Monitoring system wake-up method, monitoring system, and computer-readable storage medium

Abstract

The application provides a monitoring system wake-up method, a monitoring system and a computer readable storage medium. The method can include: when a target monitoring system is in a sleep state, a sleep monitoring module identifies a first image collected according to a first monitoring rule; when a result of the identification of the first image indicates that a probability of the presence of a target object exceeds a first threshold value, the sleep monitoring module identifies a second image collected according to a second monitoring rule, the identification frequency of the second monitoring rule is greater than the identification frequency of the first monitoring rule; and when a result of the identification of the second image indicates the presence of a target object, the target monitoring system is woken up. The energy consumption of the monitoring system can be reduced.

Description

Technical Field

[0001] This application relates to the field of surveillance technology, and more specifically, to a method for waking up a surveillance system, a surveillance system, and a computer-readable storage medium. Background Technology

[0002] Traditional surveillance systems face a significant challenge: power consumption. Most existing surveillance systems require continuous operation of high-definition cameras, video encoders, and main processors, resulting in high energy consumption. This high energy consumption can lead to the system being unable to monitor other systems when its power is depleted or cannot be replenished. Summary of the Invention

[0003] The purpose of this application is to provide a method for waking up a monitoring system, a monitoring system, and a computer-readable storage medium that can reduce the energy consumption of the monitoring system.

[0004] In a first aspect, this application provides a method for waking up a monitoring system, comprising: when the target monitoring system is in a dormant state, a dormant monitoring module identifies a first image acquired according to a first monitoring rule; when the probability of the identification result of the first image indicating the presence of a target object exceeds a first threshold, the dormant monitoring module identifies a second image acquired according to a second monitoring rule, wherein the identification frequency of the second monitoring rule is greater than the identification frequency of the first monitoring rule; and when the identification result of the second image indicates the presence of a target object, waking up the target monitoring system.

[0005] In the above implementation, energy consumption can be reduced through multi-level wake-up settings. Specifically, if a potential target object is detected in the first-level monitoring, a second-level monitoring with a higher recognition frequency can be used, making it easier to detect the target object, thereby reducing false wake-ups and saving energy.

[0006] In an optional implementation, the first monitoring pattern includes a first identification period and a first sleep period, wherein the first identification period and the first sleep period are spaced apart; the identification of the acquired first image includes: identifying one or more acquired first images within each first identification period.

[0007] In the above implementation method, by setting the identification period and the sleep time, it is possible to achieve regular identification, reduce the missed detection of target objects, and also reduce the overall energy consumption of the monitoring system by not providing identification during the sleep time.

[0008] In an optional implementation, the method for determining the first identification period includes: calculating the first identification period based on the environmental parameters of the environment in which the target monitoring system is located and the frequency of the target object appearing in the environment in which the target monitoring system is located; the method for determining the first dormancy period includes: calculating the first dormancy period based on the frequency of the target object appearing in the environment in which the target monitoring system is located.

[0009] In the above implementation method, the first sleep period can be determined based on the frequency of the target object appearing in the environment where the target monitoring system is located. This can make the determined first sleep period more in line with the monitoring needs of the environment where the target monitoring system is located, and thus reduce the chance of missing the target object.

[0010] In an optional implementation, the second monitoring pattern includes a second identification period and a second sleep period, wherein the second identification period and the second sleep period are spaced apart; the second sleep period is shorter than the first sleep period, and the second identification period is longer than the first identification period; the identification of the acquired second image includes: identifying one or more acquired second images within each second identification period.

[0011] In the above implementation, the second monitoring pattern can also be set with a second identification period and a second sleep period, so as to realize the regular monitoring of the environment where the target monitoring system is located. Furthermore, the second sleep period is shorter than the first sleep period, and the second identification period is longer than the first identification period. In the case that there may be a target object, the identification frequency can be increased, the probability of the target object being detected can be increased, and the situation of missed detection can be reduced.

[0012] In an optional implementation, the determination of the second recognition period includes: calculating the second recognition period based on the area of ​​the target object in the second image; the determination of the second dormancy period includes: calculating the second dormancy period based on the confidence level of the first-level detection, wherein the first-level detection is a detection based on the first image.

[0013] In the above implementation method, the length of the subsequent second sleep period can be set by combining the confidence level of the first-level detection. This can avoid wasting detection energy consumption and also ensure that the configured second sleep period meets the actual detection requirements.

[0014] In an optional implementation, the step of identifying one or more second images acquired in each second identification period includes: identifying multiple consecutive second images acquired in each second identification period; and when the identification results of multiple consecutive second images all indicate that the probability of the existence of a target object exceeds a second threshold, determining that the identification results of the second images indicate the existence of a target object, and the second threshold is greater than the first threshold.

[0015] In the above implementation, the recognition results of multiple consecutive images can be combined to determine whether a target object has been detected. Using the result of the target object being detected can be more reliable, and the system wake-up can also be more reliable.

[0016] In an optional implementation, the second threshold is determined by calculating the second threshold based on environmental parameters of the environment in which the target monitoring system is located and the area of ​​the target object in the second image.

[0017] In an optional implementation, the formula for calculating the second threshold includes: , ; in, L represents the preset basic threshold; S represents the light intensity of the environment where the target monitoring system is located; and S represents the area of ​​the target object in the second image. Indicates the illumination adjustment factor; Indicates the size adjustment factor; Indicates the minimum threshold; This represents the maximum threshold.

[0018] In the above implementation method, the relevant parameters (second threshold) used in the second-level monitoring can be determined by combining the environmental parameters of the environment in which the target monitoring system is located. This can make the determined relevant parameters (second threshold) more consistent with the actual situation of the detected target object in the environment in which the target monitoring system is located.

[0019] In an optional implementation, the method further includes: updating the first monitoring rule when the recognition result of the second image indicates that there is no target object, wherein the recognition frequency of the updated first monitoring rule is less than the recognition frequency of the unupdated first monitoring rule.

[0020] In the above implementation method, based on the actual detection situation, if the target object does not exist but the second level of sleep listening is entered, it may indicate that the first level of listening may have mis-listened. The recognition frequency of the first listening pattern can be appropriately reduced, which can further reduce energy consumption.

[0021] Secondly, this application provides a monitoring system, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the monitoring system is running, the machine-readable instructions are executed by the processor to perform the steps of the method described in any of the foregoing embodiments.

[0022] Thirdly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the method described in any of the foregoing embodiments.

[0023] Fourthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the method described in any of the foregoing embodiments. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a block diagram of a target monitoring system provided in an embodiment of this application; Figure 2 A flowchart of a monitoring system wake-up method provided in an embodiment of this application; Figure 3 Another flowchart of the monitoring system wake-up method provided in the embodiments of this application. Detailed Implementation

[0026] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0027] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] With the rapid development of artificial intelligence and Internet of Things technologies, intelligent monitoring systems have been widely used in security, wildlife observation, traffic management and other fields. However, traditional monitoring systems require continuous operation of high-definition cameras, video encoders and main processors, resulting in high energy consumption. This is particularly unfavorable for field monitoring scenarios powered by batteries or solar power. If the battery runs out, timely monitoring cannot be achieved. In solar-powered monitoring scenarios, the monitoring system may fail to monitor at night or when sunlight is weak. Current low-power monitoring solutions for monitoring systems mainly include: (1) periodically capturing images of the surrounding environment of the monitoring system, for example, taking images at preset time intervals, but this method may miss key events; (2) triggering recording by detecting changes in heat sources, but this is easily affected by the environment and has a high false alarm rate; (3) detecting moving objects by frame difference method, but it cannot distinguish between specific targets and non-targets (such as swaying leaves, changes in light and shadow), resulting in a large number of false triggers. Although the above solutions can meet some of the low-power requirements, it is difficult to guarantee high accuracy and there may be a large number of false alarms or missed alarms.

[0029] Based on the above research, the embodiments of this application can provide a monitoring system wake-up method, a monitoring system, and a computer-readable storage medium, which can reduce the energy consumption of the monitoring system and more accurately identify the target object.

[0030] To facilitate understanding of this embodiment, the monitoring system that performs the monitoring system wake-up method disclosed in this application embodiment will first be described in detail.

[0031] like Figure 1 The diagram shown is a block diagram of a monitoring system. The monitoring system 100 may include a memory and a processor. The memory stores machine-readable instructions executable by the processor. When the monitoring system is running, the machine-readable instructions are executed by the processor to perform the steps in the monitoring system wake-up method provided in this application embodiment.

[0032] The monitoring system 100 is divided into a hibernation monitoring module 110 and a full-function working module 120 according to their functions.

[0033] The sleep monitoring module 110 can provide low-power monitoring when the monitoring system is in sleep mode. The full-function module 120 can provide efficient and continuous monitoring.

[0034] The sleep monitoring module 110 is the core of the low-power operation of the monitoring system. It can continuously perceive the surrounding environment and make preliminary judgments on target objects. It continuously runs a lightweight recognition algorithm when the monitoring system is in standby mode. It only triggers the wake-up process when a potential target object is detected to wake up the full-function working module 120. The hardware configuration of the sleep monitoring module 110 needs to balance ultra-low power consumption and basic target detection performance.

[0035] Optionally, the sleep monitoring module 110 may include a first processor, which may include a neural network processing unit (Micro NPU). The first processor may be a chip whose power consumption can be controlled within 0.1-0.5W (e.g., 0.1W, 0.2W, 0.3W, 0.5W), and whose computing power can reach 0.5-1 TOPS (INT8 quantization precision), supporting fixed-point arithmetic and lightweight model inference acceleration.

[0036] Optionally, the chip of the first processor can integrate a hardware-level power-saving unit, support dynamic clock gating technology, and automatically shut down redundant computing units when idle, further reducing static power consumption.

[0037] In this embodiment, the sleep monitoring module 110 may further include an image sensor. Exemplarily, this image sensor may be paired with a monochrome image sensor with a first range of pixel global shutter speeds. The image sensor may provide a low-resolution operating mode, where the first range can be a range with relatively low pixel values, such as 2-5 megapixels. Exemplarily, the image sensor's resolution may support two adjustable levels: 640×480@5fps and 1280×720@3fps. The global shutter of the image sensor may be designed to avoid motion blur.

[0038] The monochrome image sensor used can achieve a signal-to-noise ratio of no less than 55dB in low-light environments (0.01 lux), making it suitable for outdoor nighttime and indoor low-light scenarios. The image sensor supports a low-power wake-up mode, which only initiates data acquisition during the listening cycle and immediately enters sleep mode after acquisition is completed, with a single acquisition power consumption of no more than 0.05W.

[0039] Optionally, the sleep monitoring module 110 may include a first memory, which may operate at a voltage of 1.1V. This first memory may be used to store a computer program for a lightweight recognition algorithm. For example, the computer program for the lightweight recognition algorithm may occupy less than 1MB of memory. The first memory may also be used for temporary data acquisition (single frame image data size not exceeding 0.5MB) and algorithm runtime caching.

[0040] For example, the first memory can be 128MB-256MB LPDDR4 memory, operating at 1.1V, with a bandwidth of not less than 1600Mbps. Optionally, the first memory can support a partial self-refresh mode, maintaining low-power refresh only in the model storage area during hibernation, while powering down the remaining areas, thereby reducing the power consumption of the first memory.

[0041] In this embodiment, the sleep monitoring module 110 may include an auxiliary sensing unit.

[0042] Optionally, the auxiliary sensing unit may include sensors such as infrared sensors and sound sensors to form a multimodal sensing matrix. The power consumption of the infrared sensor is no more than 0.03W, and the power consumption of the sound sensor is no more than 0.02W. For example, the detection range of the infrared sensor can be 5-10 meters, and the temperature response range is -20℃ to 80℃, used to assist in identifying heat source targets. For example, the sound sensor can support sound acquisition in the 100-1000Hz frequency band, with a sensitivity of no less than -40dB, and can detect sound signals generated by target movement, which can be fused with image data to improve the initial target identification accuracy.

[0043] In this embodiment, the sleep monitoring module 110 may include an interface module. For example, this interface module may be equipped with I2C or SPI low-power interfaces for communicating with the adaptive power management module 130 and transmitting target detection results and wake-up requests. For example, this interface module may integrate a GPIO interface to support hardware-level wake-up signal output with a response latency of no more than 10ms.

[0044] In this embodiment, the full-function working module 120 can be started after the monitoring system is woken up. The full-function working module 120 can be used to realize the acquisition of high-definition images or videos, and realize the accurate identification of target objects, the dissemination of identification data, and the tracking of target objects based on high-definition images or videos.

[0045] The full-function module 120 may include a second processor. For example, the second processor may be a multi-core ARM Cortex-A series processor.

[0046] Optionally, the second processor can have a clock speed of 1.5-2.0 GHz and 4-8 cores. This second processor can be equipped with 1-4 GB of LPDDR4 memory (with a bandwidth of no less than 2133 Mbps), supports the NEON accelerated instruction set and hardware floating-point operations, achieving a computing power of 5-10 TOPS, meeting the needs of complex tasks such as high-definition video encoding, multi-target tracking, and face recognition.

[0047] Optionally, the second processor can support Dynamic Voltage and Frequency Scaling (DVFS) technology, which dynamically adjusts the main frequency (300MHz-2.0GHz) and core voltage (0.8V-1.2V) according to the task load, and the idle cores automatically go into sleep mode.

[0048] In this embodiment, the full-function working module 120 may include a camera. This camera may be a high-definition camera. For example, the camera may be a high-definition dual-light image sensor with 8-12 megapixels. Exemplarily, the camera may support both color and monochrome dual-mode switching. In one example, the camera's resolution in color mode may be 4K (3840×2160)@30fps, and the resolution in monochrome mode may be 1080P (1920×1080)@60fps, with a dynamic range of not less than 120dB. Exemplarily, in low light conditions (e.g., 0.1 lux), the signal-to-noise ratio in color mode is not less than 45dB, and the signal-to-noise ratio in monochrome mode is not less than 60dB.

[0049] Optionally, the camera can also be equipped with an infrared filter switching function, automatically switching to infrared mode at night, and working with an 850nm infrared fill light (for example, the power can be adjusted in the range of 1-3W) to achieve clear imaging at night within 20 meters.

[0050] In this embodiment, the full-function working module 120 may include a video encoder.

[0051] For example, the video encoder can be an integrated H.265 / H.264 hardware encoder, supporting multi-bitrate adaptive encoding with an adjustable bitrate range of 1-10Mbps, and supporting mode switching between Constant Bitrate (CBR) and Variable Bitrate (VBR). H.265 encoding is 30% more energy-efficient than H.264. Specifically, the power consumption for 1080P@30fps video encoding is no more than 1W, and for 4K@30fps video encoding, the power consumption is no more than 2W. It supports ROI (Region of Interest) encoding, encoding only the target area in high definition while degrading the background area, further reducing encoding power consumption and data volume.

[0052] In this embodiment, the full-function working module 120 may include a gimbal tracking system.

[0053] For example, the gimbal tracking system can use a miniaturized PTZ gimbal (e.g., weighing no more than 500g). The gimbal tracking system supports horizontal rotation of 0-355° (speed can be 0.5-10° / s) and vertical rotation of -10° to 90° (speed can be 0.5-8° / s), with a positioning accuracy of no more than 0.1°, and supports automatic target tracking and preset point navigation. The gimbal driver of the gimbal tracking system can use a stepper motor, with static power consumption of no more than 0.1W and dynamic operating power consumption of no more than 2W, and supports a power-off self-locking function to prevent target loss.

[0054] In this embodiment, the full-function working module 120 may include a communication module. This communication module can integrate multi-mode communication interfaces, such as 4G LTE Cat.4 / Cat.6 (power consumption no greater than 2W), 5G NR (power consumption no greater than 3W), Wi-Fi 6 (802.11ax, power consumption no greater than 1.5W), Ethernet (10 / 100 / 1000M, power consumption no greater than 0.8W), and a Bluetooth module, such as Bluetooth 5.0 (power consumption no greater than 0.3W).

[0055] Optionally, the communication module can support wired / wireless dual-mode switching. The 4G / 5G module can support remote data upload and command reception, with an upload rate of not less than 10Mbps; the Wi-Fi 6 module supports local high-speed data transmission (rate ≥1.2Gbps), adapting to short-range scenarios such as smart homes; the Bluetooth module is used for local debugging and linkage with low-power devices.

[0056] In this embodiment, the full-function working module 120 may include a second memory. The second memory may be local storage (e.g., 128GB-1TB eMMC 5.1 with a power consumption of no more than 0.5W) and a cloud storage interface.

[0057] Optionally, the local storage supported by the second storage device can be in a circular storage mode. For example, it supports circular overwrite (with an adjustable storage period). The cloud storage of the second storage device can support encrypted transmission (e.g., AES-256 encryption) and resume interrupted transmission, meeting the requirements for data security and long-term retention.

[0058] In this embodiment, the full-function working module 120 may include an alarm and linkage module. This alarm and linkage module may include an audible and visual alarm unit (buzzer power not greater than 0.5W, LED indicator power not greater than 0.1W), a relay output interface (supporting control of external devices such as infrared lights and sirens), and linkage interfaces (RS485, CAN), which can be linked with access control systems, fire-fighting equipment, drones, etc., to achieve multi-device collaborative security.

[0059] In this embodiment, the monitoring system may further include an adaptive power management module 130. The adaptive power management module 130 can be used to control the power supply, regulate the voltage, monitor the power consumption, and process the wake-up signal for each module. Through the collaboration of hardware circuits and software algorithms, it can achieve fine-grained power consumption management.

[0060] The power supply for each module of the monitoring system can support multiple power inputs, including lithium batteries (e.g., 3.7V / 12V, capacity 10-100Ah), solar panels (e.g., 10-50W), Power over Ethernet (PoE) (e.g., 802.3af / at, 48V input), and 12V DC power, adapting to the power supply requirements of different application scenarios. For power supply functionality, a built-in power management chip can be incorporated, with a conversion efficiency of no less than 95%, supporting multiple independent outputs (3.3V, 5V, 12V) to power each module separately.

[0061] In this embodiment, the adaptive power management module 130 can provide dynamic voltage regulation. For example, a dual mechanism of DVFS+DVS (Dynamic Voltage Regulation) can be used to adjust the supply voltage according to the operating state of each module. For instance, the sleep monitoring module 110 operates at a supply voltage of 3.3V, which drops to 1.8V during sleep. The second processor operates at 0.8V under light load, rising to 1.2V under heavy load. Through coordinated regulation of voltage and frequency, optimal matching of power consumption and performance is achieved.

[0062] In this embodiment, the adaptive power management module 130 may include a power monitoring unit. For example, the power monitoring unit may include a high-precision current sensor (e.g., accuracy ±1%) and a voltage sensor (e.g., accuracy ±0.5%), which monitors the current and voltage data of each module in real time, with a sampling frequency of 100Hz, calculates the real-time power consumption of each module (P=U×I), and uploads the data to the second processor for input to the adaptive power adjustment algorithm.

[0063] In this embodiment, the adaptive power management module 130 may include a wake-up control unit. The wake-up control unit may include a dedicated wake-up controller (power consumption not greater than 0.01W), which receives the wake-up request from the sleep monitoring module 110, triggers the power supply start-up of the full-function working module 120 according to preset logic, and supports hardware-level fast wake-up (start-up time not greater than 50ms) and software-level delayed wake-up (for example, the delay can be adjusted in the range of 0-1000ms), avoiding power waste caused by false triggering.

[0064] In this embodiment, the adaptive power management module 130 may include an energy storage and protection unit. For example, the energy storage and protection unit may be a supercapacitor (e.g., with a capacity of 1-5F) to cope with sudden power outages or voltage fluctuations, ensuring the safe storage of critical data (such as target detection results and video clips); it integrates overvoltage, overcurrent, and overtemperature protection circuits, automatically cutting off power supply to protect hardware devices when the supply voltage exceeds the rated value by 15%, the current exceeds the rated value by 20%, or the module temperature exceeds 65°C.

[0065] In this embodiment, in order to make the monitoring system more adaptable to the environment, more devices that adapt to the environment can be set up.

[0066] Optionally, each component of the monitoring system (the sleep monitoring module 110 and the components included in the full-function working module 120) can be equipped with a housing. Optionally, the housing is made of aluminum alloy (thermal conductivity not less than 200W / (m·K)), and the housing has built-in heat sinks and thermal pads. In high-temperature environments (60℃), heat dissipation is assisted by a fan (e.g., fan power not greater than 0.5W, temperature-controlled start), and in low-temperature environments (-40℃), a heating film (power not greater than 1W, temperature-controlled start) ensures the normal operation of the components.

[0067] In this embodiment, the PCB board of the monitoring system can adopt a three-proof coating (moisture-proof, salt spray-proof, mildew-proof), the interface adopts a waterproof aviation plug (IP67 protection level), and the shell is sealed. It supports long-term operation in environments with relative humidity of 10%~90% (non-condensation), and is suitable for humid scenarios such as the seaside and rainforest.

[0068] In this embodiment, the power supply circuit of the monitoring system adopts an EMC filter module to suppress electromagnetic interference; the communication interface adopts differential signal transmission, which improves the anti-interference capability by 30%; the image sensor lens is equipped with an anti-fog and anti-reflection coating to avoid the impact of severe weather (rain, snow, fog) on ​​the imaging quality.

[0069] The monitoring system 100 in this embodiment can be used to execute various steps in the various methods provided in the embodiments of this application. The implementation process of the monitoring system wake-up method is described in detail below through several embodiments.

[0070] Please see Figure 2 This is a flowchart of a monitoring system wake-up method provided in an embodiment of this application. The monitoring system wake-up method provided in this embodiment can be applied to a monitoring system, through which the monitoring system executes the steps in the monitoring system wake-up method. The following will describe... Figure 2 The specific process shown will be explained in detail.

[0071] Step 210: When the target monitoring system is in a dormant state, the dormant listening module identifies the first image collected according to the first listening rule.

[0072] If the recognition result of the first image indicates that the probability of the presence of a target object exceeds a first threshold, step 220 is executed.

[0073] In this embodiment, the target monitoring system can be in a sleep state by default. The sleep monitoring module starts at a fixed period to identify the first image acquired.

[0074] The first image can be image data of the environment that the target monitoring system needs to monitor.

[0075] Optionally, the algorithm used for recognizing the first image in the sleep state can be a lightweight detection algorithm for coarse detection. For example, this lightweight detection algorithm can be a YOLO series algorithm, such as YOLOv5, YOLOv8-nano, etc.

[0076] The first threshold can be a value set as needed. For example, a 100% probability of the presence of a target object indicates the presence of a target object in the first image, while a 0% probability indicates the absence of a target object in the first image. The first threshold can be a value between 0 and 100%. For instance, step 210 is an initial detection as a dormant phase, and the first threshold can be set to a relatively smaller value, such as 25% to 40%. For example, the first threshold can be values ​​such as 25%, 30%, 33%, 35%, and 40%.

[0077] The target object can be a specific object that needs to be tracked, such as a person, an animal, or other similar object. The target object can also be a category of objects, not a specific object; for example, the category of objects corresponding to the target object could be a person or an animal. Depending on the usage environment of the target monitoring system, the target object may also differ. This application's embodiments are not limited to the usage environment or target object of the target monitoring system.

[0078] The first monitoring rule can be to intermittently identify the first images acquired. For example, the first monitoring rule can include identifying the target object only during a first preset identification period, the duration of which can be a pre-set value. For example, the duration of the first preset identification period can be 8%-12%. The duration of the first preset identification period can be 8%, 10%, 12%, 9%, etc. For example, among all acquired first images, only first images are acquired during the first preset identification period, and the first images acquired during the first preset identification period are identified to determine whether a target object exists.

[0079] The first monitoring rule can be to identify the presence of a target object by recognizing a specified number of first images within each time period.

[0080] Step 220: The hibernation monitoring module identifies the acquired second image according to the second monitoring pattern.

[0081] The recognition frequency of the second listening pattern is greater than that of the first listening pattern.

[0082] In step 220, a relatively higher frequency can be used to recognize the image, which can identify the target object more efficiently.

[0083] The second monitoring pattern can be to intermittently identify the acquired second image. For example, the second monitoring pattern can include identifying the target object only during a second preset identification period, where the duration of the second preset identification period can be a pre-set value. In this embodiment, the proportion of the second preset identification period can be greater than the proportion of the first identification period.

[0084] The second monitoring rule can be to intermittently identify the acquired second images. For example, the second monitoring rule can include identifying the target object only during a second preset identification period, where the duration of the second preset identification period can be a pre-set value. In this embodiment, the proportion of the second preset identification period can be greater than the proportion of the first identification period. For example, the proportion of the second preset identification period can be 15%-25%. The proportion of the second preset identification period can be 15%, 20%, 22%, 25%, etc. For example, among all acquired second images, second images are only acquired during the second preset identification period, and the second images acquired during the second preset identification period are identified to determine whether a target object exists.

[0085] The second monitoring pattern can be to identify the presence of a target object by recognizing a specified number of second images within each time period.

[0086] If the recognition result of the second image indicates the presence of a target object, proceed to step 230.

[0087] Step 230: Wake up the target monitoring system.

[0088] In the above implementation, the wake-up of the monitoring system can be achieved based on a two-level wake-up mechanism. The first level (coarse detection) and the second level (fine detection) balance power consumption and detection accuracy through different listening cycles and detection strategies.

[0089] In one implementation, the first monitoring pattern includes a first identification period and a first sleep period, wherein the first identification period and the first sleep period are spaced apart.

[0090] The identification of the acquired first image in step 210 above may include: identifying one or more acquired first images within each first identification time period.

[0091] For example, the duration of the first recognition period can be 100ms-500ms, and the duration of the first sleep period can be 2s-5s. For instance, the duration of the first recognition period can be 100ms, 200ms, 300ms, 400ms, 500ms, etc. The duration of the first sleep period can be 2s, 2.5s, 3s, 3.5s, 4s, 5s. Taking a first recognition period of 200ms and a first sleep period of 3s as an example, after 200ms of recognition listening, there is a 3s sleep period, followed by another 200ms of recognition listening, and so on, cycling through listening and sleep cycles.

[0092] By setting up the above-mentioned cyclic monitoring and sleep mode, the first-level sleep mode can save energy while maintaining monitoring and identification of the surroundings, thus reducing the probability of missing the target object.

[0093] In this embodiment, the method for determining the first identification time period includes: calculating the first identification time period based on the environmental parameters of the environment in which the target monitoring system is located and the frequency of the target object appearing in the environment in which the target monitoring system is located.

[0094] For example, the first identification period can be determined based on the following formula: ; in, Indicates the first identification period; This indicates the preset upper limit of illumination; This indicates the ambient light intensity of the target monitoring system's environment. The preset upper limit for light intensity can be a relatively large value, for example, Based on the formula above, the stronger the ambient light in the environment where the target monitoring system is located, the longer the first identification period will be.

[0095] The method for determining the first sleep period includes: calculating the first sleep period based on the frequency of the target object appearing in the environment where the target monitoring system is located.

[0096] For example, the first sleep period can be determined based on the following formula: ; in, Indicates the first hibernation period; This indicates the probability that the target object's historical activities exist in the area monitored by the target monitoring system; This represents the maximum probability that an activity targeting the target exists. For example, It can be 100%. Based on the above formula, the higher the probability of historical activity of the target object in the monitored area, the shorter the dormancy time, and the higher the detection frequency.

[0097] Historical activity probability can represent the frequency of occurrence of a target object during the same time period in the past 24 hours.

[0098] By implementing the above method, the sleep period can be longer when the probability of the target object appearing is low, thus reducing recognition energy consumption. Under suitable monitoring lighting conditions, the recognition period can also be longer, making it easier to detect the target object clearly.

[0099] In one implementation, the second monitoring pattern includes a second identification period and a second sleep period, wherein the second identification period and the second sleep period are spaced apart; the second sleep period is shorter than the first sleep period, and the second identification period is longer than the first identification period.

[0100] The identification of the acquired second image in step 220 above includes: identifying one or more acquired second images within each second identification time period.

[0101] For example, the duration of the second recognition period can be 200ms-800ms, and the duration of the second sleep period can be 0.5-1.5 seconds. For instance, the duration of the second recognition period can be 200ms, 300ms, 400ms, 500ms, 800ms, etc. The duration of the second sleep period can be 0.5s, 0.8s, 1s, 1.3s, 1.4s, 1.5s. Taking a second recognition period of 500ms and a second sleep period of 1s as an example, after 500ms of recognition listening, there is a 1s sleep period, followed by another 500ms of recognition listening, and this cycle of listening and sleeping repeats.

[0102] By setting up the above-mentioned loop monitoring and hibernation, the second-level hibernation stage can further improve the monitoring and identification of the surroundings while achieving energy saving, thus reducing the probability of missing the target object.

[0103] In this embodiment, the method for determining the second recognition time period includes: calculating the second recognition time period based on the area of ​​the target object in the second image.

[0104] For example, the second identification period can be determined based on the following formula: ; in, This indicates the second identification time period; S represents the pixel area of ​​the target object detected in the first level based on step 210. This indicates the preset maximum pixel area. For example, Based on the above formula, the larger the area of ​​the target object detected in the first section, the longer the determined second recognition time period will be, ensuring that the features of the target object are fully collected.

[0105] The method for determining the second sleep period includes: calculating the second sleep period based on the confidence level of the first-level detection, wherein the first-level detection is a detection based on the first image.

[0106] For example, the second sleep period can be determined based on the following formula: ; in, Indicates the second dormancy period; This represents the confidence level of the first-level detection provided in step 210. The lower the confidence level, the longer the sleep time, to avoid power waste caused by rapid repeated detection.

[0107] To further improve the effectiveness of sleep period determination, the sleep and wake-up listening cycles of the two-level detection can be dynamically adjusted based on multi-dimensional information such as time, ambient light, and historical activity records, thereby further optimizing power consumption. For example, the duration of the adjusted sleep period can be determined based on the historical activity probability of the target object, the light intensity of the environment in which the target monitoring system is located, the preset light adjustment coefficient, and the preset minimum light threshold.

[0108] ; in, This indicates the duration of the adjusted hibernation period, which can be used to determine both the first and second hibernation periods. Based on the base sleep time, for example, in the case of adjustments for the first sleep period, =2s; This is in response to adjustments made for the second sleep period. =0.5s. Of course, the base sleep time will also be different if the range of values ​​for the first sleep period and the second sleep period are different. The base sleep time can be the minimum value in the range of values ​​for the sleep period.

[0109] This represents the activity probability adjustment coefficient, which can range from 0.5 to 2.0. It indicates the weight of the target object's activity probability on the dormancy time. This indicates the probability that the target object's historical activities exist in the area monitored by the target monitoring system; This represents the preset illumination adjustment coefficient, which can range from 0.3 to 1.0, and represents the weight of illumination's influence on sleep time; L represents the illumination intensity of the environment in which the target monitoring system is located. This indicates the preset minimum illumination threshold, for example, .

[0110] when =1 (frequent activity), L=10000lux (strong light), It has the shortest dormancy time.

[0111] when When =0 (no activity) and L=0.01 lux (weak light), It has the longest dormancy period.

[0112] By introducing the historical activity probability of target objects in the monitored area of ​​the target monitoring system, the likelihood of the target appearing is judged. When the target object is frequently active, the sleep time is shortened and the detection frequency is increased. The imaging quality is judged by the light intensity. When the light is weak, the sleep time is extended to avoid false detection and power waste caused by blurred imaging.

[0113] Based on the above adjustment of the sleep period, the adaptive listening cycle can reduce the power consumption of the system by 20-30% at night and during periods of inactivity, and increase the detection frequency by 30-40% during the day and during periods of frequent activity, thus achieving a dynamic balance between power consumption and detection performance.

[0114] In this embodiment, in order to reduce the error rate of the second-level detection, step 220 above may include: Step 221: During each second recognition time period, recognize multiple consecutive second images.

[0115] In this embodiment, the number of second images to be identified can be preset, for example, three consecutive images, two images, four images, etc.

[0116] Step 222: If the recognition results of multiple consecutive second images all indicate that the probability of the existence of a target object exceeds the second threshold, then the recognition results of the second image indicate that the existence of a target object is determined.

[0117] The second threshold is greater than the first threshold.

[0118] If the first threshold is 30%, the second threshold can be a value greater than 30%. For example, the second threshold can be 50%, 60%, 80%, etc.

[0119] In this embodiment, the second threshold is determined by calculating the second threshold based on the environmental parameters of the environment in which the target monitoring system is located and the area of ​​the target object in the second image.

[0120] Optionally, the formula for calculating the second threshold includes: , ; in, L represents the pre-set baseline threshold; S represents the ambient light intensity of the target monitoring system; and S represents the area of ​​the target object in the second image. Indicates the illumination adjustment factor; Indicates the size adjustment factor; Indicates the minimum threshold; This represents the maximum threshold.

[0121] like Figure 3 As shown, when the recognition result of the second image indicates that there is no target object, the monitoring system wake-up method of this embodiment may further include: step 240, updating the first listening rule.

[0122] Among them, the recognition frequency of the first listening pattern after the update is lower than the recognition frequency of the first listening pattern before the update.

[0123] For example, when the first monitoring pattern includes a first identification period and a first sleep period, the way to update the first monitoring pattern may include: increasing the duration of the first sleep period and decreasing the duration of the first identification period; increasing only the duration of the first sleep period and keeping the duration of the first identification period unchanged; or keeping the duration of the first sleep period unchanged and decreasing only the duration of the first identification period.

[0124] In this embodiment, after the target monitoring system is woken up in startup step 230, the calculation formula for the wake-up delay of the target monitoring system can be as follows: ; ; ; in, This indicates the total wake-up latency (in milliseconds), which can be controlled between 50ms and 200ms. This indicates the hardware startup latency (in milliseconds), and the hardware startup latency value can be controlled between 20-50ms. This indicates the power-on delay (in milliseconds), which is the time it takes for the adaptive power management module 130 to power on the full-function working module, ≤10ms; This indicates the hardware reset latency (in milliseconds), which is the time it takes for the second processor of the full-function working module, the camera and other hardware modules of the full-function working module to reset and start. The hardware reset latency can be controlled between 10ms and 40ms. This represents the software initialization delay (in milliseconds). The value of the software initialization delay can be controlled between 30ms and 150ms. This indicates the operating system startup latency (in milliseconds). When using a lightweight Linux system (such as Buildroot), the startup latency can be controlled to be no more than 50ms. This indicates the full-featured model loading latency (in milliseconds). The model is stored locally in eMMC, and the loading time is no more than 100ms.

[0125] In step 230, by preloading some software modules and optimizing the hardware startup process, the total wake-up latency can be controlled within 50ms-200ms-400ms, thereby better ensuring that no key target objects are missed in the detection.

[0126] The method described in this application embodiment allows for more accurate identification of potential target objects in a dormant state based on two levels of lightweight identification.

[0127] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the monitoring system wake-up method described in the above method embodiments.

[0128] The computer program product of the monitoring system wake-up method provided in this application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the steps of the monitoring system wake-up method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed methods can also be implemented in other ways. The method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0130] In addition, the method steps in the various embodiments of this application can be integrated together to form an independent part for execution, or each method step can be executed by a separate module, or two or more steps can be formed into an independent part for execution.

[0131] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. It should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0132] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0133] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for waking up a monitoring system, characterized in that, include: When the target monitoring system is in a dormant state, the dormant listening module identifies the first image it has acquired according to the first listening rule; If the probability of the presence of a target object in the recognition result of the first image exceeds the first threshold, the dormant monitoring module recognizes the acquired second image according to the second monitoring rule, and the recognition frequency of the second monitoring rule is greater than the recognition frequency of the first monitoring rule. If the recognition result of the second image indicates the presence of a target object, the target monitoring system is activated.

2. The method according to claim 1, characterized in that, The first monitoring pattern includes a first identification period and a first sleep period, wherein the first identification period and the first sleep period are spaced apart; The identification of the acquired first image includes: identifying one or more acquired first images within each first identification time period.

3. The method according to claim 2, characterized in that, The method for determining the first identification period includes: calculating the first identification period based on the environmental parameters of the environment in which the target monitoring system is located and the frequency of the target object appearing in the environment in which the target monitoring system is located; The method for determining the first sleep period includes: calculating the first sleep period based on the frequency of the target object appearing in the environment where the target monitoring system is located.

4. The method according to claim 2, characterized in that, The second monitoring pattern includes a second identification period and a second sleep period, wherein the second identification period and the second sleep period are set at an interval; the second sleep period is shorter than the first sleep period, and the second identification period is longer than the first identification period; The identification of the acquired second image includes: identifying one or more acquired second images within each second identification time period.

5. The method according to claim 4, characterized in that, The method for determining the second recognition time period includes: calculating the second recognition time period based on the area of ​​the target object in the second image; The method for determining the second sleep period includes: calculating the second sleep period based on the confidence level of the first-level detection, wherein the first-level detection is a detection based on the first image.

6. The method according to claim 4, characterized in that, The step of identifying one or more second images acquired during each second identification time period includes: During each of the second recognition time periods, multiple consecutive second images are recognized. If the recognition results of multiple consecutive second images all indicate that the probability of the presence of a target object exceeds a second threshold, then the recognition results of the second image indicate that the presence of a target object, and the second threshold is greater than the first threshold.

7. The method according to claim 6, characterized in that, The second threshold is determined in the following ways: The second threshold is calculated based on the environmental parameters of the environment in which the target monitoring system is located and the area of ​​the target object in the second image.

8. The method according to claim 7, characterized in that, The formula for calculating the second threshold includes: ， ； in, L represents the preset basic threshold; S represents the light intensity of the environment where the target monitoring system is located; and S represents the area of ​​the target object in the second image. Indicates the illumination adjustment factor; Indicates the size adjustment factor; Indicates the minimum threshold; This represents the maximum threshold.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: If the recognition result of the second image indicates that there is no target object, the first monitoring rule is updated, wherein the recognition frequency of the updated first monitoring rule is less than the recognition frequency of the unupdated first monitoring rule.

10. A monitoring system, characterized in that, include: The processor and memory, wherein the memory stores machine-readable instructions executable by the processor, and when the monitoring system is running, the machine-readable instructions are executed by the processor to perform the steps of the method as described in any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method as described in any one of claims 1 to 9.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 9.

Images