WO2023222104A1 - 一种设备控制的方法和装置 - Google Patents

一种设备控制的方法和装置 Download PDF

Info

Publication number
WO2023222104A1
WO2023222104A1 PCT/CN2023/095174 CN2023095174W WO2023222104A1 WO 2023222104 A1 WO2023222104 A1 WO 2023222104A1 CN 2023095174 W CN2023095174 W CN 2023095174W WO 2023222104 A1 WO2023222104 A1 WO 2023222104A1
Authority
WO
WIPO (PCT)
Prior art keywords
target object
target
attribute information
detected
run
Prior art date
Application number
PCT/CN2023/095174
Other languages
English (en)
French (fr)
Inventor
李洋
张民英
龙一民
郭伟松
姚顺刚
Original Assignee
阿里云计算有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿里云计算有限公司 filed Critical 阿里云计算有限公司
Publication of WO2023222104A1 publication Critical patent/WO2023222104A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/65Control of camera operation in relation to power supply
    • H04N23/651Control of camera operation in relation to power supply for reducing power consumption by affecting camera operations, e.g. sleep mode, hibernation mode or power off of selective parts of the camera
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/61Control of cameras or camera modules based on recognised objects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/61Control of cameras or camera modules based on recognised objects
    • H04N23/611Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks
    • Y02D30/70Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the present invention relates to the technical field of the Internet of Things, and in particular to a method and device for equipment control.
  • video capture devices such as video capture devices are widely used.
  • it is usually set to enter a low-power consumption mode in the idle state and is configured with a passive detector to wake up the device. , to resume use.
  • the device can wake up after the passive detector is triggered, but the passive detector has more false triggers or triggers that do not meet the user's expectations, which in turn causes the device using the passive detector to wake up falsely, increasing the functionality of the device. consumption and reduce the standby time of the device.
  • a device control method, applied to a target device, where the target device is deployed with a passive detector, the method includes:
  • the target device When the target device is awakened by the passive detector, detect whether there is a target object in the environment;
  • running in a preset low power consumption mode when no target object is detected includes:
  • the target device If the target device is not awakened by the passive detector again within a preset time period, it runs in the second low-power mode; wherein the power consumption in the second low-power mode is less than the first low-power mode. power consumption in consumption mode.
  • the target device closes the specified running task, and in the second low power consumption mode, the target device enters a sleep state.
  • detecting whether there is a target object in the environment includes:
  • Object recognition is performed on the video code stream to detect whether there is a target object in the environment.
  • determining attribute information of the target object includes:
  • the attribute information includes the identity type of the target object, and determining the running time based on the attribute information includes:
  • a second running time is determined; wherein the second running time is longer than the first running time.
  • the target device is a video collection device
  • the passive detector is a passive infrared detector
  • a target object detection module configured to detect whether there is a target object in the environment when the target device is awakened by the passive detector
  • a module for running according to the run time used to determine the attribute information of the target object when the target object is detected, and determine the run time based on the attribute information to run according to the run time;
  • Run the module in low power mode which is used to run in the preset low power mode when the target object is not detected.
  • An electronic device including a processor, a memory, and a computer program stored on the memory and capable of running on the processor.
  • the computer program is executed by the processor, the method for controlling the device as described above is implemented. .
  • a computer-readable storage medium stores a computer program on the computer-readable storage medium.
  • the computer program is executed by a processor, the method for controlling the device as described above is implemented.
  • the target device detects whether there is a target object in the environment when the target device is awakened by the passive detector.
  • the attribute information of the object is determined, and the running time is determined based on the information.
  • run according to the duration and when no target object is detected, run in the preset low-power mode, which realizes operation control after the device wakes up, reduces the power consumption after the device wakes up by mistake, and improves the device's performance. Standby time.
  • Figure 1 is a step flow chart of a device control method provided by an embodiment of the present invention
  • Figure 2 is a step flow chart of another device control method provided by an embodiment of the present invention.
  • Figure 3 is a structural block diagram of an equipment control device provided by an embodiment of the present invention.
  • the target device can be a video collection device, such as a camera (specifically, it can be a camera equipped with a battery).
  • the target device can be deployed with a passive detector.
  • the passive detector can be a passive infrared detector ( PIR, Passive infrared detectors).
  • passive infrared detectors are mainly composed of optical systems, pyroelectric sensors (or infrared sensors) and alarm controllers.
  • the detector itself does not emit any energy but only passively receives and detects infrared radiation from the environment. Once When infrared radiation comes in and is focused by the optical system, the pyroelectric device generates a sudden change in electrical signal and issues an alarm.
  • Step 101 When the target device is awakened by the passive detector, detect whether there is a target object in the environment.
  • the passive detector in the target device After the passive detector in the target device is triggered by an object in the environment, that is, the passive detector issues an alarm and can wake up the target device. Because passive detectors have more false triggers or triggers that do not meet user expectations, such as triggering passive detection If the detector is an animal and the user expects it to be triggered by a person, then the triggering of the passive detector does not meet the user's expectations.
  • the target device in order to ensure that the target device operates on objects of interest, reduce the power consumption of operating on uninterested objects, and extend the standby time of the device, it is possible to further detect whether there is a target object in the environment.
  • the target object can be a human.
  • step 101 may include:
  • Sub-step 11 When the target device is woken up by the passive detector, obtain the video code stream collected after waking up.
  • the target device can collect video through the configured camera. Specifically, the target device can collect video within a specified length of time after waking up, such as video within 5 seconds.
  • Sub-step 12 Perform object recognition on the video stream to detect whether there is a target object in the environment.
  • the target device can perform object recognition on the video code stream, such as identifying animals, people, cars, electric fans, etc. in the video code stream. If the characteristics of the target object are recognized in the video code stream, it is determined that the object has been detected. There is a target object in the environment. For example, if the target object is a human, when humanoid features are recognized in the video code stream, it is detected that there is a person in the environment. If the characteristics of the target object are not recognized in the video code stream, it is determined that there is no human in the environment. The target object exists.
  • the video code stream is sent to the cloud, and the cloud performs object recognition of the video code stream, thereby enabling the application of the embodiments of the present invention without increasing device configuration.
  • Step 102 When the target object is detected, the attribute information of the target object is determined, and the running time is determined based on the attribute information to run according to the running time.
  • the attribute information can be the identity type of the target object.
  • the identity type can be courier, delivery person, cleaner, family member, etc.
  • different running times can be determined based on the attribute information, and then can be controlled. The target device runs according to the run time.
  • the operation of determining the attribute information of the target object can be run on the target device side or on the cloud, and can be set according to the device capabilities.
  • determining the attribute information of the target object may include:
  • Sub-step 21 When the target object is detected, the data related to the target object in the video stream is sent to the cloud, so that the cloud determines the attribute information of the target object.
  • the AI recognition algorithm required to identify the attribute information of the target object is relatively complex, and some target devices do not have the corresponding capabilities
  • the data related to the target object in the video stream can be sent to the cloud, and the AI recognition can be performed by the cloud. Algorithm to determine the attribute information of the target object.
  • Sub-step 22 Receive the attribute information of the target object returned by the cloud.
  • the attribute information of the target object can be returned to the target device, and the target device can then obtain the attribute information of the target object.
  • Sub-step 31 when the identity type of the target object is a specified type, determine the first running time.
  • the specified type that is, the white list
  • the specified type of target object is relatively safe and does not require long-term video collection.
  • the first running time can be determined.
  • the specified type of object can be a family member, etc.
  • the first running time can be 10 seconds.
  • Sub-step 32 when the identity type of the target object is a non-specified type, determine the second running time; wherein the second running time is longer than the first running time.
  • non-specified types of target objects that is, they are not in the whitelist.
  • non-specified types of target objects are relatively safe and require a long time to collect video. You can determine the second running time. If the non-specified type is The object may be a person (stranger) who is at risk other than family members, and the second running time may be longer than the first running time, such as 30 seconds.
  • the target device when the identity type of the target object is a non-specified type, can be set to perform at least two runs, and the sum of the durations of at least the two runs is equal to the second run duration.
  • Step 103 If no target object is detected, run in a preset low power consumption mode.
  • the target device can be controlled to run in a preset low-power mode, such as directly Put the device into sleep state, or enter sleep state after 3 seconds.
  • step 103 may include:
  • Sub-step 41 If the target object is not detected, run in the first low power consumption mode within a preset time period.
  • the first low-power consumption model that is, the silent mode
  • the target device can be controlled to run in the first low-power mode within a preset time period, for example, the preset time period can be 20 seconds.
  • the target device can turn off specified running tasks, such as turning off image signal processing (ISP, Image Signal Processing) and AI recognition running tasks, and only the running program remains in the memory.
  • ISP image signal processing
  • AI recognition running tasks such as turning off image signal processing (ISP, Image Signal Processing) and AI recognition running tasks
  • Sub-step 42 If the target device is not awakened by the passive detector again within the preset time period, run in the second low-power mode; wherein the power consumption in the second low-power mode is less than that in the first low-power mode. power consumption.
  • the target device If the target device is not woken up again by the passive detector within a preset period of time, for further By reducing the power consumption in the first low power consumption mode, the target device can be controlled to run in the second low power consumption mode, and in the second low power consumption mode, the target device can enter a sleep state.
  • the target device can enter the normal operating state and perform steps 101 to 103.
  • the target device detects whether there is a target object in the environment when it is awakened by the passive detector.
  • the target object determines the attribute information of the object and determines the running time based on the information. Run according to the duration, and when no target object is detected, run in the preset low-power mode, which realizes operation control after the device wakes up, reduces the power consumption after the device wakes up by mistake, and improves the standby time of the device. .
  • the target device can be a video capture device, such as a camera (specifically, it can be configured with a battery). camera), the target device can be deployed with a passive detector, for example, the passive detector can be a passive infrared detector.
  • Step 201 When the target device is awakened by the passive detector, obtain the video code stream collected after waking up.
  • the passive detector in the target device After the passive detector in the target device is triggered by an object in the environment, that is, the passive detector issues an alarm and can wake up the target device. Because passive detectors have more false triggers or triggers that do not meet user expectations, such as triggering passive detection If the detector is an animal and the user expects it to be triggered by a person, then the triggering of the passive detector does not meet the user's expectations.
  • the target device can collect video through the configured camera. , specifically, videos within a specified length of time after waking up can be collected, such as videos within 5 seconds.
  • Step 202 Perform object recognition on the video stream to detect whether there is a target object in the environment.
  • the target device can perform object recognition on the video code stream, such as identifying animals, people, cars, electric fans, etc. in the video code stream. If the characteristics of the target object are recognized in the video code stream, it is determined that the object has been detected. There is a target object in the environment. For example, if the target object is a person, the person is recognized in the video stream. If the characteristics of the target object are not recognized in the video stream, it is determined that the target object does not exist in the environment.
  • the video code stream can be sent to the cloud, and the cloud can perform object recognition of the video code stream, which can be achieved without increasing the device configuration.
  • the embodiment of the present invention is applied.
  • Step 203 When the target object is detected, the data related to the target object in the video code stream is sent to the cloud, so that the cloud determines the attribute information of the target object.
  • the attribute information can be the identity type of the target object.
  • the identity type can be courier, delivery person, cleaner, family member, etc.
  • the data related to the target object in the video stream can be sent to the cloud, and the AI recognition can be performed by the cloud.
  • Step 204 Receive the attribute information of the target object returned by the cloud.
  • the attribute information of the target object can be returned to the target device, and the target device can then obtain the attribute information of the target object.
  • Step 205 Determine the running time based on the attribute information to run according to the running time.
  • the target device After obtaining the attribute information, the target device can determine different running times based on the attribute information, and then control the target device to run according to the running time.
  • the attribute information may include the identity type of the target object.
  • the running time is determined, including:
  • the identity type of the target object When the identity type of the target object is a specified type, determine the first running time; when the identity type of the target object is a non-specified type, determine the second running time; wherein, the second running time is longer than the first running time. .
  • the specified type that is, the white list
  • the specified type of target object is relatively safe and does not require long-term video collection.
  • the first running time can be determined.
  • the specified type can be a family member, and the first running time can be determined.
  • the running time can be 10 seconds.
  • the second running time can be determined.
  • the duration can be greater than the first running duration, such as 30 seconds.
  • Step 206 If the target object is not detected, run in the first low power consumption mode within the preset time period, and if the target device is not awakened by the passive detector again within the preset time period, run in the second low power consumption mode. mode operation; wherein the power consumption in the second low power consumption mode is less than the power consumption in the first low power consumption mode.
  • the target device can be controlled to run in a preset low-power mode, such as directly Put the device into sleep state, or enter sleep state after 3 seconds.
  • the first low-power consumption model of the device can be used, that is, the silent mode , when the target object is not detected, the target device can be controlled to run in the first low-power mode within a preset time period, for example, the preset time period can be 20 seconds.
  • the target device can be controlled to run in the second low power consumption mode. mode, the target device can enter sleep state.
  • FIG. 3 a schematic structural diagram of a device control device provided by an embodiment of the present invention is shown.
  • the device can be applied to a target device, and the target device can be deployed with a passive detector.
  • the following modules can be included:
  • the target object detection module 301 can be used to detect whether there is a target object in the environment when the target device is awakened by a passive detector.
  • the run module 302 according to the run time can be used to determine the attribute information of the target object when the target object is detected, and determine the run time based on the attribute information to run according to the run time.
  • the module 303 for running in low power consumption mode may be used to run in a preset low power consumption mode when no target object is detected.
  • running module 303 in low power consumption mode may include:
  • the sub-module running in the first low power consumption mode may be used to run the submodule in the first low power consumption mode within a preset time period when the target object is not detected.
  • Running the sub-module in the second low-power mode can be used to run the sub-module in the second low-power mode if the target device is not awakened by the passive detector again within a preset time period; wherein, the power in the second low-power mode The power consumption is less than the power consumption in the first low power mode.
  • the target device in the first low power consumption mode, the target device can shut down the specified running task, and in the second low power consumption mode, the target device can enter the sleep state.
  • the target object detection module 301 may include:
  • the video stream acquisition sub-module can be used to obtain the video stream collected after waking up when the target device is awakened by a passive detector.
  • the video stream recognition sub-module can be used to perform object recognition on the video stream to detect whether there is a target object in the environment.
  • running the module 302 according to the running time may include:
  • the sending cloud terminal sub-module can be used to send the data related to the target object in the video code stream to the cloud when the target object is detected, so that the cloud can determine the attribute information of the target object.
  • the receiving cloud terminal sub-module can be used to receive the attribute information of the target object returned by the cloud.
  • the attribute information may include the identity type of the target object
  • running the module 302 according to the run time may include:
  • the first runtime determination sub-module may be used to determine the first runtime when the identity type of the target object is a specified type.
  • the second runtime determination submodule can be used when the identity type of the target object is a non-specified class In the case of type, determine the second running duration; wherein the second running duration is greater than the first running duration.
  • the target device may be a video collection device
  • the passive detector may be a passive infrared detector
  • the target device detects whether there is a target object in the environment when the target device is awakened by the passive detector.
  • the attribute information of the object is determined, and the running time is determined based on the information.
  • run according to the duration and when no target object is detected, run in the preset low-power mode, which realizes operation control after the device wakes up, reduces the power consumption after the device wakes up by mistake, and improves the device's performance. Standby time.
  • An embodiment of the present invention also provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor.
  • a computer program stored in the memory and capable of running on the processor.
  • An embodiment of the present invention also provides a computer-readable storage medium.
  • a computer program is stored on the computer-readable storage medium.
  • the above device control method is implemented.
  • the description is relatively simple. For relevant details, please refer to the partial description of the method embodiment.
  • embodiments of the present invention may be provided as methods, devices, or computer program products.
  • embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment that combines software and hardware aspects.
  • embodiments of the invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • Embodiments of the invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It should be understood that this can be implemented by computer program instructions Each process and/or block in the flowchart illustrations and/or block diagrams, and combinations of processes and/or blocks in the flowchart illustrations and/or block diagrams are presented. These computer program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine such that the instructions are executed by the processor of the computer or other programmable data processing terminal device. Means are generated for implementing the functions specified in the process or processes of the flowchart diagrams and/or the block or blocks of the block diagrams.
  • These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing terminal equipment to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the The instruction means implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, so that a series of operating steps are performed on the computer or other programmable terminal equipment to produce computer-implemented processing, thereby causing the computer or other programmable terminal equipment to perform a computer-implemented process.
  • the instructions executed on provide steps for implementing the functions specified in a process or processes of the flow diagrams and/or a block or blocks of the block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Power Sources (AREA)

Abstract

本发明实施例提供了一种设备控制的方法和装置,所述方法包括:在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象;在检测到目标对象的情况下,确定所述目标对象的属性信息,并根据所述属性信息,确定运行时长,以按照所述运行时长运行;在未检测到目标对象的情况下,以预设的低功耗模式运行。通过本发明实施例,实现了在设备唤醒后的运行控制,降低了设备误唤醒后的功耗,提升了设备的待机时长。

Description

一种设备控制的方法和装置
本申请要求于2022年05月20日提交中国专利局、申请号为202210551807.9、申请名称为“一种设备控制的方法和装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本发明涉及物联网技术领域,特别是涉及一种设备控制的方法和装置。
背景技术
随着物联网技术的发展,如视频采集设备被广泛应用,为了降低设备的运行功耗,延长设备待机时长,其通常设置在空闲状态下进入低功耗模式,并配置有被动探测器来唤醒设备,以恢复使用。
具体的,设备可以在被动探测器被触发后唤醒,但被动探测器的存在较多的误触发或不符合用户期望的触发,进而导致应用被动探测器的设备会出现误唤醒,增加设备的功耗,降低设备的待机时长。
发明内容
鉴于上述问题,提出了以便提供克服上述问题或者至少部分地解决上述问题的一种设备控制的方法和装置,包括:
一种设备控制的方法,应用于目标设备,所述目标设备部署有被动式探测器,所述方法包括:
在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象;
在检测到目标对象的情况下,确定所述目标对象的属性信息,并根据所述属性信息,确定运行时长,以按照所述运行时长运行;
在未检测到目标对象的情况下,以预设的低功耗模式运行。
可选地,所述在未检测到目标对象的情况下,以预设的低功耗模式运行,包括:
在未检测到目标对象的情况下,在预设时长内以第一低功耗模式运行;
若所述目标设备在预设时长内未再次被所述被动式探测器唤醒,以第二低功耗模式运行;其中,所述第二低功耗模式下的功耗小于所述第一低功耗模式下的功耗。
可选地,在所述第一低功耗模式下,所述目标设备关闭指定的运行任务,在所述第二低功耗模式下,所述目标设备进入休眠状态。
可选地,所述在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象,包括:
在所述目标设备被所述被动式探测器唤醒时,获取在唤醒后采集的视频码流;
对所述视频码流进行对象识别,以检测环境中是否存在目标对象。
可选地,所述在检测到目标对象的情况下,确定所述目标对象的属性信息,包括:
在检测到目标对象的情况下,将所述视频码流中与所述目标对象相关的数据发送至云端,以由所述云端确定所述目标对象的属性信息;
接收所述云端返回的所述目标对象的属性信息。
可选地,所述属性信息包括目标对象的身份类型,所述根据所述属性信息,确定运行时长,包括:
在所述目标对象的身份类型为指定类型的情况下,确定第一运行时长;
在所述目标对象的身份类型为非指定类型的情况下,确定第二运行时长;其中,所述第二运行时长大于所述第一运行时长。
可选地,所述目标设备为视频采集设备,所述被动式探测器为被动红外探测器。
一种设备控制的装置,应用于目标设备,所述目标设备部署有被动式探测器,所述装置包括:
目标对象检测模块,用于在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象;
按运行时长运行模块,用于在检测到目标对象的情况下,确定所述目标对象的属性信息,并根据所述属性信息,确定运行时长,以按照所述运行时长运行;
以低功耗模式运行模块,用于在未检测到目标对象的情况下,以预设的低功耗模式运行。
一种电子设备,包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序,所述计算机程序被所述处理器执行时实现如上所述的设备控制的方法。
一种计算机可读存储介质,所述计算机可读存储介质上存储计算机程序,所述计算机程序被处理器执行时实现如上所述的设备控制的方法。
本发明实施例具有以下优点:
在本发明实施例中,目标设备通过在目标设备被被动式探测器唤醒时,检测环境中是否存在目标对象,在检测到目标对象的情况下,确定对象的属性信息,并根据信息,确定运行时长,以按照时长运行,在未检测到目标对象的情况下,以预设的低功耗模式运行,实现了在设备唤醒后的运行控制,降低了设备误唤醒后的功耗,提升了设备的待机时长。
附图说明
为了更清楚地说明本发明的技术方案,下面将对本发明的描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是本发明一实施例提供的一种设备控制的方法的步骤流程图;
图2是本发明一实施例提供的另一种设备控制的方法的步骤流程图;
图3是本发明一实施例提供的一种设备控制的装置的结构框图。
具体实施方式
为使本发明的上述目的、特征和优点能够更加明显易懂,下面结合附图和具体实施方式对本发明作进一步详细的说明。显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
参照图1,示出了本发明一实施例提供的一种设备控制的方法的步骤流程 图,该方法可以应用于目标设备,目标设备可以为视频采集设备,如摄像头(具体可以为配置电池的摄像头),目标设备可以部署有被动式探测器,如被动式探测器可以为被动红外探测器(PIR,Passive infrared detectors)。
其中,被动式红外探测器主要由光学系统、热释电传感器(或称为红外传感器)及报警控制器等部分组成,探测器本身不发射任何能量而只被动接收、探测来自环境的红外辐射,一旦有红外线辐射进来,经光学系统聚焦就使热释电器件产生突变电信号,而发出警报。
具体的,可以包括如下步骤:
步骤101,在目标设备被被动式探测器唤醒时,检测环境中是否存在目标对象。
在目标设备中被动式探测器被环境中的对象触发后,即被动式探测器发出警报,则可以唤醒目标设备,由于被动式探测器存在较多的误触发或不符合用户期望的触发,如触发被动式探测器的是动物,而用户期望的触发时人,则被动式探测器的触发不符合用户期望。
基于此,为了保证目标设备针对感兴趣对象进行作业,减少对不感兴趣对象进行作业的功耗,延长设备待机时长,可以进一步检测环境中是否存在目标对象,如目标对象可以为人。
在本发明一实施例中,步骤101,可以包括:
子步骤11,在目标设备被被动式探测器唤醒时,获取在唤醒后采集的视频码流。
在目标设备被被动式探测器唤醒时,目标设备可以通过配置的摄像头进行视频采集,具体可以采集在唤醒后的指定时长内的视频,如5秒内的视频。
子步骤12,对视频码流进行对象识别,以检测环境中是否存在目标对象。
在获得视频码流后,可以由目标设备对视频码流进行对象识别,如识别视频码流中动物、人、车、电扇等,若在视频码流中识别到目标对象的特征,判定检测到环境中存在目标对象,如目标对象为人,在视频码流中识别到人形特征时,即检测到环境中存在人,若在视频码流中未识别到目标对象的特征,判定检测到环境中不存在目标对象。
当然,对于部分简易的设备,其无法执行对视频码流的对象识别,则可 以将视频码流发送至云端,由云端来执行视频码流的对象识别,进而可以实现在不增加设备配置的情况下,应用本发明实施例。
步骤102,在检测到目标对象的情况下,确定目标对象的属性信息,并根据属性信息,确定运行时长,以按照运行时长运行。
在检测到目标对象的情况下,即表征被动式探测器不是被误触发,且其触发符合用户期望,则为了实现对不同类型的目标对象进行不同时长的作业,进一步降低设备的功耗,可以进一步确定目标对象的属性信息,如属性信息可以为目标对象的身份类型,如身份类型可以为快递员、外卖员、保洁、家庭成员等,进而可以根据属性信息来确定不同的运行时长,进而可以控制目标设备按照运行时长运行。
需要说明的是,确定目标对象的属性信息的操作可以由目标设备侧运行,也可以由云端来运行,可以根据设备能力进行设置。
在本发明一实施例中,在检测到目标对象的情况下,确定目标对象的属性信息,可以包括:
子步骤21,在检测到目标对象的情况下,将视频码流中与目标对象相关的数据发送至云端,以由云端确定目标对象的属性信息。
由于对目标对象的属性信息的识别需要的AI识别算法较为复杂,部分目标设备不具备相应的能力,则可以将视频码流中与目标对象相关的数据发送至云端,进而可以由云端执行AI识别算法来确定目标对象的属性信息。
子步骤22,接收云端返回的目标对象的属性信息。
在云端识别目标对象的属性信息后,可以将目标对象的属性信息返回至目标设备,目标设备进而可以获得目标对象的属性信息。
在本发明实施例中,通过由目标设备侧执行对目标设备的检测,由云端执行对目标对象的属性信息的识别,实现了云端和设备的协同计算。
在本发明一实施例中,属性信息可以包括目标对象的身份类型,根据属性信息,确定运行时长,可以包括:
子步骤31,在目标对象的身份类型为指定类型的情况下,确定第一运行时长。
在具体实现中,可以预先设置指定类型,即白名单,对于视频采集设备, 指定类型的目标对象相对而言较为安全,不需要长时间进行视频采集,则在目标对象的身份类型为指定类型的情况下,可以确定第一运行时长,如指定类型的对象可以为家庭成员等不存在风险的人员,第一运行时长可以为10秒。
子步骤32,在目标对象的身份类型为非指定类型的情况下,确定第二运行时长;其中,第二运行时长大于第一运行时长。
对于非指定类型的目标对象,即不在白名单中,对于视频采集设备,非指定类型的目标对象相对而言较为安全,需要长时间进行视频采集,则可以确定第二运行时长,如非指定类型的对象可以为对于非家庭成员之外的存在风险的人员(陌生人),该第二运行时长可以大于第一运行时长,如30秒。
在一示例中,在目标对象的身份类型为非指定类型的情况下,可以设置目标设备进行至少两次运行,至少两次运行的时长之和等于第二运行时长。
步骤103,在未检测到目标对象的情况下,以预设的低功耗模式运行。
在未检测到目标对象的情况下,即表征被动式探测器是被误触发或者触发不符合用户期望,则为了降低设备的功耗,可以控制目标设备以预设的低功耗模式运行,如直接将设备进行休眠状态,又如在3秒后进入休眠状态。
在本发明一实施例中,步骤103,可以包括:
子步骤41,在未检测到目标对象的情况下,在预设时长内以第一低功耗模式运行。
由于设备从休眠状态切换到正常运行状态也需要一定的功耗,为了避免设备在休眠状态和正常运行状态之间进行频繁的切换,则可以设备第一低功耗模型,即静默模式,在未检测到目标对象的情况下,可以先控制目标设备在预设时长内以第一低功耗模式运行,如预设时长可以为20秒。
在第一低功耗模式下,目标设备可以关闭指定的运行任务,如关闭图像信号处理(ISP,Image Signal Processing)、AI识别的运行任务,仅运行程序维持在内存中。
子步骤42,若目标设备在预设时长内未再次被被动式探测器唤醒,以第二低功耗模式运行;其中,第二低功耗模式下的功耗小于第一低功耗模式下的功耗。
如果目标设备在预设时长内未再次被被动式探测器唤醒,则为了进一步 降低在第一低功耗模式下功耗,可以控制目标设备以第二低功耗模式运行,在第二低功耗模式下,目标设备可以进入休眠状态。
当然,如果目标设备在预设时长内再次被被动式探测器唤醒,则可以进行正常运行状态,执行步骤101-步骤103。
在本发明实施例中,目标设备通过在被被动式探测器唤醒时,检测环境中是否存在目标对象,在检测到目标对象的情况下,确定对象的属性信息,并根据信息,确定运行时长,以按照时长运行,在未检测到目标对象的情况下,以预设的低功耗模式运行,实现了在设备唤醒后的运行控制,降低了设备误唤醒后的功耗,提升了设备的待机时长。
参照图2,示出了本发明一实施例提供的另一种设备控制的方法的步骤流程图,该方法可以应用于目标设备,目标设备可以为视频采集设备,如摄像头(具体可以为配置电池的摄像头),目标设备可以部署有被动式探测器,如被动式探测器可以为被动红外探测器。
具体的,可以包括如下步骤:
步骤201,在目标设备被被动式探测器唤醒时,获取在唤醒后采集的视频码流。
在目标设备中被动式探测器被环境中的对象触发后,即被动式探测器发出警报,则可以唤醒目标设备,由于被动式探测器存在较多的误触发或不符合用户期望的触发,如触发被动式探测器的是动物,而用户期望的触发时人,则被动式探测器的触发不符合用户期望。
基于此,为了保证目标设备针对感兴趣对象进行作业,减少对不感兴趣对象进行作业的功耗,延长设备待机时长,在目标设备被被动式探测器唤醒时,目标设备可以通过配置的摄像头进行视频采集,具体可以采集在唤醒后的指定时长内的视频,如5秒内的视频。
步骤202,对视频码流进行对象识别,以检测环境中是否存在目标对象。
在获得视频码流后,可以由目标设备对视频码流进行对象识别,如识别视频码流中动物、人、车、电扇等,若在视频码流中识别到目标对象的特征,判定检测到环境中存在目标对象,如目标对象为人,在视频码流中识别到人 形特征时,即检测到环境中存在人,若在视频码流中未识别到目标对象的特征,判定检测到环境中不存在目标对象。
当然,对于部分简易的设备,其无法执行对视频码流的对象识别,则可以将视频码流发送至云端,由云端来执行视频码流的对象识别,进而可以实现在不增加设备配置的情况下,应用本发明实施例。
步骤203,在检测到目标对象的情况下,将视频码流中与目标对象相关的数据发送至云端,以由云端确定目标对象的属性信息。
在检测到目标对象的情况下,即表征被动式探测器不是被误触发,且其触发符合用户期望,则为了实现对不同类型的目标对象进行不同时长的作业,进一步降低设备的功耗,可以进一步确定目标对象的属性信息,如属性信息可以为目标对象的身份类型,如身份类型可以为快递员、外卖员、保洁、家庭成员等。
由于对目标对象的属性信息的识别需要的AI识别算法较为复杂,部分目标设备不具备相应的能力,则可以将视频码流中与目标对象相关的数据发送至云端,进而可以由云端执行AI识别算法来确定目标对象的属性信息
步骤204,接收云端返回的目标对象的属性信息。
在云端识别目标对象的属性信息后,可以将目标对象的属性信息返回至目标设备,目标设备进而可以获得目标对象的属性信息。
在本发明实施例中,通过由目标设备侧执行对目标设备的检测,由云端执行对目标对象的属性信息的识别,实现了云端和设备的协同计算。
步骤205,根据属性信息,确定运行时长,以按照运行时长运行。
在获得属性信息后,目标设备可以根据属性信息来确定不同的运行时长,进而可以控制目标设备按照运行时长运行。
在本发明一实施例中,属性信息可以包括目标对象的身份类型,根据属性信息,确定运行时长,包括:
在目标对象的身份类型为指定类型的情况下,确定第一运行时长;在目标对象的身份类型为非指定类型的情况下,确定第二运行时长;其中,第二运行时长大于第一运行时长。
在具体实现中,可以预先设置指定类型,即白名单,对于视频采集设备, 指定类型的目标对象相对而言较为安全,不需要长时间进行视频采集,则在目标对象的身份类型为指定类型的情况下,可以确定第一运行时长,如指定类型可以为家庭成员,第一运行时长可以为10秒。
对于非指定类型的目标对象,即不在白名单中,对于视频采集设备,非指定类型的目标对象相对而言较为安全,需要长时间进行视频采集,则可以确定第二运行时长,该第二运行时长可以大于第一运行时长,如30秒。
步骤206,在未检测到目标对象的情况下,在预设时长内以第一低功耗模式运行,且若目标设备在预设时长内未再次被被动式探测器唤醒,以第二低功耗模式运行;其中,第二低功耗模式下的功耗小于第一低功耗模式下的功耗。
在未检测到目标对象的情况下,即表征被动式探测器是被误触发或者触发不符合用户期望,则为了降低设备的功耗,可以控制目标设备以预设的低功耗模式运行,如直接将设备进行休眠状态,又如在3秒后进入休眠状态。
具体的,由于设备从休眠状态切换到正常运行状态也需要一定的功耗,为了避免设备在休眠状态和正常运行状态之间进行频繁的切换,则可以设备第一低功耗模型,即静默模式,在未检测到目标对象的情况下,可以先控制目标设备在预设时长内以第一低功耗模式运行,如预设时长可以为20秒。
如果目标设备在预设时长内未再次被被动式探测器唤醒,则为了进一步降低在第一低功耗模式下功耗,可以控制目标设备以第二低功耗模式运行,在第二低功耗模式下,目标设备可以进入休眠状态。
需要说明的是,对于方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明实施例并不受所描述的动作顺序的限制,因为依据本发明实施例,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作并不一定是本发明实施例所必须的。
参照图3,示出了本发明一实施例提供的一种设备控制的装置的结构示意图,该装置可以应用于目标设备,目标设备可以部署有被动式探测器,具体 可以包括如下模块:
目标对象检测模块301,可以用于在目标设备被被动式探测器唤醒时,检测环境中是否存在目标对象。
按运行时长运行模块302,可以用于在检测到目标对象的情况下,确定目标对象的属性信息,并根据属性信息,确定运行时长,以按照运行时长运行。
以低功耗模式运行模块303,可以用于在未检测到目标对象的情况下,以预设的低功耗模式运行。
在本发明一实施例中,以低功耗模式运行模块303,可以包括:
以第一低功耗模式运行子模块,可以用于在未检测到目标对象的情况下,在预设时长内以第一低功耗模式运行。
以第二低功耗模式运行子模块,可以用于若目标设备在预设时长内未再次被被动式探测器唤醒,以第二低功耗模式运行;其中,第二低功耗模式下的功耗小于第一低功耗模式下的功耗。
在本发明一实施例中,在第一低功耗模式下,目标设备可以关闭指定的运行任务,在第二低功耗模式下,目标设备可以进入休眠状态。
在本发明一实施例中,目标对象检测模块301,可以包括:
视频码流获取子模块,可以用于在目标设备被被动式探测器唤醒时,获取在唤醒后采集的视频码流。
视频码流识别子模块,可以用于对视频码流进行对象识别,以检测环境中是否存在目标对象。
在本发明一实施例中,按运行时长运行模块302,可以包括:
发送云端子模块,可以用于在检测到目标对象的情况下,将视频码流中与目标对象相关的数据发送至云端,以由云端确定目标对象的属性信息。
接收云端子模块,可以用于接收云端返回的目标对象的属性信息。
在本发明一实施例中,属性信息可以包括目标对象的身份类型,按运行时长运行模块302,可以包括:
第一运行时长确定子模块,可以用于在目标对象的身份类型为指定类型的情况下,确定第一运行时长。
第二运行时长确定子模块,可以用于在目标对象的身份类型为非指定类 型的情况下,确定第二运行时长;其中,第二运行时长大于第一运行时长。
在本发明一实施例中,目标设备可以为视频采集设备,被动式探测器可以为被动红外探测器。
在本发明实施例中,目标设备通过在目标设备被被动式探测器唤醒时,检测环境中是否存在目标对象,在检测到目标对象的情况下,确定对象的属性信息,并根据信息,确定运行时长,以按照时长运行,在未检测到目标对象的情况下,以预设的低功耗模式运行,实现了在设备唤醒后的运行控制,降低了设备误唤醒后的功耗,提升了设备的待机时长。
本发明一实施例还提供了一种电子设备,可以包括处理器、存储器及存储在存储器上并能够在处理器上运行的计算机程序,计算机程序被处理器执行时实现如上设备控制的方法。
本发明一实施例还提供了一种计算机可读存储介质,计算机可读存储介质上存储计算机程序,计算机程序被处理器执行时实现如上设备控制的方法。
对于装置实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
本说明书中的各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似的部分互相参见即可。
本领域内的技术人员应明白,本发明实施例可提供为方法、装置、或计算机程序产品。因此,本发明实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本发明实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明实施例是参照根据本发明实施例的方法、终端设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实 现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上,使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明实施例的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例做出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本发明实施例范围的所有变更和修改。
最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。
以上对所提供的一种设备控制的方法和装置,进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种设备控制的方法,其特征在于,应用于目标设备,所述目标设备部署有被动式探测器,所述方法包括:
    在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象;
    在检测到目标对象的情况下,确定所述目标对象的属性信息,并根据所述属性信息,确定运行时长,以按照所述运行时长运行;
    在未检测到目标对象的情况下,以预设的低功耗模式运行。
  2. 根据权利要求1所述的方法,其特征在于,所述在未检测到目标对象的情况下,以预设的低功耗模式运行,包括:
    在未检测到目标对象的情况下,在预设时长内以第一低功耗模式运行;
    若所述目标设备在预设时长内未再次被所述被动式探测器唤醒,以第二低功耗模式运行;其中,所述第二低功耗模式下的功耗小于所述第一低功耗模式下的功耗。
  3. 根据权利要求2所述的方法,其特征在于,在所述第一低功耗模式下,所述目标设备关闭指定的运行任务,在所述第二低功耗模式下,所述目标设备进入休眠状态。
  4. 根据权利要求1-3任一项所述的方法,其特征在于,所述在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象,包括:
    在所述目标设备被所述被动式探测器唤醒时,获取在唤醒后采集的视频码流;
    对所述视频码流进行对象识别,以检测环境中是否存在目标对象。
  5. 根据权利要求4所述的方法,其特征在于,所述在检测到目标对象的情况下,确定所述目标对象的属性信息,包括:
    在检测到目标对象的情况下,将所述视频码流中与所述目标对象相关的数据发送至云端,以由所述云端确定所述目标对象的属性信息;
    接收所述云端返回的所述目标对象的属性信息。
  6. 根据权利要求1所述的方法,其特征在于,所述属性信息包括目标对象的身份类型,所述根据所述属性信息,确定运行时长,包括:
    在所述目标对象的身份类型为指定类型的情况下,确定第一运行时长;
    在所述目标对象的身份类型为非指定类型的情况下,确定第二运行时长;其中,所述第二运行时长大于所述第一运行时长。
  7. 根据权利要求1所述的方法,其特征在于,所述目标设备为视频采集设备,所述被动式探测器为被动红外探测器。
  8. 一种设备控制的装置,其特征在于,应用于目标设备,所述目标设备部署有被动式探测器,所述装置包括:
    目标对象检测模块,用于在所述目标设备被所述被动式探测器唤醒时,检测环境中是否存在目标对象;
    按运行时长运行模块,用于在检测到目标对象的情况下,确定所述目标对象的属性信息,并根据所述属性信息,确定运行时长,以按照所述运行时长运行;
    以低功耗模式运行模块,用于在未检测到目标对象的情况下,以预设的低功耗模式运行。
  9. 一种电子设备,其特征在于,包括处理器、存储器及存储在所述存储器上并能够在所述处理器上运行的计算机程序,所述计算机程序被所述处理器执行时实现如权利要求1至7中任一项所述的设备控制的方法。
  10. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储计算机程序,所述计算机程序被处理器执行时实现如权利要求1至7中任一项所述的设备控制的方法。
PCT/CN2023/095174 2022-05-20 2023-05-19 一种设备控制的方法和装置 WO2023222104A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210551807.9A CN114979478A (zh) 2022-05-20 2022-05-20 一种设备控制的方法和装置
CN202210551807.9 2022-05-20

Publications (1)

Publication Number Publication Date
WO2023222104A1 true WO2023222104A1 (zh) 2023-11-23

Family

ID=82985147

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/095174 WO2023222104A1 (zh) 2022-05-20 2023-05-19 一种设备控制的方法和装置

Country Status (2)

Country Link
CN (1) CN114979478A (zh)
WO (1) WO2023222104A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114979478A (zh) * 2022-05-20 2022-08-30 阿里云计算有限公司 一种设备控制的方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110103643A1 (en) * 2009-11-02 2011-05-05 Kenneth Edward Salsman Imaging system with integrated image preprocessing capabilities
CN104811595A (zh) * 2015-04-08 2015-07-29 合肥君正科技有限公司 一种网络监控摄像机及其工作方法
CN108200329A (zh) * 2017-12-05 2018-06-22 湖南海翼电子商务股份有限公司 摄像装置及其检测启动方法
CN111679861A (zh) * 2020-05-09 2020-09-18 浙江大华技术股份有限公司 电子设备的唤醒装置、方法和计算机设备和存储介质
CN114979478A (zh) * 2022-05-20 2022-08-30 阿里云计算有限公司 一种设备控制的方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110103643A1 (en) * 2009-11-02 2011-05-05 Kenneth Edward Salsman Imaging system with integrated image preprocessing capabilities
CN104811595A (zh) * 2015-04-08 2015-07-29 合肥君正科技有限公司 一种网络监控摄像机及其工作方法
CN108200329A (zh) * 2017-12-05 2018-06-22 湖南海翼电子商务股份有限公司 摄像装置及其检测启动方法
CN111679861A (zh) * 2020-05-09 2020-09-18 浙江大华技术股份有限公司 电子设备的唤醒装置、方法和计算机设备和存储介质
CN114979478A (zh) * 2022-05-20 2022-08-30 阿里云计算有限公司 一种设备控制的方法和装置

Also Published As

Publication number Publication date
CN114979478A (zh) 2022-08-30

Similar Documents

Publication Publication Date Title
US10923905B2 (en) Intelligent control method and system
TWI714989B (zh) 智慧型裝置的持續喚醒方法、裝置、智慧型裝置和儲存媒體
US9386281B2 (en) Image surveillance and reporting technology
WO2023222104A1 (zh) 一种设备控制的方法和装置
CN109951363B (zh) 数据处理方法、装置及系统
US20140075230A1 (en) Waking An Electronic Device
US10991372B2 (en) Method and apparatus for activating device in response to detecting change in user head feature, and computer readable storage medium
CN109032345B (zh) 设备控制方法、装置、设备、服务端和存储介质
CN112634894B (zh) 一种唤醒方法、装置及终端
WO2019051813A1 (zh) 一种目标识别方法、装置和智能终端
US20190346929A1 (en) Attention Levels in a Gesture Control System
CN112908321A (zh) 设备控制方法、装置、存储介质及电子装置
CN110136716B (zh) 一种语音交互处理方法及语音交互设备
WO2024114612A1 (zh) 智能设备的录像方法及装置、电子设备和存储介质
WO2023015152A1 (en) Systems and methods for on-device person recognition and provision of intelligent alerts
CN111325877B (zh) 电子设备的控制方法、装置及电子设备
WO2018023515A1 (zh) 一种手势及情感识别家居控制系统
CN113361469A (zh) 一种覆盖状态识别方法、装置、设备及存储介质
US11032762B1 (en) Saving power by spoofing a device
CN115019798A (zh) 语音识别设备的控制方法、装置、电子设备及存储介质
CN112269322A (zh) 智能设备的唤醒方法、装置、电子设备及介质
JP2023524953A (ja) モノのインターネットに基づく動作関連付け方法、電子デバイス及び記憶媒体
CN112053530A (zh) 居住环境安全监测方法、装置及电子设备
CN112866807B (zh) 智能关机方法、装置及电子装置
CN115242975A (zh) 一种监控方法、装置、监控设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23807053

Country of ref document: EP

Kind code of ref document: A1