IoT battery camera, awakening method and equipment thereof and medium

Abstract

The invention discloses an IoT battery camera and a wake-up method, equipment and medium thereof, and particularly relates to the technical field of cameras, the IoT battery camera is connected with a PIR sensor capable of monitoring temperature change in a target range and sending an interrupt signal, and the IoT battery camera comprises a CIS system used for receiving the interrupt signal and sending the interrupt signal to the CIS system; and entering a low-resolution high-frame-rate mode under the awakening of the interrupt signal so as to simultaneously carry out automatic exposure adjustment and event judgment; awakening a master control SOC and switching a high-resolution low-frame-rate mode based on an event judgment result; and the master control SOC is used for receiving image data acquired by the CIS system in the high-resolution and low-frame-rate mode under the awakening of the CIS system, and processing the image data to output a high-resolution image.

Description

Technical Field

[0001] This invention relates to the field of camera technology, specifically to an IoT battery camera and its wake-up method, device, and medium. Background Technology

[0002] In the application of new smart security battery cameras, smart doorbells, and smart peepholes, low-power IoT design and low-power solutions have become a hot research topic. The current mainstream battery camera wake-up system works primarily by operating only ultra-low-power sensor devices, such as PIR (Passive Infrared) sensors, in the absence of any event trigger. When a temperature change is detected, the CIS (CMOS Image Sensor) and the entire camera system are activated to record and store video.

[0003] See Figure 1 , Figure 1 The diagram illustrates the existing camera wake-up process. An event-triggered PIR sends a trigger interrupt signal to wake up the main control SOC system. The main control SOC system starts up by configuring the CIS and enters a low-resolution high-speed image output mode. The main control SOC receives the low-resolution image data stream and performs rapid automatic exposure (AE AutoExpure). After AE is completed, the SOC configures and switches the CIS to enter a high-resolution image output mode and stores the video stream. In the above technical solution, relying solely on PIR for event detection without image detection, the system frequently triggers false video captures (videos without valid information) in scenarios with drastic temperature changes (such as near air vents or air conditioner outdoor units). This poses a significant challenge to the standby time of IoT low-power battery cameras.

[0004] A Chinese patent, CN113938598A, discloses a method, apparatus, device, and medium for waking up a surveillance camera. The surveillance camera includes a detection sensor and an image sensor. The method includes: when the detection sensor detects an intrusion target in the monitored area, controlling the image sensor to enter a first image acquisition mode; controlling the image sensor in the first image acquisition mode to acquire at least two frames of monitoring images; determining whether the intrusion target is a monitoring target based on the at least two frames of monitoring images; if so, switching the image sensor from the first image acquisition mode to a second image acquisition mode, and controlling the image sensor in the second image acquisition mode to acquire monitoring images containing the monitoring target. This invention improves the wake-up accuracy of the surveillance camera, reduces battery consumption, extends the camera's operating time, and reduces the frequency of battery replacement.

[0005] However, in the above technical solution, the MCU is first woken up by PIR, then the sensor is configured by the MCU, and then the first image acquisition mode is entered. Its AE algorithm and moving body detection function need to be coordinated by the MCU, which leads to frequent interaction between the MCU and the sensor, further increasing the system response time. Summary of the Invention

[0006] The technical problem this invention aims to solve is that existing systems are prone to accidental triggering, leading to reduced camera battery life and high event response latency. The goal is to provide an IoT battery camera and its wake-up method, device, and medium. This design directly wakes up the CIS system via an interrupt signal using a PIR sensor, completely bypassing the MCU wake-up process to reduce critical path latency. Therefore, in scenarios without special requirements, the CIS system can be directly started based on the triggered interrupt signal without additional configuration of CIS parameters via the I²C protocol or reliance on external SOC intervention. It defaults to a low-resolution, high-frame-rate fast image acquisition mode. By integrating automatic exposure and motion event detection within the CIS, and executing them in parallel, processing efficiency is significantly improved. Furthermore, the automatic exposure adjustment and event judgment in this solution are performed simultaneously, utilizing the image during exposure adjustment for event judgment, eliminating the need to wait for the exposure adjustment to complete before judgment, thus shortening the overall time for this period and reducing startup time, effectively preserving the critical image during the initial triggering phase.

[0007] This invention is achieved through the following technical solution:

[0008] An IoT battery camera is provided, wherein the IoT battery camera is connected to a PIR sensor capable of monitoring temperature changes within a target area and emitting an interrupt signal, the IoT battery camera comprising:

[0009] The CIS system is used to receive interrupt signals and enter a low-resolution, high-frame-rate mode when woken up by the interrupt signal, so as to perform automatic exposure adjustment and event determination simultaneously; based on the event determination result, it wakes up the main control SOC and switches to a high-resolution, low-frame-rate mode.

[0010] The main control SOC is used to receive image data acquired by the CIS system in high-resolution, low-frame-rate mode when the CIS system is woken up, and to process the image data to output high-resolution images.

[0011] Furthermore, after the CIS system enters the low-resolution, high-frame-rate mode, it specifically includes:

[0012] Automatic exposure adjustment is performed using a single-frame multiple exposure method, and the pixel array obtained from the automatic exposure adjustment is used for event determination.

[0013] Furthermore, the CIS system divides the obtained pixel array into regions to acquire multiple regions of interest (ROI) images, and detects the number of ROI images containing moving objects to obtain the event determination result.

[0014] Furthermore, when the CIS system determines that the number of frames of the region of interest of the moving object exceeds a preset threshold, it outputs a trigger signal to wake up the main control SOC and switch to high-resolution low frame rate mode; when the CIS system determines that the number of frames of the region of interest of the moving object does not exceed the preset threshold, it is determined to be a false trigger.

[0015] The present invention also provides a wake-up method for an IoT battery camera as described in any one of the above claims, the method comprising:

[0016] The CIS system receives an interrupt signal from the PIR sensor and enters a low-resolution, high-frame-rate mode upon being woken up by the interrupt signal, so as to perform automatic exposure adjustment and event determination simultaneously.

[0017] The main control SOC is woken up based on the event determination result and the high-resolution low frame rate mode is switched. The main control SOC receives the image data acquired by the CIS system in the high-resolution low frame rate mode and processes the image data to output a high-resolution image.

[0018] Furthermore, after the CIS system enters the low-resolution, high-frame-rate mode, it specifically includes:

[0019] Automatic exposure adjustment is performed using a single-frame multiple exposure method, and the pixel array obtained from the automatic exposure adjustment is used for event determination.

[0020] Furthermore, the CIS system divides the obtained pixel array into regions to acquire multiple regions of interest (ROI) images, and detects the number of ROI images containing moving objects to obtain the event determination result.

[0021] The present invention also provides a computer device, including a system memory and a processor, wherein the system memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described above.

[0022] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods described above.

[0023] The present invention also provides a computer program product containing instructions that, when executed by a cluster of computer devices, cause the cluster of computer devices to perform the method described in any of the preceding claims.

[0024] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0025] In this invention, the design of directly waking up the CIS system via an interrupt signal using a PIR sensor completely skips the MCU wake-up process, reducing critical path latency. Therefore, in scenarios without special requirements, the CIS system can be directly started based on the triggered interrupt signal without additional configuration of CIS parameters via the I²C protocol or reliance on an external SOC. It defaults to a low-resolution, high-frame-rate fast image acquisition mode. By integrating automatic exposure and motion event detection within the CIS, and executing them in parallel, processing efficiency is significantly improved. Furthermore, the automatic exposure adjustment and event judgment in this technical solution are performed simultaneously, utilizing the image during exposure adjustment for event judgment, eliminating the need to wait for the exposure adjustment to complete before judgment. This shortens the overall time for this period, thereby reducing startup time and effectively preserving the critical image from the initial triggering stage. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered 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. In the drawings:

[0027] Figure 1 This is a schematic diagram of the existing camera wake-up process;

[0028] Figure 2 This is a schematic diagram of the module connection of an IoT battery camera in this embodiment;

[0029] Figure 3 This is a schematic diagram of the workflow of an IoT battery camera in this embodiment;

[0030] Figure 4 This is a schematic diagram illustrating the implementation of a single-frame quadruple exposure method using Bayer CFA in this embodiment;

[0031] Figure 5 This is a schematic diagram illustrating the implementation of a single-frame quadruple exposure mode using Quad Bayer CFA in this embodiment;

[0032] Figure 6 This is a schematic diagram of the exposure calculation and reaction timing for the quadruple exposure in this embodiment;

[0033] Figure 7 This is a flowchart illustrating a method for waking up an IoT battery camera in this embodiment.

[0034] Figure 8 This is a schematic diagram of the structure of a computer device in this embodiment. Detailed Implementation

[0035] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0036] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0037] The terminology used in the description of the various examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0038] Example 1

[0039] This embodiment employs a faster pixel exposure method and AE adjustment scheme for AE convergence, integrating AE adjustment and event detection into the same time period. This significantly reduces the time from power-on to event detection, minimizes event content loss, and improves the security requirements of security products. The specific technical solution is as follows:

[0040] See Figure 2 , Figure 2 A schematic diagram of the module connection of an IoT battery camera is shown, wherein the IoT battery camera is connected to a PIR sensor capable of monitoring temperature changes within a target range and emitting an interrupt signal. The IoT battery camera includes:

[0041] The CIS system is used to receive interrupt signals and enter a low-resolution, high-frame-rate mode when woken up by the interrupt signal, so as to perform automatic exposure adjustment and event determination simultaneously; based on the event determination result, it wakes up the main control SOC and switches to a high-resolution, low-frame-rate mode.

[0042] The main control SOC is used to receive image data acquired by the CIS system in high-resolution, low-frame-rate mode when the CIS system is woken up, and to process the image data to output high-resolution images.

[0043] For details, see Figure 3 , Figure 3 A schematic diagram of the workflow of an IoT battery camera is shown. In this embodiment, after the PIR sensor detects a temperature change within the monitoring range, it sends an interrupt signal to wake up the CIS system. The CIS system quickly starts up on-chip and performs rapid automatic exposure adjustment and event detection and judgment. When the CIS system determines that there is an event that truly needs to be recorded, it sends an interrupt signal to wake up the entire system equipment to record video. If the CIS system determines that there is no event that truly needs to be recorded within a specified period of time, it determines that there is no need to start the main control SOC system with high power consumption, and at the same time, the main control SOC shuts down unnecessary power-consuming devices, including itself.

[0044] In this embodiment, a technical solution is provided that after the PIR sends an interrupt signal, the CIS is directly woken up to perform secondary event judgment. After the secondary judgment is successful, the CIS sends an interrupt signal to wake up the main control SOC system. At the same time, the time from the CIS system startup to the CIS completing the secondary event judgment and sending the judgment interrupt signal is shortened. More specifically, after the CIS system is powered on, it enters a dedicated high-speed low-resolution mode for high-speed automatic exposure control and event detection. After an event is detected within a specified time, an interrupt signal is immediately sent to notify the SoC system device to start receiving CIS output images and recording video. At the same time, the CIS also switches to a high-resolution large image mode for output images.

[0045] In another implementation, after the CIS system enters the low-resolution, high-frame-rate mode, it specifically includes:

[0046] Automatic exposure adjustment is performed using a single-frame multiple exposure method, and the pixel array obtained from the automatic exposure adjustment is used for event determination.

[0047] It should be noted that in this embodiment, a single-frame quadruple exposure method is used, that is, the AE convergence speed is equivalent to 4 times that of the conventional linear single exposure mode. At the same time, the single-frame quadruple exposure covers a sufficient exposure range, and the appropriate exposure target pixels can be judged for events at the same time, which also greatly advances the start time of event judgment.

[0048] It should also be noted that single-frame quad exposure can be achieved with different exposure controls under different CFA (Color Filter Array) configurations; at any given moment, the exposure parameters of different pixels are different, thus covering different light ranges; the following lists commonly used Bayer CFA array and Quad Bayer CFA array pixel exposure control methods to achieve single-frame quad exposure: See Figures 4-5 As shown, Figure 4 The diagram illustrates a single-frame quadruple exposure method implemented using Bayer CFA. A CIS system with a Bayer CFA structure can utilize the exposure partitions between every two rows. Figure 5 The diagram illustrates a single-frame quadruple exposure method implemented by Quad Bayer CFA. A CIS system with a Quad Bayer CFA structure can use four pixels of the same color in the Quad for zoned exposure.

[0049] Furthermore, this embodiment also provides a scheme for achieving rapid exposure convergence: the exposure adjustment of the CIS system takes effect after at least one frame of delay in image brightness; see [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram illustrating the exposure calculation and response timing for quadruple exposure. The new exposure time is calculated after the first frame of Read data is completed. Figure 6 The shutter corresponding to the second frame's Read data will begin during the first frame (the position calculated by Exposure 2). The new exposure time calculated from the first frame's data cannot be immediately reflected in the second frame's Read data. Instead, the new exposure time calculated from the first frame is reflected in the shutter that begins in the second frame, which is reflected in the image brightness as the third frame's image data.

[0050] Therefore, there is a one-frame delay between the calculation of the new exposure and the change in image brightness in automatic exposure. Thus, the minimum interval for exposure time adjustment is once every two frames. In this technical solution, the number of convergence frames for automatic exposure adjustment directly affects the length of the convergence time. During the single-frame quadruple exposure, this solution only performs fast AE and event trigger judgment, and does not perform synthesis similar to the conventional single-frame multi-exposure HDR mode, nor does it require image output. Therefore, the image quality degradation caused by single-frame multi-exposure itself will not have an adverse effect on this solution. Although this application example only lists the single-frame 4-exposure exposure method, the other exposure methods in a single frame can be understood as the same principle. However, too many exposures in a single frame will introduce problems such as overly complex exposure control and too low sampling rate in a single exposure space. Considering practical engineering applications, this technical solution adopts a method of no more than four exposures in a single frame.

[0051] Based on the above relationship between automatic exposure calculation and reaction time, it can be seen that there is a one-frame delay in the automatic exposure's effect on image brightness, meaning that exposure adjustment occurs every two frames; the exposure value is updated every two frames, meaning that the exposure value of every two frames is consistent. Combining this with the principle of event detection, it is usually necessary to compare the difference between the current frame and the background frame (previous frame data). Under the condition of exposure value updates in pairs, event detection can be performed simultaneously; for example... Figure 6 The process involves updating the background in the first frame, detecting events in the second frame, updating the background in the third frame, and detecting events in the fourth frame. Since event detection primarily involves comparing changes, highly precise exposure timing is not required. The single-frame multi-exposure method can cover a wide exposure range, selecting exposure data closer to the target exposure for event detection and judgment in each instance. Event detection is performed simultaneously with automatic exposure calculation, further reducing the time required from PIR event triggering to secondary event judgment. After the secondary event trigger, it is necessary to switch to high-resolution output mode for video recording. Before switching output mode, the automatic exposure in single-frame multi-exposure mode needs to converge.

[0052] Specifically, in this embodiment, secondary event detection and judgment are performed through the CIS system to reduce unnecessary false triggers and thus reduce the overall power consumption; and the single-frame multiple exposure method embedded in the CIS system reduces the AE convergence time and performs AE and event judgment simultaneously, further compressing the time from time triggering to high-resolution image output.

[0053] In another implementation, the CIS system divides the obtained pixel array into regions to acquire multiple regions of interest (ROI) images, and detects the number of ROI images containing moving objects to obtain an event determination result.

[0054] Specifically, in this embodiment, by monitoring the region of interest (ROI) images divided into M×N regions, if the number of regions where moving objects are detected exceeds a set threshold, it can be determined that an event has occurred, and a trigger signal is output to wake up the main control SOC and switch to high-resolution low frame rate mode; if the CIS system determines that the number of ROI images of moving objects does not exceed the preset number threshold, it is determined to be a false trigger; the preset data threshold is determined according to the actual situation and will not be elaborated on here.

[0055] In this technical solution, the design of directly waking up the CIS system via an interrupt signal using a PIR sensor completely bypasses the MCU wake-up process, reducing critical path latency. Therefore, in scenarios without special requirements, the CIS system can be directly started based on the triggered interrupt signal without additional configuration of CIS parameters via the I²C protocol or reliance on external SOC intervention. It defaults to a low-resolution, high-frame-rate fast image acquisition mode. By integrating automatic exposure and motion event detection within the CIS, and executing them in parallel, processing efficiency is significantly improved. Furthermore, the automatic exposure adjustment and event judgment in this solution are performed simultaneously, utilizing the image during exposure adjustment for event judgment, eliminating the need to wait for the exposure adjustment to complete before judgment. This shortens the overall time for this period, thereby reducing startup time and effectively preserving the critical image from the initial trigger phase.

[0056] Example 2

[0057] See Figure 7 This embodiment also provides a wake-up method for an IoT battery camera as described in Embodiment 1 above, the method comprising:

[0058] S1: The CIS system receives the interrupt signal from the PIR sensor and enters the low-resolution high frame rate mode when woken up by the interrupt signal, so as to perform automatic exposure adjustment and event judgment at the same time.

[0059] S2: Wake up the main control SOC and switch to high-resolution low frame rate mode based on the event determination result; The main control SOC receives image data acquired by the CIS system in high-resolution low frame rate mode and processes the image data to output high-resolution images.

[0060] In another implementation, after the CIS system enters the low-resolution, high-frame-rate mode, it specifically includes:

[0061] Automatic exposure adjustment is performed using a single-frame multiple exposure method, and the pixel array obtained from the automatic exposure adjustment is used for event determination.

[0062] In another implementation, the CIS system divides the obtained pixel array into regions to acquire multiple regions of interest (ROI) images, and detects the number of ROI images containing moving objects to obtain an event determination result.

[0063] It should be noted that the steps in the method of the above embodiment 2 correspond to the various modules in the device of embodiment 1. The working methods of each module have been described in detail in the above embodiment 1. In this embodiment 2, the steps in the method will not be described in detail.

[0064] Example 3

[0065] See Figure 8This embodiment also provides a computer device, including a system memory 1005 and a processor 1001. The system memory 1005 stores a computer program, and the processor 1001 executes the computer program to implement the steps of any of the methods described above.

[0066] It should be noted that the processor 1001 is used to execute the steps in the above method embodiments according to the instructions in the program code. Alternatively, when the processor 1001 executes the computer program, it implements the functions of each module / unit in the above system / device embodiments.

[0067] Specifically, in this embodiment, the computer program can be divided into one or more modules / units. One or more modules / units are stored in the system memory 1005 and executed by the processor 1001 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the terminal device.

[0068] The terminal device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will understand that this does not constitute a limitation on the terminal device, which may include more or fewer components than shown, or a combination of certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, etc.

[0069] The processor 1001 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0070] System memory 1005 can be an internal storage unit of the terminal device, such as a hard drive or RAM. System memory 1005 can also be a storage device 1004 of the terminal device, such as an external hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or FlashCard. Furthermore, system memory 1005 can include both internal storage units and storage device 1004. System memory 1005 is used to store computer programs and other programs and data required by the terminal device. System memory 1005 can also be used to temporarily store data that has been output or will be output.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0072] Example 4

[0073] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0074] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof, or any other form of computer-readable storage medium in the art.

[0075] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside within an application-specific integrated circuit (ASIC). In embodiments of the invention, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device.

[0076] Example 5

[0077] This embodiment also provides a computer program product containing instructions that, when executed by a cluster of computer devices, cause the cluster of computer devices to perform the method described in Embodiment 1.

[0078] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An IoT battery camera, characterized in that, The IoT battery camera is connected to a PIR sensor capable of monitoring temperature changes within a target area and issuing an interrupt signal. The IoT battery camera includes: The CIS system is used to receive interrupt signals and enter a low-resolution, high-frame-rate mode when woken up by the interrupt signal, so as to perform automatic exposure adjustment and event determination simultaneously; based on the event determination result, it wakes up the main control SOC and switches to a high-resolution, low-frame-rate mode. The main control SOC is used to receive image data acquired by the CIS system in high-resolution, low-frame-rate mode when the CIS system is woken up, and to process the image data to output high-resolution images.

2. The IoT battery camera according to claim 1, characterized in that, After the CIS system enters the low-resolution, high-frame-rate mode, the specific steps include: Automatic exposure adjustment is performed using a single-frame multiple exposure method, and the pixel array obtained from the automatic exposure adjustment is used for event determination.

3. An IoT battery camera according to claim 2, characterized in that, The CIS system divides the obtained pixel array into regions, acquires multiple regions of interest (ROI) images, and detects the number of ROI images containing moving objects to obtain event determination results.

4. An IoT battery camera according to claim 3, characterized in that, When the CIS system determines that the number of frames of the region of interest of the moving object exceeds the preset threshold, it outputs a trigger signal to wake up the main control SOC and switch to high resolution low frame rate mode; when the CIS system determines that the number of frames of the region of interest of the moving object does not exceed the preset threshold, it is determined to be a false trigger.

5. A wake-up method for an IoT battery camera according to any one of claims 1-4, characterized in that, The methods include: The CIS system receives an interrupt signal from the PIR sensor and enters a low-resolution, high-frame-rate mode upon being woken up by the interrupt signal, so as to perform automatic exposure adjustment and event determination simultaneously. The main control SOC is woken up based on the event determination result and the high-resolution low frame rate mode is switched. The main control SOC receives the image data acquired by the CIS system in the high-resolution low frame rate mode and processes the image data to output a high-resolution image.

6. The method for waking up an IoT battery camera according to claim 5, characterized in that, After the CIS system enters the low-resolution, high-frame-rate mode, the specific steps include: Automatic exposure adjustment is performed using a single-frame multiple exposure method, and the pixel array obtained from the automatic exposure adjustment is used for event determination.

7. An IoT battery camera according to claim 5, characterized in that, The CIS system divides the obtained pixel array into regions, acquires multiple regions of interest (ROI) images, and detects the number of ROI images containing moving objects to obtain event determination results.

8. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 5 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 5 to 7.

10. A computer program product containing instructions, characterized in that, When the instructions are executed by a cluster of computer devices, the cluster of computer devices causes the cluster of computer devices to perform the method as described in any one of claims 5 to 7.

Images