zone threshold Vdeadzone. Based on the comparison result, the output cursor movement velocity signal Vout is calculated. If |Vin|≤Vdeadzone|Vin|≤Vdeadzone, then Vout=0; If Vin > Vdeadzone, then Vout = Vin − Vdeadzone. If Vin < −Vdeadzone, then Vout = Vin + Vdeadzone; By filtering out the sensor's background noise and the slight physiological jitter that the user may have, dead-zone filtering eliminates the impact of such interference on the cursor at the signal source, thereby improving the accuracy of cursor movement.

[0086] Displacement accumulation: Apply a displacement accumulation mechanism to the output cursor movement speed signal to convert the continuous cursor movement speed signal into an accumulated displacement amount.

[0087] As a bridge connecting the algorithm of this embodiment with the standard system, this step uses a displacement accumulation mechanism specifically designed to process the high-precision cursor movement speed signal generated by the inverse mapping paradigm and smoothness compensation. The essence of this mechanism is discrete recursive accumulation, rather than continuous integration; through continuous addition operations, the continuous speed signal is converted into accumulated displacement. This mechanism ensures that the algorithm's sub-pixel accuracy and dynamic response characteristics are fully preserved during the conversion to the standard HID protocol, achieving lossless transmission from intent to instruction.

[0088] In practice, the output cursor movement speed signal is processed in each fixed sampling period. Internal calculation of displacement increment The displacement increment is continuously accumulated to the displacement accumulator. When the accumulated displacement in the accumulator is greater than or equal to 1 pixel, the integer part of the accumulated value is output as the displacement. Simultaneously, the integer part is subtracted from the output value from the accumulator, leaving a margin of less than 1 pixel for accumulation calculation in subsequent sampling periods. The displacement increment is then calculated. Expressed as:

[0089]

[0090] The accumulator operation value is then expressed as:

[0091]

[0092] in, , These represent the displacement increments of the cursor along the X-axis and the Y-axis, respectively.

[0093] Cursor control: The output displacement is synchronized with the interactive confirmation signal in time and encapsulated into a standard HID data packet (conventional technology) to drive the cursor to update its position and perform operations, thus achieving convenient, efficient and high-precision cursor control for AR glasses.

[0094] Furthermore, the interactive confirmation signal can be an interactive signal used by the user to confirm the execution of an operation through at least one of the physical buttons, touchpads, gesture recognition modules, or voice command modules integrated into the temples of the AR glasses.

[0095] Based on this, the AR glasses device itself collects and utilizes the user's natural head rotation posture as input commands, and constructs a reverse mapping paradigm so that the physical direction of cursor movement is opposite to the physical direction of the user's head rotation. This avoids an intuitionistic "chasing" relationship between the cursor and the target, and realizes an intuitive mapping between the user's natural head rotation and the AR glasses cursor control. Precise cursor control can be achieved without additional auxiliary actions or controllers, and it is convenient and highly private.

[0096] Example 2 This embodiment provides an AR glasses cursor control system based on head posture sensing, including an AR glasses body. The AR glasses body integrates at least a high-precision inertial measurement unit (IMU) for real-time monitoring of the user's head rotation posture, and an interactive confirmation module for user confirmation. This system is used to implement the AR glasses cursor control method based on head posture sensing as described in the above embodiment.

[0097] In summary, the AR glasses cursor control method and system based on head posture sensing provided by this invention, compared with the prior art, collects and utilizes the user's natural head rotation posture as input command through the AR glasses device itself, and constructs a reverse mapping paradigm so that the physical direction of cursor movement is opposite to the physical direction of user head rotation, avoiding the non-intuitive "chasing" relationship between the cursor and the target, realizing an intuitive mapping between the user's natural head rotation and AR glasses cursor control, achieving precise cursor control without additional auxiliary actions or controllers, and offering high convenience and privacy.

[0098] Although this paper frequently uses terms such as first spatial axis, second spatial axis, and reverse mapping paradigm, the possibility of using other terms is not excluded. These terms are used merely for the convenience of describing and explaining the essence of the invention; interpreting them as any additional limitation would contradict the spirit of the invention.

[0099] Furthermore, those skilled in the art should understand that although many problems exist in the prior art, each embodiment or technical solution of the present invention can be improved in only one or a few aspects, without necessarily solving all the technical problems listed in the prior art or the background art simultaneously. Those skilled in the art should understand that any content not mentioned in a claim should not be construed as a limitation on that claim.

[0100] 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A cursor control method for AR glasses based on head posture sensing, which collects and utilizes the user's natural head rotation posture as input commands through the AR glasses device itself, realizing an intuitive mapping between the user's natural head rotation and AR glasses cursor control, characterized in that: Includes the following steps: Data acquisition: The first angular velocity of the user's head rotating around the first spatial axis and the second angular velocity of the user's head rotating around the second spatial axis are acquired by the gyroscope; Establish mapping: Using the collected first and second angular velocities as inputs, establish a reverse mapping paradigm between the user's head rotation posture and cursor control, and output the cursor movement speed signal after smoothing compensation; Displacement accumulation: Apply a displacement accumulation mechanism to the output cursor movement speed signal to convert the continuous cursor movement speed signal into an accumulated displacement amount; Cursor control: The output displacement is synchronized with the interactive confirmation signal in time and encapsulated into a standard HID data packet to drive the cursor to update its position and perform operations, thus achieving convenient, efficient and high-precision cursor control for AR glasses.

2. The AR glasses cursor control method based on head posture sensing according to claim 1, characterized in that: The first spatial axis is a vertical axis, the second spatial axis is a horizontal axis, the first angular velocity is the angular velocity of the user's head rotating around the vertical axis along the X-axis, and the second angular velocity is the angular velocity of the user's head pitching around the horizontal axis along the Y-axis.

3. The AR glasses cursor control method based on head posture sensing according to claim 2, characterized in that: The core of the reverse mapping paradigm is that the physical direction of cursor movement is opposite to the physical direction of the user's head rotation, expressed as: in, , These represent the angular velocities of the cursor's movement along the X and Y axes, respectively, in radians. The sensitivity factor for cursor movement defined by the user. , These are the first angular velocity and the second angular velocity, respectively.

4. The AR glasses cursor control method based on head posture sensing according to claim 1, characterized in that: The smoothness compensation is achieved by collecting acceleration data of the user's head rotating around the first spatial axis / second spatial axis, converting it into acceleration values ​​and using it as a feedforward quantity. This is then directly and linearly superimposed with the angular velocity of the cursor movement to output a cursor movement speed signal, thereby compensating for the phase lag of the gyroscope, improving the smoothness of cursor movement, and reducing latency.

5. The AR glasses cursor control method based on head posture sensing according to claim 4, characterized in that: The smoothness compensation is expressed as: in, , These are the acceleration values ​​of the user's head rotating around the first spatial axis and the second spatial axis, respectively. This is a compensation factor.

6. The AR glasses cursor control method based on head posture sensing according to claim 5, characterized in that: The acceleration of the user's head rotating around the first and second spatial axes is collected by the accelerometer of the inertial measurement unit and obtained through the following formula: in, , These are the raw rotation data for the user's head rotating around the vertical axis and the raw rotation data for pitching around the horizontal axis, respectively. This is the sensitivity coefficient of the accelerometer.

7. The AR glasses cursor control method based on head posture sensing according to claim 4, characterized in that: The smoothness compensation also includes dead-zone filtering, comprising the following steps: Set a dead zone threshold. When the absolute value of the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is 0. When the cursor movement speed signal is greater than the dead zone threshold, the output speed is the difference between the original cursor movement speed signal and the dead zone threshold. When the cursor movement speed signal is less than or equal to the dead zone threshold, the output speed is the sum of the original cursor movement speed signal and the dead zone threshold.

8. The AR glasses cursor control method based on head posture sensing according to claim 1, characterized in that: The displacement accumulation mechanism is implemented through discrete recursive accumulation and includes the following steps: Fixed sampling period Calculate the displacement increment in each sampling period The displacement increment is continuously accumulated to the displacement accumulator. When the accumulated displacement in the accumulator is ≥ 1 pixel, the integer part of the accumulated value is output as the displacement. At the same time, the integer part of the output value is subtracted from the accumulator, and a margin of less than 1 pixel is retained for accumulation calculation in subsequent sampling periods. The displacement increment is then calculated. Expressed as: The accumulator operation value is then expressed as: in, , These represent the displacement increments of the cursor along the X-axis and the Y-axis, respectively.

9. The AR glasses cursor control method based on head posture sensing according to claim 1, characterized in that: The interactive confirmation signal comes from at least one of the physical buttons, touchpad, gesture recognition module, or voice command module integrated into the temples of the AR glasses.

10. A cursor control system for AR glasses based on head posture sensing, characterized in that: This method is used to implement the AR glasses cursor control method based on head posture sensing as described in any one of claims 1 to 9.

Images