Stability regulation and control method of camera system

Abstract

The invention discloses a stability regulation and control method for a camera system, and the method comprises the following steps: S1, collecting the installation position information of the camera system in real time through a multi-source sensor array, the installation position information comprising terrain elevation data, a base vibration frequency spectrum, and environment temperature and humidity distribution parameters; s2, constructing a three-dimensional stability evaluation model, and inputting the installation position information into the three-dimensional stability evaluation model to generate a stability coefficient matrix; and when any dimension parameter in the stability coefficient matrix exceeds a preset safety threshold value, activating the self-balance adjusting mechanism to perform multi-degree-of-freedom compensation adjustment. According to the invention, through fusion of environment perception, intelligent prediction and multi-mode cooperative compensation, the core problems of insufficient stability, response lag and single protection means of a traditional regulation and control method in a complex dynamic environment are solved.

Description

Technical Field

[0001] The present invention relates to the field of stability regulation, and particularly to a method for regulating the stability of a camera system. Background Art

[0002] Camera systems are widely used in fields such as security monitoring, industrial inspection, and film shooting. Among them, automatic following camera systems achieve continuous tracking of moving targets through the integration of vision recognition, sensors (such as gyroscopes, accelerometers), and servo control technologies. Such systems rely on the multi-degree-of-freedom movement of the pan-tilt head (such as pitching, rotation) to keep the position of the target stable in the frame. However, in complex dynamic environments (such as strong winds, mechanical vibrations, terrain undulations), external disturbances can easily cause the attitude of the pan-tilt head to become unstable, resulting in problems such as image jitter, target loss, or blurred imaging, severely restricting the reliability and application scope of the system. Therefore, a stability regulation method is needed to intelligently regulate the stability of the camera system.

[0003] In the existing stability regulation methods, a single compensation strategy is mostly adopted in the stability regulation process, resulting in poor stability regulation effects, which has a certain impact on the use of the stability regulation method. Therefore, a method for regulating the stability of a camera system is proposed. Summary of the Invention

[0004] The technical problem to be solved by the present invention is: how to solve the problem that in the existing stability regulation methods, a single compensation strategy is mostly adopted in the stability regulation process, resulting in poor stability regulation effects, and a method for regulating the stability of a camera system is provided.

[0005] The present invention solves the above technical problems through the following technical solutions. The present invention includes the following steps: S1: Real-time collect the installation position information of the camera system through a multi-source sensor array, and the installation position information includes terrain elevation data, pedestal vibration frequency spectrum, and environmental temperature and humidity distribution parameters; S2: Construct a three-dimensional stability evaluation model, input the installation position information into the three-dimensional stability evaluation model to generate a stability coefficient matrix; when any dimension parameter in the stability coefficient matrix exceeds the preset safety threshold, activate the self-balancing adjustment mechanism for multi-degree-of-freedom compensation adjustment; S3: The camera system performs following monitoring. During the following monitoring process, real-time collect the frequency domain characteristics of the pan-tilt head movement trajectory through a dynamic frequency analysis module, establish a mapping relationship between the movement characteristics and stability, and generate an adaptive damping adjustment instruction based on the mapping relationship between the movement characteristics and stability; S4: Use an inertial measurement unit to real-time monitor the dynamic change rate of the rotation angle of the pan-tilt head of the camera system. When it is detected that the angle change rate exceeds the preset critical curve, trigger the pre-tightening force compensation mechanism and generate reverse torque compensation parameters; S5: Establish an abnormal state classification response mechanism. When the system stability margin is lower than the first warning threshold, start the first-level compensation strategy. When it is lower than the second emergency threshold, switch to the safety lock mode and generate a fault location report.

[0006] Furthermore, the construction process of the three-dimensional stability evaluation model in S2 is as follows: Perform terrain adaptability calculation. Calculate the stress distribution under different terrain conditions through finite element analysis, and define the terrain adaptability factor as: ; α is the terrain adaptability factor, which is used to quantify the adaptability degree of the installation position to the stability of the camera system (0 ≤ α ≤ 1); is the material yield strength of the support structure of the camera system; is the actual stress value at the i-th finite element grid node (unit: MPa); N is the total number of nodes divided by the finite element mesh; Perform vibration response prediction. Use the transfer function method to establish the correlation model between the pedestal vibration and the pan-tilt shake, and define the vibration transfer gain as: ; In the formula, is the vibration transfer gain (unit: dB), which represents the amplification effect of the pedestal vibration transferred to the pan-tilt; is the vibration power spectral density of the pan-tilt, is the vibration power spectral density of the pedestal; When the adaptability factor α of any dimension < 0.8 or the vibration gain , trigger the self-balancing adjustment mechanism.

[0007] Furthermore, the analysis process of the dynamic frequency analysis module is as follows: Collect three-axis vibration data through the acceleration sensor group at a sampling rate of 1000Hz; Collect the three-axis vibration acceleration signal a(t) at a sampling rate of 1000Hz, and construct the frequency domain feature vector F through Fourier transform: ; In the formula: is the frequency domain feature vector (complex vector), which characterizes the energy distribution of the vibration signal at different frequencies, is the sampling window duration (unit: second), time domain vibration acceleration signal (unit: m / s²), is the frequency value of the k-th frequency point (unit: Hz), j is the imaginary unit, satisfying ; Input F into a pre-trained Convolutional Neural Network (CNN) to output a stability score S: ; Where S is the stability score, and the higher the score, the better the stability. is the i-th frequency domain feature vector; wi is the i-th weight parameter in the convolutional neural network, and b is the bias term of the neural network; ReLU is the rectified linear unit activation function, defined as ReLU(x) = max(0, x); When S < S threshold generate an adaptive damping adjustment instruction.

[0008] Furthermore, the specific process of S4 is as follows: Establish a differential equation for the rate of change of angle: ; Where is the rate of change of the rotation angle of the pan-tilt, θ is the rotation angle of the pan-tilt, is the torque output by the drive motor, is the equivalent torque caused by environmental interference (such as wind resistance, mechanical friction), J is the moment of inertia of the rotating components of the pan-tilt (unit: kg·m²), and K is the system transmission ratio constant; When it is detected that calculate the compensation torque : ; Where is the preset desired rate of change of angle, is the actually measured rate of change of angle; Apply the required compensation torque through the brushless motor set, and adjust the PWM duty cycle of the motor winding in real time: ; Where D is the PWM duty cycle of the brushless motor winding, K t is the motor torque constant, I max is the maximum allowable working current of the motor.

[0009] Furthermore, the specific process of the abnormal state classification response mechanism in S5 is as follows: Define the stability margin M: ; Where S current is the real-time stability score, and S max is the maximum score; When 30% ≤ M < 50%, execute the first-level compensation strategy: increase the proportional gain K of the PID controller p to 1.5 times, and control the rotational speed ω of the auxiliary balance wheel: ; In the formula, is the rotational speed coefficient (rpm / √rad), is the angle deviation (rad), is the maximum allowable deviation (rad), K p is the initial proportional gain of the PID controller, and its value is determined by calibrating the system dynamic characteristics or experimental optimization; When M < 30%, execute the second-level compensation strategy, switch to the hydraulic locking mode, and the process of controlling the hydraulic cylinder pressure P is: ; In the formula, P is the locking pressure of the hydraulic cylinder (unit: Pa), is the locking force required by the design (unit: N), is the cross-sectional area of the hydraulic cylinder piston (unit: m²), t is the duration of the locking action (unit: second), is the time constant.

[0010] Furthermore, the method further includes constructing a digital twin system with dynamic deformation coupling, and the specific process is as follows: Collect the strain components of the support structure in real time through a distributed fiber optic sensor , and construct a three-dimensional deformation gradient tensor

[0011] Solve the deformation-stability coupling equation: ; In the formula, is the initial stability score, S is the real-time stability score, k is the deformation sensitivity coefficient, is the trace of the deformation gradient tensor (representing the volume deformation rate), and α is the torque compensation weight; When it is predicted that S(t + Δt) < S within the future Δt time threshold , execute multimodal compensation in advance, that is, start the piezoelectric ceramic array to apply a reverse deformation field: ; Among them, is the piezoelectric compensation gain; Synchronously adjust the of the brushless motor as: , where is the torque coupling coefficient.

[0012] Furthermore, the method further includes a cloud-edge collaborative deformation compensation network, and the specific process is as follows: Encapsulate the deformation gradient tensor collected by the distributed fiber optic sensor and into an encrypted data packet, and the encryption algorithm is: ; is the encrypted data packet (binary data stream), is the dynamically generated 256-bit encryption key (hexadecimal string), is the deformation gradient tensor, and || is the data concatenation symbol; The cloud solves the optimization problem: ; In the formula, λ and μ are weight coefficients used to balance the optimization objectives of deformation and torque compensation, and are the optimized piezoelectric compensation gain and torque coupling coefficient; Send the optimized β and γ back to the edge node to control the piezoelectric ceramic and the brushless motor to perform composite compensation.

[0013] The present invention has the following advantages compared with the prior art: The stability control method of the camera system realizes all-round environmental adaptability adjustment by collecting terrain, vibration and environmental parameters in real time through a multi-source sensor array and combining with a three-dimensional stability evaluation model, significantly improving the stability of the camera system in complex scenarios. Using finite element analysis, frequency domain feature extraction and convolutional neural network technology, high-precision stability scoring and anomaly prediction are realized to ensure that the system responds in time to potential instability risks. By real-time monitoring the angle change rate and vibration characteristics, self-balancing adjustment, damping optimization and reverse torque compensation are triggered to effectively suppress environmental interference (such as wind resistance and mechanical vibration) and ensure the smooth movement of the pan-tilt. Based on the stability margin, multiple warning thresholds are divided, and multi-modal compensation strategies such as PID gain optimization and hydraulic locking are adopted to realize progressive safety protection from warning to emergency locking, reducing the risk of system out-of-control. By using the digital twin system to map physical deformation data in real time, combining cloud optimization algorithms and edge execution, deformation-torque coupling compensation is realized, enhancing the system's anti-deformation ability and remote control efficiency. Integrating encrypted data transmission, multi-modal sensing and intelligent algorithms, breaking through the traditional single protection mode, providing a full-link closed-loop control from data collection, analysis to execution, improving the system's reliability and maintenance convenience, thereby realizing high stability, fast response and intelligent management of the camera system in complex environments, significantly superior to the protection ability and adaptability of the prior art, making the system more worthy of popularization and use. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is the flowchart of the present invention. Detailed implementation manners

[0015] The embodiments of the present invention will be described in detail below. These embodiments are implemented on the premise of the technical solution of the present invention, and detailed implementation manners and specific operation processes are given. However, the protection scope of the present invention is not limited to the following embodiments.

[0016] As Figure 1 shown, this embodiment provides a technical solution: a method for regulating the stability of a camera system, including the following steps: S1: Real-time collect the installation position information of the camera system through a multi-source sensor array, where the installation position information includes terrain elevation data, pedestal vibration frequency spectrum, and environmental temperature and humidity distribution parameters; S2: Construct a three-dimensional stability evaluation model, input the installation position information into the three-dimensional stability evaluation model to generate a stability coefficient matrix; when any dimension parameter in the stability coefficient matrix exceeds the preset safety threshold, activate the self-balancing adjustment mechanism to perform multi-degree-of-freedom compensation adjustment; S3: The camera system performs follow-up monitoring. During the follow-up monitoring process, the frequency domain characteristics of the pan-tilt movement trajectory are real-time collected through a dynamic frequency analysis module, a mapping relationship between the movement characteristics and the stability is established, and an adaptive damping adjustment instruction is generated based on the mapping relationship between the movement characteristics and the stability; S4: Use an inertial measurement unit to real-time monitor the dynamic change rate of the pan-tilt rotation angle of the camera system. When it is detected that the angle change rate exceeds the preset critical curve, trigger the pre-tightening force compensation mechanism and generate reverse torque compensation parameters; S5: Establish an abnormal state hierarchical response mechanism. When the system stability margin is lower than the first warning threshold, start the first-level compensation strategy. When it is lower than the second emergency threshold, switch to the safety lock mode and generate a fault location report.

[0017] The construction process of the three-dimensional stability evaluation model in S2 is as follows: Perform terrain adaptability calculation. Calculate the stress distribution under different terrain conditions through finite element analysis, and define the terrain adaptability factor as: ; α is the terrain adaptability factor, which is used to quantify the adaptability degree of the installation position to the stability of the camera system (0 ≤ α ≤ 1); is the material yield strength of the camera system support structure; is the actual stress value (unit: MPa) at the i-th finite element mesh node; N is the total number of nodes divided by the finite element mesh; Vibration response prediction is carried out. The transfer function method is used to establish the correlation model between the pedestal vibration and the pan-tilt shaking. The vibration transfer gain is defined as: ; In the formula, is the vibration transfer gain (unit: dB), representing the amplification effect of the pedestal vibration transmitted to the pan-tilt; is the vibration power spectral density of the pan-tilt, is the vibration power spectral density of the pedestal; When the adaptation factor α of any dimension is less than 0.8 or the vibration gain , the self-balancing adjustment mechanism is triggered; The terrain stress distribution is calculated by finite element analysis, and the terrain adaptation factor α is defined to quantify the adaptation degree of different terrains to the stability of the camera system. It can avoid the risk of overload or inclination of the support structure caused by uneven terrain or soft geology, and ensure the optimal selection of the system installation position.

[0018] When installing the camera system in complex terrain in the wild, the system calculates the α value in real time. If it detects that α < 0.8 in a certain area (such as stress concentration in soft soil area), it will automatically prompt to adjust the installation point or activate the pedestal reinforcement module to prevent structural deformation.

[0019] The correlation model between the pedestal vibration and the pan-tilt shaking is established by the transfer function method, and the vibration transfer gain Gv is quantified to predict in advance the amplification effect of vibration on the pan-tilt stability. It can significantly reduce the interference of external vibrations (such as mechanical vibrations, vehicle passage) on the camera image.

[0020] In the bridge monitoring scenario, when the vehicle passage causes the pedestal vibration, the system detects (the vibration transfer is too strong), and immediately triggers the self-balancing mechanism for multi-degree-of-freedom compensation to offset the vibration energy and ensure the smoothness of the pan-tilt image.

[0021] Through the dual mechanisms of terrain adaptation and vibration prediction, the installation risks are avoided from the source and the external interference is dynamically suppressed, significantly improving the reliability and anti-interference ability of the camera system in complex environments.

[0022] The analysis process of the dynamic frequency analysis module is as follows: The triaxial vibration data is collected by the acceleration sensor group at a sampling rate of 1000 Hz; The triaxial vibration acceleration signal a(t) is collected at a sampling rate of 1000 Hz, and the frequency domain feature vector F is constructed through Fourier transform: ; In the formula: is the frequency domain feature vector (complex vector), representing the energy distribution of the vibration signal at different frequencies, is the sampling window duration (unit: seconds), Time domain vibration acceleration signal (unit: m / s²), is the frequency value of the kth frequency point (unit: Hz), j is an imaginary unit, satisfying ; Input F into the pre-trained convolutional neural network (CNN) and output the stability score S: ; In the formula, S is the stability score, and the higher the score, the better the stability. is the i-th frequency domain eigenvector; wi is the i-th weight parameter in the convolutional neural network, and b is the bias term of the neural network; in security monitoring in areas prone to abnormal vibrations ReLU is the rectified linear unit activation function, defined as ReLU(x)=max(0,x); When S<S threshold When the adaptive damping adjustment command is generated, S threshold is the preset stability score threshold; The three-axis vibration data is collected by the acceleration sensor at a high sampling rate of 1000Hz, and the frequency domain features are extracted by Fourier transform to comprehensively analyze the vibration energy distribution, avoiding the missed detection problem of traditional time domain analysis.

[0023] For example, in a highway monitoring scenario, heavy trucks may cause high-frequency vibrations (such as instantaneous impacts above 200 Hz) when they pass by. The system can quickly identify the energy peaks of abnormal frequency bands through the frequency domain feature vector F, accurately locate the vibration source, and prevent the gimbal from blurring the image due to high-frequency jitter.

[0024] A pre-trained convolutional neural network (CNN) is used to perform nonlinear modeling of frequency domain features, output a dynamic stability score, and trigger adaptive damping adjustment based on the threshold to achieve closed-loop control from perception to compensation.

[0025] For example, in typhoon weather, the camera system's gimbal produces low-frequency shaking (such as 5-10Hz) due to strong wind interference. The CNN model analyzes the frequency domain characteristics and determines that the stability score S is less than the threshold. It immediately generates a damping adjustment instruction to increase the gimbal damping coefficient, suppress low-frequency swing, and ensure image stability.

[0026] Through high-frequency vibration analysis and intelligent scoring mechanism, rapid identification and targeted compensation of complex vibration patterns are achieved, significantly improving the camera system's active anti-vibration capability and image stability in dynamic interference environments.

[0027] The specific process of S4 is as follows: Establish the differential equation for the rate of change of angle: ; Wherein, is the change rate of the rotation angle of the pan-tilt, θ is the rotation angle of the pan-tilt, is the torque output by the driving motor, is the equivalent torque caused by environmental interference (such as wind resistance and mechanical friction), J is the moment of inertia of the rotating components of the pan-tilt (unit: kg·m²), and K is the system transmission ratio constant; When detecting , calculate the compensation torque : ; Wherein, is the preset expected angle change rate, is the actually measured angle change rate; is the preset expected angle, is the actually measured angle; Apply the compensation torque through the brushless motor set, and adjust the PWM duty cycle of the motor winding in real time: ; Wherein, D is the PWM duty cycle of the brushless motor winding, K t is the motor torque constant, I max is the maximum allowable working current of the motor; By establishing a differential equation of the angle change rate, the dynamic change rate of the rotation angle of the pan-tilt of the fixed camera system is monitored in real time, and combined with the equivalent calculation of the environmental interference torque (such as strong wind and mechanical friction), the rapid detection and compensation of the angle deviation are realized. It can effectively avoid the pan-tilt jitter or picture deviation caused by sudden interference (such as strong wind and equipment vibration).

[0028] For example, in the outdoor monitoring and tracking scenario in coastal areas, the strong wind causes the change rate of the rotation angle of the fixed pan-tilt to suddenly increase. The system immediately calculates the reverse compensation torque and applies the reverse torque through the brushless motor, so that the pan-tilt can return to the preset angle within 0.2 seconds, ensuring that the monitoring picture is stable and without ghosting.

[0029] Through the dynamic adjustment of the PWM duty cycle of the brushless motor set, the compensation torque is accurately converted into a motor drive signal, realizing a compensation action with high response speed and low delay, and ensuring the smooth movement of the pan-tilt in a fixed scenario.

[0030] In the monitoring of urban traffic intersections, the vibration of the ground caused by a heavy truck passing by leads to an abnormal change rate of the pan-tilt angle. The system generates a PWM duty cycle command according to the compensation formula, and the motor quickly outputs a reverse torque to offset the angle deviation caused by the vibration, keeping the picture stable and clear.

[0031] Through a triple mechanism of dynamic monitoring, precise modeling, and efficient execution, rapid identification and active compensation for abnormal pan-tilt rotation of a fixed camera system are achieved, significantly enhancing its anti-offset ability and control accuracy in interference environments such as strong winds and vibrations, and ensuring the continuity and reliability of image acquisition.

[0032] The specific process of the abnormal state classification response mechanism in S5 is as follows: Define the stability margin M: ; where S current is the real-time stability score, and S max is the maximum score; When 30% ≤ M < 50%, execute the first-level compensation strategy: increase the proportional gain K_p of the PID controller to 1.5 times and control the rotation speed ω of the auxiliary balance wheel: in high-incidence areas ; In the formula, is the speed coefficient (rpm / √rad), is the angle deviation (rad), is the maximum allowable angle deviation (rad), and K p is the initial proportional gain of the PID controller, and its value is determined by calibrating the system dynamic characteristics or experimental optimization; When M < 30%, execute the second-level compensation strategy, switch to the hydraulic locking mode, and control the hydraulic cylinder pressure P. The process of controlling the hydraulic cylinder pressure P is as follows: ; is the locking force required by the design (unit: N), is the cross-sectional area of the hydraulic cylinder piston (unit: m²), t is the duration of the locking action (unit: seconds), is the time constant; The classification response enhances the system's toughness: by defining the stability margin M and dividing multiple warning thresholds (first-level compensation when 30% ≤ M < 50%, second-level compensation when M < 30%), a progressive protection from warning to emergency locking is achieved, avoiding insufficient response or over-intervention of a single strategy, and enhancing the system's fault tolerance in a continuous abnormal state.

[0033] For example, in a fixed monitoring scenario, when equipment vibration causes the stability margin M to drop to 40%, the system automatically increases the PID proportional gain and accelerates the rotation of the balance wheel to quickly suppress the angle deviation caused by vibration; if the vibration further intensifies and M drops to 25%, it immediately switches to the hydraulic locking mode and fixes the pan-tilt through the hydraulic cylinder pressure to prevent equipment damage.

[0034] Dynamic Parameter Optimization and Emergency Locking: The primary compensation strategy achieves active deviation correction by adjusting the PID gain and the balance wheel speed. The secondary compensation strategy ensures reliable locking in emergency situations through a hydraulic locking pressure curve (such as exponential progressive pressurization), taking into account both rapid response and equipment protection.

[0035] In the security monitoring of areas prone to abnormal vibrations, at the initial stage of vibration, the pan-tilt head shakes (M = 35%), and the system automatically increases the PID control gain. The balance wheel counteracts the shake at an adaptive speed. If the vibration continues to escalate (M = 20%), the hydraulic cylinder gradually pressurizes to lock the pan-tilt head according to the preset pressure curve, preventing damage to the mechanical structure due to instantaneous impact.

[0036] Through a hierarchical response mechanism and a multi-modal compensation strategy, a full-link protection from active deviation correction to emergency locking is achieved, significantly enhancing the stability and security of the fixed camera system under continuous or sudden abnormal conditions, and ensuring the continuity of image acquisition and the reliability of equipment in critical scenarios.

[0037] The method also includes constructing a digital twin system with dynamic deformation coupling, and the specific process is as follows: Collect the strain components of the support structure in real time through distributed fiber optic sensors , and construct a three-dimensional deformation gradient tensor

[0038] Solve the deformation-stability coupling equation: ; In the formula, is the initial stability score, S is the real-time stability score, k is the deformation sensitivity coefficient, is the trace of the deformation gradient tensor (representing the volume deformation rate), and α is the torque compensation weight; When it is predicted that S(t + Δt) < S within the future Δt time threshold , execute multi-modal compensation in advance, that is, start the piezoelectric ceramic array to apply a reverse deformation field: ; Among them, is the piezoelectric compensation gain; Synchronously adjust the of the brushless motor as: , where is the torque coupling coefficient; Deformation-Stability Coupling Prediction and Active Compensation: Real-time monitor the three-dimensional strain of the support structure through distributed fiber optic sensors, combine with the digital twin system to predict the impact of deformation on stability, and start the piezoelectric ceramics to apply a reverse deformation field in advance to avoid system instability caused by sudden deformation.

[0039] In the fixed monitoring scenario of a large bridge, the bridge body undergoes slight deformation due to the day-night temperature difference (such as the stretching of the support structure). The system predicts through digital twin that the stability score S will be lower than the threshold within the next 10 minutes, and immediately controls the piezoelectric ceramic array to generate a reverse deformation field to offset the thermal expansion and contraction effect, ensuring that the pan-tilt angle has no deviation.

[0040] Dynamically couple deformation compensation (piezoelectric ceramics) and torque compensation (brushless motors), and through parameter optimization, achieve the collaborative suppression of deformation and torque, improving the comprehensive anti-interference performance of the system in complex mechanical environments.

[0041] In the vibration monitoring scenario of an industrial plant, the operation of heavy equipment causes the superposition of local deformation and vibration of the support structure. The system synchronously adjusts the deformation compensation amount of the piezoelectric ceramics and the compensation torque of the brushless motor , eliminating the influence of composite interference on the stability of the pan-tilt and ensuring that the high-definition image has no distortion.

[0042] Through the deformation prediction and multi-modal compensation linkage mechanism of the digital twin system, the early intervention and dynamic suppression of the deformation of the support structure are realized, significantly improving the anti-deformation ability and stability of the fixed camera system in long-term load, temperature change or composite interference environments, and avoiding image distortion or equipment damage caused by structural deformation.

[0043] The method further includes a cloud-edge collaborative deformation compensation network, and its specific process is as follows: Encapsulate the deformation gradient tensor collected by the distributed fiber optic sensor and into an encrypted data packet, and the encryption algorithm is: ; is the encrypted data packet (binary data stream), is the dynamically generated 256-bit encryption key (hexadecimal string), is the deformation gradient tensor, and || is the data concatenation symbol; The cloud solves the optimization problem: ; In the formula, λ and μ are weight coefficients used to balance the optimization objectives of deformation and torque compensation, and are the optimized piezoelectric compensation gain and torque coupling coefficient; Return the optimized and to the edge node to control the piezoelectric ceramics and brushless motors to perform composite compensation.

[0044] Dynamically encrypt the deformation gradient tensor and compensation torque through the AES256 encryption algorithm to ensure that sensitive data is tamper-proof and theft-proof during cloud-edge transmission, and safeguard the security of the system data chain.

[0045] For example, in the monitoring scenario of a transportation hub, when the system detects abnormal deformation data of the support structure, it encrypts the data packet with a dynamically generated 256-bit key and uploads it to the cloud. Even if the network is attacked, the encrypted data cannot be cracked, avoiding the cloud platform from getting out of control due to malicious tampering of the compensation parameters.

[0046] The cloud solves the global optimization problem based on the weight coefficients of deformation and torque, and sends back the optimal compensation parameters to the edge nodes to achieve the global optimal coordination of deformation and torque compensation, breaking through the computing power limitation of a single node.

[0047] Example: In security monitoring, multiple camera systems detect the coupling interference of deformation and vibration of the support structure. The cloud centrally analyzes the data of all nodes and optimizes and parameters and then distributes them to each edge node to ensure the consistency and efficiency of the compensation strategy in the entire area.

[0048] Through the edge nodes to execute the piezoelectric ceramic compensation and brushless motor torque compensation optimized by the cloud in real time, rapid response and precise cancellation under complex interference are achieved.

[0049] For example, during the monitoring and tracking near a substation, sudden electromagnetic interference causes high-frequency deformation of the support structure. Based on the β and γ parameters optimized by the cloud, the edge node synchronously controls the piezoelectric ceramic array to generate a reverse deformation field and adjusts the output compensation torque of the brushless motor to eliminate the interference effect within 0.5 seconds and ensure the stability of the equipment monitoring screen.

[0050] Through the collaborative mechanism of encrypted transmission, cloud global optimization and edge rapid execution, both the data security is guaranteed, and the dynamic coordination and precise execution of the multi-node compensation strategy are realized, significantly improving the anti-deformation ability and overall stability of the fixed camera system in complex and multi-interference scenarios, while reducing the consumption of local computing resources.

[0051] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0052] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0053] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for regulating the stability of a camera system, characterized in that, It includes the following steps: S1: Real-time collect the installation position information of the camera system through a multi-source sensor array, where the installation position information includes terrain elevation data, pedestal vibration frequency spectrum, and environmental temperature and humidity distribution parameters; S2: Construct a three-dimensional stability evaluation model, input the installation position information into the three-dimensional stability evaluation model to generate a stability coefficient matrix; when any dimension parameter in the stability coefficient matrix exceeds the preset safety threshold, activate the self-balancing adjustment mechanism for multi-degree-of-freedom compensation adjustment; S3: The camera system performs follow-up monitoring. During the follow-up monitoring process, the frequency domain characteristics of the pan-tilt movement trajectory are real-time collected through a dynamic frequency analysis module, establish a mapping relationship between the movement characteristics and stability, and generate an adaptive damping adjustment instruction based on the mapping relationship between the movement characteristics and stability; S4: Use an inertial measurement unit to real-time monitor the dynamic change rate of the pan-tilt rotation angle of the camera system. When the detected angle change rate exceeds the preset critical curve, trigger a pre-tightening force compensation mechanism and generate reverse torque compensation parameters; S5: Establish an abnormal state classification response mechanism. When the system stability margin is lower than the first warning threshold, start a primary compensation strategy. When it is lower than the second emergency threshold, switch to the safety lock mode and generate a fault location report.

2. The stability regulation method of a camera system according to claim 1, characterized in that: The construction process of the three-dimensional stability evaluation model in S2 is as follows: Perform terrain adaptability calculation, calculate the stress distribution under different terrain conditions through finite element analysis, and define the terrain adaptability factor ; Perform vibration response prediction, establish the correlation model between the pedestal vibration and the gimbal shake by using the transfer function method, and define the vibration transfer gain ; When the adaptation factor of any dimension or the vibration gain is reached, the self-balancing adjustment mechanism is triggered.

3. The stability regulation method of a camera system according to claim 2, characterized in that: The analysis process of the dynamic frequency analysis module is as follows: Collect triaxial vibration data through an acceleration sensor group at a preset sampling rate; Collect triaxial vibration acceleration signals a(t) at a preset sampling rate, and construct a frequency domain feature vector F through Fourier transform; Input F into a pre-trained convolutional neural network and output a stability score S; When S < S threshold an adaptive damping adjustment command is generated.

4. The stability regulation method of a camera system according to claim 3, characterized in that: The specific process of S4 is: Establish an angle change rate differential equation: ； When is detected, calculate the compensation torque : ； Apply the torque to be compensated by a brushless motor set , and adjust the PWM duty ratio D of the motor winding in real time.

5. A method for regulating the stability of a camera system according to claim 1, characterized in that: The specific process of the abnormal state classification response mechanism in S5 is: Define the stability margin M; When 30% ≤ M < 50%, execute the first-level compensation strategy: increase the proportional gain K of the PID controller p to 1.5 times and control the rotational speed ω of the auxiliary balance wheel; When M < 30%, execute a secondary compensation strategy, switch to the hydraulic lock mode, and control the hydraulic cylinder pressure P.

6. The stability control method of a camera system according to claim 4, characterized in that: The method further includes constructing a digital twin system with dynamic deformation coupling, and its specific process is as follows: Real-time acquisition of the strain components of the support structure through a distributed fiber optic sensor , and constructing a three-dimensional deformation gradient tensor ; Solve the deformation-stability coupling equation: ； When it is predicted that S(t + Δt) < S within the future time Δt threshold , perform multimodal compensation in advance, that is, activate the piezoelectric ceramic array to apply a reverse deformation field: ； Among them, is the piezoelectric compensation gain; Synchronous adjustment of the brushless motor is as follows: , where is the torque coupling coefficient.

7. A method for regulating the stability of a camera system according to claim 6, characterized in that: The method further includes a cloud-edge collaborative deformation compensation network, and its specific process is: The deformation gradient tensor collected by the distributed fiber optic sensor and are encapsulated into an encrypted data packet, and then cloud-based solution optimization is performed. After the optimization is completed, the optimized β and γ are sent back to the edge node to control the piezoelectric ceramic and the brushless motor to perform composite compensation.

Images