Parking safety monitoring method and device based on AI and Internet of Things technology

Abstract

The invention relates to the technical field of vehicle safety, and discloses a parking safety monitoring method and device based on AI and Internet of Things technology, and the method comprises the steps: calculating a target judgment value corresponding to a vehicle according to the multi-dimensional feature information of a detected object detected by a detection device corresponding to the determined vehicle; according to the environment information of the environment where the vehicle is located, a self-adaptive judgment threshold value of the vehicle about the environment is determined; according to the judgment value and a self-adaptive judgment threshold value, whether the vehicle meets a preset awakening condition or not is judged; and when it is judged that the vehicle meets the awakening condition, the vehicle is controlled to enter an awakening state so as to execute corresponding safety monitoring operation of the vehicle. Visibly, the vehicle monitoring accuracy and reliability can be improved by implementing the method and the device, so that the probability that the vehicle is mistakenly awakened can be reduced while a good parking safety monitoring effect is kept.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle safety technology, and in particular to a parking safety monitoring method and device based on AI and Internet of Things technology. BACKGROUND

[0002] With the development of automobile intelligence, parking safety monitoring technology is increasingly concerned. At present, the parking safety monitoring method is mainly based on millimeter wave radar technology. Based on millimeter wave radar technology, the vehicle can monitor the surrounding environment when the vehicle is unattended after parking, and can wake up the vehicle to timely remind the owner or take appropriate measures when an abnormal situation is detected, which is beneficial to improve the parking safety monitoring effect.

[0003] However, it is found in practice that the existing parking safety monitoring method simply uses the time distance (ratio of distance and speed) of the vehicle and its surrounding objects detected by the millimeter wave radar to judge the type of objects approaching the vehicle based on the time distance threshold preset based on experience value, which is relatively single in feature and is easy to cause a high probability of false wake-up of the vehicle. Therefore, it is particularly important to propose a technical solution that can reduce the probability of false wake-up of the vehicle while maintaining good parking safety monitoring effect. SUMMARY The present application provides a parking safety monitoring method and device based on AI and Internet of Things technology, which can reduce the probability of false wake-up of the vehicle while maintaining good parking safety monitoring effect.

[0004] In order to solve the above technical problems, the first aspect of the present application discloses a parking safety monitoring method based on AI and Internet of Things technology, which comprises: According to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle, the target judgment value corresponding to the vehicle is calculated; By determining the environmental information of the environment where the vehicle is located, the adaptive judgment threshold of the vehicle about the environment is calculated; According to the target judgment value and the adaptive judgment threshold, it is judged whether the vehicle meets the preset wake-up condition; When it is judged that the vehicle meets the wake-up condition, the vehicle is controlled to enter the wake-up state, and after the vehicle is woken up, the matching safety monitoring device of the detection device is controlled to perform corresponding safety monitoring operation on the vehicle.

[0005] As an optional implementation, in the first aspect of the present application, the target judgment value corresponding to the vehicle is calculated according to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle, which comprises: acquire detection information of a detection device corresponding to the vehicle, the detection information comprising at least one of a starting frequency bandwidth and a sweep frequency period; calculate, according to the detection information, multi-dimensional feature information of a detected object detected by the detection device, the detected object being an object within a preset range where the vehicle is located, the multi-dimensional feature information comprising a plurality of sub-class feature information, and all the sub-class feature information comprising at least two of a speed, a distance, a micro-Doppler feature and an RCS value; calculate, for each of the sub-class feature information, a judgment value of the sub-class feature information, and determine a weight coefficient corresponding to the sub-class feature information; calculate, according to the judgment values of all the sub-class feature information and the weight coefficient corresponding to each of the sub-class feature information, a target judgment value corresponding to the vehicle.

[0006] As an optional implementation, in the first aspect of the present application, the calculation of the judgment value of the sub-class feature information comprises: when the sub-class feature information is the micro-Doppler feature, determining, according to the detection information, a phase time sequence signal of the detection device; performing short-time Fourier transform on the phase time sequence signal to obtain a time-frequency spectrogram, and extracting a frequency of a maximum energy peak from a plurality of energy peak frequencies indicated by the time-frequency spectrogram as a main modulation frequency; if the main modulation frequency is greater than or equal to a first preset frequency threshold and less than or equal to a second preset frequency threshold, determining the judgment value of the micro-Doppler feature as a first judgment value, the first preset frequency threshold being less than the second preset frequency threshold; if the main modulation frequency is greater than the second preset frequency threshold and less than or equal to a third preset frequency threshold, determining the judgment value of the micro-Doppler feature as a second judgment value, the second preset frequency threshold being less than the third preset frequency threshold; if the main modulation frequency is less than the first preset frequency threshold or greater than the third preset frequency threshold, determining the judgment value of the micro-Doppler feature as a third judgment value, the first judgment value being greater than the second judgment value, and the second judgment value being greater than the third judgment value.

[0007] As an optional implementation, in the first aspect of the present application, the calculation of the adaptive judgment threshold of the vehicle with respect to the environment of the vehicle comprises: acquiring positioning information of the vehicle and wake-up record information of the vehicle; According to the positioning information of the vehicle, an environment type of an environment where the vehicle is located is determined, and the environment type corresponds to a risk level; according to the risk level corresponding to the environment type, a reference judgment value corresponding to the environment type is determined, and the risk level is negatively correlated with the reference judgment value; According to the wake-up record information of the vehicle, a wake-up record feature value of the vehicle is calculated, and the wake-up record feature value is calculated under the condition that the vehicle is in the same positioning information; According to the reference judgment value corresponding to the environment type and the wake-up record feature value of the vehicle, an adaptive judgment threshold of the vehicle with respect to the environment is calculated.

[0008] As an optional implementation, in the first aspect of the present application, the judging whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold comprises: comparing the target judgment value and the adaptive judgment threshold to obtain a comparison result; when the comparison result indicates that the target judgment value is greater than the adaptive judgment threshold, it is determined that the vehicle meets the preset wake-up condition; when the comparison result indicates that the target judgment value is less than or equal to the adaptive judgment threshold, it is determined that the vehicle does not meet the preset wake-up condition.

[0009] As an optional implementation, in the first aspect of the present application, the controlling the safety monitoring device matched with the detection device to perform corresponding safety monitoring operation on the vehicle comprises: controlling the safety monitoring device matched with the detection device to monitor image data related to the vehicle according to the position of the detection device; analyzing the image data to determine whether the vehicle meets a preset warning condition; when it is determined that the vehicle meets the warning condition, sending a warning notification information to the owner bound to the vehicle.

[0010] As an optional implementation, in the first aspect of the present application, the image data comprises video data and / or image data; and, the analyzing the image data to determine whether the vehicle meets a preset warning condition comprises: when the image data is video data, performing splitting processing on the video data to obtain a plurality of initial video frames corresponding to the video data; inputting each initial video frame into a pre-trained classification model for classification to obtain an object type of a foreground object indicated by the initial video frame; select all target video frames of an object type being a preset type from all the initial video frames according to an object type of a foreground object indicated by all the initial video frames; calculate a ratio between the number of the target video frames and the number of the initial video frames, and determine whether the ratio is greater than a preset ratio; determine that the vehicle meets a preset warning condition when it is determined that the ratio is greater than the preset ratio; determine that the vehicle does not meet a preset warning condition when it is determined that the ratio is less than or equal to the preset ratio.

[0011] The second aspect of the present application discloses a parking safety monitoring device based on AI and Internet of Things technology, which comprises: A calculation module is configured to calculate a target judgment value corresponding to the vehicle according to multi-dimensional feature information of a detected object detected by a detection device corresponding to the vehicle. The calculation module is further configured to calculate an adaptive judgment threshold of the vehicle with respect to an environment by determining environment information of the environment. A judgment module is configured to determine whether the vehicle meets a preset wake-up condition according to the target judgment value and the adaptive judgment threshold. A control module is configured to control the vehicle to enter a wake-up state when the judgment module determines that the vehicle meets the wake-up condition, and control a safety monitoring device matched with the detection device to perform a corresponding safety monitoring operation on the vehicle after the vehicle is woken up.

[0012] As an optional implementation, in the second aspect of the present application, the specific manner in which the calculation module calculates the target judgment value corresponding to the vehicle according to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle comprises: Obtain detection information of a detection device corresponding to the vehicle, the detection information comprising at least one of a starting frequency bandwidth and a sweep frequency period. According to the detection information, calculate multi-dimensional feature information of a detected object detected by the detection device, the detected object being an object within a preset range of the vehicle, the multi-dimensional feature information comprising a plurality of sub-class feature information, and all the sub-class feature information comprising at least two of speed, distance, micro-Doppler feature and RCS value. For each sub-class feature information, calculate a judgment value of the sub-class feature information and determine a weight coefficient corresponding to the sub-class feature information. According to the judgment values of all the sub-class feature information and the weight coefficient corresponding to each sub-class feature information, calculate the target judgment value corresponding to the vehicle.

[0013] As an optional implementation, in the second aspect of the present application, the specific manner in which the calculation module calculates the judgment value of the sub-class feature information comprises: When the sub-class feature information is the micro-Doppler feature, according to the detection information, a phase timing signal of the detection device is determined; The phase timing signal is subjected to short-time Fourier transform to obtain a time-frequency spectrogram; and a frequency of a maximum energy peak is extracted from a plurality of energy peak frequencies indicated by the time-frequency spectrogram as a main modulation frequency; If the main modulation frequency is greater than or equal to a first preset frequency threshold and less than or equal to a second preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a first judgment value, the first preset frequency threshold being less than the second preset frequency threshold; If the main modulation frequency is greater than the second preset frequency threshold and less than or equal to a third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a second judgment value, the second preset frequency threshold being less than the third preset frequency threshold; If the main modulation frequency is less than the first preset frequency threshold or greater than the third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a third judgment value, the first judgment value being greater than the second judgment value, and the second judgment value being greater than the third judgment value.

[0014] As an optional implementation, in the second aspect of the present application, the specific manner in which the calculation module calculates the adaptive judgment threshold of the vehicle with respect to the environment comprises: Obtaining positioning information of the vehicle and wake-up record information of the vehicle; According to the positioning information of the vehicle, an environment type of the environment in which the vehicle is located is determined, the environment type having a corresponding risk level; according to the risk level corresponding to the environment type, a reference judgment value corresponding to the environment type is determined, the risk level being negatively correlated with the reference judgment value; According to the wake-up record information of the vehicle, a wake-up record feature value of the vehicle is calculated, the wake-up record feature value being calculated under the condition that the vehicle is in the same positioning information; According to the reference judgment value corresponding to the environment type and the wake-up record feature value of the vehicle, an adaptive judgment threshold of the vehicle with respect to the environment is calculated.

[0015] As an optional implementation, in the second aspect of the present application, the specific manner in which the judgment module judges whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold comprises: comparing the target determination value with the adaptive determination threshold to obtain a comparison result; when the comparison result indicates that the target determination value is greater than the adaptive determination threshold, determining that the vehicle meets a preset wake-up condition; when the comparison result indicates that the target determination value is less than or equal to the adaptive determination threshold, determining that the vehicle does not meet the preset wake-up condition.

[0016] As an optional implementation, in the second aspect of the present application, the control module controls the matching safety monitoring device of the detection device to perform a corresponding safety monitoring operation on the vehicle, comprising: controlling the matching safety monitoring device of the detection device to monitor image data related to the vehicle according to the position of the detection device; analyzing the image data to determine whether the vehicle meets a preset warning condition; when it is determined that the vehicle meets the warning condition, sending a warning notification message to the vehicle owner bound to the vehicle.

[0017] As an optional implementation, in the second aspect of the present application, the image data comprises video data and / or image data; and the control module analyzes the image data to determine whether the vehicle meets a preset warning condition, comprising: when the image data is video data, performing splitting processing on the video data to obtain a plurality of initial video frames corresponding to the video data; inputting each initial video frame into a pre-trained classification model for classification to obtain the object type of the foreground object indicated by the initial video frame; selecting all target video frames of a preset type from all the initial video frames according to the object types of the foreground objects indicated by all the initial video frames; calculating the ratio between the number of target video frames and the number of initial video frames, and determining whether the ratio is greater than a preset ratio; when it is determined that the ratio is greater than the preset ratio, determining that the vehicle meets a preset warning condition; when it is determined that the ratio is less than or equal to the preset ratio, determining that the vehicle does not meet the preset warning condition.

[0018] The third aspect of the present application discloses another parking safety monitoring device based on AI and Internet of Things technology, comprising: a memory storing executable program code; a processor coupled to the memory; The processor invokes the executable program code stored in the memory to execute the AI and Internet of Things technology-based parking safety monitoring method disclosed in the first aspect of the application.

[0019] The fourth aspect of the application discloses a computer storage medium storing computer instructions, which are invoked to execute the AI and Internet of Things technology-based parking safety monitoring method disclosed in the first aspect of the application.

[0020] Compared with the prior art, the embodiments of the application have the following beneficial effects: In the embodiments of the application, the target judgment value corresponding to the vehicle is calculated according to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle, the adaptive judgment threshold of the vehicle with respect to the environment is determined according to the environmental information of the environment in which the vehicle is located, whether the vehicle meets the preset wake-up condition is judged according to the target judgment value and the adaptive judgment threshold, and when it is judged that the vehicle meets the wake-up condition, the vehicle is controlled to enter a wake-up state, and after the vehicle is woken up, the safety monitoring device matched with the detection device is controlled to perform corresponding safety monitoring operations on the vehicle. It can be seen that, by implementing the application, the target judgment value corresponding to the vehicle can be accurately calculated according to the determined multi-dimensional feature information of the detected object, the adaptive judgment threshold of the vehicle with respect to the environment can be automatically determined according to the environmental information of the environment in which the vehicle is located, then whether the vehicle meets the preset wake-up condition can be accurately judged according to the target judgment value and the adaptive judgment threshold, which can make the judgment threshold used as the basis for vehicle wake-up judgment adaptively change with the change of the environment in which the vehicle is located, so as to better apply to different scenarios, and is conducive to reducing the probability of misjudgment, thereby being conducive to reducing the probability of vehicle miswaking up; and after the vehicle is woken up, the safety monitoring device matched with the detection device is controlled to perform corresponding safety monitoring operations on the vehicle, which can improve the matching degree of the detection device and the safety monitoring device with control requirements, thereby being able to improve the accuracy and efficiency of controlling the safety monitoring device, and being conducive to maintaining good safety monitoring effect. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a flowchart of an AI and Internet of Things technology-based parking safety monitoring method disclosed by the embodiments of the application; Figure 2is a flow diagram of another AI and Internet of Things technology-based parking safety monitoring method disclosed by an embodiment of the present application; Figure 3 is a flow diagram of still another AI and Internet of Things technology-based parking safety monitoring method disclosed by an embodiment of the present application; Figure 4 is a structural diagram of a parking safety monitoring device disclosed by an embodiment of the present application; Figure 5 is a structural diagram of an AI and Internet of Things technology-based parking safety monitoring device disclosed by an embodiment of the present application; Figure 6 is a structural diagram of another AI and Internet of Things technology-based parking safety monitoring device disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor fall within the scope of protection of the present application.

[0024] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or end.

[0025] In this document, the term "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] The application discloses a parking safety monitoring method and device based on AI and Internet of Things technology, which can accurately calculate the target judgment value corresponding to the vehicle according to the multi-dimensional feature information of the detected object determined, and automatically determine the adaptive judgment threshold of the vehicle about the environment according to the environment information of the environment where the vehicle is located, and then accurately judge whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold, so that the judgment threshold used as the basis for vehicle wake-up judgment can adaptively change with the change of the environment where the vehicle is located, better adapt to different scenes, and help reduce the probability of misjudgment, thereby helping to reduce the probability of vehicle miswakeup; and after the vehicle is woken up, the safety monitoring device matched with the detection device is controlled to perform corresponding safety monitoring operation on the vehicle, which can improve the matching degree of the detection device and the safety monitoring device with control requirements, thereby improving the accuracy and efficiency of controlling the safety monitoring device, and helping to maintain good safety monitoring effect. The following will be described in detail.

[0027] Embodiment one Please refer to Figure 1 , Figure 1 is a flowchart of a parking safety monitoring method based on AI and Internet of Things technology disclosed by the embodiment of the application. Among them, Figure 1 The AI and Internet of Things technology-based parking safety monitoring method described can be applied to an AI and Internet of Things technology-based parking safety monitoring device, wherein the device can include a monitoring device or a monitoring server, wherein the monitoring server can include a cloud server or a local server, and the embodiment of the application does not limit it. As Figure 1 The AI and Internet of Things technology-based parking safety monitoring method can include the following operations: 101. Calculate the target judgment value corresponding to the vehicle according to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle determined.

[0028] In the embodiment of the application, the detection device can be a millimeter wave radar, a laser radar, or other devices that can have the same detection effect, and the embodiment of the application does not limit it.

[0029] In the embodiment of the application, the detected object is an object within a preset range where the vehicle is located, such as an object detected by the detection device within 5 meters away from the vehicle.

[0030] 102. Calculate the adaptive judgment threshold of the vehicle about the environment by determining the environment information of the environment where the vehicle is located.

[0031] Optionally, the environment information can include an environment type, and can also include at least one of the following: a number of pedestrians, a density of pedestrians, a number of vehicles, a density of vehicles, and the like.

[0032] In the embodiment of the present application, specifically, the environment type of the environment in which the vehicle is located is determined, and the adaptive determination threshold of the vehicle with respect to the environment is calculated according to the environment type; or, the pedestrian and vehicle related information in the scene in which the vehicle is located is determined, and the adaptive determination threshold of the vehicle with respect to the environment is calculated according to the pedestrian and vehicle related information.

[0033] In the embodiment of the present application, there is no sequence between step 102 and step 101, that is, step 102 can occur before step 101, can occur after step 101, or can occur simultaneously with step 101, and the embodiment of the present application is not limited.

[0034] 103. Determine whether the vehicle meets the preset wake-up condition according to the target determination value and the adaptive determination threshold.

[0035] Optionally, the wake-up condition can be used to represent a condition that the target determination value is greater than the adaptive determination threshold, or can be used to represent a condition that an absolute value difference between the target determination value and the adaptive determination threshold is greater than a preset difference value, and the embodiment of the present application is not limited.

[0036] In the embodiment of the present application, when the determination result of step 103 is yes, that is, when it is determined that the vehicle meets the wake-up condition, step 104 is triggered to be executed; when the determination result of step 103 is no, that is, when it is determined that the vehicle does not meet the wake-up condition, the operations of steps 101-102 can be re-executed, or the present process can be ended, and the embodiment of the present application is not limited.

[0037] 104. Control the vehicle to enter a wake-up state, and after the vehicle is woken up, control the matched safety monitoring device of the detection device to perform corresponding safety monitoring operations on the vehicle.

[0038] Optionally, the safety monitoring device can be a camera, and can also be a sensor, such as an infrared sensor, and the embodiment of the present application is not limited. For example, after the vehicle is woken up, the matched camera of the millimeter wave radar is controlled by the shooting device on the vehicle to perform corresponding safety monitoring operations on the vehicle.

[0039] It can be seen that, by implementing the method of the present application, the vehicle can be woken up in a timely manner, and the safety monitoring operations on the vehicle can be performed in a timely manner. Figure 1The AI and Internet of Things technology-based parking safety monitoring method described herein can accurately calculate the target judgment value corresponding to the vehicle according to the determined multi-dimensional feature information of the detected object, automatically determine the adaptive judgment threshold of the vehicle with respect to the environment according to the environmental information of the environment in which the vehicle is located, and then accurately judge whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold. This can make the judgment threshold used as the basis for vehicle wake-up judgment adaptively change with the change of the environment in which the vehicle is located, better adapt to different scenarios, and help reduce the probability of misjudgment, thereby helping to reduce the probability of vehicle miswakeup. After the vehicle is woken up, the safety monitoring device matched with the detection device is controlled to perform corresponding safety monitoring operations on the vehicle, which can improve the matching degree of the detection device and the safety monitoring device with control requirements, thereby improving the accuracy and efficiency of controlling the safety monitoring device and helping to maintain good safety monitoring effect.

[0040] In an optional embodiment, the step of calculating the target judgment value corresponding to the vehicle according to the determined multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle in step 101 can include: obtaining detection information of the detection device corresponding to the vehicle; calculating the multi-dimensional feature information of the detected object detected by the detection device according to the detection information, the multi-dimensional feature information including a plurality of sub-class feature information; for each sub-class feature information, calculating a judgment value of the sub-class feature information and determining a weight coefficient corresponding to the sub-class feature information; calculating the target judgment value corresponding to the vehicle according to the judgment values of all sub-class feature information and the weight coefficient corresponding to each sub-class feature information.

[0041] In the embodiments of the present application, optionally, the detection information includes at least one of the starting frequency bandwidth and the sweep frequency period, which is not limited in the embodiments of the present application.

[0042] In the embodiment of the present application, optionally, all sub-class feature information of the multi-dimensional feature information includes at least two of speed, distance, micro-Doppler feature and RCS value (reflective cross-sectional area), wherein the micro-Doppler feature can be used to represent the volume of the detected object, and the RCS value can be used to represent the type of the detected object (such as: pedestrian type, or small animal type), which is not limited in the embodiment of the present application. In this way, not only the speed and distance of the object close to the vehicle are considered, but also the judgment values of the RCS and micro-Doppler features, which are two types of parameters, are considered, so that in addition to the probability of waking up the vehicle being greater when the speed of the object is faster and the distance is closer, the type and volume of the object are also judged, so that when the type of the object belongs to the human body, the object can be preferentially woken up, in addition, the larger the volume, the higher the probability of waking up, so that the probability of false wake-up caused by small animals close to the vehicle can be reduced.

[0043] In the embodiment of the present application, the calculation formula of the distance of the detected object is as follows: ; Among them, is the distance, is the spectral peak position, is the speed of light, is the scanning period, is the scanning bandwidth.

[0044] In the embodiment of the present application, the calculation formula of the speed of the detected object is as follows: ; Among them, represents the speed, represents the Doppler shift, represents the wavelength.

[0045] In the embodiment of the present application, the calculation formula of the RCS value of the detected object is as follows: RCS=(P_r·(4π)^3·d^4) / (P_t·G²·λ²); Among them, P_r is the target echo power, P_t is the radar transmitting power, G is the antenna gain, and λ represents the wavelength.

[0046] In the embodiment of the present application, the micro-Doppler feature of the detected object can be a micro-Doppler frequency threshold, wherein the micro-Doppler frequency threshold can be used to distinguish pedestrians and vehicles. Specifically, when the micro-Doppler frequency threshold is 1-5Hz, it represents the frequency of the pedestrian's limb swing; when the micro-Doppler frequency threshold is 5-50Hz, it represents the frequency of the vehicle vibration.

[0047] In the embodiment of the present application, specifically, for each sub-class feature information in distance, speed, and RCS value, the corresponding normalization processing is performed on the sub-class feature information to obtain the judgment value of the sub-class feature information.

[0048] In the embodiment of the present application, the calculation formula of the target judgment value corresponding to the vehicle is as follows: ; Among them, is the judgment value, , , , is the four weight coefficients, indicates the normalization processing on d, vs is a preset speed threshold value, indicates the normalization processing on , indicates the normalization processing on , indicates a preset contrast value, is the judgment value of the micro-Doppler feature.

[0049] In the embodiment of the present application, the value of each weight coefficient can be obtained based on multi-scene experimental verification. Specifically, 200 groups of data (including pedestrians, vehicles, small animals, and other targets) are collected at the roadside / underground garage / outdoor parking lot, and the false wake-up rate under different weight combinations is counted. The statistical results of the false wake-up rate are shown in Table 1:

[0050] As shown in Table 1, when the weight coefficients are α1=0.3, α2=0.3, α3=0.2, and α4=0.2, the best.

[0051] For example, the preset speed threshold value is vs=10m / s, wherein the speed threshold value can be set by the following method: according to the traffic research data, the walking speed of pedestrians is usually 0.5-2m / s, and the running speed can reach 5-7m / s, so 10m / s is taken to distinguish normal approach and rapid threat, for example: speed lower than or equal to 10m / s indicates that the pedestrian approaches the vehicle at normal speed, and speed higher than 10m / s indicates that the pedestrian approaches the vehicle quickly and may threaten the vehicle.

[0052] For example, the preset contrast value is sRCS=300m², wherein the contrast value can be set by the following method: the experimental measurement shows that the RCS mean value of small animals (such as cats, dogs, etc.) is <1m², the RCS mean value of human body is between 1-2m², and the vehicle is >10m². Taking 300m² can filter more than 99% of small animal interference.

[0053] It can be seen that the optional embodiment can calculate the multi-dimensional feature information of the detected object detected by the detection device according to the acquired detection information of the detection device corresponding to the vehicle, so as to calculate the judgment value of each sub-class feature information and determine the weight coefficient corresponding to the sub-class feature information, thereby accurately calculating the target judgment value corresponding to the vehicle according to the judgment value of all sub-class feature information and the weight coefficient corresponding to each sub-class feature information, improving the calculation accuracy and reliability of the target judgment value corresponding to the vehicle, thereby facilitating the improvement of the judgment accuracy of whether the vehicle meets the wake-up condition based on the target judgment value, and further facilitating the reduction of the probability of the vehicle being mistakenly woken up.

[0054] In the optional embodiment, as an optional implementation, calculating the judgment value of the sub-class feature information can include: When the sub-class feature information is the micro-Doppler feature, determining the phase time sequence signal of the detection device according to the detection information; performing short-time Fourier transform on the phase time sequence signal to obtain a time-frequency spectrum, and extracting the frequency of the maximum energy peak from the multiple energy peak frequencies indicated by the time-frequency spectrum as the main modulation frequency; if the main modulation frequency is greater than or equal to a first preset frequency threshold and less than or equal to a second preset frequency threshold, determining the judgment value of the micro-Doppler feature as a first judgment value, the first preset frequency threshold being less than the second preset frequency threshold; if the main modulation frequency is greater than the second preset frequency threshold and less than or equal to a third preset frequency threshold, determining the judgment value of the micro-Doppler feature as a second judgment value, the second preset frequency threshold being less than the third preset frequency threshold; if the main modulation frequency is less than the first preset frequency threshold or greater than the third preset frequency threshold, determining the judgment value of the micro-Doppler feature as a third judgment value, the first judgment value being greater than the second judgment value, and the second judgment value being greater than the third judgment value.

[0055] For example, if the main modulation frequency is greater than or equal to the first preset frequency threshold and less than or equal to the second preset frequency threshold, the judgment value of the micro-Doppler feature is determined as 1, at this time, the probability that the RCS value can be further deduced to represent the pedestrian is greater; if the main modulation frequency is greater than the second preset frequency threshold and less than or equal to the third preset frequency threshold, the judgment value of the micro-Doppler feature is determined as 0.5; if the main modulation frequency is less than the first preset frequency threshold or greater than the third preset frequency threshold, the judgment value of the micro-Doppler feature is determined as 0. The first preset frequency threshold can be 1 Hz, the second preset frequency threshold can be 5 Hz, and the third preset frequency threshold can be 50 Hz.

[0056] It can be seen that the optional embodiment can automatically determine the phase timing signal of the detection device according to the detection information for the micro-Doppler feature, and perform short-time Fourier transform on the phase timing signal to obtain a time-frequency spectrum, and extract the frequency of the maximum energy peak from the multiple energy peak frequencies indicated by the time-frequency spectrum as the main modulation frequency, which can improve the extraction accuracy of the main modulation frequency used as the determination basis of the judgment value of the micro-Doppler feature. At this time, if the main modulation frequency is greater than or equal to the first preset frequency threshold and less than or equal to the second preset frequency threshold, the judgment value of the micro-Doppler feature is determined as the first judgment value. If the main modulation frequency is greater than the second preset frequency threshold and less than or equal to the third preset frequency threshold, the judgment value of the micro-Doppler feature is determined as the second judgment value. If the main modulation frequency is less than the first preset frequency threshold, or greater than the third preset frequency threshold, the judgment value of the micro-Doppler feature is determined as the third judgment value. The comparison result of the multiple preset frequency thresholds and the main modulation frequency can improve the accuracy and reliability of determining the judgment value of the micro-Doppler feature, thereby facilitating to improve the accuracy and reliability of the target judgment value of the vehicle calculated by the judgment value of the micro-Doppler feature.

[0057] In another optional embodiment, the step 102 of calculating the adaptive judgment threshold of the vehicle about the environment by determining the environment information of the environment where the vehicle is located can include: obtaining the positioning information of the vehicle and the wake-up record information of the vehicle; determining the environment type of the environment where the vehicle is located according to the positioning information of the vehicle, and the environment type has a corresponding risk level; determining the reference judgment value corresponding to the environment type according to the risk level corresponding to the environment type; calculating the wake-up record feature value of the vehicle according to the wake-up record information of the vehicle, and the wake-up record feature value is calculated under the condition that the vehicle is in the same positioning information; calculating the adaptive judgment threshold of the vehicle about the environment according to the reference judgment value corresponding to the environment type and the wake-up record feature value of the vehicle.

[0058] In the embodiment of the application, optionally, the environment type can be set to at least one of a roadside type, an underground garage type, and an outdoor parking lot type, etc., wherein the underground garage corresponding to the underground garage type can include a company garage and a garage at a place where a user lives. The roadside type, the outdoor parking lot type, and the underground garage type correspond to different risk levels, which are not limited in the embodiment of the application.

[0059] In this embodiment of the invention, the risk level is negatively correlated with the benchmark judgment value; that is, the higher the risk level of an environment type, the smaller its corresponding benchmark judgment value. For example, the benchmark judgment values ​​for roadside type, outdoor parking lot type, and underground garage type can be 0.5, 0.75, and 1, respectively, and this embodiment of the invention does not impose any limitations.

[0060] In this embodiment of the invention, the vehicle's wake-up record information can be used to calculate the vehicle's false alarm rate. The higher the false alarm rate, the larger the corresponding wake-up record feature value is set. Specifically, the calculation formula for the wake-up record feature value is as follows: ; in, To wake up the recorded feature value, Under the condition of the same location, the nearest In this series of wake-ups, the number of false wake-ups refers to the situation where the content captured after being woken up and taking pictures does not meet the warning conditions. For example, the settings in this invention... The value is 20. If the cumulative number of wake-ups is less than 20, then... The value is set to the cumulative number of wake-ups.

[0061] In this embodiment of the invention, the specific formula for calculating the adaptive judgment threshold can be as follows: ; in, To adaptively determine the threshold, The characteristic value of the vehicle's environmental type. As the benchmark judgment value, The weight (e.g., it can be set to 0.5) can be adjusted according to actual needs.

[0062] In this embodiment of the invention, optionally, the baseline judgment value can be determined by setting different values ​​for a limited number of trials in different environmental types, and then using the value with the lowest false wake-up probability as the adaptive judgment threshold. That is, under the same test conditions, different values ​​are set as the baseline judgment value to statistically analyze the probability of false wake-up. This makes the adaptive judgment threshold no longer a fixed value, but can adaptively change based on the vehicle's environmental type and wake-up records. This makes it more applicable to different scenarios and can effectively reduce the probability of false wake-up. An example of the experiment is as follows: 10 vehicles are deployed in each of the three scenarios, and the number of false wake-ups is recorded over 7 days, as shown in Table 2.

[0063] As shown in Table 2, the adaptive judgment threshold can significantly reduce the false wake-up rate in high-interference scenarios.

[0064] As can be seen, this optional embodiment can automatically determine the environment type of the vehicle's environment based on the acquired vehicle positioning information, and determine the benchmark judgment value corresponding to the environment type based on the risk level corresponding to the environment type. It can improve the accuracy and efficiency of determining the benchmark judgment value based on the risk level corresponding to the environment type, and can quickly and accurately calculate the vehicle's wake-up record feature value based on the vehicle's wake-up record information. Thus, based on the benchmark judgment value and the wake-up record feature value, it can calculate the vehicle's adaptive judgment threshold with respect to the environment, thereby improving the accuracy and reliability of calculating the adaptive judgment threshold.

[0065] In another optional embodiment, step 103 above, determining whether the vehicle meets the preset wake-up conditions based on the target judgment value and the adaptive judgment threshold, may include: The comparison results are obtained by comparing the target judgment value with the adaptive judgment threshold; When the comparison result indicates that the target judgment value is greater than the adaptive judgment threshold, it is determined that the vehicle meets the preset wake-up conditions; When the comparison result indicates that the target judgment value is less than or equal to the adaptive judgment threshold, it is determined that the vehicle does not meet the preset wake-up conditions.

[0066] As can be seen, this optional embodiment can compare the target judgment value and the adaptive judgment threshold, and when the comparison result indicates that the target judgment value is greater than the adaptive judgment threshold, it determines that the vehicle meets the preset wake-up conditions, thereby improving the accuracy and reliability of determining that the vehicle meets the preset wake-up conditions. Conversely, when the comparison result indicates that the target judgment value is less than or equal to the adaptive judgment threshold, it determines that the vehicle does not meet the preset wake-up conditions, thereby improving the accuracy and reliability of determining that the vehicle does not meet the preset wake-up conditions.

[0067] Example 2 Please see Figure 2 , Figure 2 This is a flowchart illustrating a parking safety monitoring method based on AI and IoT technologies disclosed in an embodiment of the present invention. Figure 2 The described parking safety monitoring method based on AI and IoT technologies can be applied to parking safety monitoring devices based on AI and IoT technologies. These devices may include monitoring equipment or a monitoring server, which may include a cloud server or a local server; this embodiment of the invention does not impose limitations. Figure 2 As shown, this parking safety monitoring method based on AI and IoT technologies may include the following operations: 201. Based on the multi-dimensional feature information of the detected object detected by the detection equipment corresponding to the vehicle, calculate the target judgment value corresponding to the vehicle.

[0068] 202. By determining the environmental information of the vehicle's environment, calculate the vehicle's adaptive judgment threshold regarding the environment.

[0069] In this embodiment of the invention, there is no order between step 202 and step 201. That is, step 202 can occur before step 201, after step 201, or simultaneously with step 201. This embodiment of the invention does not impose any limitations.

[0070] 203. Based on the target judgment value and the adaptive judgment threshold, determine whether the vehicle meets the preset wake-up conditions.

[0071] In this embodiment of the invention, when the judgment result of step 203 is yes, that is, when it is determined that the vehicle meets the wake-up condition, step 204 is triggered; when the judgment result of step 203 is no, the operation of steps 201-202 can be re-executed, or the process can be terminated. This embodiment of the invention does not limit the scope of the process.

[0072] 204. Control the vehicle to enter the wake-up state, and after the vehicle is woken up, control the safety monitoring equipment that matches the detection equipment to monitor the vehicle-related image data according to the location of the detection equipment.

[0073] In this embodiment of the invention, optionally, the safety monitoring device (such as a camera) matching the detection device can be the safety monitoring device closest to the detection device among all the safety monitoring devices corresponding to the vehicle. Compared to the traditional method of activating all cameras to take pictures, which results in excessive standby power consumption because only the camera in the direction in which an object approaches the vehicle can capture the image, this solution can activate the camera closest to the detection device (such as millimeter-wave radar) to take pictures, which not only reduces the vehicle's standby power consumption but also improves the accuracy and efficiency of image data monitoring. Further optionally, the safety monitoring device matching the detection device can also be one or more safety monitoring devices determined based on the vehicle model. Specifically, for low-computing-power vehicles, a lightweight splicing stream solution can be used to achieve basic monitoring with only a single camera; for high-computing-power vehicles, a multi-camera stream solution can be used to achieve comprehensive monitoring by multiple cameras.

[0074] In this embodiment of the invention, the image data may optionally include video data and / or image data, and the amount of image data can be obtained by setting the monitoring duration of the security monitoring device. For example, the camera can shoot a video of a preset duration (such as 20 seconds) when shooting. This embodiment of the invention does not limit this.

[0075] In this embodiment of the invention, for other descriptions of steps 201-204, please refer to the detailed description of steps 101-104 in Embodiment 1. These descriptions will not be repeated in this embodiment of the invention.

[0076] 205. Analyzing the image data to determine whether the vehicle meets a preset warning condition.

[0077] In the embodiment of the present application, optionally, the warning condition can be used to represent a condition that the proportion of video frames in which the preset type of foreground object exists in the video data is greater than a preset proportion value, and can also be used to represent a condition that the proportion of image data in which the preset type of foreground object exists in the image data is greater than a preset proportion value. The preset type of foreground object is a human body, which is not limited in the embodiment of the present application.

[0078] In the embodiment of the present application, when the determination result of step 205 is yes, that is, when it is determined that the vehicle meets the warning condition, step 206 is triggered for execution; when the determination result of step 205 is no, that is, when it is determined that the vehicle does not meet the warning condition, the operation of steps 204-205 can be re-executed, or the present process can be ended, which is not limited in the embodiment of the present application.

[0079] 206. Sending a warning notification information to the owner bound to the vehicle.

[0080] In the embodiment of the present application, optionally, the notification channel for sending the warning notification information to the owner can be an APP push channel or a short message notification channel, and the priority of the APP push channel is higher than that of the short message notification channel, wherein the notification process of the APP push channel can be to send an encrypted push through an official APP of the vehicle enterprise, containing a warning level, a time, a location and a video summary (first frame + key frame) and the like, and the short message notification channel can be to send an SMS containing a short chain (link pointing to a cloud video) when the APP does not respond.

[0081] Optionally, the communication protocol for sending the warning notification information to the owner can be a CP / IP protocol based on T5G NSA / SA network supported in the vehicle-mounted communication module, or can be an HTTPS protocol, the HTTPS protocol is used to upload the video stream compressed by a video compression standard (H.265) to the cloud through the HTTPS protocol, and the video format can be packaged into a JSON format, such as: JSON packaging metadata: {"alert_id":"xxx","location":"GPS coordinates","risk_level":"high"}.

[0082] It can be seen that, by implementing the present application Figure 2The AI and Internet of Things technology-based parking safety monitoring method described herein can accurately calculate the target judgment value corresponding to the vehicle according to the determined multi-dimensional feature information of the detected object, and automatically determine the adaptive judgment threshold of the vehicle with respect to the environment according to the environmental information of the environment in which the vehicle is located, and then accurately judge whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold, so that the judgment threshold used as the basis for vehicle wake-up judgment can adaptively change with the change of the environment in which the vehicle is located, better adapt to different scenarios, and help reduce the probability of misjudgment, thereby helping to reduce the probability of vehicle miswakeup. After the vehicle is woken up, the safety monitoring device matched with the detection device is controlled to perform corresponding safety monitoring operations on the vehicle, which can improve the matching degree of the detection device and the safety monitoring device with control requirements, thereby improving the accuracy and efficiency of controlling the safety monitoring device, and helping to maintain good safety monitoring effect. In addition, after the vehicle is woken up, the safety monitoring device matched with the detection device can be controlled to monitor the image data related to the vehicle according to the position of the detection device, which can improve the monitoring accuracy and efficiency of the image data, so as to analyze the image data to accurately judge whether the vehicle meets the preset warning condition. If the vehicle meets the warning condition, the vehicle owner bound to the vehicle is accurately and timely sent a warning notification information.

[0083] In an optional embodiment, the step 205 of analyzing the image data to determine whether the vehicle meets the preset warning condition can include: When the image data is video data, the video data is split to obtain a plurality of initial video frames corresponding to the video data; Each initial video frame is input into a pre-trained classification model for classification to obtain the object type of the foreground object indicated by the initial video frame; According to the object type of the foreground object indicated by all initial video frames, all target video frames with the object type being the preset type are selected from all initial video frames; The ratio between the number of target video frames and the number of initial video frames is calculated, and it is determined whether the ratio is greater than a preset ratio; When it is determined that the ratio is greater than the preset ratio, it is determined that the vehicle meets the preset warning condition; When it is determined that the ratio is less than or equal to the preset ratio, it is determined that the vehicle does not meet the preset warning condition.

[0084] In the embodiment of the present application, specifically, a low-power NPU (Neural Processing Unit, i.e. embedded neural network processor) can be arranged in the vehicle to analyze the video, the NPU divides the video into multiple frames, and each video frame is input into a pre-trained classification model for analysis, so as to determine the type of the foreground object in the video frame.

[0085] In the embodiment of the present application, optionally, the number of target video frames can be zero or an integer greater than zero. When the number of target video frames is zero, it indicates that the object types of the foreground objects indicated by all video frames are not the preset type (such as the human body type), and when the number of target video frames is an integer greater than zero, it indicates that there is a foreground object of the preset type in the foreground objects indicated by all video frames, which is not limited in the embodiment of the present application.

[0086] Illustratively, the classification model can be a YOLOv13 model, which introduces a Hypergraph theory, models high-order semantic association between multiple targets, significantly improves the detection ability of occluded and small targets (such as distant pedestrians), and the mAP of the Nano version on the COCO dataset reaches 41.6%, with a calculation amount of only 6.4 GFLOPs, which is suitable for vehicle embedded deployment. The HyperGraph structure can process occluded targets (such as pedestrians behind a garage column), and the Nano version is suitable for vehicle NPU; The training materials of the classification model can use AI to generate materials based on existing small amount of materials (such as video frames manually labeled with object types), so as to achieve the purpose of expanding the number of materials. For example, conditional generative adversarial networks (CGANs) can be used to add conditional information such as class labels in the information input to the model to generate images of specified categories. The conditional generative adversarial network can be MCMC-CGAN, which is used to combine Markov Chain Monte Carlo algorithm to filter high-quality samples in latent space to improve the clarity and diversity of generated images, which can be applied to MNIST, CelebA and other labeled data sets. The conditional generative adversarial network can also be ACGAN (GAN with auxiliary classifier), which is used to add a classification task in the discriminator to ensure that the generated images are strongly related to the labels, which is commonly used for biological image generation. The process of generating training data can specifically include: obtaining basic data through a public dataset, such as COCO-Person (e.g. 50,000 human-labeled images); using ACGAN (Auxiliary Classifier GAN) generative adversarial network to expand the data of the basic data; using MCMC-CGAN to sample the generated images and remove blurred / structurally abnormal samples (Top 30% clear samples are retained); Furthermore, the classification model can be optimized for deployment. The optimization process can include: class pruning, reducing the original model from supporting 80 classes to only retaining the "person" class output layer, which helps reduce the computational load of the model; setting a frame analysis strategy, in which the frame sampling frequency is set (e.g., 100 frames are extracted from a 20-second video at 5fps); and setting an early warning condition in the frame analysis strategy, where the early warning condition is triggered when a human body is detected in 50 or more frames (i.e., the proportion is greater than or equal to 0.5).

[0087] As can be seen, this optional embodiment can split the monitored video data to obtain multiple initial video frames, and input each initial video frame into a pre-trained classification model for classification to obtain the object type of the foreground object indicated by the initial video frame. This improves the accuracy and efficiency of classifying foreground objects in each frame of the video. Based on the object types of the foreground objects indicated by all initial video frames, it selects all target video frames with a preset object type from all initial video frames, improving the accuracy and efficiency of selecting target video frames belonging to the preset type. Subsequently, it calculates the ratio between the number of target video frames and the number of initial video frames, and determines whether the ratio is greater than a preset ratio. When the ratio is greater than the preset ratio, it is determined that the vehicle meets the preset warning conditions, improving the accuracy and reliability of determining whether the vehicle meets the preset warning conditions. When the ratio is less than or equal to the preset ratio, it is determined that the vehicle does not meet the preset warning conditions, improving the accuracy and reliability of determining whether the vehicle does not meet the preset warning conditions.

[0088] For example, such as Figure 3 As shown, Figure 3 This is a flowchart illustrating another parking safety monitoring method based on AI and IoT technologies disclosed in an embodiment of the present invention. The parking safety monitoring method based on AI and IoT technologies may include the following steps: S1 determines whether the vehicle meets the wake-up conditions by acquiring detection information from the millimeter-wave radar on the vehicle.

[0089] After being activated, the vehicle's camera system uses the millimeter-wave radar to control the corresponding camera to start and take pictures.

[0090] S3 analyzes the captured video to determine whether it meets the warning conditions.

[0091] S4 sends a warning notification to the vehicle owner when the warning conditions are met.

[0092] Specifically, step S1 may include the following steps: S10 calculates the target's velocity, range, micro-Doppler characteristics, and RCS value based on the detection information; S20, calculating a judgment value according to the speed, the distance, the micro-Doppler feature and the RCS value; S30, comparing the judgment value with an adaptive judgment threshold value to determine whether the wake-up condition is met.

[0093] The determination process of the adaptive judgment threshold value in step S30 comprises: Firstly, the environment type of the vehicle is obtained based on the positioning of the vehicle; Secondly, the wake-up record of the vehicle is obtained; Thirdly, the adaptive judgment threshold value is calculated based on the environment type and the wake-up record.

[0094] The above method of the present application not only utilizes the ranging result of the millimeter wave radar, but also combines the speed, the micro-Doppler feature and the RCS value to calculate the judgment value, which can effectively reduce the probability of false wake-up compared with the judgment only relying on the distance; and the judgment threshold value is not a fixed threshold value, but can be adaptively changed based on the environment type of the vehicle and the wake-up record of the vehicle, which can be better applied to different scenarios and can effectively reduce the probability of false wake-up.

[0095] Exemplarily, in order to realize the above method, the present application further provides a parking safety monitoring device, as shown in Figure 4 , Figure 4 is a structural schematic diagram of a parking safety monitoring device disclosed by an embodiment of the present application, wherein the parking safety monitoring device can comprise a millimeter wave radar, a vehicle-mounted SOC, a camera and a communication module; wherein: The millimeter wave radar is used to obtain detection information in the direction of installation and transmit the detection information to the vehicle-mounted SOC; The vehicle-mounted SOC is used to determine whether the vehicle meets the wake-up condition by obtaining the detection information of the millimeter wave radar on the vehicle, and is used to send a control shooting instruction to the camera according to the position of the millimeter wave radar corresponding to the detection information when the vehicle meets the wake-up condition; The camera is used to shoot in the direction of installation to obtain a video after receiving the shooting instruction, and is used to transmit the obtained video to the vehicle-mounted SOC; The vehicle-mounted SOC is further used to analyze the video obtained by shooting to determine whether the early warning condition is met, and is used to control the communication module to send an early warning notification to the vehicle owner when the early warning condition is met.

[0096] The communication protocol adopted between each device contained in the parking safety monitoring device is as follows: The communication protocol between the millimeter wave radar and the vehicle-mounted SOC can be CAN / CAN FD protocol, which has the characteristics of low delay (millisecond level), anti-interference and multi-node networking; The communication protocol between the camera and the vehicle SOC can be the MIPI CSI-2 + D-PHY / C-PHY protocol, which has the characteristics of high bandwidth (1-10 Gbps), dynamic rate adaptation, and I2C control channel; The communication protocol between the vehicle SOC and the communication module can be the TCP / IP protocol, which can be used to run the vehicle Ethernet; The communication protocol for internal subsystem coordination of the vehicle SOC can be the SOME / IP + AUTOSAR protocol.

[0097] Embodiment three Please refer to Figure 5 , Figure 5 is a structural schematic diagram of a parking safety monitoring device based on AI and Internet of Things technology disclosed by the embodiment of the application. Among them, Figure 5 The AI and Internet of Things technology-based parking safety monitoring device described can include a monitoring device or a monitoring server, wherein the monitoring server can include a cloud server or a local server, and the embodiment of the application does not limit it. As shown in Figure 5 The AI and Internet of Things technology-based parking safety monitoring device can include: The calculation module 301 is configured to calculate a target judgment value corresponding to the vehicle according to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle.

[0098] The calculation module 301 is further configured to calculate an adaptive judgment threshold of the vehicle with respect to the environment by determining the environmental information of the environment in which the vehicle is located.

[0099] The judgment module 302 is configured to judge whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold.

[0100] The control module 303 is configured to control the vehicle to enter a wake-up state when the judgment module 302 judges that the vehicle meets the wake-up condition, and to control the matching safety monitoring device of the detection device to perform corresponding safety monitoring operations on the vehicle after the vehicle is woken up.

[0101] It can be seen that the embodiment Figure 5The AI and Internet of Things technology-based parking safety monitoring device described can accurately calculate the target judgment value corresponding to the vehicle according to the determined multi-dimensional feature information of the detected object, and automatically determine the adaptive judgment threshold of the vehicle with respect to the environment according to the environmental information of the environment in which the vehicle is located, and then accurately judge whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold, so that the judgment threshold used as the basis for vehicle wake-up judgment can adaptively change with changes in the environment in which the vehicle is located, better adapting to different scenarios, helping to reduce the probability of misjudgment, thereby helping to reduce the probability of vehicle miswakeup; and after the vehicle is woken up, the safety monitoring device matched with the detection device is controlled to perform corresponding safety monitoring operations on the vehicle, which can improve the matching degree of the detection device and the safety monitoring device with control requirements, thereby improving the accuracy and efficiency of controlling the safety monitoring device, and helping to maintain good safety monitoring effect.

[0102] In an optional embodiment, the specific manner in which the computing module 301 calculates the target judgment value corresponding to the vehicle according to the determined multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle includes: Obtaining detection information of the detection device corresponding to the vehicle, the detection information including at least one of a starting frequency bandwidth and a sweep frequency period; According to the detection information, calculating the multi-dimensional feature information of the detected object detected by the detection device, the detected object being an object within a preset range of the vehicle, the multi-dimensional feature information including a plurality of sub-class feature information, and all the sub-class feature information including at least two of speed, distance, micro-Doppler feature, and RCS value; For each sub-class feature information, calculating a judgment value of the sub-class feature information and determining a weight coefficient corresponding to the sub-class feature information; According to the judgment values of all the sub-class feature information and the weight coefficient corresponding to each sub-class feature information, calculating the target judgment value corresponding to the vehicle.

[0103] As can be seen, this optional embodiment can calculate the multi-dimensional feature information (including a plurality of sub-class feature information) of the detected object detected by the detection device according to the obtained detection information of the detection device corresponding to the vehicle, thereby calculating the judgment value of each sub-class feature information and determining the weight coefficient corresponding to the sub-class feature information, and accurately calculating the target judgment value corresponding to the vehicle according to the judgment values of all the sub-class feature information and the weight coefficient corresponding to each sub-class feature information, which can improve the calculation accuracy and reliability of the target judgment value corresponding to the vehicle, thereby helping to improve the judgment accuracy of whether the vehicle meets the wake-up condition based on the target judgment value, and further helping to reduce the probability of vehicle miswakeup.

[0104] In the optional embodiment, as an optional implementation, the specific manner in which the computing module 301 calculates the judgment value of the sub-class feature information includes: When the sub-class feature information is the micro-Doppler feature, according to the detection information, a phase timing signal of the detection device is determined; The phase timing signal is subjected to a short-time Fourier transform to obtain a time-frequency spectrogram; and a frequency of a maximum energy peak is extracted from a plurality of energy peak frequencies indicated by the time-frequency spectrogram as a main modulation frequency; If the main modulation frequency is greater than or equal to a first preset frequency threshold and less than or equal to a second preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a first judgment value, the first preset frequency threshold being less than the second preset frequency threshold; If the main modulation frequency is greater than the second preset frequency threshold and less than or equal to a third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a second judgment value, the second preset frequency threshold being less than the third preset frequency threshold; If the main modulation frequency is less than the first preset frequency threshold or greater than the third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a third judgment value, the first judgment value being greater than the second judgment value, and the second judgment value being greater than the third judgment value.

[0105] It can be seen that, in this optional implementation, for the micro-Doppler feature, the phase timing signal of the detection device can be automatically determined according to the detection information, and the phase timing signal is subjected to a short-time Fourier transform to obtain a time-frequency spectrogram, and a frequency of a maximum energy peak is extracted from a plurality of energy peak frequencies indicated by the time-frequency spectrogram as a main modulation frequency, which can improve the extraction accuracy of the main modulation frequency used as the basis for determining the judgment value of the micro-Doppler feature. At this time, if the main modulation frequency is greater than or equal to the first preset frequency threshold and less than or equal to the second preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is the first judgment value, if the main modulation frequency is greater than the second preset frequency threshold and less than or equal to the third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is the second judgment value, and if the main modulation frequency is less than the first preset frequency threshold or greater than the third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is the third judgment value. The comparison result of the plurality of preset frequency thresholds and the main modulation frequency can improve the accuracy and reliability of determining the judgment value of the micro-Doppler feature, thereby facilitating the improvement of the accuracy and reliability of the target judgment value of the vehicle calculated by the judgment value of the micro-Doppler feature.

[0106] In another optional embodiment, the specific manner in which the computing module 301 calculates the adaptive judgment threshold of the vehicle with respect to the environment by determining the environment information of the environment in which the vehicle is located includes: Obtaining positioning information of the vehicle and wake-up record information of the vehicle; According to the positioning information of the vehicle, an environment type of an environment where the vehicle is located is determined, and the environment type corresponds to a risk degree; According to the risk degree corresponding to the environment type, a reference judgment value corresponding to the environment type is determined, and the risk degree is negatively correlated with the reference judgment value; According to the wake-up record information of the vehicle, a wake-up record feature value of the vehicle is calculated, and the wake-up record feature value is calculated under the condition that the vehicle is in the same positioning information; According to the reference judgment value corresponding to the environment type and the wake-up record feature value of the vehicle, an adaptive judgment threshold of the vehicle about the environment is calculated.

[0107] It can be seen that the optional embodiment can automatically determine the environment type of the environment where the vehicle is located according to the obtained positioning information of the vehicle, and determine the reference judgment value corresponding to the environment type according to the risk degree corresponding to the environment type, which can improve the determination accuracy and efficiency of the reference judgment value based on the risk degree corresponding to the environment type, and quickly and accurately calculate the wake-up record feature value of the vehicle according to the wake-up record information of the vehicle, so as to calculate the adaptive judgment threshold of the vehicle about the environment according to the reference judgment value and the wake-up record feature value, thereby improving the accuracy and reliability of calculating the adaptive judgment threshold.

[0108] In yet another optional embodiment, the specific manner in which the judgment module 302 judges whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold includes: Comparing the target judgment value and the adaptive judgment threshold to obtain a comparison result; When the comparison result indicates that the target judgment value is greater than the adaptive judgment threshold, it is determined that the vehicle meets the preset wake-up condition; When the comparison result indicates that the target judgment value is less than or equal to the adaptive judgment threshold, it is determined that the vehicle does not meet the preset wake-up condition.

[0109] It can be seen that the optional embodiment can compare the target judgment value and the adaptive judgment threshold, and when the comparison result indicates that the target judgment value is greater than the adaptive judgment threshold, it is determined that the vehicle meets the preset wake-up condition, thereby improving the determination accuracy and reliability of the vehicle meeting the preset wake-up condition, and when the comparison result indicates that the target judgment value is less than or equal to the adaptive judgment threshold, it is determined that the vehicle does not meet the preset wake-up condition, thereby improving the determination accuracy and reliability of the vehicle not meeting the preset wake-up condition.

[0110] In yet another optional embodiment, the control module 303 controls the safety monitoring device matched with the detection device to perform corresponding safety monitoring operations on the vehicle, including: According to the position of the detection device, the safety monitoring device matched with the detection device is controlled to monitor image data related to the vehicle; analyze the image data to determine whether the vehicle meets a preset warning condition; when it is determined that the vehicle meets the warning condition, send a warning notification message to the owner of the vehicle.

[0111] It can be seen that the optional embodiment can control the matching safety monitoring device of the detection device to monitor the image data related to the vehicle according to the position of the detection device after the vehicle is woken up, which can improve the monitoring accuracy and efficiency of the image data, so as to analyze the image data to accurately determine whether the vehicle meets the preset warning condition, and if the vehicle meets the warning condition, accurately and timely send a warning notification message to the owner of the vehicle.

[0112] In the optional embodiment, as an optional implementation, the image data includes video data and / or image data. In addition, the control module 303 analyzes the image data to determine whether the vehicle meets a preset warning condition, including: when the image data is video data, split the video data to obtain a plurality of initial video frames corresponding to the video data; input each initial video frame into a pre-trained classification model for classification to obtain the object type of the foreground object indicated by the initial video frame; select all target video frames with the object type being the preset type from all initial video frames according to the object types of the foreground objects indicated by all initial video frames; calculate the ratio between the number of target video frames and the number of initial video frames, and determine whether the ratio is greater than a preset ratio; when it is determined that the ratio is greater than the preset ratio, it is determined that the vehicle meets the preset warning condition; when it is determined that the ratio is less than or equal to the preset ratio, it is determined that the vehicle does not meet the preset warning condition.

[0113] It can be seen that the optional embodiment can split the video data for the monitored video data, obtain a plurality of initial video frames corresponding to the video data, and input each initial video frame into the pre-trained classification model for classification to obtain the object type of the foreground object indicated by the initial video frame, thereby improving the classification accuracy and efficiency of each frame of foreground object in the video, so as to select all target video frames of the object type of the preset type from all initial video frames according to the object type of the foreground object indicated by all initial video frames, thereby improving the selection accuracy and efficiency of the target video frame belonging to the preset type, and then calculating the ratio between the number of target video frames and the number of initial video frames, and determining whether the ratio is greater than a preset ratio, when it is determined that the ratio is greater than the preset ratio, it is determined that the vehicle meets the preset warning condition, thereby improving the determination accuracy and reliability of the vehicle meeting the preset warning condition, when it is determined that the ratio is less than or equal to the preset ratio, it is determined that the vehicle does not meet the preset warning condition, thereby improving the determination accuracy and reliability of the vehicle not meeting the preset warning condition.

[0114] Embodiment four Please refer to Figure 6 , Figure 6 is another structure schematic view of the parking safety monitoring device based on AI and Internet of Things technology disclosed by the embodiment of the application. As shown in Figure 6 , the parking safety monitoring device based on AI and Internet of Things technology can include: a memory 401 storing executable program codes; a processor 402 coupled with the memory 401; The processor 402 calls the executable program codes stored in the memory 401 to execute the steps of the parking safety monitoring method based on AI and Internet of Things technology described in the embodiment one or the embodiment two of the application.

[0115] Embodiment five The embodiment of the application discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, the steps of the parking safety monitoring method based on AI and Internet of Things technology described in the embodiment one or the embodiment two of the application are executed.

[0116] Embodiment six The embodiment of the application discloses a computer program product, which includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the parking safety monitoring method based on AI and Internet of Things technology described in the embodiment one or the embodiment two.

[0117] The apparatus embodiments described above are only illustrative, wherein the modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, i.e., can be located in one place or distributed to multiple network modules. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0118] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, including a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically-Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, a magnetic disk storage, a magnetic tape storage, or any other computer readable medium that can be used to carry or store data.

[0119] Finally, it should be noted that: the disclosed parking safety monitoring method and device based on AI and Internet of Things technology disclosed by the embodiments of the present application are only the preferred embodiments of the present application, and are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that; it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A parking safety monitoring method based on AI and Internet of Things technology, characterized in that, The method comprises: According to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle determined, a target judgment value corresponding to the vehicle is calculated; By determining the environmental information of the environment where the vehicle is located, an adaptive judgment threshold of the vehicle with respect to the environment is calculated; According to the target judgment value and the adaptive judgment threshold, it is judged whether the vehicle meets the preset wake-up condition; When it is judged that the vehicle meets the wake-up condition, the vehicle is controlled to enter a wake-up state, and after the vehicle is woken up, the matching safety monitoring device of the detection device is controlled to perform corresponding safety monitoring operation on the vehicle. 2.The AI and Internet of Things technology-based parking safety monitoring method according to claim 1, characterized in that, According to the multi-dimensional feature information of the detected object detected by the detection device corresponding to the vehicle determined, a target judgment value corresponding to the vehicle is calculated, comprising: Obtain the detection information of the detection device corresponding to the vehicle, the detection information comprising at least one of the starting frequency bandwidth and the sweep frequency period; According to the detection information, the multi-dimensional feature information of the detected object detected by the detection device is calculated, the detected object being an object within a preset range of the vehicle, the multi-dimensional feature information comprising a plurality of sub-class feature information, and all the sub-class feature information comprising at least two of speed, distance, micro-Doppler feature and RCS value; For each sub-class feature information, a judgment value of the sub-class feature information is calculated, and a weight coefficient corresponding to the sub-class feature information is determined; According to the judgment values of all the sub-class feature information and the weight coefficient corresponding to each sub-class feature information, the target judgment value corresponding to the vehicle is calculated. 3.The AI and Internet of Things technology-based parking safety monitoring method according to claim 2, characterized in that, The calculation of the judgment value of the sub-class feature information comprises: When the sub-class feature information is the micro-Doppler feature, the phase time sequence signal of the detection device is determined according to the detection information; The short-time Fourier transform is performed on the phase time sequence signal to obtain a time-frequency spectrum, and the frequency of the maximum energy peak is extracted from the multiple energy peak frequencies indicated by the time-frequency spectrum as the main modulation frequency; If the main modulation frequency is greater than or equal to a first preset frequency threshold and less than or equal to a second preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a first judgment value, the first preset frequency threshold being less than the second preset frequency threshold; If the main modulation frequency is greater than the second preset frequency threshold and less than or equal to a third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a second judgment value, the second preset frequency threshold being less than the third preset frequency threshold; If the main modulation frequency is less than the first preset frequency threshold, or greater than the third preset frequency threshold, it is determined that the judgment value of the micro-Doppler feature is a third judgment value, the first judgment value being greater than the second judgment value, and the second judgment value being greater than the third judgment value. 4.The AI and Internet of Things technology-based parking safety monitoring method according to any one of claims 1-3, characterized in that, The calculation of the adaptive judgment threshold of the vehicle with respect to the environment by determining the environmental information of the environment where the vehicle is located comprises: Obtain the positioning information of the vehicle and the wake-up record information of the vehicle; According to the positioning information of the vehicle, an environment type of an environment where the vehicle is located is determined, and the environment type corresponds to a risk level; According to the risk level corresponding to the environment type, a reference judgment value corresponding to the environment type is determined, and the risk level is negatively correlated with the reference judgment value; According to the wake-up record information of the vehicle, a wake-up record feature value of the vehicle is calculated, and the wake-up record feature value is calculated under the condition that the vehicle is in the same positioning information; According to the reference judgment value corresponding to the environment type and the wake-up record feature value of the vehicle, an adaptive judgment threshold of the vehicle with respect to the environment is calculated. 5.The AI and Internet of Things technology-based parking safety monitoring method according to claim 4, characterized in that, The determination of whether the vehicle meets the preset wake-up condition according to the target judgment value and the adaptive judgment threshold includes: Comparing the target judgment value and the adaptive judgment threshold to obtain a comparison result; When the comparison result indicates that the target judgment value is greater than the adaptive judgment threshold, it is determined that the vehicle meets the preset wake-up condition; When the comparison result indicates that the target judgment value is less than or equal to the adaptive judgment threshold, it is determined that the vehicle does not meet the preset wake-up condition. 6.The AI and Internet of Things (IoT) technology-based parking safety monitoring method according to any one of claims 1, 2, 3, and 5, wherein, The control of the safety monitoring device matched with the detection device to perform corresponding safety monitoring operations on the vehicle includes: According to the position of the detection device, the safety monitoring device matched with the detection device is controlled to monitor image data related to the vehicle; The image data is analyzed to determine whether the vehicle meets a preset warning condition; When it is determined that the vehicle meets the warning condition, a warning notification is sent to the vehicle owner bound to the vehicle. 7.The AI and Internet of Things technology-based parking safety monitoring method according to claim 6, characterized in that, The image data includes video data and / or image data; And the analysis of the image data to determine whether the vehicle meets the preset warning condition includes: When the image data is video data, the video data is split to obtain a plurality of initial video frames corresponding to the video data; Each initial video frame is input into a pre-trained classification model for classification to obtain an object type of a foreground object indicated by the initial video frame; According to the object types of the foreground objects indicated by all the initial video frames, all target video frames of the preset type are selected from all the initial video frames; The ratio between the number of target video frames and the number of initial video frames is calculated, and it is determined whether the ratio is greater than a preset ratio; When it is determined that the ratio is greater than the preset ratio, it is determined that the vehicle meets the preset warning condition; When it is determined that the ratio is less than or equal to the preset ratio, it is determined that the vehicle does not meet the preset warning condition. 8.A parking safety monitoring device based on AI and Internet of Things technology, characterized in that, The device includes: A calculation module configured to calculate a target judgment value corresponding to the vehicle according to multi-dimensional feature information of a detected object detected by a detection device corresponding to the vehicle; The calculation module is further configured to calculate an adaptive judgment threshold of the vehicle with respect to an environment by determining environment information of the environment where the vehicle is located; A judgment module is configured to judge whether the vehicle meets a preset wake-up condition according to the target judgment value and the adaptive judgment threshold value. A control module is configured to control the vehicle to enter a wake-up state when the judgment module judges that the vehicle meets the wake-up condition, and control the matching safety monitoring device of the detection device to perform a corresponding safety monitoring operation on the vehicle after the vehicle is woken up. 9.A parking safety monitoring device based on AI and Internet of Things technology, characterized in that, The device comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the AI and Internet of Things technology-based parking safety monitoring method according to any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which are invoked to execute the AI and Internet of Things technology-based parking safety monitoring method according to any one of claims 1-7.

Images