Adjusting method of tactical AR helmet

Abstract

The invention relates to a helmet adjusting method, in particular to a tactical AR helmet adjusting method. According to the technical scheme, the method comprises the following steps: S1, dynamic adjustment based on self-adaptive head tracking: detecting the head position and posture of a user in real time by an inertial measurement unit IMU and a head tracking sensor which are arranged in a helmet, and establishing initial space coordinates; s2, an optical adjustment system based on environment feedback: a light sensor is arranged in the helmet to monitor the surrounding illumination intensity in real time, and in a tactical scene, ambient light has frequent changes including day and night alternation and indoor and outdoor conversion; s3, wearing comfort self-adjustment based on physiological feedback; S4, content presentation adjustment based on task priority: an AI module arranged in the helmet analyzes a tactical task scene, identifies the priority of a current task including enemy alarm and team indication, and preferentially displays important task information; and dynamically adjusting the brightness, position and size of the display content according to a head tracking and physiological feedback system.

Description

Technical Field

[0001] The present invention relates to a method for adjusting a helmet, and in particular to a method for adjusting a tactical AR helmet. Background Art

[0002] There are some deficiencies and drawbacks in the current adjustment methods for tactical AR helmets, especially when compared with the AR helmet adjustment method and system in China's invention patent 202011256008.6 (hereinafter referred to as the "comparative document"), the limitations of the current technology can be pointed out more clearly. The AR helmet adjustment method mentioned in the comparative document mainly controls the wearing comfort and stability of the helmet through the inflation and deflation operations of the airbag and the fixing device, while using sensors to collect physiological data such as temperature, humidity and pressure, and combining the decision-making model to adjust the tightness. This method does improve the user's wearing comfort and stability to a certain extent, but in actual tactical application scenarios, there are still the following deficiencies and disadvantages.

[0003] First, the adjustment method is relatively simple and cannot dynamically respond to complex battlefield needs. The AR helmet adjustment method in the comparative document mainly relies on the inflation and deflation of the airbag and the tightness control of the fixing device. Although this mechanical adjustment can improve the comfort of wearing, its adjustment speed and flexibility are obviously insufficient in a rapidly changing tactical environment. In tactical tasks, soldiers need to move frequently, lower their heads, turn around, and so on, but the response speed of the airbag adjustment is slow and cannot adapt to these dynamic changes in real time. This may cause the helmet to become loose or too tight during intense actions, affecting the soldier's freedom of movement and battlefield perception. In addition, the inflation and deflation operation of the airbag may cause wear or leakage during long-term use, resulting in a gradual weakening of the adjustment effect, which will cause obvious discomfort and operational burden to soldiers during long-term tasks.

[0004] Secondly, the adjustment method is too dependent on preset sensor data and lacks intelligent and multi-dimensional perception capabilities. The helmet adjustment method in the comparative document is mainly based on temperature sensors, humidity sensors and pressure sensors to detect the user's physiological state, and adjust the tightness through a decision model. However, this adjustment method based on limited sensor data has great limitations, especially in a complex battlefield environment, where a single physiological data cannot fully reflect the true state of the soldier. For example, when a soldier is performing a task, physiological data such as heart rate and skin resistance may better reflect his tension and fatigue state, but the adjustment method in the comparative document does not consider these more relevant physiological indicators. In addition, the current technology fails to combine the relationship between environmental factors (such as noise, explosion vibration, etc.) and the physiological response of soldiers to make more intelligent adjustment decisions, and lacks intelligent perception and feedback mechanisms for users' multi-dimensional physiological and battlefield data.

[0005] Third, there is a lack of dynamic adjustment capabilities for task priorities and tactical information. Although the AR helmet adjustment method in the comparative document can adjust the wearing comfort and stability of the helmet through sensors, it does not involve how to dynamically adjust the information display during the execution of tactical tasks. In actual tactical scenarios, soldiers need to process a large amount of information in a short period of time, such as enemy alerts, team instructions, environmental changes, etc. The current technology cannot intelligently adjust the displayed information according to the priority of tactical tasks, which can easily lead to information overload for soldiers in high-pressure environments. The methods in the comparative documents only focus on the adjustment of the wearing status, ignoring the linkage between information display and the user's physiological state and tactical tasks, and lack the optimization of soldiers' perception in dynamic task environments. Therefore, when soldiers perform complex tasks, they may be unable to obtain key information in a timely manner, which may affect combat decisions and task execution results.

[0006] Therefore, although the adjustment methods and systems in the comparative documents have certain effects in improving the comfort and stability of AR helmets, they still have many deficiencies in actual tactical application scenarios. The adjustment method is relatively simple and it is difficult to dynamically respond to complex battlefield needs; the adjustment method relies on limited sensor data and lacks intelligent multi-dimensional perception capabilities; it cannot be dynamically adjusted according to task priorities and tactical information, and lacks a comprehensive perception and response mechanism for battlefield threats. Summary of the invention

[0007] The purpose of the present invention is to provide a method for adjusting a tactical AR helmet, thereby solving some of the drawbacks and shortcomings pointed out in the background technology.

[0008] The present invention solves the above-mentioned technical problems by adopting the following technical solution, which comprises the following steps:

[0009] S1. Dynamic adjustment based on adaptive head tracking:

[0010] S1.1. The helmet’s built-in inertial measurement unit (IMU) and head tracking sensor detect the user’s head position and posture in real time and establish initial spatial coordinates;

[0011] S1.2, based on the user's rapid movement in tactical scenarios, the system tracks the slight changes in the head angle in real time and adjusts the position and angle of the AR display content through intelligent algorithms;

[0012] S1.3. When the user moves violently or switches his / her sight quickly, the helmet display content is fine-tuned through feedback from the accelerometer and gyroscope;

[0013] S2. Optical adjustment system based on environmental feedback:

[0014] S2.1. The built-in light sensor in the helmet monitors the surrounding light intensity in real time. In tactical scenarios, the ambient light changes frequently, including day and night, and indoor and outdoor transitions.

[0015] S2.2. Adjust the brightness and contrast of the AR display screen according to the feedback from the light sensor;

[0016] S3. Self-adjustment of wearing comfort based on physiological feedback:

[0017] S3.1. Through built-in physiological monitoring sensors including heart rate and body temperature sensors, the user's physical condition data is collected in real time to determine whether there are signs of discomfort or fatigue;

[0018] S3.2. When physiological feedback shows that the user is uncomfortable due to long-term wearing or intense movements, the helmet adjusts the tightness through a micro-mechanical device;

[0019] S3.3, combining ambient light and physiological feedback, when the user's body temperature rises, the heat dissipation inside the helmet is turned on to adjust the temperature;

[0020] S4. Content presentation adjustment based on task priority:

[0021] S4.1. The AI ​​module built into the helmet analyzes tactical mission scenarios, identifies the priority of current tasks including enemy alerts and team instructions, and prioritizes the display of important mission information;

[0022] S4.2. Dynamically adjust the brightness, position and size of the displayed content based on the head tracking and physiological feedback system;

[0023] S4.3. Switch the presentation mode of AR content according to different mission requirements, including mission mode to display tactical information and rest mode to reduce visual burden.

[0024] Furthermore, the method for establishing the initial spatial coordinates includes: fusing multiple sensors built into the helmet, including an inertial measurement unit IMU, a visual sensor, and a laser ranging sensor, and the IMU is used to obtain preliminary posture information of the head movement by capturing the angular velocity and acceleration data of the head in real time. The formula is as follows:

[0025]

[0026] Among them, P(t) represents the posture position of the user's head at time t, A(t) is the time dependency of the acceleration data, reflecting the change of the linear motion of the head, and B(t) is the angular velocity correction coefficient of the system. is the rate of change of angular velocity, indicating the speed of head rotation; the overall motion posture trajectory of the user's head between time t0 and t is calculated by integration.

[0027] Furthermore, the visual sensor is used to capture feature points in the surrounding environment, and combined with a laser ranging sensor, it is used to calculate the relative distance change between the head and objects in the environment, and the initial three-dimensional space coordinates are constructed using the feature point coordinates. The data fusion and calibration between the built-in sensors of the helmet are realized through the formula:

[0028]

[0029] Among them, C s (t) represents the spatial coordinates after fusion and correction at time t, D i (t) is the relative distance measured by the i-th sensor at time t, R i (t) is the coordinate value of the environmental reference point corresponding to the sensor, indicating the relative position from the feature point to the user's head. α is the attenuation factor when fusing data between sensors, controlling the rate at which sensor data decays over time. F(·) is the fusion function within the system, which is used to integrate multi-sensor data to correct the position error of the head.

[0030] Among them: In dynamic scenes, when the user's head changes dramatically, the IMU collects acceleration data in real time and combines it with the environmental change information of the visual sensor to adjust the sensor operating frequency according to the following adaptive tracking formula:

[0031]

[0032] Where S(t) is the sensor operating frequency at time t, indicating the sampling frequency of the sensor at that moment; ΔH(t) is the amplitude of the position change of the user's head within time t, reflecting the moving distance of the head; ΔT is the time interval, indicating the movement rate of the head within a period of time; V(t) is the instantaneous speed of the user at time t, indicating the speed change rate of the head movement; G(·) is the frequency adjustment function, which is used to dynamically adjust the operating frequency of the sensor according to the amplitude of the head movement.

[0033] Furthermore, the method for judging whether there are signs of wearing discomfort or fatigue is:

[0034] S1. First, the heart rate sensor monitors the user's heart rate fluctuations in real time and calculates the real-time heart rate change rate using the formula:

[0035]

[0036] Where H(t) represents the heart rate change rate at time t, R(t) is the user's instant heart rate value at time t, and R avgis the user's historical average heart rate, indicating the user's baseline heart rate when not stressed or fatigued. Δt is the time interval from t0 to t. The deviation of the heart rate is calculated by integration to detect whether the user has abnormal heart rate fluctuations.

[0037] S2. Secondly, the body temperature sensor monitors the temperature changes in the user's head area, and combines the body temperature fluctuations during activities to calculate the local overheating degree of the user's wearing area through the following formula:

[0038]

[0039] Among them, T local (t) is the local temperature of the user's head wearing area at time t, T0 is the user's initial body temperature, which represents the reference temperature of the head area when not wearing a helmet or in a static state, β is the temperature response coefficient, which reflects the sensitivity of body temperature to user movement, P(t) is the user's activity temperature curve at time t, which represents the dynamic change of body temperature during the activity, and P rest This is the user's baseline temperature curve in a resting state;

[0040] S3. Finally, the skin electrical sensor reflects the user's emotions and stress state by monitoring the change of skin resistance; the change of skin resistance is calculated by the following formula:

[0041]

[0042] Wherein, E(t) is the rate of change of skin resistance at time t, reflecting the skin electrical response of the user at time t; γ is the pressure sensitivity coefficient, indicating the sensitivity of skin resistance to pressure; G(t) is the instantaneous skin resistance value of the user at time t, representing the conductive properties of the skin under different pressure states.

[0043] Furthermore, the built-in AI module performs real-time analysis of tactical tasks, combines natural language processing (NLP), image recognition and audio signal processing, and perceives dynamic changes in mission scenarios in multiple dimensions;

[0044] The AI ​​module uses NLP technology to parse text and voice commands from the headquarters or team, identify key mission information and assign priorities. The mission priority label is calculated using the following formula:

[0045]

[0046] Among them, P(t) is the priority of the task at time t, α, β, and γ are the priority weight coefficients set by the system according to the characteristics of the task, α represents the weight of the urgency of the task, β represents the weight of the dynamic change rate of the task, and γ represents the weight of the importance of the task content; L(t) is the urgency level of the task at time t, which is assigned according to the context of the instruction. is the dynamic change rate of the task, indicating the speed at which the importance or urgency of the task changes at time t. It is used to capture enemy alerts or other rapidly changing task information. Ct is the content importance of the task, which is obtained based on AI content analysis of the task text or voice command.

[0047] Furthermore, the image recognition technology is used, and the AI ​​module captures threat targets on the battlefield through the helmet camera, and updates the priority according to the importance and distance of the threat targets through the following formula:

[0048]

[0049] Where V(t) is the comprehensive priority of all threat targets at time t, which represents the evaluation of multiple threat sources; N in the formula V(t) is the number of threat targets detected at the same time, and W i is the importance weight of the i-th target, indicating the threat level or strategic importance of a target in the current tactical scenario. i (t) is the distance between the i-th target and the user, indicating the proximity of the threat target. The smaller the distance, the greater the threat. i (t) is the duration after the target appears, indicating how long the threat exists, and λ is the time decay coefficient, indicating the rate at which the target threat weakens over time.

[0050] Furthermore, the audio sensor captures audio signals including explosions and calls in the battlefield in real time, and analyzes the threat level of the audio signals through the AI ​​algorithm; the priority display weight of the audio signal is calculated by the following formula:

[0051]

[0052] Where A(t) is the priority display weight of the audio signal at time t, indicating the relative importance of the audio signal in the tactical mission, and S audio (t) is the audio signal strength at time t, reflecting the threat intensity of the audio source, including the volume of the explosion or gunshot, μ is the attenuation coefficient of the audio signal, indicating that the importance of the audio signal decays over time, and t0 is the time point when the audio signal is first detected.

[0053] The adjustment method of the tactical AR helmet of the present invention has the following beneficial effects:

[0054] By integrating AI modules and combining natural language processing (NLP), image recognition and audio signal processing technologies, the helmet can analyze various dynamic changes in tactical scenarios in real time and fully perceive the battlefield environment. This ensures that soldiers can obtain the latest mission information at any time and improve their battlefield perception capabilities.

[0055] Through a variety of sensors and AI algorithms, task priorities are calculated and adjusted in real time according to the urgency of the task, the rate of dynamic change, and the importance of the content. Through this intelligent priority management, soldiers can focus on the most urgent and important tasks in complex environments, effectively avoiding information overload. The helmet of the present invention can also detect surrounding threat targets through image and audio sensors at the same time, and comprehensively evaluate their priorities based on the importance, distance, and duration of the threat. This function enables soldiers to quickly identify multiple threat sources and reasonably allocate attention to ensure the safety and effectiveness of operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of a method for adjusting a tactical AR helmet according to the present invention.

[0057] Figure 2 A flow chart of the method for establishing initial space coordinates for the present invention.

[0058] Figure 3 The present invention is a flow chart of a method for determining whether there are signs of wearing discomfort or fatigue. DETAILED DESCRIPTION

[0059] The specific implementation modes of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0060] Combined with Figure 1 , a method for adjusting a tactical AR helmet comprises the following steps:

[0061] S1. Dynamic adjustment based on adaptive head tracking. First, in S1.1, the helmet's built-in inertial measurement unit (IMU) and head tracking sensor detect the user's head position and posture in real time and establish an initial spatial coordinate system. This process ensures that when the user starts using it, the system can build an accurate three-dimensional space model through sensor data fusion to define the initial position and posture of the head in the space.

[0062] In S1.2, the system tracks the slight changes in the angle of the head in real time according to the user's rapid movement in the tactical scene. This is achieved through an intelligent algorithm that processes the data from the IMU and head tracking sensors to accurately calculate the angular velocity and acceleration of the user's head, and then dynamically adjusts the position and angle of the AR display content through these data, so that the virtual information is always aligned and synchronized with the real environment. Finally, in S1.3, when the user moves violently or switches his line of sight quickly, the system fine-tunes through the feedback of the accelerometer and gyroscope, which means that when the sensor detects that the user's head moves quickly or the line of sight changes drastically, the angle and position of the AR display content will automatically adjust according to these changes to ensure that the user can still accurately obtain the required virtual information during intense tactical actions.

[0063] S2. Optical adjustment system based on environmental feedback. First, in S2.1, the built-in light sensor in the helmet can monitor the light intensity of the surrounding environment in real time, especially in tactical scenarios, where the ambient light may change frequently, including the transition from day to night or from indoor to outdoor environments. This light monitoring function ensures that the system can always accurately perceive the current lighting conditions, whether the user is operating during the day or at night, or in a bright indoor or dark outdoor environment, the light sensor will capture these changes and provide data support for the subsequent display adjustments.

[0064] In S2.2, based on the feedback from the light sensor, the system automatically adjusts the brightness and contrast of the AR display to ensure that users can clearly see the AR content under different lighting conditions. When the ambient light is strong, the system will increase the brightness and contrast of the display to ensure that the virtual information is still visible; in a weak light environment, the system will appropriately reduce the display brightness to avoid the screen being too bright and causing interference to the user, and ensure that the AR content is naturally integrated with the real environment. This adjustment mechanism effectively improves the user's visual experience in various tactical environments.

[0065] S3. Self-adjustment of wearing comfort based on physiological feedback. First, in S3.1, the helmet has built-in physiological monitoring equipment including heart rate and body temperature sensors, which can collect the user's physical condition data in real time. These sensors monitor the user's heart rate, body temperature and other physiological parameters to determine whether the user has signs of fatigue or discomfort due to long-term wearing or strenuous movements. Through real-time analysis of these physiological data, the system can determine whether the user's physical condition has entered the discomfort range or is at risk of fatigue.

[0066] In S3.2, when physiological feedback shows that the user is uncomfortable due to wearing the helmet for a long time or due to high-intensity movements, the system will trigger the micro-mechanical device in the helmet to automatically adjust the tightness of the helmet. Through this automatic adjustment function, the helmet can adapt to the user's immediate needs, ensuring that the user's comfort is not affected when worn for a long time, and avoiding the discomfort caused by compression or tightness of the helmet. In S3.3, the system will combine the changes in ambient light with physiological feedback data for further adjustments. When the user's body temperature is detected to rise, the system will automatically start the heat dissipation mechanism inside the helmet. By turning on the heat dissipation system in the helmet, the temperature inside the helmet is adjusted in time to ensure that the user maintains a comfortable temperature environment during high-intensity tactical activities.

[0067] S4. Content presentation adjustment based on task priority. First, in S4.1, the built-in AI module of the helmet can identify the priority of the current task by analyzing the tactical mission scenario, including key information such as enemy situation alerts and team movement instructions. The system automatically prioritizes these tasks according to their importance and urgency, and displays the most important task information on the user's AR interface first, to ensure that the user can quickly obtain the necessary tactical information at critical moments.

[0068] In S4.2, the system combines head tracking and physiological feedback systems to dynamically adjust the brightness, position and size of AR display content. For example, when it is detected that the user's line of sight is focused on a specific task area, the system will automatically increase the brightness and highlight the content in that area, while other lower-priority task information will be reduced or dimmed accordingly to prevent the user from being disturbed by too much information. At the same time, the physiological feedback system will further optimize the presentation of the displayed content based on the user's physical condition, such as stress and fatigue, to ensure that the user maintains the best condition under high-intensity operation.

[0069] In S4.3, the system supports automatic switching of AR content presentation modes according to the needs of different tasks, mainly including task mode and rest mode. In task mode, the system will focus on displaying important tactical information, such as enemy situation, map, instructions, etc., to ensure that users can concentrate on task execution; while in rest mode, the system will reduce visual burden, reduce the complexity and intensity of information display, provide users with a short visual rest, and help relieve fatigue caused by long-term use.

[0070] Embodiment 1:

[0071] A special forces soldier is carrying out a complex tactical mission. The mission requires him to enter an unfamiliar building at night to detect the enemy's movements and obtain important intelligence. To this end, the soldier wears the latest tactical AR helmet, which has multiple sensors built into the helmet, including inertial measurement unit (IMU), visual sensor and laser ranging sensor, to help him quickly and accurately perceive the environment and adjust the AR display content of the helmet during the action.

[0072] Establish the initial space coordinates:

[0073] When a soldier enters a building, the helmet first establishes the initial spatial coordinates through multi-sensor fusion. The inertial measurement unit (IMU) is responsible for capturing the real-time angular velocity and acceleration data of the soldier's head, the visual sensor is used to capture the characteristic points of the environment, and the laser ranging sensor provides depth information. The system combines these data to calculate the posture position of the soldier's head in real time.

[0074] The formula is:

[0075]

[0076] in:

[0077] P(t) represents the soldier’s head posture position at time t;

[0078] A(t) is the acceleration data at time t, reflecting the change in the linear motion of the soldier’s head;

[0079] B(t) is the angular velocity correction coefficient, which generally ranges from 0.8 to 1.2. The specific value is adjusted dynamically according to the actual situation. It is the rate of change of angular velocity, which indicates the speed at which the soldier's head rotates, usually in radians per second.

[0080] For example, at a certain moment t0=0, the soldier starts to turn his head quickly to the right to check the environment. The IMU detects that the acceleration A(t) at this time is 0.5m / s 2 , rate of change of angular velocity The angular velocity correction factor B(t) is set to 1. The calculation can be performed at t = 2 seconds:

[0081]

[0082] At this time, the posture position P(2) of the soldier's head is 5. This value reflects the soldier's head rotation within 2 seconds. The system automatically adjusts the AR display content through this data to synchronize the virtual information with the real environment.

[0083] Dynamically adjust AR display content:

[0084] During tactical missions, soldiers need to react quickly. Through the sensor data of the helmet, the system can adjust the position and angle of the AR display content in real time according to the soldier's head movement. For example, when a soldier suddenly discovers the enemy's position and quickly turns his head, the IMU of the helmet detects the changes in acceleration and angular velocity. The system calculates the head posture position through the aforementioned formula and dynamically adjusts the content of the AR display to keep the most important tactical information in the soldier's field of view.

[0085] Assuming that the soldier's head continues to turn within 4 seconds, the system captures data once a second to calculate the posture position at each moment.

[0086] At t = 1 second, A(1) = 0.4 m / s 2 , B(1)=1.1,

[0087]

[0088] At t = 2 seconds, A(2) = 0.5 m / s 2 , B(2)=1.0,

[0089]

[0090] At t = 3 seconds, A(3) = 0.6 m / s 2 , B(3)=0.9,

[0091]

[0092] At t = 4 seconds, A(4) = 0.7 m / s 2 , B(4)=1.0,

[0093]

[0094] In 4 seconds, the posture positions of the soldier's head were P(1) = 2.38, P(2) = 2.5, P(3) = 2.58, and P(4) = 3.2. These values ​​represent the dynamic changes of the soldier's head. The system uses these posture data to adjust the display content in real time, so that the soldier can always obtain accurate AR visual feedback during the mission, ensuring that key tactical information is always presented in the center of his field of vision.

[0095] When a soldier enters a building for reconnaissance at night, in addition to tracking the movement of the head through the inertial measurement unit (IMU), the helmet also uses visual sensors and laser ranging sensors to capture feature points in the surrounding environment and calculate the relative distance to objects in the environment. This is crucial for accurately constructing the initial three-dimensional spatial coordinates, thereby ensuring that AR information can be accurately superimposed on the real environment.

[0096] In actual scenarios, soldiers use the visual sensors on their helmets to capture the feature points of walls, furniture, and other objects in buildings. The coordinate information of these feature points will be recorded by the system, and the laser rangefinder will continuously measure the relative distance between the soldier's head and these objects. Then, the system fuses the data from these sensors through the following formula to correct the spatial position of the soldier's head in the environment:

[0097]

[0098] In this formula:

[0099] C s (t) represents the spatial coordinates after data fusion and correction at time t, that is, the exact position of the soldier's head in the current environment;

[0100] D i(t) is the relative distance measured by the i-th sensor at time t, for example, the distance between a soldier’s head and an object in the environment measured by a laser ranging sensor, in meters;

[0101] R i (t) is the coordinate value of the environmental reference point corresponding to the i-th sensor, indicating the fixed position of the object in the environment;

[0102] α is the attenuation factor, which usually ranges from 0.01≤α≤0.1. It controls the decay rate of sensor data over time, indicating that the importance of some sensor data gradually decreases over time;

[0103] F(·) is the fusion function within the system, which is used to integrate these sensor data and correct the position error of the soldier’s head.

[0104] Assume that the feature points captured by the soldier's helmet include three objects: a wall, a table, and a chair. The visual sensor captures the fixed coordinates of these objects through image recognition technology, which are R1(t) = (5, 2, 0), R2(t) = (3, 3, 1), and R3(t) = (2, 1, 1) meters. At the same time, the laser ranging sensor measures the relative distances between the soldier's head and these objects at t = 2 seconds, which are D1(2) = 1.5 meters, D2(2) = 1.8 meters, and D3(2) = 2.1 meters, assuming the attenuation factor α = 0.05.

[0105] Substitute into the formula to calculate:

[0106] C s (2)=F((1.5·(5,2,0)+1.8·(3,3,1)+2.1·(2,1,1))·e -0.05·2 )

[0107] First calculate each term:

[0108] 1.5·(5,2,0)=(7.5,3,0)

[0109] 1.8·(3,3,1)=(5.4,5.4,1.8)

[0110] 2.1·(2,1,1)=(4.2,2.1,2.1)

[0111] Add them together:

[0112] (7.5,3,0)+(5.4,5.4,1.8)+(4.2,2.1,2.1)=(17.1,10.5,3.9)

[0113] Next, calculate the effect of the attenuation factor:

[0114] e -0.05·2=e -0.1 ≈0.9048

[0115] Substituting this attenuation value into:

[0116] C s (2) = (17.1, 10.5, 3.9) · 0.9048 = (15.47, 9.5, 3.53)

[0117] After fusion and calibration, the spatial coordinates of the soldier's head at t = 2 seconds are C s (2) = (15.47, 9.5, 3.53) meters. This coordinate is the precise result after multi-sensor data fusion and time decay, indicating the actual position of the soldier in the current environment. Through this multi-sensor fusion method, the soldier's AR helmet can adjust the spatial position of the head in real time, and the helmet can maintain accurate positioning even when moving quickly or the environment changes.

[0118] During the reconnaissance mission, the soldier suddenly discovered a potential threat and quickly adjusted his head to check the battlefield situation. At this time, the IMU (inertial measurement unit) and visual sensors in the tactical AR helmet need to respond to drastic head changes in real time to ensure that the AR display content can accurately adjust with the soldier's rapid rotation. In this case, the operating frequency of the helmet's sensor needs to be dynamically adjusted according to the soldier's head movement to maintain high-precision data collection and real-time display content.

[0119] To achieve this, the system uses an adaptive tracking formula to adjust the operating frequency of the sensor:

[0120]

[0121] in:

[0122] S(t) is the operating frequency of the sensor at time t, which indicates the sampling frequency of the sensor at that moment;

[0123] ΔH(t) is the change in the position of the user's head within time t, reflecting the distance the head moves during this period, in meters;

[0124] ΔT is the time interval, which indicates the movement rate of the head in a period of time, in seconds;

[0125] V(t) is the instantaneous velocity of the user’s head at time t, in meters per second;

[0126] G(·) is the frequency adjustment function, which represents the mechanism of dynamically adjusting the sensor operating frequency according to the amplitude of head movement.

[0127] Assume that the soldier starts to turn his head quickly at t = 0 seconds and continues for 3 seconds. The sensor collects data once per second, and the sensor operating frequency at each time point can be calculated.

[0128] At t = 1 second, the IMU detects that the position change of the soldier's head is ΔH(1) = 0.8 meters, the time interval ΔT = 1 second, the instantaneous speed V(1) = 0.5 meters / second, and the frequency adjustment function G(x) = 2x, then:

[0129]

[0130] At t=1 second, the operating frequency of the sensor is S(1)=1.7578 Hz.

[0131] At t = 2 seconds, the position change amplitude ΔH(2) = 1.2 meters, the instantaneous speed V(2) = 1.0 meters per second, the time interval remains unchanged at 1 second, and the frequency adjustment function remains unchanged:

[0132]

[0133] The operating frequency of the sensor at this time is S(2)=1.6634 Hz.

[0134] At t = 3 seconds, the distance moved by the soldier's head increases, the position change amplitude is ΔH(3) = 1.5 meters, and the instantaneous speed V(3) = 1.2 meters / second:

[0135]

[0136] At t=3 seconds, the operating frequency of the sensor is S(3)=1.8183 Hz.

[0137] In this scenario, the soldier's head moves violently, and the IMU collects acceleration and position information in real time, combines it with the environmental change data of the visual sensor, and dynamically adjusts the sensor's operating frequency through an adaptive tracking formula. By increasing the sampling frequency of the sensor, the system can ensure that when the soldier's head turns quickly, the display content of the AR helmet can still accurately follow the soldier's line of sight.

[0138] The sensor operating frequency is dynamically adjusted according to the head movement amplitude and speed, ensuring that the system can provide sufficient frequency support when a higher sampling rate is required. For example, at t = 3 seconds, when the soldier's head movement amplitude and speed reach the maximum value, the sensor operating frequency is increased to 1.8183 Hz. This means that the sensor can collect data nearly twice per second, ensuring that the AR information in the soldier's field of view can be updated synchronously with the head movement.

[0139] Embodiment 2:

[0140] When a soldier wears a tactical AR helmet for a long time, the system will monitor his physiological state in real time to ensure that his body does not show signs of fatigue or discomfort. Tactical missions are tense and high-intensity, so the sensors in the helmet need to evaluate the soldier's heart rate, body temperature and emotional fluctuations in real time to ensure that the soldier can perform the mission in the best condition. The following will introduce the system's method of judging signs of discomfort or fatigue, and demonstrate its feasibility through calculation examples.

[0141] S1: Heart rate sensor monitors user's heart rate fluctuations:

[0142] When a soldier is performing a mission, the heart rate sensor monitors his heart rate changes in real time, and the system calculates the heart rate change rate using the following formula:

[0143]

[0144] in:

[0145] H(t) is the rate of change of heart rate at time t;

[0146] R(t) is the soldier’s instantaneous heart rate at time t, in beats / minute;

[0147] R avg is the historical average heart rate of soldiers in normal conditions, assuming that the soldier's baseline heart rate is 70 beats / minute;

[0148] Δt is the time interval from t0 to t, in seconds.

[0149] Assume that during the reconnaissance process, the soldier's heart rate rises from 70 beats / minute to 90 beats / minute due to the discovery of the enemy. The heart rate change can be calculated. At t = 5 seconds, the soldier's heart rate rises from the baseline heart rate R avg =70 rises to R(5)=90, time interval Δt=5 seconds. Substitute into the formula for calculation:

[0150]

[0151] The soldier's heart rate change rate H(5) = 20, indicating that the heart rate has fluctuated significantly. At this time, the system will issue an alarm to remind the user that he may be in a state of tension.

[0152] S2: Body temperature sensor monitors the temperature change of the user's head:

[0153] The system also monitors the soldier's body temperature, especially in the helmet wearing area. The body temperature sensor calculates the local overheating level using the following formula:

[0154]

[0155] in:

[0156] Tlocal (t) is the local temperature of the soldier’s head wearing area at time t;

[0157] T0 = ​​36.5°C is the soldier’s initial body temperature;

[0158] β is the temperature response coefficient, which generally ranges from 0.1≤β≤0.5 and reflects the sensitivity of body temperature to user movement;

[0159] P(t) is the soldier’s activity temperature curve at time t;

[0160] P rest =36.5℃ is the baseline temperature curve for soldiers at rest.

[0161] Assume that during the reconnaissance process, the soldier's body temperature rises from the initial body temperature T0 = 36.5°C to 37.5°C (i.e. P(t) = 37.5°C), which lasts for t = 10 seconds, and the temperature response coefficient β = 0.3. Substitute it into the formula for calculation:

[0162]

[0163] The local temperature of the wearing area on the soldier's head rises to 39.5℃ within 10 seconds. When the system detects the abnormal temperature rise, it will automatically turn on the helmet's heat dissipation device to reduce the local temperature.

[0164] S3: Galvanic skin sensor monitors emotions and stress states:

[0165] The system also monitors the soldier's emotions and stress status through skin electrical sensors. The change in skin resistance is calculated using the following formula:

[0166]

[0167] in:

[0168] E(t) is the rate of change of skin resistance at time t;

[0169] γ is the pressure sensitivity coefficient, and its value range is generally 0.5≤γ≤1.5, which indicates the sensitivity of skin resistance to pressure;

[0170] G(t) is the instantaneous skin resistance value of the soldier at time t, in ohms.

[0171] Assume that the soldier becomes increasingly nervous within 15 seconds, the skin resistance decreases from G(0)=2000Ω to G(15)=1500Ω, and the pressure sensitivity coefficient γ=1. The rate of change of skin resistance can be calculated:

[0172]

[0173] The soldier's skin resistance change rate E(15) = -33.33Ω / s indicates that his emotions and stress status have changed significantly. The system will combine the heart rate and body temperature data to determine that the soldier may be in a state of high stress or fatigue, and prompt him to make adjustments or rest.

[0174] Through these three steps, the system can accurately detect the physiological state of soldiers during the mission. When the heart rate fluctuates, the body temperature rises, or the skin resistance changes significantly, the system can make judgments through intelligent algorithms, promptly remind soldiers of possible signs of discomfort or fatigue, and help soldiers maintain the best physical condition by adjusting the heat dissipation or tightness of the helmet, thereby ensuring the smooth progress of the mission.

[0175] Embodiment 3:

[0176] When special forces soldiers are performing tasks at night, the tactical AR helmets they wear are integrated with a built-in AI module, which can perceive the dynamic changes of the mission scene in multiple dimensions and help soldiers quickly adapt to the changing tactical environment. The helmet uses natural language processing (NLP), image recognition and audio signal processing technology to analyze the text and voice commands of the headquarters or team in real time, identify key information in the mission, and assign priorities based on the urgency of the mission, the rate of dynamic change and the importance of the content, ensuring that the most important mission information can be displayed first in the soldier's AR interface.

[0177] Soldiers are performing reconnaissance missions through buildings. The headquarters sends voice commands to soldiers via wireless communication: "The enemy is moving quickly within 500 meters to your right. Confirm the location immediately and avoid contact." This is an urgent command. The AI ​​module immediately analyzes the voice information through NLP technology and identifies key information such as "enemy", "500 meters to the right", "moving quickly", and "avoiding contact". This information will be used as a reference factor for the importance of the task. At the same time, the system will also analyze the enemy's position and dynamic information fed back by image recognition and audio signal processing, and adjust the task priority in real time.

[0178] NLP technology analyzes task information and assigns priorities:

[0179] After the AI ​​module analyzes the instructions and identifies the key elements in the task through NLP technology, the system calculates the priority of the task based on the urgency, speed of change and importance of the information. The task priority is calculated using the following formula:

[0180]

[0181] in:

[0182] P(t) is the priority of the task at time t;

[0183] α, β, and γ are the priority weight coefficients of task characteristics, assuming that α = 0.6, β = 0.25, and γ = 0.15, which are adjusted according to task characteristics and situations;

[0184] L(t) represents the urgency level of the task. Considering the enemy situation, it is assumed that the urgency level of the task is 9 (out of 10);

[0185] Indicates the dynamic change rate of the task. Assuming that the enemy moves fast, the importance change rate is 6;

[0186] C(t) represents the importance of the task content. According to the analysis of the instruction content, the importance of the task is assigned a value of 8 (out of 10).

[0187] Substituting these values ​​into the priority formula:

[0188] P(t)=0.6·9+0.25·6+0.15·8=5.4+1.5+1.2=8.1

[0189] At this time, the system calculates the task priority as 8.1, indicating that the task is very urgent in the current tactical scenario and must be handled first. The soldier's AR helmet automatically places information related to the task in a prominent position on the display, ensuring that the soldier can respond and take action immediately.

[0190] Feedback on image recognition and audio signal processing:

[0191] The AI ​​module not only processes voice and text commands, but also combines other perception technologies in real time. The image recognition module captures the surrounding environment through the camera on the helmet. The AI ​​detects the enemy's movement 500 meters to the right of the soldier and feeds this data back to the system, further increasing the urgency of the mission. Similarly, the audio signal processing module captures the sound of enemy weapons firing. By analyzing the source of the audio signal, the AI ​​module identifies the specific location of the enemy and adjusts the mission priority in real time.

[0192] Assuming that in the new situation, the enemy's movement speed increases, and the audio signal indicates that the enemy's firepower has increased, the system will dynamically change the rate of change of the task From 6 to 8, and at the same time the task urgency level L(t) increases from 9 to 10. At this time, the priority of the task is recalculated:

[0193] P(t)=0.6·10+0.25·8+0.15·8=6+2+1.2=9.2

[0194] The priority level rises to 9.2, and the system further increases the urgency of the mission and adjusts the AR display information related to the enemy's location to a higher brightness and larger size to ensure that soldiers can respond quickly.

[0195] Through this multi-dimensional task priority calculation method based on NLP, image recognition and audio processing, the system can dynamically adjust the importance of tasks to ensure that soldiers always give priority to the most urgent tasks in complex tactical environments. The task priority has risen from the initial 8.1 to 9.2, reflecting the intensification of enemy activities and the update of instructions. The system can not only extract key information of instructions through natural language processing, but also adjust the dynamic priority of tasks in real time based on environmental feedback.

[0196] Suppose a soldier is performing a complex reconnaissance mission and the surrounding environment becomes more dangerous. The AI ​​module captures multiple threat targets on the battlefield through the helmet camera, including enemy infantry, vehicles, and possible ambush points.

[0197] To help soldiers determine the priority of each threat, the system uses image recognition technology to detect threat targets and updates the priority in real time based on the importance and distance of the target. The AI ​​module calculates the comprehensive priority of multiple threat targets using the following formula:

[0198]

[0199] in:

[0200] V(t) represents the comprehensive priority of all threat targets at time t;

[0201] N is the number of threat targets detected simultaneously;

[0202] W i is the importance weight of the i-th goal, indicating the strategic importance of the goal, and its value range is 0.5≤W i ≤1.5, the higher the value, the greater the threat;

[0203] D i (t) is the distance between the i-th target and the soldier, in meters. The smaller the distance, the greater the threat;

[0204] T i (t) is the duration after the target appears, in seconds;

[0205] λ is the time attenuation coefficient, which indicates the rate at which the target threat decreases over time, and its value range is 0.01≤λ≤0.1.

[0206] The soldier captured three threats through the helmet camera:

[0207] 1. The enemy infantry is located at 200 meters, with importance weight W1=1.2 and duration T1(t)=5 seconds.

[0208] 2. The enemy vehicle is located at 300 meters, with importance weight W2 = 1.0 and duration T2(t) = 3 seconds.

[0209] 3. The ambush point is located at 150 meters, the importance weight W3 = 1.5, and the duration T3(t) = 10 seconds.

[0210] By capturing the distance and duration of these threat targets, combined with their strategic importance, the comprehensive priority of each threat is calculated. Assuming the time decay coefficient λ = 0.05, the priority contribution of each threat can be calculated separately.

[0211] 1. Enemy Infantry (Target 1):

[0212] Infantry distance D1(t) = 200 meters, importance weight W1 = 1.2, duration T1(t) = 5 seconds:

[0213]

[0214] 2. Enemy Vehicle (Target 2):

[0215] Vehicle distance D2(t) = 300 meters, importance weight W2 = 1.0, duration T2(t) = 3 seconds:

[0216]

[0217] 3. Ambush point (target 3):

[0218] Ambush point distance D3(t) = 150 meters, importance weight W3 = 1.5, duration T3(t) = 10 seconds:

[0219]

[0220] Comprehensive threat priority calculation:

[0221] Now add up the priorities of all threats to get the total threat priority V(t):

[0222] V(t)=187.0+258.2+136.5=581.7

[0223] Based on this comprehensive threat priority, the system decides to display the most dangerous enemy vehicles and infantry-related AR information in the center of the soldier's field of vision, and reminds the soldier to pay attention to these high-priority targets through different colors and sizes. The ambush point is greatly affected by time decay and the threat level gradually decreases, so the display position will be slightly to the side, but it still maintains a certain warning.

[0224] The tactical AR helmets worn by soldiers not only capture threat targets through image recognition, but also capture audio signals from different sources on the battlefield in real time through audio sensors. The AI ​​module analyzes the threat level of these audio signals, such as explosions, calls or gunshots, and the system dynamically adjusts the priority display content based on the intensity and time lapse of these audio signals.

[0225] During the mission, the soldier suddenly heard two different audio signals coming from nearby while conducting reconnaissance: the first was an explosion 100 meters ahead, and the second was a call from about 200 meters to the left. The audio sensor in the helmet captured these audio signals separately, and the AI ​​module needed to analyze the threat intensity of each audio and decide how to prioritize the information displayed on the AR interface.

[0226] The priority display weight A(t) of the audio signal is calculated by the following formula:

[0227]

[0228] in:

[0229] A(t) is the priority display weight of the audio signal at time t;

[0230] S audio (t) is the audio signal strength at time t, reflecting the threat intensity of the audio signal;

[0231] μ is the attenuation coefficient of the audio signal, and its value range is generally 0.01≤μ≤0.1, indicating that the importance of the audio signal decays over time;

[0232] t0 is the time point when the audio signal is first detected.

[0233] 1. Calculation of the threat of explosion sound:

[0234] AI detects an explosion 100 meters ahead. The explosion first occurs at t0 = 0 seconds. The audio intensity of the explosion is relatively high. Assume that S audio (t) = 80 decibels. The attenuation coefficient of the audio signal μ = 0.05. Calculate the audio priority display weight at t = 5 seconds:

[0235]

[0236] Therefore, at t=5 seconds, the priority display weight of the explosion sound is 311.52. The system determines that the explosion sound is extremely threatening and displays it in a prominent position on the soldier's AR interface, prompting the soldier to be alert to the threat ahead.

[0237] 2. Calculation of threat of calling sound:

[0238] AI also captured a call from 200 meters to the left. The call first appeared at t0 = 2 seconds, and the audio intensity was low. Assuming S audio (t) = 50 decibels, the attenuation coefficient of the audio signal is the same as that of the explosion, still μ = 0.05. At t = 5 seconds, the priority display weight of the call sound is:

[0239]

[0240] At t = 5 seconds, the priority display weight of the call sound is 129.11, which is less threatening than the explosion sound. The system displays the audio information in a secondary position on the AR interface, using a smaller logo to remind the soldier to pay attention to the call sound on the left, but it will not interfere with the main task.

[0241] In this example, the explosion sound has a priority display weight of 311.52 due to its loud volume and close distance. The system considers the explosion sound to be a higher threat, so it is displayed and highlighted in the soldier's AR interface. The call sound has a priority display weight of only 129.11 due to its long distance and low volume, and its display position is relatively secondary. The AI ​​module combines audio signal strength and time attenuation to conduct a comprehensive analysis of audio from different sources to ensure that soldiers can quickly identify the most urgent threats in complex combat scenarios.

[0242] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for adjusting a tactical AR helmet, characterized in that The steps include: S1. Dynamic adjustment based on adaptive head tracking: S1.

1. The helmet’s built-in inertial measurement unit (IMU) and head tracking sensor detect the user’s head position and posture in real time and establish initial spatial coordinates; S1.2, based on the user's rapid movement in tactical scenarios, the system tracks the slight changes in the head angle in real time and adjusts the position and angle of the AR display content through intelligent algorithms; S1.

3. When the user moves violently or switches his / her sight quickly, the helmet display content is fine-tuned through feedback from the accelerometer and gyroscope; S2. Optical adjustment system based on environmental feedback: S2.

1. The built-in light sensor in the helmet monitors the surrounding light intensity in real time. In tactical scenarios, the ambient light changes frequently, including day and night, and indoor and outdoor transitions. S2.

2. Adjust the brightness and contrast of the AR display screen according to the feedback from the light sensor; S3. Self-adjustment of wearing comfort based on physiological feedback: S3.

1. Through built-in physiological monitoring sensors including heart rate and body temperature sensors, the user's physical condition data is collected in real time to determine whether there are signs of discomfort or fatigue; S3.

2. When physiological feedback shows that the user is uncomfortable due to long-term wearing or intense movements, the helmet adjusts the tightness through a micro-mechanical device; S3.3, combining ambient light and physiological feedback, when the user's body temperature rises, the heat dissipation inside the helmet is turned on to adjust the temperature; S4. Content presentation adjustment based on task priority: S4.

1. The AI ​​module built into the helmet analyzes tactical mission scenarios, identifies the priority of current tasks including enemy alerts and team instructions, and prioritizes the display of important mission information; S4.

2. Dynamically adjust the brightness, position and size of the displayed content based on the head tracking and physiological feedback system; S4.

3. Switch the presentation mode of AR content according to different mission requirements, including mission mode to display tactical information and rest mode to reduce visual burden.

2. The method for adjusting a tactical AR helmet according to claim 1, characterized in that The method for establishing the initial spatial coordinates includes: fusing multiple sensors built into the helmet, including an inertial measurement unit (IMU), a visual sensor, and a laser ranging sensor, and the IMU is used to obtain preliminary posture information of the head movement by capturing the angular velocity and acceleration data of the head in real time.

3. The method for adjusting a tactical AR helmet according to claim 2, characterized in that The visual sensor is used to capture feature points in the surrounding environment, combined with a laser ranging sensor to calculate the relative distance change between the head and objects in the environment, and the initial three-dimensional space coordinates are constructed using the feature point coordinates. The data fusion and calibration between the built-in sensors of the helmet are realized through the formula: Among them, C s (t) represents the spatial coordinates after fusion and correction at time t, D i (t) is the relative distance measured by the i-th sensor at time t, R i (t) is the coordinate value of the environmental reference point corresponding to the sensor, indicating the relative position from the feature point to the user's head. α is the attenuation factor when fusing data between sensors, which controls the rate at which sensor data decays over time. F(·) is the fusion function within the system, which is used to integrate multi-sensor data to correct the position error of the head.

4. The method for adjusting a tactical AR helmet according to claim 1, characterized in that The method used to determine whether there are signs of wearing discomfort or fatigue is: S1. First, the heart rate sensor monitors the user's heart rate fluctuations in real time and calculates the real-time heart rate change rate using the formula: Where H(t) represents the heart rate change rate at time t, R(t) is the user's instant heart rate value at time t, and R avg is the user's historical average heart rate, indicating the user's baseline heart rate when not stressed or fatigued. Δt is the time interval from t0 to t. The deviation of the heart rate is calculated by integration to detect whether the user has abnormal heart rate fluctuations. S2. Secondly, the body temperature sensor monitors the temperature changes in the user's head area, and combines the body temperature fluctuations during activities to calculate the local overheating degree of the user's wearing area through the following formula: Among them, t local (t) is the local temperature of the user's head wearing area at time t, t0 is the user's initial body temperature, which represents the reference temperature of the head area when not wearing a helmet or in a static state, β is the temperature response coefficient, which reflects the sensitivity of body temperature to user movement, P(t) is the user's activity temperature curve at time t, which represents the dynamic change of body temperature during the activity, and P rest This is the user's baseline temperature curve in a resting state; S3. Finally, the skin electrical sensor reflects the user's emotions and stress state by monitoring the change of skin resistance; the change of skin resistance is calculated by the following formula: Wherein, E(t) is the rate of change of skin resistance at time t, reflecting the skin electrical response of the user at time t; γ is the pressure sensitivity coefficient, indicating the sensitivity of skin resistance to pressure; G(t) is the instantaneous skin resistance value of the user at time t, representing the conductive properties of the skin under different pressure states.

5. The method for adjusting a tactical AR helmet according to claim 1, characterized in that The built-in AI module performs real-time analysis of tactical tasks, and combines natural language processing (NLP), image recognition, and audio signal processing to perceive dynamic changes in mission scenarios in multiple dimensions.

6. The method for adjusting a tactical AR helmet according to claim 5, characterized in that The image recognition technology is used. The AI ​​module captures threat targets on the battlefield through the helmet camera and updates the priority according to the importance and distance of the threat targets using the following formula: Where V(t) is the comprehensive priority of all threat targets at time t, which represents the evaluation of multiple threat sources; N in the formula V(t) is the number of threat targets detected at the same time, and W i is the importance weight of the i-th target, indicating the threat level or strategic importance of a target in the current tactical scenario. i (t) is the distance between the i-th target and the user, indicating the proximity of the threat target. The smaller the distance, the greater the threat. i (t) is the duration after the target appears, indicating how long the threat exists, and λ is the time decay coefficient, indicating the rate at which the target threat weakens over time.

7. The method for adjusting a tactical AR helmet according to claim 5, characterized in that The audio sensor is used to capture audio signals including explosions and calls in the battlefield in real time, and the threat level of the audio signals is analyzed by the AI ​​algorithm; the priority display weight of the audio signal is calculated by the following formula: Where A(t) is the priority display weight of the audio signal at time t, indicating the relative importance of the audio signal in the tactical mission, and S audio (t) is the audio signal strength at time t, reflecting the threat intensity of the audio source, including the volume of the explosion or gunshot, μ is the attenuation coefficient of the audio signal, indicating that the importance of the audio signal decays over time, and t0 is the time point when the audio signal is first detected.

Images