Anti-shake method and device for electronic rearview mirror, electronic equipment and storage medium

Abstract

The invention provides an anti-shake method and device of an electronic rearview mirror, electronic equipment and a storage medium, the method comprises the following steps: obtaining current inertial navigation data of the electronic rearview mirror and historical estimation parameters of a previous moment, the current inertial navigation data comprising angular velocity data and acceleration data, performing multi-scale decomposition on the current inertial navigation data, and obtaining a historical estimation parameter of the previous moment; the method comprises the steps of obtaining multiple pieces of scale transformation data of different decomposition types, fusing the scale transformation data of the same scale feature in the same decomposition type to obtain fused data, performing reconstruction based on the fused data corresponding to different decomposition types to obtain a to-be-detected fused signal, and performing jitter detection according to the to-be-detected fused signal and historical estimation parameters to obtain a jitter detection result. Obtaining a jitter detection result of the electronic rearview mirror; through multi-scale decomposition of the current inertial navigation data and data fusion based on scales and decomposition types, different frequency components in the data can be better captured, and the accuracy and robustness of data fusion are improved, so that the accuracy of jitter detection is improved.

Description

Technical Field

[0001] This application relates to the technical field of electronic rearview mirrors, and particularly to an anti-shake method, device, electronic device and storage medium for an electronic rearview mirror. Background Art

[0002] With the continuous development of automotive technology, the limitations of traditional optical rearview mirrors have gradually emerged, especially when encountering complex road conditions during vehicle driving. Traditional optical rearview mirrors are easily affected by vehicle vibrations, resulting in jitter phenomena, which affect the driver's observation of the rear road conditions and may even cause safety hazards due to blurred vision.

[0003] With the development of electronic technology, electronic rearview mirrors have gradually emerged, but there are still deficiencies in the anti-shake performance of electronic rearview mirrors, and the problem of image instability caused by vehicle vibrations has not been completely overcome. Summary of the Invention

[0004] This application provides an anti-shake method, device, electronic device and storage medium for an electronic rearview mirror to solve the technical problem that the electronic rearview mirror is prone to jitter during vehicle driving.

[0005] In some embodiments of this application, an anti-shake method for an electronic rearview mirror is provided, including: obtaining the current inertial navigation data of the electronic rearview mirror and the historical estimation parameters at the previous moment, where the current inertial navigation data includes angular velocity data and acceleration data; performing multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types; fusing the scale transformation data with the same scale feature in the same decomposition type to obtain fusion data, and reconstructing based on the fusion data corresponding to different decomposition types to obtain a signal to be detected for fusion; performing jitter detection based on the signal to be detected for fusion and the historical estimation parameters to obtain the jitter detection result of the electronic rearview mirror.

[0006] In some embodiments of this application, performing multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types includes: performing wavelet transform on the angular velocity data to obtain a first approximation coefficient and a first detail coefficient with different scale features; performing wavelet transform on the acceleration data to obtain a second approximation coefficient and a second detail coefficient with different scale features; where the decomposition type includes an approximation coefficient type and a detail coefficient type, and the scale transformation data includes the first approximation coefficient and the second approximation coefficient of the approximation coefficient type, and the first detail coefficient and the second detail coefficient of the detail coefficient type.

[0007] In some embodiments of the present application, the scale transformation data of the same scale feature in the same decomposition type is fused to obtain fused data, including: weighting the first approximation coefficient and the second approximation coefficient of the same scale feature based on a preset weight coefficient to obtain an approximate fusion parameter; determining the maximum value among the absolute value of the first detail coefficient and the absolute value of the second detail coefficient of the same scale feature as the detail fusion parameter; wherein the fused data includes the approximate fusion parameter and the detail fusion parameter.

[0008] In some embodiments of the present application, a to-be-detected fusion signal is reconstructed based on the fused data corresponding to different decomposition types, including: determining the detail reconstruction parameter of the same scale feature based on the preset scale function and the detail fusion parameter of the same scale feature; determining the approximate reconstruction parameter of the same scale feature according to the preset wavelet basis function and the approximate fusion parameter of the same scale feature; reconstructing based on the detail reconstruction parameters of different scale features and the approximate reconstruction parameters of different scale features to obtain a to-be-detected fusion signal.

[0009] In some embodiments of the present application, jitter detection is performed according to the to-be-detected fusion signal and the historical estimation parameter to obtain the jitter detection result of the electronic rearview mirror, including: the historical estimation parameter includes a historical estimation state vector and a historical posterior estimation covariance; constructing a current measurement state vector based on the to-be-detected fusion signal and the derivative of the to-be-detected fusion signal; determining a current estimation state vector according to the historical posterior estimation covariance, the historical estimation state vector, and the current measurement state vector; if the absolute value of at least one estimated element in the current estimation state vector is greater than the corresponding preset jitter threshold, then determining the jitter detection result of the electronic rearview mirror as a jitter phenomenon occurring.

[0010] In some embodiments of the present application, determining a current estimation state vector according to the historical posterior estimation covariance, the historical estimation state vector, and the current measurement state vector includes: determining a current prior estimation covariance according to the historical posterior estimation covariance, the state transition matrix of the preset state equation, and the preset process noise; determining a Kalman gain based on the current prior estimation covariance, the measurement matrix of the preset measurement equation, and the measurement noise covariance; determining a current prior state estimation according to the state transition matrix and the historical estimation state vector; determining a current estimation state vector based on the current prior state estimation, the Kalman gain, the measurement matrix, and the current measurement state vector.

[0011] In some embodiments of the present application, after determining that the jitter detection result of the electronic rearview mirror shows a jitter phenomenon, the method further includes: determining a jitter parameter according to the to-be-detected fusion signal, where the jitter parameter includes a jitter amplitude, a jitter frequency, and a jitter direction; and performing jitter compensation on the electronic rearview mirror based on the jitter parameter to cancel out the jitter.

[0012] In some embodiments of the present application, the present application provides an anti-jitter device for an electronic rearview mirror, including: an acquisition module configured to acquire current inertial navigation data of the electronic rearview mirror and historical estimation parameters at a previous moment, where the current inertial navigation data includes angular velocity data and acceleration data; a multi-scale decomposition module configured to perform multi-scale decomposition on the current inertial navigation data to obtain a plurality of scale transformation data of different decomposition types; a fusion and reconstruction module configured to fuse the scale transformation data of the same scale feature in the same decomposition type to obtain fusion data, and perform reconstruction based on the fusion data corresponding to different decomposition types to obtain a to-be-detected fusion signal; and a jitter detection module configured to perform jitter detection according to the to-be-detected fusion signal and the historical estimation parameters to obtain the jitter detection result of the electronic rearview mirror.

[0013] In some embodiments of the present application, the present application provides an electronic device, where the electronic device includes: one or more processors; a storage device configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the anti-jitter method of the electronic rearview mirror as described in any one of the above.

[0014] In some embodiments of the present application, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor of a computer, the computer executes the anti-jitter method of the electronic rearview mirror as described in any one of the above.

[0015] Advantages of the embodiments of the present application: The present application provides an anti-jitter method, device, electronic device, and storage medium for an electronic rearview mirror. By performing multi-scale decomposition on the current inertial navigation data including angular velocity data and acceleration data, and performing data fusion based on the scale and decomposition type and then data reconstruction, the embodiments of the present application can better capture different frequency components in the data, improve the accuracy and robustness of data fusion, and thus improve the accuracy of jitter detection.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Description of the Drawings

[0017] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application. Obviously, the accompanying drawings in the following description are only some embodiments of this application, and those of ordinary skill in the art can obtain other accompanying drawings based on these drawings without creative efforts. In the accompanying drawings:

[0018] Figure 1 A schematic diagram showing an exemplary system architecture to which the technical solution of the embodiment of this application can be applied;

[0019] Figure 2 A schematic flowchart showing the anti-shake method of an electronic rearview mirror according to an embodiment of this application;

[0020] Figure 3 A block diagram showing the anti-shake device of an electronic rearview mirror according to an embodiment of this application;

[0021] Figure 4 A schematic diagram showing the structure of a computer system of an electronic device suitable for implementing the embodiment of this application. Detailed implementation manners

[0022] The following uses specific specific examples to illustrate the implementation manners of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0023] The drawings provided in the following embodiments only illustrate the basic concept of this application schematically. Therefore, only the components related to this application are shown in the drawings, rather than being drawn according to the number, shape, and size of the components in actual implementation. The form, quantity, and proportion of each component in actual implementation can be an arbitrary change, and the layout form of its components may also be more complex.

[0024] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of this application. However, it is obvious to those skilled in the art that the embodiments of this application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of this application difficult to understand.

[0025] Please refer to Figure 1 , Figure 1 A schematic diagram showing an exemplary system architecture to which the technical solution of the embodiment of this application can be applied. AsFigure 1 As shown in the figure, the system architecture may include a motion detection module 101, a main control processor 102, an image sensor 103, and a display screen 104. Among them, the motion detection module 101 includes a gyroscope for measuring angular velocity data and an accelerometer for measuring acceleration data, and transmits them to the main control processor 102 for anti-shake control; the image sensor 103, the main control processor 102, and the display screen 104 respectively provide the functions of image perception, image processing, and image display of the electronic rearview mirror.

[0026] Exemplarily, the main control processor 102 obtains the current inertial navigation data of the electronic rearview mirror and the historical estimation parameters at the previous moment. The current inertial navigation data includes angular velocity data and acceleration data; performs multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types; fuses the scale transformation data of the same scale feature in the same decomposition type to obtain fused data, and reconstructs based on the fused data corresponding to different decomposition types to obtain a signal to be detected for fusion; performs jitter detection according to the signal to be detected for fusion and the historical estimation parameters to obtain the jitter detection result of the electronic rearview mirror.

[0027] In the related art, the electronic rearview mirror still has deficiencies in anti-shake performance and fails to completely overcome the problem of image instability caused by vehicle vibration.

[0028] To solve the above technical problems, the present application provides an anti-shake method, device, electronic device, and storage medium for an electronic rearview mirror. The implementation details of the technical solutions of the embodiments of the present application are elaborated in detail below.

[0029] Please refer to Figure 2 , Figure 2 which shows a schematic flow chart of an anti-shake method for an electronic rearview mirror according to an embodiment of the present application. As Figure 2 shown, in an exemplary embodiment, the anti-shake method for an electronic rearview mirror includes at least steps S210 to S240, which are introduced in detail as follows:

[0030] Step S210, obtain the current inertial navigation data of the electronic rearview mirror and the historical estimation parameters at the previous moment.

[0031] Among them, the current inertial navigation data includes angular velocity data and acceleration data.

[0032] In some embodiments of the present application, a gyroscope of a Micro-Electro-Mechanical System (MEMS) is usually selected, which has the characteristics of small volume, low power consumption, and high precision.

[0033] In some embodiments of the present application, the angular velocity data of the vehicle in three axial directions is measured by a gyroscope, that is, the angular velocity measurement value is obtained, providing information on the rotational motion of the vehicle for the present application.

[0034] In some embodiments of the present application, the acceleration of the vehicle in three axial directions is measured by an accelerometer, providing information on the linear motion of the vehicle for the present application. Among them, an MEMS accelerometer is usually selected, which has the characteristics of high sensitivity, low noise, and fast response.

[0035] In some embodiments of the present application, in an electronic rearview mirror, an image sensor with high resolution and high dynamic range is selected to ensure that clear and real rearview images can be captured. The types of image sensors include CMOS (Complementary Metal - Oxide - Semiconductor) type and CCD (Charge - Coupled Device) type, which can be selected according to cost, performance, and requirements. The installation position of the image sensor should ensure that the required rearview field of view can be covered, and factors such as waterproofing, dustproofing, and earthquake resistance should be considered.

[0036] In some embodiments of the present application, a high - performance microprocessor is used as the main control processor, which is responsible for receiving the data from the gyroscope and accelerometer, processing the image signal, and controlling the operation of the anti - shake system. The main control processor needs to have sufficient memory resources and storage resources to support the processing and caching of image data. Moreover, it should also have a high - speed communication interface for data transmission with other modules.

[0037] In some embodiments of the present application, an LCD (Liquid Crystal Display) or OLED (Organic Light - Emitting Diode) display with high brightness and high contrast is selected to display the rearview image. The size and resolution of the display should be selected according to actual needs to ensure that the driver can clearly see the rearview image. The installation position of the display should be convenient for the driver to observe, and factors such as viewing angle, reflection, and occlusion should be considered. An adjustable - angle installation method can be adopted to meet the needs of different drivers.

[0038] In some embodiments of the present application, the internal components of the electronic rearview mirror are protected by a rugged, waterproof, and dustproof housing. The housing material can be selected from plastics, metals, or composite materials. The mounting bracket should have good stability and reliability and be able to firmly mount the electronic rearview mirror on the vehicle. Suction cups, clips, or screw - fixing methods can be adopted to ensure that the electronic rearview mirror does not shake or fall off during driving.

[0039] In some embodiments of the present application, the acquired angular velocity data and acceleration data are preprocessed, and the preprocessed angular velocity data and preprocessed acceleration data are used as the current inertial navigation data for data fusion. Among them, the preprocessing includes noise removal, filtering, and calibration to improve the data quality and accuracy.

[0040] In some embodiments of the present application, the angular velocity data is as follows:

[0041] ω(t) = [ω x (t), ω y (t), ω z (t)] Equation (1)

[0042] Among them, ω(t) is the angular velocity data at time t, ω x (t) is the measured angular velocity value around the x-axis at time t, ω y (t) is the measured angular velocity value around the y-axis at time t, ω z (t) is the measured angular velocity value around the z-axis at time t.

[0043] In some embodiments of the present application, the acceleration data is as follows:

[0044] a(t) = [a x (t), a y (t), a z (t)] Equation (2)

[0045] Among them, a(t) is the acceleration data at time t, a x (t) is the measured acceleration value around the x-axis at time t, a y (t) is the measured acceleration value around the y-axis at time t, a z (t) is the measured acceleration value around the z-axis at time t.

[0046] Step S220, perform multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types.

[0047] In some embodiments of the present application, performing multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types includes: performing wavelet transform on the angular velocity data to obtain a first approximation coefficient and a first detail coefficient with different scale features; performing wavelet transform on the acceleration data to obtain a second approximation coefficient and a second detail coefficient with different scale features; among them, the decomposition types include approximation coefficient type and detail coefficient type, and the scale transformation data includes the first approximation coefficient and the second approximation coefficient of the approximation coefficient type, and the first detail coefficient and the second detail coefficient of the detail coefficient type.

[0048] In some embodiments of the present application, the scaling transformation data of the approximation coefficient type is used to characterize the trend information or average information retained by the data. The scaling transformation data of the detail coefficient type is used to characterize the fast-changing features retained by the data, such as edges or mutations.

[0049] In some embodiments of the present application, the scaling features include at least one of the scaling parameter and the translation parameter in the wavelet transform.

[0050] In some embodiments of the present application, different scaling features include different scaling parameters and the same translation parameter; or, different scaling features include different scaling parameters and different translation parameters; or, different scaling features include the same scaling parameter and different translation parameters.

[0051] In some embodiments of the present application, the decomposition of the angular velocity data is as follows:

[0052]

[0053] where is the first approximation coefficient of the angular velocity data at the scaling parameter j and the translation parameter k, ω(t) is the angular velocity data at time t, and Ψ j,k (t) is the preset scaling function corresponding to the scaling parameter j and the translation parameter k at time t, is the first detail coefficient of the angular velocity data at the scaling parameter j and the translation parameter k, and φ j,k (t) is the preset wavelet basis function corresponding to the scaling parameter j and the translation parameter k at time t.

[0054] In some embodiments of the present application, the decomposition of the acceleration data is as follows:

[0055]

[0056] where is the second approximation coefficient of the acceleration data at the scaling parameter j and the translation parameter k, a(t) is the acceleration data at time t, and Ψ j,k (t) is the preset scaling function corresponding to the scaling parameter j and the translation parameter k at time t, is the second detail coefficient of the acceleration data at the scaling parameter j and the translation parameter k, and φ j,k (t) is the preset wavelet basis function corresponding to the scaling parameter j and the translation parameter k at time t.

[0057] In some embodiments of the present application, the preset scaling function is as follows:

[0058] Ψ j,k (t) = 2 j / 2 Ψ(2 j t - k) Equation (5)

[0059] Among them, Ψ j,k (t) is the preset scaling function corresponding to the scaling parameter j and the translation parameter k at time t.

[0060] In some embodiments of the present application, the preset wavelet basis function is as follows:

[0061] φ j,k (t) = 2 j / 2 φ(2 j t - k) Equation (6)

[0062] Among them, φ j,k (t) is the preset wavelet basis function corresponding to the scaling parameter j and the translation parameter k at time t.

[0063] Step S230: Fuse the scale transformation data of the same scale feature in the same decomposition type to obtain fused data, and reconstruct based on the fused data corresponding to different decomposition types to obtain the signal to be detected for fusion.

[0064] In some embodiments of the present application, fusing the scale transformation data of the same scale feature in the same decomposition type to obtain fused data includes: weighting the first approximation coefficient and the second approximation coefficient of the same scale feature based on a preset weight coefficient to obtain an approximate fusion parameter; determining the maximum value of the absolute value of the first detail coefficient and the absolute value of the second detail coefficient of the same scale feature as the detail fusion parameter; where the fused data includes the approximate fusion parameter and the detail fusion parameter.

[0065] In some embodiments of the present application, the scale transformation data corresponding to the approximation coefficient type can be fused by weighted averaging. The approximate fusion parameter is as follows:

[0066]

[0067] Among them, is the approximate fusion parameter at the scale parameter j and the translation parameter k, A is the preset weight coefficient, is the first approximation coefficient of the angular velocity data at the scale parameter j and the translation parameter k, is the second approximation coefficient of the acceleration data at the scale parameter j and the translation parameter k.

[0068] In some embodiments of the present application, the preset weight coefficient can be adjusted based on the actual working condition, and the value ranges from 0 to 1.

[0069] In some embodiments of the present application, the scale transformation data corresponding to the detail coefficient type can be fused by taking the larger absolute value. The detail fusion coefficient is as follows:

[0070]

[0071] Among them, is the detail fusion coefficient on the scale parameter j and the translation parameter k, is the first detail coefficient of the angular velocity data on the scale parameter j and the translation parameter k, is the second detail coefficient of the acceleration data on the scale parameter j and the translation parameter k.

[0072] In some embodiments of the present application, reconstruction is performed based on the fusion data corresponding to different decomposition types to obtain the fusion signal to be detected, including: determining the detail reconstruction parameters of the same scale feature based on the preset scale function and the detail fusion parameters of the same scale feature; determining the approximate reconstruction parameters of the same scale feature according to the preset wavelet basis function and the approximate fusion parameters of the same scale feature; performing reconstruction based on the detail reconstruction parameters of different scale features and the approximate reconstruction parameters of different scale features to obtain the fusion signal to be detected.

[0073] In some embodiments of the present application, the product of the preset scale function and the detail fusion parameters of the same scale feature is determined as the detail reconstruction parameters of the same scale feature; the product of the preset wavelet basis function and the approximate fusion parameters of the same scale feature is determined as the approximate reconstruction parameters of the same scale feature; the detail reconstruction parameters of different scale features are summed, and the approximate reconstruction parameters of different scale features are summed, and the sum of the summed detail reconstruction parameters and the summed approximate reconstruction parameters is determined as the fusion signal to be detected.

[0074] In some embodiments of the present application, the fusion signal to be detected is as follows:

[0075]

[0076] Among them, f z (t) is the fusion signal to be detected at time t, is the approximate fusion parameter on the scale parameter j and the translation parameter k, Ψ j,k (t) is the preset scale function corresponding to the scale parameter j and the translation parameter k at time t, is the detail fusion coefficient on the scale parameter j and the translation parameter k, φ j,k (t) is the preset wavelet basis function corresponding to the scale parameter j and the translation parameter k at time t.

[0077] Step S240, perform jitter detection according to the fusion signal to be detected and the historical estimation parameters to obtain the jitter detection result of the electronic rearview mirror.

[0078] In some embodiments of the present application, jitter detection is performed based on the to-be-detected fusion signal and historical estimation parameters to obtain the jitter detection result of the electronic rearview mirror, including: the historical estimation parameters include the historical estimation state vector and the historical posterior estimation covariance; a current measurement state vector is constructed based on the to-be-detected fusion signal and the derivative of the to-be-detected fusion signal; the current estimation state vector is determined according to the historical posterior estimation covariance, the historical estimation state vector, and the current measurement state vector; if the absolute value of at least one estimated element in the current estimation state vector is greater than the corresponding preset jitter threshold, the jitter detection result of the electronic rearview mirror is determined to be a jitter phenomenon.

[0079] In some embodiments of the present application, the present application will take the t-th moment as the current moment and the (t - 1)-th moment as the previous moment as an example to illustrate the anti-shake of the electronic rearview mirror.

[0080] In some embodiments of the present application, the actual state vector is constructed as follows:

[0081]

[0082] where, Φ(t) is the actual state vector at the t-th moment, and f(t) is the actual fusion signal at the t-th moment. is the derivative of the actual fusion signal at the t-th moment.

[0083] In some embodiments of the present application, the current measurement state vector is as follows:

[0084]

[0085] where, Z(t) is the current measurement state vector at the t-th moment, and f z (t) is the to-be-detected fusion signal at the t-th moment. is the derivative of the to-be-detected fusion signal at the t-th moment.

[0086] In some embodiments of the present application, determining the current estimation state vector according to the historical posterior estimation covariance, the historical estimation state vector, and the current measurement state vector includes: determining the current prior estimation covariance according to the historical posterior estimation covariance, the state transition matrix of the preset state equation, and the preset process noise; determining the Kalman gain based on the current prior estimation covariance, the measurement matrix of the preset measurement equation, and the measurement noise covariance; determining the current prior state estimation according to the state transition matrix and the historical estimation state vector; determining the current estimation state vector based on the current prior state estimation, the Kalman gain, the measurement matrix, and the current measurement state vector.

[0087] In some embodiments of the present application, the current estimation state vector is determined by Kalman filtering.

[0088] In some embodiments of the present application, the preset state equation is as follows:

[0089] Φ(t) = FΦ(t - 1) + W(t - 1) Equation (12)

[0090] Wherein, Φ(t) is the actual state vector at time t, F is the state transition matrix, and W(t - 1) is the preset process noise at time t - 1.

[0091] In some embodiments of the present application, the state transition matrix is as follows:

[0092]

[0093] Wherein, F is the state transition matrix, and Δt is the measurement sampling period of the current inertial navigation data.

[0094] In some embodiments of the present application, the preset process noise includes Gaussian white noise with a mean of 0 and a process noise covariance matrix of Q. Wherein, the process noise covariance matrix is as follows:

[0095]

[0096] Wherein, Q is the process noise covariance matrix, q 11 is the process noise variance corresponding to the actual fusion signal, q 12 , q 21 is the process noise covariance between the actual fusion signal and the derivative of the actual fusion signal, q 22 is the process noise variance corresponding to the derivative of the actual fusion signal.

[0097] In some embodiments of the present application, the value of the process noise covariance matrix Q is determined based on the characteristics of the preset process noise.

[0098] In some embodiments of the present application, the historical estimated state vector at the initial time can be determined according to the evaluation of the fusion signal to be detected corresponding to the initial time and its change rate. The historical estimated state vector at the initial time is as follows:

[0099]

[0100] Wherein, is the historical estimated state vector at the initial time, is the estimated value of the fusion signal at the initial time, is the derivative of the estimated value of the fusion signal at the initial time.

[0101] In some embodiments of the present application, the historical posterior estimation covariance at the initial time is as follows:

[0102]

[0103] Among them, P(0) is the historical posterior estimation covariance at the initial moment, and p 11 (0) is the initial estimation variance of the fusion signal estimation value at the initial moment, and p 12 (0), p 21 (0) is the initial estimation covariance between the fusion signal estimation value and the derivative of the fusion signal estimation value at the initial moment, and p 22 (0) is the initial estimation variance of the derivative of the fusion signal estimation value at the initial moment.

[0104] In some embodiments of the present application, the historical posterior estimation covariance at the initial moment is usually set to an appropriate value according to the historical estimation state vector.

[0105] In some embodiments of the present application, the current prior estimation covariance is as follows:

[0106] P - (t) = FP(t - 1)F T + Q Equation (17)

[0107] Among them, P - (t) is the current prior estimation covariance at time t, F is the state transition matrix, P(t - 1) is the historical posterior estimation covariance at time k - 1, and Q is the process noise covariance matrix.

[0108] In some embodiments of the present application, the preset measurement equation is as follows:

[0109] Z(t) = HΦ(t)+V(t) Equation (18)

[0110] Among them, Z(t) is the current measurement state vector at time t, H is the measurement matrix, Φ(t) is the actual state vector at time t, and V(t) is the preset measurement noise at time t.

[0111] In some embodiments of the present application, the measurement matrix H = [1 0].

[0112] In some embodiments of the present application, the preset measurement noise includes Gaussian white noise with a mean of 0 and a measurement noise covariance of R.

[0113] In some embodiments of the present application, the Kalman gain is as follows:

[0114] K(t) = P - (t)H T (HP - (t)H T + R) -1 Equation (19)

[0115] Among them, K(t) is the Kalman gain at time t, and P -(t) is the current prior estimation covariance at time t, H is the measurement matrix, and R is the measurement noise covariance.

[0116] In some embodiments of the present application, the current prior state estimation is as follows:

[0117]

[0118] Wherein, is the current prior state estimation at time t, F is the state transition matrix, is the historical estimation state vector at time t - 1.

[0119] In some embodiments of the present application, the determination of the current estimated state vector is as follows:

[0120]

[0121] Wherein, is the current estimated state vector at time t, is the current prior state estimation at time t, K(t) is the Kalman gain at time t, Z(t) is the current measurement state vector at time t, and H is the measurement matrix.

[0122] In some embodiments of the present application, the determination of the current posterior estimation covariance is as follows:

[0123] P(t) = (I - K(t)H)P - (t) Equation (22)

[0124] Wherein, P(t) is the current posterior estimation covariance at time t, I is the identity matrix, K(t) is the Kalman gain at time t, H is the measurement matrix, and P - (t) is the current prior estimation covariance at time t.

[0125] In some embodiments of the present application, a preset first threshold M is preset f and a preset second threshold

[0126]

[0127] In some embodiments of the present application, if in the fused signal estimated value in the derivative of the fused signal estimated value at least one of them, it is preliminarily determined that the electronic rearview mirror has a jitter phenomenon.

[0128] In some embodiments of the present application, based on the current posterior estimation covariance, the estimation covariance value between the current time fused signal estimated value and the derivative of the fused signal estimated value can evaluate the reliability of the jitter detection result.

[0129] In some embodiments of the present application, the present application performs wavelet transform on the original current inertial navigation data at different scale features to achieve multi-scale decomposition, and respectively applies filtering algorithms such as weighted average and maximum absolute value on different scale features to fuse the angular velocity data and acceleration data, and finally reconstructs the fused result. By decomposing, fusing, and reconstructing the data at multiple scales, different frequency components in the data can be better captured, improving the accuracy and robustness of the fusion.

[0130] In some embodiments of the present application, after determining that the jitter detection result of the electronic rearview mirror shows a jitter phenomenon, the method further includes: determining jitter parameters according to the fusion signal to be detected, where the jitter parameters include jitter amplitude, jitter frequency, and jitter direction; performing jitter compensation on the electronic rearview mirror based on the jitter parameters to cancel the jitter.

[0131] In some embodiments of the present application, the main control processor obtains jitter parameters such as jitter amplitude, jitter frequency, and jitter direction through analysis based on the fusion signal to be detected.

[0132] In some embodiments of the present application, the main control processor drives the anti-jitter mechanism of the electronic rearview mirror to perform jitter compensation based on the jitter parameters. The anti-jitter mechanism includes a lens group or an image sensor. For example, the lens group will make small movements or angle adjustments within a preset range according to the jitter parameters to cancel the jitter of the electronic rearview mirror.

[0133] In some embodiments of the present application, the vibration state of the vehicle can be detected in real time through a gyroscope and an accelerometer. The main control processor controls a micro-motor to adjust the position of the image sensor according to the detected signal, which can effectively eliminate the jitter of the electronic rearview mirror caused by vehicle vibration, improve the driver's observation effect of the rear road conditions, and enhance driving safety; and it has a simple structure, is easy to install and maintain, and is applicable to various types of vehicles; under different road conditions, the main control processor can adjust the working parameters of the micro-motor according to the actual working conditions to achieve the best anti-jitter effect.

[0134] Please refer to Figure 3 , Figure 3 which shows a block diagram of an anti-jitter device for an electronic rearview mirror according to an embodiment of the present application. This device can be applied to Figure 1 the shown implementation environment and is specifically configured in the main control processor 102. This device can also be applicable to other exemplary implementation environments and is specifically configured in other devices. This embodiment does not limit the implementation environment applicable to this device.

[0135] As Figure 3 shown, an anti-jitter device 300 for an electronic rearview mirror according to an embodiment of the present application includes: an acquisition module 301, a multi-scale decomposition module 302, a fusion and reconstruction module 303, and a jitter detection module 304.

[0136] Among them, the acquisition module 301 is used to acquire the current inertial navigation data of the electronic rearview mirror and the historical estimation parameters at the previous moment. The current inertial navigation data includes angular velocity data and acceleration data;

[0137] The multi-scale decomposition module 302 is used to perform multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types;

[0138] The fusion and reconstruction module 303 is used to fuse the scale transformation data with the same scale features in the same decomposition type to obtain fusion data, and perform reconstruction based on the fusion data corresponding to different decomposition types to obtain the fusion signal to be detected;

[0139] The jitter detection module 304 is used to perform jitter detection based on the fusion signal to be detected and the historical estimation parameters to obtain the jitter detection result of the electronic rearview mirror.

[0140] The anti-shake device of the electronic rearview mirror provided in the above embodiment and the anti-shake method of the electronic rearview mirror provided in the above embodiment belong to the same concept. The specific ways in which each module and unit perform operations have been described in detail in the method embodiment, and will not be repeated here. In practical applications, the anti-shake device of the electronic rearview mirror provided in the above embodiment can, according to needs, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above. This is not limited here either.

[0141] An embodiment of the present application also provides an electronic device, including: one or more processors; a storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the electronic device implements the anti-shake method of the electronic rearview mirror provided in each of the above embodiments.

[0142] Please refer to Figure 4 , Figure 4 , which shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application. Figure 4 The computer system 400 of the electronic device shown is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present application.

[0143] Such as Figure 4As shown, computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a Read-Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403, such as executing the method in the above embodiments. In the Random Access Memory 403, various programs and data required for system operation are also stored. The Central Processing Unit 401, the Read-Only Memory 402, and the Random Access Memory 403 are connected to each other via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0144] The following components are connected to the Input / Output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the Input / Output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed.

[0145] Specifically, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the Central Processing Unit (CPU) 401, various functions defined in the system of the present application are executed.

[0146] The computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0147] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0148] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation on the units themselves in some cases. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of this application.

[0149] Another aspect of this application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of the computer, the computer is enabled to execute the anti-shake method of the electronic rearview mirror provided in each of the above embodiments. The computer-readable storage medium can be included in the electronic device described in the above embodiments, or can exist alone without being assembled into the electronic device.

[0150] In the above embodiments, unless otherwise specified, by using serial numbers such as "first" and "second" to describe common objects, it only indicates different instances of the same object, rather than indicating that the objects to be described must be in a given order, whether in terms of time, space, sorting, or any other way.

[0151] The above embodiments only exemplarily illustrate the principles and effects of this application, rather than being used to limit this application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in this application should still be covered by the claims of this application.

Claims

1. An anti-shake method for an electronic rearview mirror, characterized in that: The method comprises: Acquire current inertial navigation data of the electronic rearview mirror and historical estimated parameters at a previous moment, wherein the current inertial navigation data includes angular velocity data and acceleration data; Performing multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types; The scale transformation data of the same scale feature in the same decomposition type are fused to obtain fused data, and the fused data corresponding to different decomposition types are reconstructed to obtain a fused signal to be detected; The jitter detection is performed according to the fused signal to be detected and the historical estimated parameters to obtain a jitter detection result of the electronic rearview mirror.

2. The anti-shake method of the electronic rearview mirror according to claim 1, characterized in that: The current inertial navigation data is subjected to multi-scale decomposition to obtain a plurality of scale transformation data of different decomposition types, including: Performing wavelet transform on the angular velocity data to obtain first approximate coefficients and first detail coefficients of different scale features; Performing wavelet transformation on the acceleration data to obtain second approximate coefficients and second detail coefficients of different scale features; The decomposition type includes an approximate coefficient type and a detail coefficient type, and the scale transformation data includes a first approximate coefficient and a second approximate coefficient of the approximate coefficient type, and a first detail coefficient and a second detail coefficient of the detail coefficient type.

3. The anti-shake method of the electronic rearview mirror according to claim 2, characterized in that: The scale transformation data of the same scale feature in the same decomposition type are fused to obtain fused data, including: The first approximate coefficient and the second approximate coefficient of the same scale feature are weighted based on a preset weight coefficient to obtain an approximate fusion parameter; Determine the maximum value of the absolute value of the first detail coefficient and the absolute value of the second detail coefficient of the same scale feature as the detail fusion parameter; The fusion data includes the approximate fusion parameters and the detail fusion parameters.

4. The anti-shake method of the electronic rearview mirror according to claim 3, characterized in that: Reconstruct the fusion data corresponding to different decomposition types to obtain the fusion signal to be detected, including: Determining detail reconstruction parameters of the same scale feature based on a preset scale function and detail fusion parameters of the same scale feature; Determining an approximate reconstruction parameter of the same scale feature according to a preset wavelet basis function and an approximate fusion parameter of the same scale feature; Reconstruction is performed based on detail reconstruction parameters of features at different scales and approximate reconstruction parameters of features at different scales to obtain a fused signal to be detected.

5. The anti-shake method of the electronic rearview mirror according to any one of claims 1 to 4, characterized in that: Performing jitter detection according to the fused signal to be detected and the historical estimated parameters to obtain a jitter detection result of the electronic rearview mirror includes: The historical estimation parameters include historical estimation state vector and historical posterior estimation covariance; constructing a current measurement state vector based on the fused signal to be detected and a derivative of the fused signal to be detected; Determine a current estimated state vector according to the historical a posteriori estimated covariance, the historical estimated state vector and the current measured state vector; If the absolute value of at least one estimated element in the current estimated state vector is greater than the corresponding preset jitter threshold, the jitter detection result of the electronic rearview mirror is determined as the occurrence of a jitter phenomenon.

6. The anti-shake method of the electronic rearview mirror according to claim 5, characterized in that: Determining a current estimated state vector according to the historical a posteriori estimated covariance, the historical estimated state vector and the current measured state vector comprises: Determine the current a priori estimated covariance according to the historical a posteriori estimated covariance, the state transfer matrix of the preset state equation and the preset process noise; Determining a Kalman gain based on the current a priori estimated covariance, a measurement matrix of a preset measurement equation, and a measurement noise covariance; Determine a current priori state estimate based on the state transfer matrix and the historical estimated state vector; A current estimated state vector is determined based on the current a priori state estimate, the Kalman gain, the measurement matrix, and the current measured state vector.

7. The anti-shake method of the electronic rearview mirror according to claim 5, characterized in that: After determining that the jitter detection result of the electronic rearview mirror is that a jitter phenomenon occurs, the method further includes: Determining jitter parameters according to the fused signal to be detected, wherein the jitter parameters include jitter amplitude, jitter frequency and jitter direction; The electronic rearview mirror is subjected to jitter compensation based on the jitter parameter to offset the jitter.

8. An anti-shake device for an electronic rearview mirror, characterized in that: The device comprises: An acquisition module, used to acquire current inertial navigation data of the electronic rearview mirror and historical estimated parameters at a previous moment, wherein the current inertial navigation data includes angular velocity data and acceleration data; A multi-scale decomposition module, used for performing multi-scale decomposition on the current inertial navigation data to obtain multiple scale transformation data of different decomposition types; A fusion and reconstruction module is used to fuse the scale transformation data of the same scale feature in the same decomposition type to obtain fused data, and reconstruct the fused data corresponding to different decomposition types to obtain a fused signal to be detected; The jitter detection module is used to perform jitter detection according to the fused signal to be detected and the historical estimated parameters to obtain a jitter detection result of the electronic rearview mirror.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the anti-shake method for the electronic rearview mirror as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the anti-shake method for an electronic rearview mirror according to any one of claims 1 to 7.

Images