Intelligent monitoring control method, electronic device and medium

Abstract

The present disclosure provides a kind of intelligent monitoring control method, electronic equipment and medium, method includes: by the first radio signal perception detection mode to the environmental change detection of monitoring area, obtains environmental change score;When environmental change score is greater than the first preset threshold, by the second radio signal perception detection mode to the target detection of monitoring area, obtains radio signal score;When radio signal score is greater than the second preset threshold, the trajectory prediction of the target detected is carried out, obtains the trajectory prediction result of target;According to trajectory prediction result, control visual module carries out tracking shooting to the target that will enter preset visual monitoring area.This disclosure works through multi-stage cooperation, effectively reduces the running power consumption of monitoring camera, significantly prolongs the service life of equipment, reduces invalid energy consumption and redundant invalid video data, realizes the efficient, low consumption and intelligent operation of intelligent monitoring.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent security technology, and in particular to an intelligent monitoring and control method, electronic device and medium. Background Technology

[0002] Existing intelligent monitoring systems typically rely on cameras to continuously capture video images and perform target recognition. While this method can achieve environmental monitoring, it has the following problems: long-term camera operation leads to high system power consumption; and cameras generate a large amount of invalid video data when there is no target.

[0003] Therefore, reducing the power consumption of surveillance cameras and minimizing invalid video data have become problems that need to be solved. Summary of the Invention

[0004] In a first aspect, embodiments of this disclosure provide an intelligent monitoring and control method, the method comprising: detecting environmental changes in a monitoring area using a first radio signal sensing and detection method to obtain an environmental change score; when the environmental change score is greater than a first preset threshold, detecting a target in the monitoring area using a second radio signal sensing and detection method to obtain a radio signal score; when the radio signal score is greater than a second preset threshold, predicting the trajectory of the detected target to obtain a trajectory prediction result for the target; and controlling a vision module to track and capture images of the target that is about to enter a preset visual monitoring area based on the trajectory prediction result.

[0005] In some embodiments, the first radio signal sensing and detection method includes WIFI change sensing and detection; the step of detecting environmental changes in the monitoring area and obtaining an environmental change score by means of the first radio signal sensing and detection method includes: collecting WIFI signal parameters in the monitoring area to obtain a wireless signal feature vector; and determining the environmental change score based on the wireless signal feature vector.

[0006] In some embodiments, the wireless signal feature vector includes at least Received Signal Strength Indication (RSSI) and Channel State Information (CSI); determining the environmental change score based on the wireless signal feature vector includes: determining the standard deviation of the CSI and the absolute value of the change in the RSSI based on the wireless signal feature vector; and performing a weighted summation of the standard deviation of the CSI and the absolute value of the change in the RSSI to obtain the environmental change score.

[0007] In some embodiments, the second radio signal sensing and detection method includes radar monitoring, and the radio signal scoring includes radar scoring; the step of detecting a target in the monitoring area and obtaining a radio signal score through the second radio signal sensing and detection method includes: transmitting an electromagnetic wave signal to the monitoring area through a radar module and receiving an echo signal; performing signal analysis based on the transmitted signal of the radar module and the echo signal to obtain the target's distance information and velocity information; and determining the target's radar score based on the target's distance information and velocity information.

[0008] In some embodiments, determining the radar score of the target based on the target's distance information and speed information includes: determining a distance score based on the target's distance information and a preset distance-related scoring function; determining a speed score based on the target's speed information and a preset speed-related scoring function; and performing a weighted summation of the distance score and the speed score to obtain the target's radar score.

[0009] In some embodiments, the step of predicting the trajectory of the detected target to obtain the trajectory prediction result of the target includes: constructing a target motion state sequence based on the target's distance information and velocity information; and based on the target motion state sequence, predicting the target's motion direction change and motion speed change through a pre-trained trajectory prediction model to obtain the target's trajectory prediction result.

[0010] In some embodiments, controlling the vision module to track and capture images of the target about to enter a preset visual monitoring area based on the trajectory prediction result includes: determining whether the target is about to enter the preset visual monitoring area based on the trajectory prediction result; if it is determined that the target is about to enter the preset visual monitoring area, activating the vision module and adjusting the camera's internal parameters and / or shooting posture parameters so that the vision module tracks and captures images of the target; and deactivating the vision module after the target leaves the preset visual monitoring area. The camera's internal parameters include at least one of resolution, frame rate, focal length, aperture, shutter speed, ISO sensitivity, white balance, exposure compensation, field of view, and image format. The shooting posture parameters include at least one of shooting direction, shooting angle, shooting distance, shooting height, camera orientation, and tilt angle.

[0011] In some embodiments, the step of predicting the trajectory of the detected target to obtain the trajectory prediction result of the target includes at least one of the following: determining the type of the detected target; if the target type belongs to a preset valid target type, then determining the target as a valid target, and performing trajectory prediction on the valid target to obtain the trajectory prediction result of the valid target; if the number of detected targets is two or more, then performing motion correlation analysis between the targets, and performing trajectory prediction on each target based on the motion correlation analysis result to obtain the trajectory prediction result of each target.

[0012] Secondly, embodiments of this disclosure provide an electronic device, including: one or more processors; and a memory storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above-described intelligent monitoring and control method.

[0013] Thirdly, embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the above-described intelligent monitoring and control method.

[0014] This disclosure provides an intelligent monitoring and control method, electronic device, and medium. The method includes: detecting environmental changes in a monitoring area using a first radio signal sensing and detection method to obtain an environmental change score; when the environmental change score is greater than a first preset threshold, detecting a target in the monitoring area using a second radio signal sensing and detection method to obtain a radio signal score; when the radio signal score is greater than a second preset threshold, predicting the trajectory of the detected target to obtain a trajectory prediction result; and controlling a vision module to track and capture images of a target about to enter a preset visual monitoring area based on the trajectory prediction result. This disclosure, through multi-level collaborative operation, improves the real-time performance, completeness, and accuracy of monitoring while effectively reducing the operating power consumption of monitoring cameras, significantly extending equipment lifespan, reducing ineffective energy consumption and redundant video data, and achieving efficient, low-power, and intelligent operation of intelligent monitoring. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of the intelligent monitoring and control system provided in the embodiments of this disclosure.

[0016] Figure 2 This is a flowchart illustrating the intelligent monitoring and control method provided in an embodiment of the present disclosure.

[0017] Figure 3 This is another schematic diagram of the intelligent monitoring and control method provided in the embodiments of this disclosure.

[0018] Figure 4A schematic diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions of this disclosure will be described in detail below with reference to the accompanying drawings.

[0020] Exemplary embodiments will be described more fully below with reference to the accompanying drawings; however, these exemplary embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will enable those skilled in the art to fully understand the scope of this disclosure.

[0021] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0022] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0023] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded.

[0024] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined herein.

[0025] The technical solutions of this disclosure and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this disclosure will now be described with reference to the accompanying drawings.

[0026] Figure 1 This is a schematic diagram of the structure of an intelligent monitoring and control system provided in an embodiment of this disclosure. This intelligent monitoring and control system is used to implement the intelligent monitoring and control method provided in this disclosure, such as... Figure 1As shown, the intelligent monitoring and control system mainly includes a system control module, a radio signal sensing and detection module (specifically including a WIFI change sensing and detection module and a radar module), a trajectory prediction module (which can be integrated into the system control module or exist separately), a vision module (such as one or more cameras), and a storage module (which can be integrated into the system control module or exist separately, not shown in the figure).

[0027] Optionally, the intelligent monitoring and control system also includes a wireless communication module (not shown in the figure), which is used to realize wireless communication between the modules in the system.

[0028] The specific forms of the system control module include, but are not limited to: microcontrollers (MCUs), embedded processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), industrial control computers, local servers, cloud servers, host computers or mobile terminals, and dedicated control units formed by the above hardware with control software or firmware. For example, Figure 1 The system control module is represented as a server (local server or cloud server).

[0029] The radio signal sensing and detection module, under the control of the system control module, detects the monitoring area. This includes detecting environmental changes in the monitoring area via the WIFI change sensing and detection module (by analyzing changes in wireless signal propagation), and detecting targets in the monitoring area via the radar module. The system control module determines whether to perform target detection in the monitoring area via the radar module based on the environmental change detection results (environmental change score) from the WIFI change sensing and detection module, and determines whether to perform target trajectory prediction via the trajectory prediction module based on the target detection results (radio signal score) from the radar module.

[0030] The trajectory prediction module predicts the target trajectory based on the target detection results from the radar module.

[0031] For example, Figure 1 The trajectory prediction module predicts the motion trajectories of target 1, target 2, and target 3 respectively (the dashed lines with arrows in the figure represent the predicted motion trajectories of each target). Target 1 is predicted to enter the preset visual monitoring area at point A and leave the preset visual monitoring area at point B; target 2 is predicted to enter the preset visual monitoring area at point C and leave the preset visual monitoring area at point D; the predicted motion trajectory of target 3 does not pass through the preset visual monitoring area.

[0032] The system control module controls the vision module to track and capture targets that are about to enter the preset visual monitoring area based on the trajectory prediction results of the trajectory prediction module. Specifically, the system control module controls the camera internal parameters and / or shooting posture parameters of the camera in the vision module to adjust.

[0033] For example, Figure 1 If the predicted motion trajectories of targets 1 and 2 pass through the preset visual monitoring area, when target 1 reaches point A, the system control module adjusts the camera's internal parameters and / or shooting posture parameters to control the visual module to start tracking and shooting target 1; when target 1 reaches point B, the system control module controls the visual module to stop tracking and shooting target 1.

[0034] Similarly, when target 2 reaches point C, the system control module adjusts the camera's internal parameters and / or shooting posture parameters to control the vision module to start tracking and shooting target 2; when target 2 reaches point D, the system control module controls the vision module to stop tracking and shooting target 2.

[0035] In addition, since the predicted motion trajectory of target 3 does not pass through the preset visual monitoring area, the system control module does not control the visual module to track and photograph target 3.

[0036] Optionally, the vision module may include one or more cameras.

[0037] When there is a single camera, the vision module can enable the single camera to track and capture images of a single target (only one target or the target with the highest priority among multiple targets), and / or enable the single camera to track and capture images of multiple targets simultaneously.

[0038] When there are multiple cameras, the vision module can adopt one or more of the following strategies: 1. Use only one camera to track and capture a single target (only one target or the target with the highest priority among multiple targets); 2. Use only one camera to track and capture multiple targets simultaneously; 3. Use at least two cameras to track and capture one or more of the multiple targets respectively.

[0039] The storage module stores videos containing the target object captured by the vision module.

[0040] Specifically, when the system control module does not control the vision module to perform target tracking and shooting, the vision module is in a closed or dormant state to reduce the operating power consumption of the surveillance camera and reduce invalid video data.

[0041] based on Figure 1The intelligent monitoring and control system disclosed herein provides an intelligent monitoring and control method based on multi-level perception and trajectory prediction. Through hierarchical environmental perception, target detection, and trajectory prediction, it enables advance control and on-demand activation of cameras. The method mainly includes the following four stages: Phase 1: Wireless environmental sensing and detection of environmental changes; Phase Two: Radar detection of moving targets; Phase 3: Artificial intelligence predicts the target's trajectory; Phase 4: Control the operation of the camera based on the prediction results.

[0042] This disclosure, through the aforementioned multi-level sensing mechanism, can reduce camera runtime, improve system energy efficiency, and reduce false triggering.

[0043] Figure 2 This is a flowchart illustrating the intelligent monitoring and control method provided in an embodiment of this disclosure. Figure 3 This is another schematic diagram of the intelligent monitoring and control method provided in the embodiments of this disclosure, as shown below. Figure 2 as well as Figure 3 As shown, this disclosure provides an intelligent monitoring and control method, wherein the executing entity of the intelligent monitoring and control method can be... Figure 1 The method includes steps S1-S4, as follows: (The system control module in the system, such as a server, etc.) S1. Environmental changes in the monitoring area are detected by the first radio signal sensing and detection method, and an environmental change score is obtained.

[0044] Specifically, when the vision module is in a closed or dormant state, this disclosure first uses a first radio signal sensing and detection method to detect environmental changes in the monitoring area. By analyzing the changes in the propagation of the radio signal, the environmental changes in the monitoring area are detected, and an environmental change score is obtained. The environmental change score is used to determine whether environmental changes have occurred in the monitoring area, or to determine whether the degree of environmental changes in the monitoring area meets preset requirements.

[0045] This disclosure employs a first radio signal sensing and detection method to detect environmental changes in the monitoring area and obtain an environmental change score. It can sense environmental disturbances non-contactly and in all weather conditions, without being limited by conditions such as light or dust. It achieves a refined characterization of the degree of environmental change through quantitative scoring, with high detection sensitivity and strong real-time performance. This makes it easy for the system to accurately judge the environmental state and respond. Furthermore, it is simple to deploy and highly adaptable.

[0046] In some embodiments, the first radio signal sensing and detection method includes WIFI change sensing and detection.

[0047] The environmental change score is obtained by detecting environmental changes in the monitoring area using the first radio signal sensing and detection method, including: S11, collecting WIFI signal parameters in the monitoring area to obtain wireless signal feature vectors; S12, determining the environmental change score based on the wireless signal feature vectors.

[0048] The sources of wireless signals in the monitoring area include, but are not limited to: Wi-Fi signals emitted by terminal devices connected to the Wi-Fi change sensing and detection module, wireless detection signals actively sent by the Wi-Fi change sensing and detection module, and wireless signals emitted by other wireless devices in the environment. Terminal devices include mobile terminal devices, computer devices, and IoT devices. When the Wi-Fi change sensing and detection module operates as a wireless access point, the data communication between the terminal device and the Wi-Fi change sensing and detection module generates wireless signals, which can be used for environmental sensing.

[0049] The physical layer parameters obtained by collecting WIFI signal parameters in the monitoring area include, but are not limited to: Received Signal Strength Indication (RSSI), Channel State Information (CSI), subcarrier amplitude information, and signal phase information.

[0050] Among them, RSSI is an indicator that measures the total RF signal power detected by the receiver; CSI is a precise measurement of the amplitude and phase of each subcarrier in an OFDM (Orthogonal Frequency Division Multiplexing) system; subcarrier amplitude information is the strength or amplitude of the signal on each independent subcarrier in an OFDM system, reflecting the degree of attenuation or gain of the signal after propagation through the channel; signal phase information refers to the relative position of the signal waveform in the periodic cycle (such as peaks and troughs), used to describe the time offset and synchronization state of the signal.

[0051] In some embodiments, the wireless signal feature vector includes at least Received Signal Strength Indicator (RSSI) and Channel State Information (CSI).

[0052] In this step, the WIFI change sensing and detection module collects wireless signal parameters and forms a wireless signal feature vector in each sampling period, for example: Among them, X t RSSI is the feature vector of a wireless signal. t The received signal strength indicator at time t is a scalar value representing the overall signal strength. The channel state information of the i-th subcarrier at time t is usually a complex number, containing amplitude and phase information; n is the number of subcarriers, representing the total number of subcarriers after the wireless signal is decomposed (such as OFDM subcarriers in WIFI).

[0053] The above formula means that at time t, the 1-dimensional RSSI and n-dimensional CSI features are concatenated to form an (n+1)-dimensional feature vector X. t .

[0054] This disclosure combines RSSI and CSI, taking advantage of the computational simplicity of RSSI while retaining the fine-grained perception capability of CSI, thereby improving the accuracy and stability of subsequent target detection or environmental status judgment.

[0055] In this disclosure, the environmental change score is determined based on the wireless signal feature vector, including: determining the standard deviation of CSI and the absolute value of the change in RSSI based on the wireless signal feature vector; and performing a weighted summation of the standard deviation of CSI and the absolute value of the change in RSSI to obtain the environmental change score.

[0056] Specifically, based on the feature vector of wireless signals, the environmental change score is determined using the following formula: in, Score environmental change. The standard deviation of CSI (reflects the degree of fluctuation of CSI over time; the larger the standard deviation, the more drastic the change in channel state). The absolute value of the change in RSSI (reflecting the magnitude of the change in received signal strength), The larger the value, the more significant the signal enhancement / attenuation. They are respectively and The weighting coefficients (used to balance the contributions of CSI fluctuations and RSSI changes to the environmental change score, and can be determined experimentally or through optimization algorithms) are used to calculate the overall variation characteristics of WiFi signals by combining the fluctuations of CSI and the magnitude of RSSI changes.

[0057] The following are determined in this disclosure Specific examples of optimization algorithms.

[0058] Algorithm 1: Adaptive Weight Update Based on Sliding Window Statistics The historical mean values ​​of the CSI standard deviation and RSSI change were statistically analyzed over M consecutive sampling periods, and the weighting coefficients were dynamically updated based on the relative fluctuations of the two types of features.

[0059] The historical mean of the CSI standard deviation is: Where M is the length of the sliding window. Let CSI be the standard deviation of the k-th sampling period. This represents the average degree of change of the CSI feature within the sliding window.

[0060] The historical mean of RSSI change is: in, The absolute value of the RSSI change in the k-th sampling period. This represents the average degree of change of the RSSI feature within the sliding window.

[0061] The weighting coefficients are dynamically calculated based on the historical mean of the CSI standard deviation and the historical mean of the RSSI change. The above weighting coefficients satisfy: Using the above formula, when CSI fluctuations are more pronounced, it automatically increases... The percentage; when RSSI changes more significantly, automatically increase The proportion of environmental change scores is increased to enhance their adaptability to different scenarios.

[0062] Algorithm 2: Scene-type-based weight library (users can manually set the scene) For different scenarios, a pre-stored scenario weight table is provided: The principle behind weighted differential configuration is explained in this disclosure as follows: (1) CSI signals are susceptible to wireless multipath effects. In open environments with few obstacles, multipath effects are the main cause of environmental changes, making CSI more sensitive to environmental disturbances. Therefore, conventional indoor environments such as open halls, offices, and homes require special protection for CSI signals. Set greater weights and rely on CSI features to perceive dynamic changes in the environment.

[0063] (2) RSSI signals are more sensitive to signal attenuation caused by obstructions and metallic obstacles. In complex environments with a lot of metallic materials, the signal strength fluctuations caused by obstructions are much stronger than the channel changes caused by multipath propagation. Therefore, it is necessary to increase the weight of RSSI. The degree of environmental disturbance is characterized by the change in RSSI.

[0064] (3) There are significant differences in obstacle density, spatial layout and material properties in different indoor scenarios. The environmental perception sensitivity of CSI and RSSI features is different. Therefore, it is necessary to set different optimal weight ratios to improve the adaptability and detection accuracy of environmental change scoring in various scenarios.

[0065] In practical applications, when a specific scenario is detected, the corresponding parameters are automatically loaded. For example, when the scenario is detected as "family residence," the parameters are automatically loaded. .

[0066] Algorithm 3: CSI Feature Dimensionality Reduction Based on Principal Component Analysis Since CSI contains information from multiple subcarriers and has a high dimensionality, Principal Component Analysis (PCA) can be used to reduce the dimensionality of CSI features.

[0067] Let the CSI feature matrix be: Extract the top k principal components using PCA: Where H' is the dimensionality-reduced CSI feature matrix, k <n。

[0068] Calculate the standard deviation based on the principal components after dimensionality reduction: Then Substitute the values ​​into the environmental change scoring formula to reduce computational complexity and improve real-time performance.

[0069] In this disclosure, when the environmental change score is... Greater than the first preset threshold At that time, that is At that time, the target detection and processing procedure enters the monitoring area.

[0070] This disclosure utilizes a WIFI change sensing and detection module to perceive environmental changes in a monitored area, significantly reducing hardware costs and deployment complexity, achieving "one network for multiple uses," and improving equipment utilization. Simultaneously, this detection method is non-contact and non-intrusive, without collecting images or other private data, effectively avoiding the privacy leakage risks of traditional visual monitoring, resulting in high user acceptance. Furthermore, WIFI signals have the characteristics of penetrating non-conductive obstacles and being unaffected by light, smoke, or dust, enabling stable perception of non-line-of-sight areas. This overcomes the shortcomings of traditional sensors, such as susceptibility to obstruction and environmental interference, offering a wide detection range and strong anti-interference capabilities. Moreover, by analyzing multi-dimensional characteristics such as WIFI signal strength, phase, and latency, it can not only identify the occurrence of environmental changes but also quantify and assess the severity, duration, and impact range of these changes, providing reliable data support for subsequent alarm and control decisions. It can be widely applied in various scenarios such as smart homes, security, smart elderly care, and industrial environmental monitoring, offering advantages such as convenient deployment, low cost, privacy security, strong adaptability, and good scalability.

[0071] S2. When the environmental change score is greater than the first preset threshold, the monitoring area is targeted by the second radio signal sensing and detection method to obtain the radio signal score.

[0072] Specifically, when the environmental change score Greater than the first preset threshold Furthermore, this disclosure further performs target detection in the monitoring area using a second radio signal sensing and detection method to obtain a radio signal score for measuring the target detection result.

[0073] This disclosure uses a radio signal sensing and detection method to detect targets in the monitoring area and obtain radio signal scores. It does not require contact sensors, is not affected by environmental factors such as light and dust, and has a wide range of applications. It achieves a refined assessment of the target status through quantitative scoring, with high detection sensitivity and strong real-time performance, which facilitates intelligent judgment and early warning by the system. At the same time, it is easy to deploy, low in cost, and easy to expand and maintain.

[0074] In some embodiments, the second radio signal sensing and detection method includes radar monitoring, and the radio signal scoring includes radar scoring.

[0075] The target detection in the monitoring area is performed by a second radio signal sensing and detection method to obtain a radio signal score, including: S21, transmitting electromagnetic wave signals to the monitoring area through a radar module and receiving echo signals; S22, performing signal analysis based on the transmitted signals and echo signals of the radar module to obtain the target's distance and speed information; S23, determining the target's radar score based on the target's distance and speed information.

[0076] Specifically, the radar module radiates electromagnetic wave signals directionally or omnidirectionally into the monitoring area under a preset operating frequency band and transmission power. When a target is present in the monitoring area, the electromagnetic waves are reflected by the target to form an echo signal, which is acquired and preprocessed by the radar module's receiving channel. Then, the radar module performs time-domain, frequency-domain, or correlation-domain analysis on the transmitted and echo signals. For example, it obtains the distance information between the target and the radar module through ranging algorithms and extracts the radial velocity information of the target relative to the radar module through Doppler velocity measurement principles, thereby completing the preliminary calculation of target parameters. Finally, based on characteristics such as target distance, speed, and motion state, a quantitative score is obtained according to preset weights or threshold rules, resulting in a radar score that reflects the probability of target presence, the degree of target threat, or the target activity level. This score serves as the basis for subsequent fusion judgments based on radio signal dimensions.

[0077] For example, the target distance can be calculated using the following formula: Where D is the distance between the radar and the target, c is the speed of light (approximately 3 × 10⁸ m / s in air), and Δt is the total flight time (round trip time) of the electromagnetic wave from transmission to reception.

[0078] For example, the target velocity can be calculated using Doppler frequency shift: Where λ is the wavelength of the electromagnetic wave emitted by the radar, and satisfies λ=c / f, c is the speed of light, and f is the carrier frequency. d This is the Doppler frequency shift.

[0079] In some embodiments, determining a radar score for a target based on its distance and velocity information includes: determining a distance score based on the target's distance information and a preset distance-related scoring function; determining a velocity score based on the target's velocity information and a preset velocity-related scoring function; and performing a weighted summation of the distance score and the velocity score to obtain the target's radar score.

[0080] Specifically, based on the target's range and velocity information, the target's radar score is determined using the following formula: in, Radar rating of the target. For the target's speed information, For the distance information of the target, This is a velocity-related scoring function (used to quantify the impact of the target's motion state on its importance). This is a distance-related scoring function (used to quantify the impact of target distance on importance). They are respectively and The weighting coefficients.

[0081] Among them, the function Based on the target's speed Assign a score, for example: the faster the target, the higher the risk / priority. The larger the value, or when it approaches a certain threshold (such as approaching the speed limit), It was magnified. This determines the proportion of the "speed factor" in the total score.

[0082] For example, velocity-related evaluation functions It can be: Where V is the target's velocity, V max The preset maximum reference speed threshold (e.g., 30 m / s (approximately 108 km / h)); when the target speed reaches or exceeds V max When f(V) = 1, it represents the highest priority; when it is below this value, it increases linearly.

[0083] For example, the speed-related evaluation function It can be: This function means: low-speed targets (speed less than 5m / s) receive no points, medium-speed targets (speed greater than or equal to 5m / s but less than 15m / s) are given medium priority, and high-speed targets (speed greater than or equal to 15m / s) are given full priority.

[0084] Among them, the function A score will be assigned based on the distance D between the target and the radar. For example, the closer the target is, the higher its threat / priority. The larger the value, the more likely it is to exceed a certain distance. Rapid decay reduces the weight of distant targets. This determines the proportion of the "distance factor" in the total score.

[0085] For example, the distance-related evaluation function g(D) can be: Where D is the straight-line distance between the target and the radar, D max This represents the radar's maximum effective detection range (e.g., 100m); when the target is directly below the radar (D=0), =1; the score decreases linearly with increasing distance, and becomes 0 when it exceeds Dmax.

[0086] For example, the distance-related evaluation function It can be: The above function indicates that: close-range targets (distance less than 20m) have the highest priority, medium-range targets (distance greater than or equal to 20m but less than 50m) have medium priority, and long-range targets (distance greater than or equal to 50m) are ignored.

[0087] In this disclosure, , The weighting coefficients for speed and distance are respectively, satisfying... + =1, the above calculation formula can be adjusted. and It can implement different strategies such as "prioritizing close-range targets" or "prioritizing high-speed targets". For example, it can be set according to the needs of the scenario. =0.4、 =0.6, to prioritize the monitoring of nearby targets.

[0088] In this disclosure, when the target's radar score Greater than the second preset threshold At that time, that is At that time, the target trajectory prediction and processing flow begins.

[0089] This disclosure employs the aforementioned radar signal sensing and detection method, which can actively emit electromagnetic waves and receive echo signals. It is unaffected by environmental factors such as light, obstruction, and smoke, and can operate stably even in complex scenarios such as nighttime and inclement weather, effectively improving the robustness and all-weather adaptability of target detection. By analyzing the emitted and echo signals, the distance and velocity information of the target can be accurately obtained, achieving reliable perception of the target's position and motion state, avoiding misjudgments caused by relying solely on images or a single sensor. Furthermore, this disclosure generates a radar score, quantifying target features into scoring indicators that can be directly used for decision-making. This facilitates subsequent multi-source information fusion and intelligent judgment, improving the system's accuracy, sensitivity, and automation in target identification, thereby enhancing the overall reliability and intelligence of the monitoring solution.

[0090] S3. When the radio signal score is greater than the second preset threshold, the trajectory of the detected target is predicted to obtain the trajectory prediction result of the target.

[0091] Specifically, when the radio signal score (i.e. radar score) is greater than the second preset threshold, it indicates that the currently detected target meets the triggering conditions for trajectory prediction. At this time, the target's distance and speed information have sufficient accuracy and reliability to provide effective basic data support for trajectory prediction, thereby performing trajectory prediction on the detected target and obtaining the trajectory prediction result of the target.

[0092] In some embodiments, trajectory prediction is performed on the detected target to obtain the trajectory prediction result of the target, including: S31, constructing a target motion state sequence based on the target's distance information and velocity information; S32, based on the target motion state sequence, predicting the target's motion direction change and motion speed change through a pre-trained trajectory prediction model to obtain the target's trajectory prediction result.

[0093] Specifically, a target motion state sequence is constructed based on the target position and velocity information continuously detected by radar: Among them, Z t x represents the target motion state observation vector at time t. t The y-coordinate represents the lateral position coordinate of the target in the planar coordinate system at time t. t v represents the longitudinal position coordinate of the target in the planar coordinate system at time t. t This represents the velocity of the target at time t.

[0094] Then, an artificial intelligence model is used to predict the target's future trajectory. This AI model is a pre-trained trajectory prediction model, which can be trained based on historical trajectory data, and is used to estimate the target's future direction of motion and velocity changes. The trajectory prediction model predicts the target's future position as follows: Where k represents the prediction time window, x t+k Let y represent the horizontal coordinate of the target at a future time t+k. t+k This represents the vertical position coordinate of the target at a future time t+k.

[0095] In this disclosure, the artificial intelligence model can be either a Kalman trajectory prediction model or a neural network model based on time-series data learning. Taking a neural network model based on time-series data learning as an example, the specific implementation method is as follows: The target's historical motion state sequence is represented as follows: in: The target's horizontal position; The target's longitudinal position; The target speed.

[0096] The model input is the motion state sequence of the most recent N time moments, and the model output is the position prediction result for the next K time moments. In some embodiments, trajectory prediction is performed on the detected target to obtain the trajectory prediction result of the target, including: determining the type of the detected target; if the target type belongs to a preset valid target type, the target is determined to be a valid target, and trajectory prediction is performed on the valid target to obtain the trajectory prediction result of the valid target.

[0097] In this disclosure, after target detection is completed, the features of the detected target are extracted and compared with a preset effective target type library to determine the effective and invalid targets. Only for effective targets, the appropriate algorithm is selected to predict the trajectory based on their motion characteristics and environmental constraints, and the results are output. Invalid targets are directly filtered out. At the same time, the accuracy of judgment and prediction can be improved by dynamically updating the type library and correcting prediction anomalies.

[0098] This disclosure can filter invalid targets, reduce computational redundancy, save hardware resources, improve prediction real-time performance and accuracy, and reduce the probability of false positives and false negatives by judging the type of detected targets. The preset type library can be customized to adapt to multiple scenarios, focusing on key targets to optimize decision-making efficiency, while reducing equipment load and maintenance costs, extending equipment life, and providing support for intelligent applications in multiple fields, helping to form a virtuous cycle of algorithm optimization.

[0099] In some embodiments, trajectory prediction is performed on the detected targets to obtain trajectory prediction results for the targets, including: if the number of detected targets is two or more, then motion correlation analysis is performed between the targets, and trajectory prediction is performed on each target based on the motion correlation analysis results to obtain trajectory prediction results for each target.

[0100] In this disclosure, when two or more targets are detected, motion analysis is no longer performed on individual targets in isolation. Instead, motion correlation analysis is first conducted among multiple targets, comprehensively considering the correlation characteristics of each target in terms of motion speed, motion direction, spatial relative position, motion sequence, and interaction behavior, to establish motion constraint relationships and linkage models between targets. Based on this, and combining the interaction laws between targets and the overall motion trend obtained from the motion correlation analysis, trajectory prediction is performed on each target separately to obtain the trajectory prediction results for each target.

[0101] This disclosure, through motion correlation analysis between targets, can effectively overcome the problem of insufficient prediction accuracy caused by the susceptibility of single-target prediction to environmental interference, information loss, and sudden motion changes. It makes the trajectory prediction results of each target more consistent with the actual motion scenario, improves the accuracy, continuity and reliability of trajectory prediction, and enhances the system's situational awareness and future state prediction capabilities in complex multi-target environments. This provides more accurate and reliable data support for subsequent processing stages such as target tracking, behavior understanding, and intelligent decision-making.

[0102] In some embodiments, trajectory prediction is performed on the detected target to obtain the trajectory prediction result of the target, including: determining the type of the detected target; if the target type belongs to a preset valid target type and the number of detected valid targets is two or more, then performing motion correlation analysis between valid targets, and performing trajectory prediction on each valid target based on the motion correlation analysis result to obtain the trajectory prediction result of each valid target.

[0103] This disclosure, by classifying detected targets and performing motion correlation analysis between valid targets, can filter out invalid targets, reduce computational redundancy, save hardware resources, improve prediction real-time performance and accuracy, and reduce the probability of false positives and false negatives. Furthermore, it effectively overcomes the problem of insufficient prediction accuracy caused by environmental interference, missing information, and sudden motion changes in single-target prediction, making the trajectory prediction results of each target more closely match the actual motion scenario, improving the accuracy, continuity, and reliability of trajectory prediction. Simultaneously, it enhances the system's situational awareness and future state prediction capabilities in complex multi-target environments, providing more accurate and reliable data support for subsequent processing stages such as target tracking, behavior understanding, and intelligent decision-making.

[0104] S4. Based on the trajectory prediction results, control the vision module to track and photograph the target that is about to enter the preset visual monitoring area.

[0105] In this disclosure, based on the target's trajectory prediction results, the future movement path and spatial position change trend of the target can be predicted in advance. Based on this, the vision module can be precisely controlled to actively align with and continuously track the target about to enter the preset visual monitoring area. This achieves predictive, pre-emptive tracking and shooting of the target, rather than passively waiting for the target to enter the monitoring area before initiating the shooting process. By tracking and shooting targets about to enter the preset visual monitoring area, this disclosure effectively avoids problems such as target loss and incomplete shooting footage caused by lag in the vision module's response. Simultaneously, the video data acquired during the tracking and shooting process is saved in real time, forming a complete and continuous target image record. This provides reliable image data for subsequent target identity verification, behavior tracing, and event evidence collection, further improving the integrity and effectiveness of visual monitoring and enhancing the system's ability to continuously observe and retain information about targets in dynamic scenarios.

[0106] In some embodiments, based on the trajectory prediction result, controlling the vision module to track and capture a target that is about to enter a preset visual monitoring area includes: determining whether the target is about to enter the preset visual monitoring area based on the trajectory prediction result; if it is determined that the target is about to enter the preset visual monitoring area, activating the vision module and adjusting the camera's internal parameters and / or shooting posture parameters so that the vision module can track and capture the target; and deactivating the vision module after the target leaves the preset visual monitoring area.

[0107] The camera's internal parameters include at least one of the following: resolution, frame rate, focal length, aperture, shutter speed, ISO sensitivity, white balance, exposure compensation, field of view, and image format.

[0108] Among them, the shooting posture parameters include at least one of the following: shooting direction, shooting angle, shooting distance, shooting height, camera orientation, and tilt angle.

[0109] In this disclosure, based on trajectory prediction results, the future movement position and path of a target can be predicted in advance, thereby accurately determining whether the target is about to enter a preset visual monitoring area, achieving advance perception and intelligent judgment of the target's movement status. When it is determined that the target is about to enter the preset visual monitoring area, the system automatically activates the vision module and dynamically adjusts the camera's internal parameters and shooting posture parameters according to the target's position, size, movement speed, and lighting conditions.

[0110] For example, the following are specific examples of adjusting camera internal parameters and / or shooting posture parameters: (1) The camera orientation control is adjusted according to the predicted target position: Where θ is the adjusted camera orientation, (x c y c (x) represents the camera location. t+k ,y t+k () is used to predict the target location.

[0111] (2) The camera focal length is adjusted according to the target distance: Where F is the adjusted camera focal length, F0 is the base focal length value, k′ is the distance-focal length adjustment coefficient, and D is the distance between the target and the camera.

[0112] (3) The camera frame rate is adjusted according to the target speed: Where R is the adjusted camera frame rate, R0 is the base frame rate, c′ is the speed-frame rate adjustment coefficient, and V is the target's movement speed.

[0113] This disclosure ensures that the vision module can clearly, stably, and completely track and capture images of the target through the collaborative optimization and precise adaptation of multi-dimensional parameters. Once the target has passed through and left the preset visual monitoring area, the system automatically shuts down the vision module. This ensures complete monitoring and recording while reducing ineffective working time, lowering system power consumption and equipment wear, and achieving intelligent, refined, and efficient control of visual acquisition. This improves the effectiveness and reliability of target tracking and capturing, and optimizes the overall system's operating efficiency and resource utilization.

[0114] As described in the above embodiments, the intelligent monitoring and control method provided in this disclosure, through the coordinated operation of hierarchical environmental perception, target detection, and trajectory prediction, achieves advance prediction control and on-demand start / stop of cameras, which has significant advantages over traditional monitoring methods that are continuously powered on or passively triggered, including: (1) Wireless environmental sensing is used to quickly capture environmental changes, enabling large-scale, all-weather preliminary monitoring in a low-power manner, avoiding long-term idle operation of the camera; (2) By accurately detecting moving targets with radar, invalid information such as environmental interference and static clutter can be effectively filtered out, thereby improving the reliability and anti-interference capability of target identification; (3) By using artificial intelligence algorithms to predict the trajectory of the target, the direction of the target's movement and the area it will reach can be known in advance, realizing the transformation from "passive response" to "active prediction"; (4) Based on the prediction results, the operation of the camera is controlled in a refined manner to start on demand and aim accurately, so as to ensure that the monitoring screen is complete and the target is not lost, and to significantly reduce the power consumption of the equipment and the pressure of data storage.

[0115] This overall solution, through multi-level collaborative work, improves the real-time performance, completeness, and accuracy of monitoring while effectively reducing the operating power consumption of surveillance cameras, significantly extending the service life of equipment, reducing ineffective energy consumption and redundant video data, and achieving efficient, low-power, and intelligent operation of intelligent monitoring.

[0116] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0117] In some embodiments, this disclosure provides an electronic device. Figure 4 A schematic diagram of an electronic device provided in an embodiment of this disclosure, such as... Figure 4 As shown, it includes: one or more processors 201; a memory 202 storing one or more programs, which, when executed by one or more processors, enable one or more processors to implement the intelligent monitoring and control method described above; and one or more I / O interfaces 203 connected between the processors and the memory, configured to enable information interaction between the processors and the memory.

[0118] The processor 201 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 202 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 203 is connected between the processor 201 and the memory 202, enabling information exchange between the processor 201 and the memory 202, including but not limited to a data bus (Bus).

[0119] In some embodiments, the processor 201, memory 202, and I / O interface 203 are interconnected via bus 204, and thus connected to other components of the computing device.

[0120] In some embodiments, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described intelligent monitoring and control methods.

[0121] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0122] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in connection with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in connection with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this disclosure as set forth by the appended claims.

Claims

1. An intelligent monitoring and control method, characterized in that, The method includes: Environmental changes in the monitoring area are detected using the first radio signal sensing and detection method, and an environmental change score is obtained. When the environmental change score is greater than the first preset threshold, the monitoring area is targeted by the second radio signal sensing and detection method to obtain the radio signal score; When the radio signal score is greater than the second preset threshold, trajectory prediction is performed on the detected target to obtain the trajectory prediction result of the target; Based on the trajectory prediction results, the vision module is controlled to track and capture images of the target that is about to enter the preset visual monitoring area.

2. The intelligent monitoring and control method according to claim 1, characterized in that, The first radio signal sensing and detection method includes WIFI change sensing and detection; The environmental change detection of the monitoring area using a first radio signal sensing and detection method, and the resulting environmental change score, includes: The monitoring area is used to collect WIFI signal parameters to obtain wireless signal feature vectors; The environmental change score is determined based on the wireless signal feature vector.

3. The intelligent monitoring and control method according to claim 2, characterized in that, The wireless signal feature vector includes at least Received Signal Strength Indication (RSSI) and Channel State Information (CSI); The determination of the environmental change score based on the wireless signal feature vector includes: Based on the wireless signal feature vector, determine the standard deviation of CSI and the absolute value of the change in RSSI; The environmental change score is obtained by weighted summing of the standard deviation of the CSI and the absolute value of the change in the RSSI.

4. The intelligent monitoring and control method according to claim 1, characterized in that, The second radio signal sensing and detection method includes radar monitoring, and the radio signal scoring includes radar scoring; The step of performing target detection in the monitoring area using a second radio signal sensing and detection method to obtain a radio signal score includes: The radar module transmits electromagnetic wave signals to the monitoring area and receives echo signals. Signal analysis is performed based on the transmitted signal and the echo signal of the radar module to obtain the target's range and velocity information; The radar score of the target is determined based on the target's distance and speed information.

5. The intelligent monitoring and control method according to claim 4, characterized in that, The step of determining the radar score of the target based on the target's distance and velocity information includes: Based on the distance information of the target and a preset distance-related scoring function, a distance score is determined; A speed score is determined based on the target's speed information and a preset speed-related scoring function; The radar score of the target is obtained by weighted summation of the distance score and the speed score.

6. The intelligent monitoring and control method according to claim 4, characterized in that, The step of predicting the trajectory of the detected target to obtain the trajectory prediction result of the target includes: Based on the target's distance and velocity information, a sequence of target motion states is constructed; Based on the target motion state sequence, a pre-trained trajectory prediction model is used to predict changes in the target's motion direction and speed, thereby obtaining the target's trajectory prediction result.

7. The intelligent monitoring and control method according to claim 1, characterized in that, The step of controlling the vision module to track and capture images of the target that is about to enter the preset visual monitoring area based on the trajectory prediction result includes: Based on the trajectory prediction results, it is determined whether the target is about to enter the preset visual monitoring area; If it is determined that the target is about to enter the preset visual monitoring area, the visual module is activated and the internal parameters of the camera and / or the shooting posture parameters are adjusted so that the visual module can track and shoot the target. The vision module is turned off when the target leaves the preset visual monitoring area. The camera's internal parameters include at least one of the following: resolution, frame rate, focal length, aperture, shutter speed, ISO sensitivity, white balance, exposure compensation, field of view, and image format. The shooting posture parameters include at least one of the following: shooting direction, shooting angle, shooting distance, shooting height, camera orientation, and tilt angle.

8. The intelligent monitoring and control method according to any one of claims 1 to 7, characterized in that, The trajectory prediction of the detected target, to obtain the trajectory prediction result of the target, includes at least one of the following: The detected target is type-determined. If the target type belongs to a preset valid target type, the target is determined to be a valid target, and trajectory prediction is performed on the valid target to obtain the trajectory prediction result of the valid target. If two or more targets are detected, motion correlation analysis is performed between the targets, and trajectory prediction is performed on each target based on the motion correlation analysis results to obtain the trajectory prediction results of each target.

9. An electronic device, characterized in that, include: One or more processors; A memory having stored one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the intelligent monitoring and control method according to any one of claims 1 to 8.

10. A computer-readable medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the intelligent monitoring and control method according to any one of claims 1 to 8.

Images