Window breaking detection method and device and electronic equipment

Abstract

The invention provides a window breaking detection method and device and electronic equipment, and the method comprises the steps: obtaining a reflection signal of a to-be-detected window, determining a current micro-Doppler feature according to the reflection signal, the window breaking detection result is determined based on the current micro-Doppler feature, micro-Doppler feature extraction is performed on the reflected signal obtained by reflecting the sent signal through the window to be detected, and whether window breaking occurs is judged based on the micro-Doppler feature, so that the problem of low accuracy of window breaking detection depending on vibration is avoided, and the window breaking detection accuracy is improved. The detection accuracy is improved, and the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a broken window detection method, apparatus, and electronic device. Background Technology

[0002] Vehicle windows may be forcibly broken, potentially causing unnecessary financial losses for the owner. To address this, relevant technologies have incorporated window breakage detection functions. These functions detect breakage by capturing the vibration signals emitted when glass is struck or broken, using accelerometers, pressure sensors, and vibration sensors.

[0003] However, this direct contact detection method is highly susceptible to sensitivity issues, which can lead to false alarms. If the sensitivity is set too high, wind, rain, or construction vibrations can trigger false alarms, affecting user experience and reducing the reliability of the alarm system. If the sensitivity is set too low, although false alarms can be reduced, it may lead to missed detections of some minor or cleverly designed window breaking attempts, leaving potential safety hazards. Summary of the Invention

[0004] This application provides a broken window detection method, apparatus, and electronic device to solve the technical problems in related technologies where the broken window detection function is greatly affected by sensitivity, has poor detection accuracy, and results in a low user experience.

[0005] This application provides a broken window detection method, the method comprising: acquiring a reflected signal of a window to be detected, the reflected signal including a signal reflected by the window to be detected from a transmitted signal during a detection time period; determining a current micro-Doppler feature based on the reflected signal; and determining a broken window detection result based on the current micro-Doppler feature.

[0006] In one embodiment of this application, determining the broken window detection result based on the current micro-Doppler features includes: inputting the current micro-Doppler features into a detection model to obtain the broken window detection result, wherein the detection model is trained using sample signal data, the sample signal data including sample micro-Doppler features and sample broken window results, the sample micro-Doppler features being determined based on reflected signals collected during the broken window process in the sample collection phase; wherein the sample broken window results include: a broken window; or, a broken window and broken window detail data, the broken window detail data including glass type and / or broken window tool.

[0007] In one embodiment of this application, before inputting the current micro-Doppler features into the detection model, the method further includes: determining one or more of phase change data, frequency change data, and spectral broadening data based on the current micro-Doppler features; determining a preliminary detection result based on one or more of the phase change data, frequency change data, and spectral broadening data; and if the preliminary detection result is the target result, triggering the step of inputting the current micro-Doppler features into the detection model.

[0008] In one embodiment of this application, determining the broken window detection result based on the current micro-Doppler features includes: determining one or more of phase change data, frequency change data, and spectrum broadening data based on the current micro-Doppler features; determining a preliminary detection result based on one or more of the phase change data, frequency change data, and spectrum broadening data; and using the preliminary detection result as the broken window detection result.

[0009] In one embodiment of this application, determining a preliminary detection result based on one or more of the phase change data, frequency change data, and spectral broadening data includes: if the phase change data shows a negative phase change trend, determining the preliminary detection result as a broken window, indicating the initial stress stage; if the frequency change data shows a high-frequency change trend, determining the preliminary detection result as a broken window, indicating the crack initiation and propagation stage; if the phase change data includes both negative and positive phase change trends, and the spectral broadening data shows a spectral broadening trend, determining the preliminary detection result as a broken window, indicating the glass fragment scattering and falling off stage.

[0010] In one embodiment of this application, acquiring the reflected signal of a window to be detected includes: a UWB anchor point transmitting a signal; the UWB anchor point receiving a signal reflected by an obstacle at a preset distance within a detection time period, to obtain an initial signal, wherein the obstacle includes one or more of the window to be detected and fragments of the window to be detected; noise removal and / or low-frequency filtering are performed on the initial signal to obtain the reflected signal; or, a UWB anchor point transmitting a signal, wherein the UWB anchor point is located inside the vehicle, and the number of UWB anchor points is multiple, with at least one UWB anchor point corresponding to at least one window to be detected; the UWB... Anchor point B receives the signal reflected by obstacles from the transmitted signal within a preset distance during the detection period to obtain an initial signal. The obstacles include one or more of the window to be detected and fragments of the window to be detected. All initial signals are time-synchronized to obtain the reflected signal. Alternatively, a base signal is obtained, which is generated by receiving the transmitted signal after transmitting the signal in the initial stage when no window breakage has occurred. During the detection stage, the reflected signal of the transmitted signal is used as the initial signal. The initial signal is filtered by the base signal, and the filtered initial signal is used as the reflected signal.

[0011] In one embodiment of this application, before acquiring the reflected signal of the window to be tested, the method further includes: transmitting a signal, wherein the transmitted signal is a pulsed UWB signal; determining the signal transmission power and pulse width of the transmitted signal according to the window size of the window to be tested; or, acquiring the current temperature and the current received signal strength indication, determining a power adjustment value according to the current temperature, the current received signal strength indication, the target temperature, and the target received signal strength indication, adjusting the transmission power of the transmitted signal based on the power adjustment value, wherein the adjusted transmission power is greater than a preset minimum power and less than a preset maximum power.

[0012] In one embodiment of this application, after determining the broken window detection result based on the current micro-Doppler features, the method further includes: if the broken window detection result includes a broken window, generating an alarm message and displaying it.

[0013] This application embodiment also provides a broken window detection device, which includes: an acquisition module, a determination module, and a detection module, wherein: the acquisition module is used to acquire the reflected signal of the window to be detected, the reflected signal including the signal reflected by the window to be detected from the transmitted signal during the detection time period; the determination module is used to determine the current micro-Doppler feature based on the reflected signal; and the detection module is used to determine the broken window detection result based on the current micro-Doppler feature.

[0014] This application also provides an electronic device, including: a memory storing a computer program thereon; and a processor for executing the computer program in the memory to implement the steps of the method described in any of the above embodiments.

[0015] This invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being used to cause a computer to perform the method provided in any of the above embodiments.

[0016] The beneficial effects of this application are as follows: The broken window detection method, apparatus, and electronic device proposed in this application obtain the reflected signal of the window to be detected, which includes the signal reflected by the window to be detected during the detection period. The current micro-Doppler feature is determined based on the reflected signal, and the broken window detection result is determined based on the current micro-Doppler feature. This method extracts micro-Doppler features from the reflected signal obtained by the window to be detected reflecting the transmitted signal, and judges whether a broken window has occurred based on the micro-Doppler feature. This avoids the problem of low accuracy of broken window detection relying on vibration, improves detection accuracy, and enhances user experience. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] In the attached diagram: Figure 1 This is a schematic diagram illustrating an application scenario of a broken window detection method provided in an embodiment of this application; Figure 2 A schematic flowchart of a broken window detection method provided in one embodiment of this application; Figure 3 A schematic diagram of a broken window detection device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The following specific examples illustrate the implementation 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 embodiments. 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. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. The drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the shape, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0021] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present application.

[0022] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of this application. For example... Figure 1As shown, taking the application of this broken window detection method to a vehicle as an example, with the transmitted signal sent through a UWB (Ultra Wide Band) sensor, it is assumed that corresponding UWB sensors 1, 2, 3, and 4 are respectively installed on the windshield, rear windshield, left door window, and right door window of the vehicle. These UWB sensors 1, 2, 3, and 4 are connected to the main control unit via a CAN (Controller Area Network) bus. The main control unit also communicates with the vehicle owner's mobile phone via the vehicle network and is connected to an audible and visual alarm device via the CAN bus. The UWB sensors include transmitting and receiving antennas, installed inside the vehicle, and are used to transmit signals to the corresponding windows and receive reflected signals. For example, the UWB sensor corresponding to the left door window is used to detect the left front and rear door windows, and the UWB sensor corresponding to the right door window is used to detect the right front and rear door windows. By transmitting signals to the corresponding car windows using UWB sensors and receiving the reflected signals, the main control unit obtains the transmitted signals from four UWB sensors, synchronizes them in time, and then extracts the micro-Doppler features from the reflected signals to obtain the broken window detection result. The broken window detection result is determined, for example, by inputting the micro-Doppler features into a pre-trained detection model, which then outputs the broken window detection result. When a broken window event is confirmed, the main control unit controls the audible and visual alarm device to sound an alarm, and simultaneously transmits the information to the owner's mobile app via the vehicle network, promptly notifying the owner. This allows for perception throughout the entire broken window process, enabling earlier and more intelligent detection of the broken window result, timely warnings, and more accurate detection results, thus improving the user experience.

[0023] It should be noted that the above scenario is only an example of an application scenario provided by the embodiments of this application. The method can also be applied to other scenarios according to the user's needs. The embodiments of this application do not limit the actual form, quantity, or correspondence of various devices, components, etc. included in the scenario. In the specific application of the solution, it can be set according to actual needs. Please see Figure 2 , Figure 2 A schematic flowchart of a broken window detection method provided in an embodiment of this application is shown below. Figure 2 As shown, the method includes the following steps: Step S210: Obtain the reflection signal of the window to be detected.

[0024] The reflected signal includes the signal reflected by the window to be detected from the transmitted signal during the detection period.

[0025] In one embodiment, acquiring the reflected signal of the window to be detected includes: a UWB anchor point transmitting a signal; the UWB anchor point receiving the signal reflected by an obstacle at a preset distance within a detection time period to obtain an initial signal, wherein the obstacle includes one or more of the window to be detected and fragments of the window to be detected; and noise removal and / or low-frequency filtering are performed on the initial signal to obtain the reflected signal. Wherein, "multiple" refers to two or more.

[0026] In one embodiment, taking a vehicle as an example, the transmitted signal sent through the UWB anchor point returns to the UWB anchor point after being transmitted through the vehicle window, and the reflected signal is received as the initial signal. When a window breakage occurs, there may be glass fragments in the window. Unbroken glass and these fragments will also generate reflected signals, which return to the UWB anchor point and are also used as the initial signal. Since the UWB anchor point receives signals not only emitted from the vehicle window glass but also signals reflected back from other objects inside the vehicle, a preset distance can be set to prioritize the processing of signals reflected from the vehicle window glass, while ignoring reflected signals that are too far away, such as those outside the window, or too close, such as those reflected from objects like seats. The preset distance can be determined based on the distance between the UWB anchor point and the vehicle window. The detection time period can be set according to the needs of those skilled in the art; for example, it can be real-time monitoring, with subsequent micro-Doppler feature extraction performed on the real-time signals.

[0027] See also Figure 1 Each UWB sensor receives reflected signals: the UWB receiving antenna receives signals reflected from the car window glass (and other objects inside the vehicle). To accurately distinguish signals from those from the glass from other objects inside the vehicle (seats, doors, etc.), a distance value can be set for the glass. Signals reflected from the glass surface are prioritized, ignoring reflections from objects that are too far or too close. Utilizing UWB's high-precision ranging capabilities, a distance value is set to focus only on signals reflected from the car window surface, ignoring reflections from more distant or closer objects such as doors and seats, thus eliminating irrelevant interference. For example, the time-of-flight (TOF) technology of UWB can be used to accurately measure the signal propagation delay and calculate the actual distance to the glass. Then, algorithms such as Kalman filtering are applied to the original signal (initial signal) to remove system noise and retain the effective components. A high-pass filter is further used to filter out low-frequency interference, retaining only high-frequency information related to glass breakage.

[0028] In one embodiment, acquiring the reflected signal of the window to be detected includes: UWB anchor points transmitting signals, the UWB anchor points being set inside the vehicle, the number of UWB anchor points being multiple, and at least one UWB anchor point corresponding to at least one window to be detected; the UWB anchor points receiving signals reflected by obstacles at a preset distance within a detection time period to obtain initial signals, the obstacles including one or more of the window to be detected and fragments of the window to be detected; and time synchronizing all the initial signals to obtain the reflected signal.

[0029] When this method is used in a specific space such as a vehicle, multiple UWB sensors can be used simultaneously to detect whether multiple windows have broken. Each UWB sensor detects one window. In order to ensure the real-time nature of subsequent warnings, the reflected signals received by all UWB sensors can be synchronized in the time dimension, and then the broken window detection method provided in this embodiment can be used for detection. If the broken window detection result corresponding to the reflected signal received by a certain UWB sensor is a broken window, an alarm will be triggered in time.

[0030] See also Figure 1 Taking the MCU (Microcontroller Unit) as the main control unit as an example, the MCU is responsible for receiving data from four UWB modules (UWB sensors) and performing timing synchronization. Each UWB node (UWB sensor) needs to ensure the accuracy and synchronization of the data through timestamps or synchronization signals.

[0031] In one embodiment, before acquiring the reflected signal from the window to be detected, the method further includes: transmitting a signal, wherein the transmitted signal is a pulsed UWB signal; and determining the signal transmission power and pulse width of the transmitted signal based on the window size of the window to be detected. The window size can be the width, area, etc. of the window. As an example, taking a vehicle window as an example, the width can be the maximum width of the vehicle window parallel to the ground. Due to the strong anti-interference characteristics of UWB signals, the detection method is more reliable.

[0032] In one embodiment, before acquiring the reflected signal from the window to be detected, the method further includes: acquiring the current temperature and the current received signal strength indication; determining a power adjustment value based on the current temperature, the current received signal strength indication, the target temperature, and the target received signal strength indication; adjusting the transmission power of the transmitted signal based on the power adjustment value, wherein the adjusted transmission power is greater than a preset minimum power and less than a preset maximum power. The transmission power can be adjusted using temperature and the received signal strength indication to ensure that the reflected signal can be captured promptly and accurately. By limiting the threshold of the transmission power, the safety and stability of the sensor transmitting the signal are ensured. The preset minimum power and preset maximum power can be set by those skilled in the art as needed. The target temperature can be the temperature at the initial moment of detection or a temperature set by those skilled in the art, and the target received signal strength indication can be set by those skilled in the art. This method allows for timely compensation of the transmission power, ensuring both that the transmitted signal can be received and the safety of the device. It avoids insufficient signal strength due to factors such as temperature, which could affect the reception of the transmitted signal.

[0033] As an example, a target temperature can be preset. The temperature difference between the current temperature and the target temperature is determined. Then, based on a preset temperature-power relationship and the temperature difference, the power adjustment value affected by temperature factors is determined. The preset temperature-power relationship indicates the corresponding power adjustment value for the temperature difference (which can be positive or negative) between the current temperature and the target temperature. For example, increasing the temperature by one degree increases the power by a certain amount, and decreasing it by one degree decreases the power accordingly. This can compensate for the temperature-dependent drift of the UWB RF chip's output power.

[0034] As an example, the current received signal strength indicator can be compared with the target received signal strength indicator. If the current received signal strength indicator is less than the target received signal strength indicator, the power is increased. It is necessary to verify whether the increased power exceeds the preset maximum power. If it does, the preset maximum power is maintained and no further increase is made.

[0035] For example, signal strength can be guaranteed using a dynamic power control (APC) algorithm: dynamically adjusting the trigger conditions and monitoring the reflected signal strength (RSSI) every 200ms. An example code implementation is as follows: def apc_control(current_rssi): # Define the dynamic power control function # Preset intensity threshold LOW_THRESHOLD = -60# dBm (Minimum effective signal strength) HIGH_THRESHOLD = -40# dBm (Receiver saturation critical point) POWER_STEP = 1# dB (Power adjustment step size) if current_rssi<LOW_THRESHOLD:# If the current RSSI value < low threshold increase_power(POWER_STEP)# Call the function to increase power<000,0121>elif current_rssi>HIGH_THRESHOLD:# If the current RSSI value > high threshold decrease_power(POWER_STEP)# Call the function to decrease power else: maintain_power()# Maintain the current power It is assumed that the hardware implementing this method includes a UWB RF chip, an RSSI detection circuit, and a temperature compensation module (the power change coefficient with temperature is +0.03 dB / °C). Increasing the power is triggered only when RSSI < -60dBm is detected continuously for 3 times to avoid instantaneous interference.

[0036] Power safety margin: MAX_POWER = 0# dBm# Maximum power = 0 dBm (Power upper limit specified by FCC) MIN_POWER = -41.3 # dBm # Minimum power = 41.3 dBm (The lowest power that the chip can output) def increase_power(step): # Calculate the new power value new_power = current_power + step # Set the transmit power value to ensure it does not exceed the maximum power limit set_power(min(new_power, MAX_POWER)) def decrease_power(step): # Calculate the new power value new_power = current_power – step# New power value = current power value - adjustment step size # Set the power value to ensure it is not lower than the lower limit set_power(max(new_power, MIN_POWER)) As an example, continuing with the application of this method to broken car windows detection, UWB pulses are continuously emitted, and the reflected UWB pulses are received. The signal transmission power and pulse width need to be adjusted according to the size and reflection characteristics (dielectric constant, conductivity, etc.) of the car window to ensure the clarity of the monitoring area and the intensity of the reflected signal.

[0037] As an example, pulsed UWB or frequency modulated continuous wave (FMCW) is used, with pulse mode as the default priority. A Gaussian pulse sequence with a width of 2ns (repetition frequency of 10MHz) is transmitted. In FMCW mode, the linear frequency modulation bandwidth is 500MHz (center frequency of 6.5GHz), and the sweep period is 2ms. When targeting coated (weakly reflective) glass, FMCW mode is activated to enhance the signal-to-noise ratio.

[0038] If the vehicle window type is a small-sized window, the first power adjustment value for the window is determined based on the ratio of the minimum effective transmission width reference value to the actual window size. The signal transmission power is then obtained by superimposing the reference power and power loss compensation on this first power adjustment value. For example, the formula corresponding to the transmission power for a small-sized window (e.g., approximately 0.8~1.2m wide) is as follows: Formula (1), Among them, P t The adjusted transmit power is P0, where P0 is the reference power (the transmit power before adjustment), and w min Here, W is the preset minimum effective reflection width reference value, Γ is the actual window width, and Γ is the reflection coefficient, which is the ratio of the reflected signal amplitude to the incident signal amplitude. Small windows have a small reflection area, requiring additional power compensation to compensate for signal attenuation.

[0039] The method for determining power compensation is as follows: Formula (2), in, The term (dB) is used to compensate for the power loss caused by glass reflection. Γ is the reflection coefficient. When a UWB signal is incident on the glass surface, part of it is reflected and part is transmitted. This term is used to offset the energy loss caused by reflection.

[0040] The formula for pulse width is: Formula (3) τ ≤ 2·Δd / c Where τ is the pulse width, Δd is the difference between the farthest and closest distances that a sensor such as radar or lidar can detect, and c is the speed of light. This allows for improved range resolution within a narrow pulse.

[0041] If the vehicle window type is a large-size window (the comparison threshold for size can be set by those skilled in the art as needed), the second power adjustment value for the window is determined based on the ratio of the maximum glass area to the actual glass area. The signal transmission power is obtained by subtracting the glass penetration loss term from the reference power value, which is then added to the second power adjustment value. For example, the formula corresponding to the transmission power for a large-size windshield (e.g., approximately 1.5~2.0m wide) is as follows: Formula (4), Formula (5), Among them, P t The adjusted transmit power is given by P0, where P0 is the reference power (transmit power before adjustment), A is the glass area, and A0 is the preset maximum glass area. Glass transmission loss term (dB) For glass signal attenuation systems (dB / cm, power loss per centimeter of glass thickness). The thickness of the glass is a factor. Windshields are thicker and have more complex structures (such as double-layered laminated glass). When a UWB signal penetrates the glass, energy absorption and loss occur within the glass medium. This loss is linearly related to the glass thickness. The power loss due to the glass thickness needs to be deducted from the transmission power compensation to offset the energy loss during medium penetration.

[0042] Because large windows reflect light strongly, but require multiple layers of glass to penetrate, the pulse width formula is: τ = k·△d·μ·σ formula (6), Where τ is the pulse width, Δd is the difference between the farthest and closest detection distances of a sensor such as radar or lidar, k is a scaling factor used to correct for signal transmission loss, μ is the dielectric constant of the medium (car window), and σ is the conductivity of the medium (car window). This allows for enhanced material penetration through a wide pulse.

[0043] It should be noted that, as an example, the following two schemes can also be used simultaneously: the signal transmission power and pulse width are determined based on the window size; and the transmission power is adjusted based on the current temperature and the current received signal strength indication.

[0044] In one embodiment, acquiring the reflected signal of the window to be detected includes: acquiring a base signal, which is generated by transmitting and receiving a transmitted signal in a scenario where no window breakage has occurred in the initial stage; during the detection stage, the reflected signal of the received transmitted signal is used as the initial signal; the initial signal is filtered using the base signal; and the filtered initial signal is used as the reflected signal. It can be understood that the base signal includes signals reflected by objects such as seats and car doors. When a window breakage event occurs, the car window will crack or even shatter; filtering can suppress static reflections from seats / metal frames, etc.

[0045] In one embodiment, the signal is transmitted via a sensor whose beam angle with the window to be detected can be determined based on the distance between the sensor and the window to be detected, thereby ensuring coverage of the entire window waiting to be detected.

[0046] One example of how the beam angle is determined is as follows: θ=arctan(0.5*W / d) formula (7), Where θ is the beam angle, W is the actual window width, and d is the distance between the sensor and the window to be detected.

[0047] See also Figure 1 A 4x4 UWB phased array antenna can be used to generate a 30° narrow beam focusing glass area.

[0048] It should be noted that this step may involve performing one or more preprocessing methods on the initial signal, such as noise removal and / or low-frequency filtering, time synchronization, or filtering the initial signal using the base signal, to obtain the reflected signal.

[0049] Step S220: Determine the current micro-Doppler characteristics based on the reflected signal.

[0050] For example, by extracting signal segments from the transmitted signal and applying the Short Time Fourier Transform (STFT) to generate a time-spectrum graph, which shows the frequency change over time, the current micro-Doppler features can be extracted.

[0051] Currently, the extraction of micro-Doppler features can also be achieved through micro-Doppler feature extraction methods known to those skilled in the art, which will not be elaborated here.

[0052] Step S230: Determine the broken window detection result based on the current micro-Doppler features.

[0053] In one embodiment, determining the broken window detection result based on the current micro-Doppler features includes: inputting the current micro-Doppler features into the detection model to obtain the broken window detection result. The detection model is trained using sample signal data, which includes sample micro-Doppler features and sample broken window results. The sample micro-Doppler features are determined based on the reflected signals collected during the broken window process in the sample collection phase.

[0054] An example sample broken window result includes: broken window.

[0055] Another example of a broken window analysis result includes: the broken window and detailed data about it, including the type of glass and / or the breaking tool. This allows us to determine not only whether a broken window event occurred, but also what type of glass was broken, what breaking tool was used, or both.

[0056] The corresponding broken window test results include broken window, or both broken window and glass type and / or broken window. tool.

[0057] If the current microDoppler feature cannot identify a broken window, it can be assumed that no broken window has occurred.

[0058] As an example, time-frequency analysis is performed on the received signal to extract signal features such as micro-Doppler characteristics, energy distribution, spectral characteristics, and frequency domain broadening.

[0059] In one embodiment, determining the broken window detection result based on the current micro-Doppler features includes comparing the extracted current micro-Doppler features (time-spectrum) with a pre-trained "broken window feature database." The database includes feature data samples of broken windows using different glass types and tools. The database contains broken window signal features (sample micro-Doppler features) recorded under various conditions (different glass types, different window-breaking tools). Machine learning algorithms (such as Support Vector Machines (SVM), Convolutional Neural Networks (CNN), etc.) are used to quickly classify and identify the features. For example, see [continued]. Figure 1 The algorithm module inputs the time-frequency graphs, spectral characteristics, and micro-Doppler signals of each sensor into the machine learning model. The extracted features are then compared with the broken window feature database. An alarm is triggered when the comparison result matches the broken window pattern.

[0060] In one embodiment, before inputting the current micro-Doppler features into the detection model, the method further includes: determining one or more of phase change data, frequency change data, and spectral broadening data based on the current micro-Doppler features; determining a preliminary detection result based on one or more of the phase change data, frequency change data, and spectral broadening data; and if the preliminary detection result is the target result, triggering the step of inputting the current micro-Doppler features into the detection model. It can be understood that by first determining whether the spectral features match the various stages of a broken window event using one or more of the phase change data, frequency change data, and spectral broadening data, and then inputting them into the detection model for detailed classification such as specific broken window tools, a more accurate result can be obtained.

[0061] In another embodiment, determining the broken window detection result based on the current micro-Doppler characteristics includes: determining one or more of phase change data, frequency change data, and spectral broadening data based on the current micro-Doppler characteristics; determining a preliminary detection result based on one or more of the phase change data, frequency change data, and spectral broadening data, and using the preliminary detection result as the broken window detection result. It can be understood that here, the current micro-Doppler characteristics can be judged based on the spectral characteristics of each stage of the broken window. If they match, then a broken window is considered to have occurred; otherwise, it is considered normal and no broken window has occurred.

[0062] Following the above embodiments, a preliminary detection result is determined based on one or more of phase change data, frequency change data, and spectral broadening data, including: if the phase change data shows a negative phase change trend, the preliminary detection result is determined to be a broken window, indicating the initial stress stage; if the frequency change data shows a high-frequency change trend, the preliminary detection result is determined to be a broken window, indicating the crack initiation and propagation stage; if the phase change data includes both negative and positive phase change trends, and the spectral broadening data shows a spectral broadening trend, the preliminary detection result is determined to be a broken window, indicating the glass fragments are scattering and falling off.

[0063] The broken window phenomenon involves multiple stages, each with dynamic characteristics (such as impact, crack propagation, and fragmentation) that manifest differently in the frequency domain. The Doppler effect allows for accurate identification of these dynamic changes.

[0064] 1. Impact / Initial Stress Stage (If the window is broken intentionally): The moment the tool contacts the glass, it causes a tiny, inward displacement. UWB radar will detect a brief, low-speed negative velocity (towards the radar). Micro-Doppler characteristic: a brief negative frequency pulse (negative Doppler shift).

[0065] 2. Crack Initiation and Propagation Stages: Glass is a brittle material, and cracks propagate at extremely high speeds (up to kilometers per second). Although the crack itself is transverse, its initiation and propagation trigger minute vibrations and deformations on the glass surface. Micro-Doppler characteristics: Generate a complex, non-stationary signal composed of multiple high-frequency components.

[0066] 3. Glass Shard Splashing / Falling Stage: After the glass breaks, fragments scatter in all directions. These fragments have different radial velocities (some towards the radar, some away). Micro-Doppler Characteristics: In the frequency domain, both positive (away from the radar) and negative (towards the radar) Doppler frequencies appear simultaneously, and the spectrum broadens instantaneously, dispersing energy over a wide frequency range. This characteristic can be detected by the spectral broadening and the rate of change in the frequency domain.

[0067] As an example, still taking the application of this method to a vehicle, in a scenario where a single-node UWB sensor (integrating transmit and receive antennas) is deployed near the window, the transmitted signal needs to be reflected by the window before returning to the receiver. Essentially, this is a "reflection path," that is, the shortest transmission path across the glass surface. To achieve static reflection interference resolution, the following method can be used: (1) Static background modeling: Collect more than 30 frames (N frames) of RDM (distance-Doppler matrix) data when the vehicle is stationary, calculate the average value to generate a static background template: static background =AVERAGE (RDM frame1 RDM frame2 RDM frameN ) formula (8), static background For a static background template (basic signal), AVERAGE() calculates the average value, RDM. frame1 RDM frame2 RDM frameN The data consists of RDM data for the first frame, the second frame, and the Nth frame. This RDM data includes the reflection characteristics of fixed objects such as seats and metal frames.

[0068] (2) Real-time dynamic filtering: The static background is subtracted from the real-time signal, and the dynamic components generated during the window breaking process are retained: RDM dynamic = RDM current - α × static background Formula (9), Among them, RDM dynamic For dynamic components (reflected signals), RDM current This is the real-time signal (initial signal), and α is the attenuation factor, which can be set as needed, for example, to 0.98. (static)background This is a static background template (basic signal).

[0069] Broken window detection is achieved through RDM → time-spectrum graph → feature extraction: signal segments are extracted from the moving units in RDM_dynamic, and a time-spectrum graph is generated using Short Time Fourier Transform (STFT) to show the frequency variation over time; micro-Doppler features are extracted. (1) Striking, characterized by a brief negative frequency pulse, with a time spectrum of a low-frequency narrow-band pulse; (2) Crack propagation is characterized by high-frequency non-stationary signals, and the time spectrum is a broadband high-frequency speckle. (3) Fragmentation is characterized by positive / negative frequency mixing + spectral broadening, and the time spectrum diagram shows symmetrical frequency band diffusion.

[0070] For example, a range-Doppler matrix (RDM) can be designed to suppress static reflection interference from seats / metal frames: Let the received signal be s(t), and a two-dimensional matrix be generated through pulse compression and Fast Fourier Transform (FFT): Formula (10), in, It is a two-dimensional matrix, where r is the distance element, v is the velocity element, and f is the velocity element. c The center frequency is used to divide the signal into distance units (e.g., one unit every 15 cm) and velocity units (e.g., one unit every 0.5 m / s). s(t) is the reflected signal at time t, and j is the imaginary unit.

[0071] An example code implementation for static background modeling is as follows: Initialize the static background template (collected when the vehicle is stationary). static_background = np.zeros((num_range_bins, num_doppler_bins)) Collect N frames continuously (N≥30) for frame in range(N_frames): # Obtain a single frame RDM rdm_frame = capture_rdm() # Accumulate RDM data for each frame static_background += rdm_frame Generate average static template static_background / = N_frames Real-time filtering calculation: Formula (11), Among them, RDM dynamic (r,v) represents the dynamic components (reflected signal), RDM current (r, v) represents the real-time signal (initial signal), and α is the attenuation factor, which can be set as needed, for example, to 0.98. (static) background (r,v) is the static background template (basic signal).

[0072] In one embodiment, after determining the broken window detection result based on the current micro-Doppler features, the method further includes: if the broken window detection result includes a broken window, generating an alarm message and displaying it. The display method can be implemented in a manner known to those skilled in the art, including but not limited to prompts such as sound, light, electricity, and video, as well as prompts via SMS, email, push notifications, etc.

[0073] For example, see continue. Figure 1 The system receives processing results from various nodes via the MCU (Microcontroller Unit). Once a broken window is confirmed, the MCU controls the audible and visual alarm to sound an alarm. After the alarm is triggered, the MCU sends the alarm signal to the owner's mobile app via the CAN bus, notifying the owner of the broken window incident.

[0074] The broken window detection method proposed in the above embodiments acquires the reflected signal of the window to be detected, which includes the signal reflected by the window during the detection period. The current micro-Doppler feature is determined based on the reflected signal, and the broken window detection result is determined based on the current micro-Doppler feature. This method extracts micro-Doppler features from the reflected signal obtained by the window to be detected reflecting the transmitted signal, and determines whether a broken window has occurred based on the micro-Doppler feature. This avoids the problem of low accuracy of broken window detection relying on vibration, improves detection accuracy, and enhances user experience.

[0075] The broken window detection method provided in the above embodiments, by applying UWB technology to broken window detection, has a core advantage over related broken window detection methods in that it can leap from detecting "vibration results" to sensing "damage processes," thereby achieving earlier and smarter early warnings, high-precision broken window detection, and avoiding false alarms and missed alarms. It also has high environmental adaptability, adapting to various environments, including temperature changes, rain and snow, and dynamic changes inside the vehicle, because UWB signals have good penetration and anti-interference capabilities, effectively penetrating glass and unaffected by interference from common wireless devices (such as Wi-Fi and Bluetooth).

[0076] In one embodiment, a broken window detection device is provided, which is used to perform the broken window detection method provided in any of the above embodiments. Please refer to [link to previous document]. Figure 3 , Figure 3A schematic diagram of a broken window detection device provided in an embodiment of this application is shown below. Figure 3 As shown, the broken window detection device 300 includes: an acquisition module 320, a determination module 330, and a detection module 340, wherein: the acquisition module 320 is used to acquire the reflected signal of the window to be detected, the reflected signal including the signal reflected by the window to be detected from the transmitted signal during the detection time period; the determination module 330 is used to determine the current micro-Doppler feature based on the reflected signal; and the detection module 340 is used to determine the broken window detection result based on the current micro-Doppler feature.

[0077] As an example, see further. Figure 3 The acquisition module can be integrated into the UWB sensor 310. The transmission signal is sent by the UWB sensor 310.

[0078] In another embodiment, the UWB sensor is also used to receive an initial signal, and the device further includes a signal preprocessing module for converting the initial signal into a reflected signal so that the acquisition module can acquire the reflected signal.

[0079] In one embodiment, the device further includes an alarm device for generating and displaying an alarm message if the broken window detection result includes a broken window.

[0080] Specific limitations regarding the broken window detection device can be found in the limitations of the broken window detection method described above, and will not be repeated here. Each module in the aforementioned broken window detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the corresponding operations of each module.

[0081] In this embodiment, the broken window detection device is essentially equipped with multiple modules to execute the broken window detection method in any of the above embodiments. The specific functions and technical effects can be referred to in the above embodiments, and will not be repeated here.

[0082] See Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown below. Figure 4 As shown, this embodiment of the invention also provides an electronic device 400, including a processor 401, a memory 402, and a communication bus 403; the communication bus 403 is used to connect the processor 401 and the memory 402; the processor 401 is used to execute a computer program stored in the memory 402 to implement the method described in any of the above embodiments.

[0083] As an example, this electronic device could be a smart vehicle.

[0084] This invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being used to cause a computer to perform the method provided in any of the above embodiments.

[0085] This application also provides a non-volatile readable storage medium storing one or more modules (programs) that, when applied to a device, enable the device to execute the instructions included in the steps provided in this application.

[0086] This application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.

[0087] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can 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 program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0088] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0089] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] It should be understood that the terms "first," "second," etc., used in this application are used to distinguish similar objects and do not necessarily indicate a specific order or sequence. The technical features to which these terms are used can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0092] It should be understood that although the flowcharts provided in the embodiments of this application indicate the various steps with arrows, the order indicated by the arrows does not necessarily limit the implementation order of these steps. Those skilled in the art can perform these steps in other orders according to different implementation scenarios and requirements.

[0093] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A broken window detection method, characterized in that, The method includes: Acquire the reflected signal of the window to be detected, the reflected signal including the signal reflected by the transmitted signal during the detection period through the window to be detected; The current microDoppler characteristic is determined based on the reflected signal; The broken window detection result is determined based on the current micro-Doppler features.

2. The broken window detection method as described in claim 1, characterized in that, Determining the broken window detection result based on the current micro-Doppler features includes: The current micro-Doppler features are input into the detection model to obtain the broken window detection result. The detection model is trained using sample signal data, which includes sample micro-Doppler features and sample broken window results. The sample micro-Doppler features are determined based on the reflected signals collected during the broken window process in the sample collection phase. The broken window results of the samples include: Broken window; or, The broken window and detailed data on the broken window, including the type of glass and / or the tool used to break the window.

3. The broken window detection method as described in claim 2, characterized in that, Before inputting the current micro-Doppler features into the detection model, the method further includes: Based on the current microDoppler characteristics, determine one or more of the phase change data, frequency change data, and spectral broadening data; A preliminary detection result is determined based on one or more of the phase change data, frequency change data, and spectrum broadening data. If the preliminary detection result is the target result, the step of inputting the current micro-Doppler features into the detection model is triggered.

4. The broken window detection method as described in claim 1, characterized in that, Determining the broken window detection result based on the current micro-Doppler features includes: Based on the current microDoppler characteristics, determine one or more of the phase change data, frequency change data, and spectral broadening data; A preliminary detection result is determined based on one or more of the phase change data, frequency change data, and spectrum broadening data, and the preliminary detection result is used as the broken window detection result.

5. The broken window detection method as described in claim 3 or 4, characterized in that, Preliminary detection results are determined based on one or more of the phase change data, frequency change data, and spectral broadening data, including: If the phase change data shows a negative phase change trend, the preliminary detection result is determined to be a broken window, indicating that the device is in the initial stress stage. If the frequency change data shows a high-frequency trend, the preliminary detection result is determined to be a broken window, indicating that the crack is in the stage of initiation and propagation. If the phase change data includes both negative and positive phase change trends, and the spectral broadening data is a spectral broadening trend, the preliminary detection result is determined to be a broken window, indicating that the glass is in the stage of shattering and falling.

6. The broken window detection method according to any one of claims 1-5, characterized in that, Acquire the reflected signal from the window to be detected, including: The UWB anchor point transmits a transmission signal; the UWB anchor point receives the signal reflected by an obstacle at a preset distance within a detection time period to obtain an initial signal, wherein the obstacle includes one or more of the window to be detected and fragments of the window to be detected; the initial signal is subjected to noise removal and / or low-frequency filtering to obtain the reflected signal; or, UWB anchors transmit signals, and the UWB anchors are set inside the vehicle. There are multiple UWB anchors, and at least one UWB anchor corresponds to at least one window to be detected. The UWB anchor receives the transmitted signal reflected by an obstacle within a preset distance during the detection time period to obtain an initial signal. The obstacle includes one or more of the window to be detected and fragments of the window to be detected. All initial signals are time-synchronized to obtain the reflected signal. or, A basic signal is acquired, which is generated by receiving the transmitted signal after sending the transmitted signal in the initial stage when no window breakage occurs. In the detection stage, the reflected signal of the transmitted signal is received as the initial signal. The initial signal is filtered by the basic signal, and the filtered initial signal is used as the reflected signal.

7. The broken window detection method according to any one of claims 1-5, characterized in that, Before acquiring the reflection signal of the window to be detected, the method further includes: A transmission signal is transmitted, wherein the transmission signal is a pulse UWB signal; the signal transmission power and pulse width of the transmission signal are determined according to the window size of the window to be detected; or, The system acquires the current temperature and the current received signal strength indication, determines a power adjustment value based on the current temperature, the current received signal strength indication, the target temperature, and the target received signal strength indication, adjusts the transmission power of the transmitted signal based on the power adjustment value, and the adjusted transmission power is greater than a preset minimum power and less than a preset maximum power.

8. The broken window detection method according to any one of claims 1-5, characterized in that, After determining the broken window detection result based on the current micro-Doppler features, the method further includes: if the broken window detection result includes a broken window, generating an alarm message and displaying it.

9. A broken window detection device, characterized in that, The device includes an acquisition module, a determination module, and a detection module, wherein: The acquisition module is used to acquire the reflected signal of the window to be detected, the reflected signal including the signal reflected by the window to be detected of the transmitted signal during the detection time period; The determining module is used to determine the current micro-Doppler feature based on the reflected signal; The detection module is used to determine the broken window detection result based on the current microDoppler features.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 8.

Images