Monitoring method, monitoring device and electronic equipment

Abstract

The invention discloses a monitoring method, a monitoring device and electronic equipment, and the monitoring method comprises the steps: obtaining triggering information which comprises the movement data of a moving target; in response to the trigger information, controlling the main chip to be switched from a sleep mode to a first mode; when the main chip is in the sleep mode, the main chip is used for controlling the image acquisition module to stop working, and when the main chip is in the first mode, the main chip is used for controlling the image acquisition module to acquire an image frame and acquire an image detection result based on the image frame; in response to the image detection result that the target object exists in the image frame, controlling the main chip to be switched from the first mode to a second mode; and when the main chip is in the second mode, the main chip is used for controlling the image acquisition module to acquire the monitoring video stream of the target object. According to the method, the dual judgment information is obtained, when the dual information judgment conditions are met, the video monitoring function is started, false triggering can be reduced, only part of functions of the image acquisition module are called for each piece of information judgment, and power consumption can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of camera monitoring, in particular to a monitoring method, a monitoring device and an electronic device. BACKGROUND

[0002] With the continuous development and improvement of modern communication technology, in recent years, network video monitoring systems have been maturely applied in various industries and have become an important part of the security and protection system of various enterprises and institutions. The existing network video monitoring system includes a monitoring client and a video monitoring device, and the monitoring client and the video monitoring device are connected through the Internet. Specifically, the video monitoring device is mainly a security camera, and the battery version of the security camera is powered by a battery, so the endurance time becomes an important indicator of the security camera.

[0003] The existing security camera uses a mobile detection method for monitoring. Mobile detection usually detects the entire image captured by the camera, and any movement of objects in the image will trigger a response. For example, mobile detection cannot filter the triggers caused by the swaying of flowers, trees and other objects blown by the wind, that is, there is a problem of easy false triggering. Moreover, since mobile detection needs to frequently acquire image data, it leads to high power consumption of the security camera, thereby reducing the effective endurance time of the security camera. SUMMARY

[0004] The present application provides a monitoring method, which can solve the problems of easy false triggering and high power consumption of the existing security camera.

[0005] The first aspect of the present application provides a monitoring method, which comprises:

[0006] acquiring trigger information, wherein the trigger information comprises movement data of a moving target;

[0007] in response to the trigger information, controlling the main chip to switch from a sleep mode to a first mode; wherein, when the main chip is in the sleep mode, the main chip is used to control the image acquisition module to stop working, and when the main chip is in the first mode, the main chip is used to control the image acquisition module to acquire an image frame and obtain an image detection result based on the image frame;

[0008] in response to the image detection result being that the image frame contains a target object, controlling the main chip to switch from the first mode to a second mode; when the main chip is in the second mode, the main chip is used to control the image acquisition module to acquire a monitoring video stream of the target object.

[0009] Further, the main chip further comprises a deep learning model, and the monitoring method further comprises:

[0010] in response to the working state of the main chip being the first mode, initializing and setting the deep learning model;

[0011] The image detection is performed on the image frames by using the deep learning model after the initialization setting, and an image detection result is obtained.

[0012] Further, the step of performing image detection on the image frames by using the deep learning model after the initialization setting to obtain an image detection result comprises:

[0013] Obtaining image data of a target object, the image data of the target object being a training set of the deep learning model;

[0014] Comparing the image frames and the image data of the target object to obtain an image detection result, the image detection result being that the image frames contain the target object or that the image frames do not contain the target object.

[0015] Further, the number of image frames is two, and the step of comparing the image frames and the image data of the target object to obtain an image detection result comprises:

[0016] In response to any one of the two image frames containing the target object, determining that the detection result is that the image frames contain the target object;

[0017] In response to neither of the two image frames containing the target object, determining that the detection result is that the image frames do not contain the target object.

[0018] Further, the monitoring method further comprises:

[0019] In response to the image detection result being that the image frames do not contain the target object, controlling the main chip to switch from the first mode to a sleep mode.

[0020] Further, in response to the image detection result being that the image frames contain the target object, the step of controlling the main chip to switch from the first mode to a second mode comprises:

[0021] In response to the image frames containing the target object, controlling the image acquisition module to obtain video stream data;

[0022] Obtaining a monitoring video stream based on the image frames and the video stream data.

[0023] Further, the step of obtaining a monitoring video stream based on the image frames and the video stream data comprises:

[0024] Changing the data format of the image frames so that the data format of the image frames matches the data format of the video stream data;

[0025] Splicing the image frames after the change of the data format and the video stream data to obtain a monitoring video stream.

[0026] Further, the step of obtaining the trigger information comprises:

[0027] In response to the existence of the moving target in the current monitoring environment, angle data and a moving distance of the moving target are acquired, wherein the angle data is an included angle between a position of the moving target and a position of the monitoring device in two adjacent monitoring image frames, and the moving distance is a coordinate difference of the moving target in the two adjacent monitoring image frames.

[0028] In response to the angle data being less than a first threshold value, trigger information is generated.

[0029] Alternatively, in response to the moving distance being less than a second threshold value, the trigger information is generated.

[0030] The second aspect of the present application provides a monitoring device, which comprises:

[0031] A trigger detection system is configured to acquire trigger information, wherein the trigger information comprises moving data of the moving target.

[0032] A microprocessor and a main chip, in response to the trigger information, the microprocessor is configured to control the main chip to switch from a sleep mode to a first mode, wherein, when the main chip is in the sleep mode, the main chip is configured to control the image acquisition module to stop working, and when the main chip is in the first mode, the main chip is configured to control the image acquisition module to acquire an image frame and acquire an image detection result based on the image frame.

[0033] In response to the image detection result being that the image frame contains a target object, the microprocessor is further configured to control the main chip to switch from the first mode to a second mode, and when the main chip is in the second mode, the main chip is configured to control the image acquisition module to acquire a monitoring video stream of the target object.

[0034] The third aspect of the present application provides an electronic device, which comprises a memory and a processor coupled with each other, and the processor is configured to execute program instructions stored in the memory to implement the monitoring method as described above.

[0035] Different from the prior art, the present application generates trigger information based on moving data of the moving target, which can be trigger information acquired by the main chip in the sleep mode, and specifically, whether the monitoring picture contains a moving object is detected to realize preliminary judgment of the monitoring picture. Meanwhile, the main chip of the present application switches from the sleep mode to the first mode based on the trigger information to perform secondary detection, specifically, image detection is performed on the image frame acquired by the image acquisition module, and the main chip only switches from the first mode to the second mode when the image detection result is that the image frame contains a target object to perform video monitoring, that is, the monitoring video stream of the target object is acquired by the image acquisition module. The present application acquires double judgment information, and enables the video monitoring function when the double information judgment conditions are both satisfied, which can reduce false triggering, and each double information judgment only mobilizes part of the functions of the image acquisition module, which can reduce power consumption.

[0036] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not restrictive of the application. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0038] Figure 1 is a flowchart of a first embodiment of the monitoring method of the present application;

[0039] Figure 2 is a specific flowchart of an embodiment of step S11 in the method; Figure 1

[0040] Figure 3 is a specific flowchart of an embodiment of step S13 in the method; Figure 1

[0041] Figure 4 is a specific flowchart of an embodiment of step S132 in the method; Figure 3

[0042] Figure 5 is a flowchart of a second embodiment of the monitoring method of the present application;

[0043] Figure 6 is a flowchart of a third embodiment of the monitoring method of the present application;

[0044] Figure 7 is a specific flowchart of an embodiment of step S22 in the method; Figure 6

[0045] Figure 8 is a structural diagram of the monitoring device of the present application;

[0046] Figure 9 is a framework diagram of an embodiment of the electronic device of the present application;

[0047] Figure 10 is a framework diagram of an embodiment of the computer readable storage medium of the present application. DETAILED DESCRIPTION

[0048] ​​​​In order for those skilled in the art to better understand the technical solutions of the present application, the monitoring method, the monitoring device and the electronic equipment provided by the present application are further described in detail below in combination with the drawings and specific embodiments. It can be understood that the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0049] The terms "first", "second" and the like in the present application are used to distinguish different objects, not to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units not listed, or optionally also includes other steps or units inherent to the process, method, product or device.

[0050] The existing security camera uses motion detection for monitoring. Motion detection acquires images from the camera at different frame rates, and then further calculates and compares the images through the CPU according to a certain algorithm. When the picture changes, such as someone passing by or the lens being moved, the calculated and compared result will exceed the threshold value and indicate that the system can automatically make corresponding processing. Therefore, the existing security camera needs to frequently acquire image data, calculate and compare the image data collected at each moment, and trigger at any moment when the picture changes, so that the security camera is continuously in an awake state, resulting in increased power consumption of the security camera, and further resulting in reduced effective endurance time of the security camera. Moreover, the existing security camera needs to compare a large amount of data, and cannot accurately realize monitoring of a target object, which is likely to cause false triggering, such as shaking of flowers, trees and the like caused by wind, or falling of rain or snow in rain or snow scenes, etc. For a battery version security camera, frequent false triggering will result in too short endurance, which may cause many key events to be unable to be recorded due to insufficient power of the security camera itself, which is undoubtedly a great loss to the user.

[0051] In order to solve the above technical problems, the present application provides a monitoring method, which can be applied to various products in different security fields, and can be specifically applied to a battery version security camera, such as a battery version doorbell, a battery version camera or a battery version gimbal camera, etc.

[0052] On the other hand, the monitoring method of the present application can be applied to various scenes, and can be specifically applied to indoor, street, forest or farm scenes, or any scene in which a battery version security camera can be used for video monitoring.

[0053] The monitoring method of the present application can realize accurate monitoring of the monitoring object through double trigger condition judgment, reduce the false trigger frequency of the camera, and the monitoring method of the present application needs much less data matching than the image data required by mobile detection, which can reduce the power consumption of the security camera and further improve the endurance time of the security camera.

[0054] Among them, the execution subject of the monitoring method of the present application can be a monitoring device, for example, the monitoring method can be executed by a terminal device or a server or other processing device, wherein the monitoring device can be a user equipment (User Equipment, UE) such as a security camera, a mobile device, a user terminal, a terminal, a personal digital processing (Personal Digital Assistant, PDA), a handheld device, a computing device, etc. In some possible implementation ways, the compensation method can be realized by calling the computer readable instructions stored in the memory by the processor.

[0055] Specifically, the monitoring device of the present application can include a trigger detection system, a microprocessor, and a main chip. The trigger detection system can be used to monitor the monitoring picture once, to judge whether the current monitoring picture changes, that is, any object moves, and to generate trigger information when it is judged that there is a moving object; the microprocessor wakes up the main chip based on the trigger information, so that the main chip performs secondary monitoring on the image data corresponding to the trigger information, to extract the image data of the monitoring target, that is, the target object (including human body and / or object).

[0056] Please refer to Figure 1 , Figure 1 is the flowchart of the first embodiment of the monitoring method of the present application. Specifically, the monitoring method of the present application can include the following steps:

[0057] Step S11: obtaining trigger information.

[0058] Among them, the trigger information of the present embodiment includes the movement data of the moving target. Specifically, the trigger detection system of the present embodiment can include a radar, or include a radar and a passive infrared device.

[0059] Optionally, in an embodiment, the trigger detection system of the present embodiment only includes a radar, and the radar of the present embodiment can include a 1D mode and a 2D mode. When the radar is in the 1D mode, it can be judged whether there is a target moving, specifically, the radar signal can be emitted, the object reflects the radar signal, and the reflected signal is transmitted to the radar, and the radar can judge whether the object moves through the reflected signal; when the radar is in the 2D mode, the angle and distance of the moving target can be obtained.

[0060] Optionally, in an embodiment, the trigger detection system of the present embodiment comprises a radar and a passive infrared device, the core component of the passive infrared device is an infrared detection device (infrared sensor), which can detect the change of thermal radiation in a certain three-dimensional prevention space through the cooperation of the optical system. When there is no moving human body or other targets in the prevention area, since the infrared radiation energy of all background objects (such as walls, furniture, etc.) at room temperature is small and basically stable, it cannot trigger an alarm. When a human body moves in the detection area, it will cause a change in the infrared thermal radiation energy. The infrared sensor converts the change of infrared thermal radiation energy between the moving human body and the background object received into a corresponding electrical signal, which is sent to the alarm controller after appropriate processing, and an alarm signal is issued.

[0061] Further, the process of obtaining trigger information is described in detail in Figure 2 , Figure 2 is Figure 1 a specific flowchart of an embodiment of step S11. Specifically, it includes the following steps:

[0062] Step S111: In response to the existence of a moving target in the current monitoring environment, the angle data and the moving distance of the moving target are obtained.

[0063] In the embodiment, the angle data is the included angle between the position connecting line of the moving target and the monitoring device in the adjacent two monitoring image frames, and the moving distance is the coordinate difference value of the moving target in the adjacent two monitoring image frames.

[0064] Specifically, the present embodiment can determine whether there is a moving target in the current monitoring environment based on the point cloud data collected by the radar in 1D mode or the electrical signal converted by the change of infrared thermal radiation energy collected by the passive infrared device.

[0065] Further, when the passive infrared device is triggered or the 1D mode of the radar is triggered, that is, when it is judged that there is a moving target in the current monitoring environment, the 2D mode of the radar is further used for detection to view the angle and distance of the target triggering the passive infrared device or the 1D mode of the radar.

[0066] Specifically, the 2D mode of the radar can obtain the angle data and the moving distance of the moving target, wherein the angle data is the included angle between the position connecting line of the moving target and the monitoring device in the adjacent two monitoring image frames, that is, the included angle between the position connecting line of the moving target and the radar in the adjacent two point cloud data frames collected by the radar; and the moving distance is the coordinate difference value of the moving target in the adjacent two monitoring image frames, that is, the coordinate difference value of the moving target in the adjacent two point cloud data frames collected by the radar.

[0067] If the angle and distance change of the moving target has no regularity, it is considered that it is a scene such as snowfall or rainfall, and no trigger information is sent out; if the trajectory of the target is indeed moving and within a certain range, trigger information is sent out. Therefore, the embodiment reduces the generation of trigger information due to changes in environmental factors by identifying the moving trajectory of the moving target, thereby reducing false triggering of the main chip.

[0068] Step S112: in response to the angle data being less than the first threshold value, generating trigger information.

[0069] In the embodiment, the angle data is the angle between the position of the moving target and the position of the monitoring device in the adjacent two monitoring image frames, and the trigger information is generated in response to the angle data being less than the first threshold value. Alternatively, the first threshold value in the embodiment can be a first threshold value data set by the user, which can be set according to the image coordinate system corresponding to the monitoring range.

[0070] Step S113: in response to the moving distance being less than the second threshold value, generating trigger information.

[0071] In the embodiment, the moving distance is the coordinate difference of the moving target in the adjacent two monitoring image frames, and the trigger information is generated in response to the angle data being less than the first threshold value. Alternatively, the second threshold value in the embodiment can be a second threshold value data set by the user, which can be set according to the image coordinate system corresponding to the monitoring range.

[0072] Alternatively, in another embodiment, the trigger monitoring system can also compare the angle data and the moving distance in the first video stream, and determine that the corresponding monitoring target is a moving target only when the angle data is less than the first threshold value and the moving distance is less than the second threshold value.

[0073] The embodiment replaces the conventional moving detection judgment by radar and / or passive infrared devices, does not need to obtain image data, and only needs to judge the moving trajectory of the monitoring object. When it is judged that the monitoring object has a moving trajectory generated by regular movement and the moving trajectory is within a certain range, it is further confirmed that there is a moving object. This can reduce the amount of data to be obtained and compared, save power consumption, and also improve the judgment degree of the monitoring target.

[0074] Step S12: in response to the trigger information, controlling the main chip to switch from the sleep mode to the first mode.

[0075] When the main chip is in the sleep mode, the main chip is used to control the image acquisition module to stop working. Alternatively, when the main chip is in the sleep mode, the main chip that acquires images is in a power-off state. When the main chip is in the first mode, the main chip is used to control the image acquisition module to obtain image frames and obtain image detection results based on the image frames.

[0076] The application also provides another monitoring method for obtaining an image detection result, which can be referred to as Figure 6 , Figure 6 is a flowchart of a third embodiment of the monitoring method of the application. Specifically, the monitoring method of the embodiment of the application can include the following steps:

[0077] Step S21: initializing and setting a deep learning model in response to the working state of the main chip being the first mode.

[0078] In this embodiment, the main chip is built-in with a deep learning model, and the deep learning model is used for image detection. Optionally, the deep learning model in this embodiment is an AI model (artificial intelligence large model), which is a huge computing model integrating a large amount of data and complex algorithms, and realizes deep learning and intelligent analysis of data by simulating the working principle of human brain.

[0079] Step S22: performing image detection on the image frame by using the deep learning model after initialization and setting, to obtain an image detection result.

[0080] In this embodiment, the deep learning model can be initialized and set, that is, the deep learning model is pre-trained by using a preset target image, and the deep learning model after initialization and setting is further used for image detection on the image frame obtained by the image acquisition module. Specifically, the image frame can be obtained by an AI detection module in the image acquisition module.

[0081] Further, the process of performing image detection on the image frame by using the deep learning model after initialization and setting to obtain an image detection result will be described in detail with reference to Figure 7 , Figure 7 is a specific flowchart of step S22 in Figure 6 . Specifically, it includes the following steps:

[0082] Step S221: obtaining image data of a target object.

[0083] In this embodiment, the image data of the target object is a training set of the deep learning model, and the deep learning model can be pre-trained by using the image data of the target object. Specifically, the target object can be a target object preset by a user, and can be a monitoring object that can be photographed by a security camera in the current installation state, and specifically can be an object or a person.

[0084] Step S222: comparing the image frame and the image data of the target object to obtain an image detection result.

[0085] The image detection result of the embodiment includes that the image frame contains the target object or the image frame does not contain the target object, where the target object is a person or object matching the object to be detected.

[0086] Specifically, the deep learning model of the embodiment only performs secondary monitoring on a single frame or two frames of video frames captured by the security camera at a time. Optionally, the two frames of video frames can be adjacent two frames of video frames or any two randomly selected frames of video frames.

[0087] When the number of image frames is two, the comparison of the image data of the image frames and the target object can be performed by comparing the two frames of image frames with the image data of the target object respectively. In response to the presence of the target object in any one of the two frames of image frames, the detection result is determined to be that the image frame contains the target object. In response to the absence of the target object in both of the two frames of image frames, the detection result is determined to be that the image frame does not contain the target object.

[0088] When the main chip is awakened by the trigger information, the embodiment only needs to initialize the data related to the deep learning model in the image acquisition module, reduces the amount of data initialized at a time, can accelerate the secondary monitoring of the trigger information, reduces the false triggering of the main chip, improves the monitoring efficiency by using the deep learning model, and reduces the power consumption.

[0089] Step S13: In response to the image detection result being that the image frame contains the target object, the main chip is controlled to switch from the first mode to the second mode.

[0090] When the main chip is in the second mode, the main chip is used to control the image acquisition module to acquire the monitoring video stream of the target object. When the image detection result is that the image frame contains the target object, it is determined that the target object exists in the current monitoring environment and needs to be monitored by video for a long time.

[0091] Further, the process of acquiring the monitoring video stream of the target object will be described in detail with reference to Figure 3 , Figure 3 is Figure 1 the specific flowchart of an embodiment of step S13. Specifically, the following steps are included:

[0092] Step S131: In response to the image frame containing the target object, the image acquisition module is controlled to acquire the video stream data.

[0093] The deep learning model of the embodiment can be part of the image acquisition module. The image acquisition module can further include a real-time stream and monitoring. The real-time stream module can be used to acquire the real-time data stream of the security camera.

[0094] Since it takes a certain time to determine whether to wake up the main chip, when the main chip is woken up to the external host to complete the start-up, the monitoring object may have moved a distance during this period of time, resulting in the loss of the monitoring video during this period of time, and the monitoring video during this period of time may include important content. Therefore, the monitoring module is used to obtain monitoring video data, and the data collected by the security camera can be processed to obtain video data.

[0095] Step S132: Obtain the monitoring video stream based on the image frame and the video stream data.

[0096] In this embodiment, the video stream data can be real-time data stream obtained based on a real-time stream module, and the monitoring module can obtain the monitoring video stream in combination with the obtained image frame data and the real-time data stream.

[0097] Further, the process of obtaining the monitoring video stream based on the image frame and the video stream data will be described in detail with reference to Figure 4 , Figure 4 is Figure 3 a specific flowchart of step S132 in an embodiment of the present application. Specifically, the method comprises the following steps:

[0098] Step S1321: Change the data format of the image frame, so that the data format of the image frame matches the data format of the video stream data.

[0099] In this embodiment, the data format of the image data collected by the AI detection module of the image acquisition module when the main chip is in the first mode is different from the data format of the image data collected by the real-time stream module of the image acquisition module when the main chip is switched to the second mode, so the monitoring module needs to change the data format of the image data collected by the security camera before the main chip is woken up, so that the data format of the image frame matches the data format of the video stream data.

[0100] Step S1322: Splice the image frame after the data format is changed and the video stream data to obtain the monitoring video stream.

[0101] In this embodiment, the monitoring module splices the image frame after the data format is changed and the video stream data to obtain the monitoring video stream, and the monitoring video stream includes the complete monitoring data of the target object.

[0102] The present application also provides another monitoring method, which will be described in detail with reference to Figure 5 , Figure 5 is a flowchart of a second embodiment of the monitoring method of the present application. Specifically, the monitoring method of the present application can comprise the following steps:

[0103] Step S11: Obtain trigger information.

[0104] Step S12: In response to the trigger information, control the main chip to switch from sleep mode to the first mode.

[0105] In this embodiment, steps S11 and S12 are the same as those described above, and will not be repeated here.

[0106] Step S14: In response to the image detection result indicating that the target object does not exist in the image frame, control the main chip to switch from the first mode to the sleep mode.

[0107] When the image detection result indicates that the target object does not exist in the image frame, it is determined that there is no target object in the current monitoring environment, and long-term video monitoring is not required. In order to reduce power consumption, the microprocessor can control the main chip to switch from the first mode to the sleep mode.

[0108] This application generates trigger information based on the movement data of a moving target. This trigger information can be obtained by the main chip in sleep mode, specifically to determine whether a moving object exists in the monitored screen, thus achieving a preliminary judgment of the monitored screen. Simultaneously, the main chip of this application switches from sleep mode to a first mode based on the trigger information for secondary detection. Specifically, it performs image detection on image frames acquired by the image acquisition module. The main chip switches from the first mode to the second mode for video monitoring only when the image detection result indicates the presence of a target object in the image frame, i.e., it acquires the monitoring video stream of the target object using the image acquisition module. By acquiring dual judgment information, this application enables the video monitoring function when both judgment conditions are met, reducing false triggers. Furthermore, each judgment only activates a portion of the image acquisition module's functions, reducing power consumption.

[0109] Meanwhile, the deep learning model of this application only needs to perform image detection on two image frames, without comparing pixel sets of multiple frames, which can reduce the amount of data processing, improve the accuracy and efficiency of monitoring, and reduce power consumption.

[0110] This application also provides a monitoring device for performing the steps in any of the above-described monitoring method embodiments. Please refer to [link / reference needed]. Figure 8 , Figure 8 This is a structural schematic diagram of the monitoring device of this application. (See attached diagram.) Figure 8 As shown, the monitoring device 30 in this embodiment includes a trigger detection system 31, a microprocessor 32, and a main chip 33.

[0111] Specifically, the trigger detection system 31 is configured to obtain trigger information, wherein the trigger information comprises movement data of a moving target, and the microprocessor 32 is configured to control the main chip 33 to switch from a sleep mode to a first mode in response to the trigger information; when the main chip 33 is in the sleep mode, the main chip 33 is configured to control an image acquisition module in the main chip 33 to stop working, and when the main chip 33 is in the first mode, the main chip 33 is configured to control the image acquisition module to obtain an image frame, the image frame can be obtained by an AI detection module in the image acquisition module, and an image detection result can be obtained based on the image frame. Specifically, the main chip 33 can perform image detection on the image frame by using a built-in deep learning model.

[0112] Further, in response to the image detection result indicating that the target object exists in the image frame, the microprocessor 32 is further configured to control the main chip 33 to switch from the first mode to a second mode; when the main chip 33 is in the second mode, the main chip 33 is configured to control the image acquisition module to obtain a monitoring video stream of the target object. Optionally, the image acquisition module further comprises a real-time stream module and a monitoring module, real-time stream data can be obtained by using the real-time stream module, or the monitoring data obtained by the main chip before and after the mode switching can be spliced by using the monitoring module, so as to realize complete monitoring of the target object.

[0113] The monitoring device 30 of the present application uses a radar and / or a passive infrared device in the trigger detection system 31 to determine whether a moving object exists in a monitoring picture, and further uses a deep learning model initialized by the main chip 33 to realize secondary monitoring, obtain a corresponding target object, reduce the amount of data obtained, improve the monitoring accuracy, reduce the possibility of false triggering, and reduce power consumption. Meanwhile, the mode of the main chip 33 can be switched to obtain corresponding real-time stream data or complete monitoring data of the target object, without losing important image data.

[0114] The present application also provides an electronic device, please refer to Figure 9 , Figure 9 is a schematic diagram of the framework of an embodiment of the electronic device of the present application. The electronic device 40 comprises a memory 41 and a processor 42 coupled to each other, and the processor 42 is configured to execute program instructions stored in the memory 41 to implement the steps in any of the above monitoring method embodiments. In a specific implementation scenario, the electronic device 40 can include but is not limited to a microcomputer, a server, in addition, the electronic device 40 can also include a notebook computer, a tablet computer and other mobile devices, which are not limited here.

[0115] Specifically, the processor 42 is configured to control itself and the memory 41 to implement the steps in any of the above-mentioned monitoring method embodiments. The processor 42 can also be referred to as a CPU (Central Processing Unit). The processor 42 can be an integrated circuit chip having a processing capability of signals. The processor 42 can also be a general processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The general processor can be a microprocessor or the processor can also be any conventional processor or the like. In addition, the processor 42 can be jointly implemented by integrated circuit chips.

[0116] The present application also provides a computer readable storage medium, please refer to Figure 10 , Figure 10 is a schematic diagram of an embodiment of the computer readable storage medium of the present application. The computer readable storage medium 50 stores a computer program 51 capable of being executed by a processor, and the computer program 51 is configured to implement the steps in any of the above-mentioned monitoring method embodiments.

[0117] In some embodiments, the apparatus provided by the embodiments of the present disclosure has functions or includes modules for performing the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For brevity, details are not repeated here.

[0118] The above description of various embodiments tends to emphasize the differences between various embodiments, and the same or similar parts can be mutually referred to. For brevity, details are not repeated here.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed method and device can be implemented in other ways. For example, the above-described device implementation is only schematic; for example, the division of the modules or units is only a logical function division, and there can be another division manner in actual implementation; for example, a unit or component can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0120] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0121] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application, essentially or in part, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various other media that can store program codes.

[0122] The above is only an embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent flow transformation based on the content of the specification and drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A monitoring method, characterized in that, include: Acquire trigger information, wherein the trigger information includes movement data of the moving target; In response to the trigger information, the main chip is controlled to switch from sleep mode to the first mode; wherein, when the main chip is in the sleep mode, the main chip controls the image acquisition module to stop working, and when the main chip is in the first mode, the main chip controls the image acquisition module to acquire image frames and acquire image detection results based on the image frames; In response to the image detection result indicating the presence of a target object in the image frame, the main chip is controlled to switch from the first mode to the second mode; when the main chip is in the second mode, the main chip is used to control the image acquisition module to acquire the monitoring video stream of the target object.

2. The monitoring method according to claim 1, characterized in that, The main chip further includes a deep learning model, and the monitoring method further includes: In response to the main chip's operating state being the first mode, the deep learning model is initialized and configured. The deep learning model, after initialization, is used to perform image detection on the image frame to obtain the image detection result.

3. The monitoring method according to claim 2, characterized in that, The step of using the deep learning model after initialization to perform image detection on the image frame and obtain the image detection result includes: Acquire image data of the target object, wherein the image data of the target object is the training set of the deep learning model; The image frame and the image data of the target object are compared to obtain the image detection result, which indicates that the target object exists in the image frame or that the target object does not exist in the image frame.

4. The monitoring method according to claim 3, characterized in that, The number of image frames is two, and the step of comparing the image frames with the image data of the target object to obtain the image detection result includes: In response to the presence of the target object in either of the two image frames, the detection result is determined to indicate that the target object exists in the image frame. In response to the absence of the target object in both of the image frames, the detection result is determined to be that the target object does not exist in the image frame.

5. The monitoring method according to claim 3, characterized in that, The monitoring method further includes: In response to the image detection result indicating that the target object does not exist in the image frame, the main chip is controlled to switch from the first mode to the sleep mode.

6. The monitoring method according to claim 1, characterized in that, The step of controlling the main chip to switch from the first mode to the second mode in response to the image detection result indicating the presence of a target object in the image frame includes: In response to the presence of the target object in the image frame, the image acquisition module is controlled to acquire video stream data; The monitoring video stream is obtained based on the image frames and the video stream data.

7. The monitoring method according to claim 6, characterized in that, The step of obtaining the monitoring video stream based on the image frames and the video stream data includes: The data format of the image frame is changed to match the data format of the video stream data. The image frames and video stream data after the data format change are spliced ​​together to obtain the monitoring video stream.

8. The monitoring method according to claim 1, characterized in that, The step of obtaining trigger information includes: In response to the presence of the moving target in the current monitoring environment, the angle data and movement distance of the moving target are acquired; wherein the angle data is the angle between the moving target and the line connecting the position of the monitoring device in two adjacent monitoring image frames, and the movement distance is the coordinate difference of the moving target in two adjacent monitoring image frames; The trigger information is generated in response to the angle data being less than a first threshold; Alternatively, the trigger information may be generated in response to the movement distance being less than the second threshold.

9. A monitoring device, characterized in that, include: A trigger detection system is used to acquire trigger information, wherein the trigger information includes movement data of a moving target; The microprocessor and main chip, in response to the trigger information, the microprocessor controls the main chip to switch from sleep mode to a first mode; wherein, when the main chip is in the sleep mode, the main chip controls the image acquisition module to stop working, and when the main chip is in the first mode, the main chip controls the image acquisition module to acquire image frames and acquire image detection results based on the image frames; In response to the image detection result indicating the presence of a target object in the image frame, the microprocessor is further configured to control the main chip to switch from the first mode to the second mode; when the main chip is in the second mode, the main chip is configured to control the image acquisition module to acquire the monitoring video stream of the target object.

10. An electronic device, characterized in that, It includes a memory and a processor coupled to each other, the processor being used to execute program instructions stored in the memory to implement the monitoring method as described in any one of claims 1-8.

Images