CN114785954A - Processor wake-up method, device, system, storage medium and AR glasses - Google Patents
Processor wake-up method, device, system, storage medium and AR glasses Download PDFInfo
- Publication number
- CN114785954A CN114785954A CN202210459577.3A CN202210459577A CN114785954A CN 114785954 A CN114785954 A CN 114785954A CN 202210459577 A CN202210459577 A CN 202210459577A CN 114785954 A CN114785954 A CN 114785954A
- Authority
- CN
- China
- Prior art keywords
- processor
- image data
- wake
- image
- control module
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000011521 glass Substances 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000004891 communication Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 18
- 238000003062 neural network model Methods 0.000 claims description 4
- 230000002618 waking effect Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 238000001514 detection method Methods 0.000 description 6
- 238000005265 energy consumption Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/65—Control of camera operation in relation to power supply
- H04N23/651—Control 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
Abstract
The embodiment of the invention discloses a processor awakening method, a processor awakening device, a processor awakening system, a storage medium and AR glasses, relates to the technical field of AR, and aims to solve the problem that a processor in the prior art is large in power consumption when continuously processing data. The method mainly comprises the following steps: acquiring first image data acquired by a camera shooting assembly at a low frequency; carrying out image recognition processing on the first image data to obtain an image recognition result; and if the image recognition result comprises a target recognition object, sending a wake-up signal to a processor in a standby state so as to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency.
Description
Technical Field
The present invention relates to the field of AR technologies, and in particular, to a processor wake-up method, apparatus, system, storage medium, and AR glasses.
Background
With the rapid development of Augmented Reality (AR) technology, AR devices have been gradually applied to various industries, and particularly, specific behaviors may be recognized by the AR devices to perform corresponding AR operations. The AR equipment comprises an AR equipment body, a processor and a camera shooting assembly, wherein the camera shooting assembly of the AR equipment collects video data, then the video data are transmitted to the processor serving as a main control end to conduct behavior recognition, and corresponding AR operation is executed after the behavior recognition is completed.
At present, in the process of collecting video data, whether the video data containing specific behaviors are collected or not, a processor serving as a main control end can perform data operation in real time and can enter an invalid identification or invalid data processing state. However, the invalid video data identification increases the system load stress of the processor and also generates a large amount of power consumption, thereby affecting the endurance time of the processor.
Disclosure of Invention
In view of this, the present invention provides a processor wake-up method, an apparatus, a system, a storage medium, and AR glasses, which are used to solve the problem in the prior art that a processor continuously performs data processing and has large power consumption.
To achieve one or a part of or all of the above or other objects, the present invention provides a processor wake-up method, including:
acquiring first image data acquired by a camera shooting assembly at a low frequency;
carrying out image recognition processing on the first image data to obtain an image recognition result;
and if the image recognition result comprises a target recognition object, sending a wake-up signal to a processor in a standby state so as to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency.
Preferably, the performing image recognition processing on the image data to obtain an image recognition result includes:
and performing image recognition processing on the first image data based on an image recognition model which is trained based on an image training sample set containing a pre-configured target recognition object, so as to obtain an image recognition result, wherein the target recognition object is a target object for waking up the processor.
Preferably, before the acquiring the first image data acquired by the camera assembly at low frequency, the method further includes:
detecting whether the processor is in a standby state;
if the processor is not in the standby state, sending a standby instruction to the processor to indicate the processor to enter the standby state;
the acquiring of the first image data acquired by the camera shooting assembly at low frequency comprises:
and if the processor is in a standby state, starting the camera shooting assembly to acquire first image data according to a preset low-frequency.
Preferably, the method further comprises:
establishing a data communication connection with the processor based on a wake-up interface;
the sending of the wake-up signal to the processor in the standby state includes:
sending a wake-up signal to the processor in a standby state based on the wake-up interface;
the sending a standby instruction to the processor comprises:
sending a standby instruction to the processor in an unsStandby state based on the wake-up interface.
Preferably, after sending the wake-up signal to the processor in the standby state, the method further comprises:
and if the processor is detected to enter the standby state again, starting the camera shooting assembly to acquire first image data according to a preset low-frequency.
Preferably, after the image recognition processing is performed on the first image data to obtain an image recognition result, the method further includes:
and if the image recognition result does not comprise the target recognition object, re-executing the step of acquiring the first image data acquired by the camera shooting assembly at the low frequency so as to re-perform image recognition processing on the first image data.
To achieve one or a part of or all of the above objects or other objects, there is provided a processor wake-up apparatus, comprising:
the acquisition module is used for acquiring first image data acquired by the camera shooting assembly at a low frequency;
the processing module is used for carrying out image recognition processing on the first image data to obtain an image recognition result;
and the sending module is used for sending a wake-up signal to a processor in a standby state if the image recognition result comprises a target recognition object so as to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency.
Preferably, the processing module is specifically configured to perform image recognition processing on the first image data based on an image recognition model that has been model trained, so as to obtain an image recognition result, where the image recognition model is obtained by training based on an image training sample set that includes a preconfigured target recognition object, and the target recognition object is a target object for waking up the processor.
Preferably, the apparatus further comprises: a detection module for detecting the position of the optical fiber,
the detection module is used for detecting whether the processor is in a standby state;
the sending module is further configured to send a standby instruction to the processor to instruct the processor to enter a standby state;
the acquisition module is further used for starting the camera shooting assembly to acquire first image data according to a preset low-frequency if the processor is in a standby state.
Preferably, the apparatus further comprises: a module is established for establishing the data transmission mode,
the establishing module is used for establishing data communication connection with the processor based on a wake-up interface;
the sending module is further configured to send a wake-up signal to the processor in a standby state based on the wake-up interface;
the sending module is further configured to send a standby instruction to the processor in an unsaved state based on the wake-up interface.
Preferably, the apparatus further comprises:
and the starting module is used for starting the camera shooting assembly to acquire first image data according to a preset low-frequency if the processor is detected to reenter the standby state.
Preferably, the apparatus further comprises:
and the execution module is used for re-executing the step of acquiring the first image data acquired by the camera shooting assembly at the low frequency if the image recognition result does not include the target recognition object so as to re-perform image recognition processing on the first image data.
To achieve one or a part of or all of the above objects or other objects, there is provided a processor wake-up system, comprising: a camera module consisting of a camera component and a first processor, a second processor,
the camera shooting assembly is in data communication with the first processor and the second processor respectively and is used for collecting image data;
the first processor is in data communication with the second processor and is used for acquiring first image data acquired by the camera shooting assembly at a low frequency; performing image recognition processing on the first image data to obtain an image recognition result; if the image recognition result comprises a target recognition object, sending a wake-up signal to a second processor in a standby state;
and the second processor is used for carrying out image processing based on second image data acquired by the camera shooting assembly at high frequency after receiving the wake-up signal.
To achieve one or a part of or all of the above objects or other objects, a storage medium is provided, where at least one executable instruction is stored, and the executable instruction causes a processor to perform an operation corresponding to the processor wake-up method.
To achieve one or a part or all of the above objects or other objects, there is provided AR glasses including: a camera module group consisting of a camera and a control module, and a main control module,
the camera is in data communication with the control module and the main control module respectively, and the control module is in data communication with the main control module;
the control module is used for acquiring first image data acquired by the camera at a low frequency and identifying the first image data based on the trained deep neural network model; if the recognized result is a target gesture or a target face, sending a wake-up signal to the main control module in a standby state;
and the main control module is used for collecting second image data which are collected by the camera at high frequency after receiving the wake-up signal so as to process data based on the second image data.
Preferably, an interrupt pin is configured on the camera module, and the control module and the main control module perform data communication through the interrupt pin;
the control module is specifically configured to send a wake-up signal to the main control module through the interrupt pin.
Preferably, the control module is further configured to send a standby instruction to the main control module through the interrupt pin when it is detected that the main control module is not in a standby state;
the main control module is further configured to enter a standby state based on the standby instruction received by the interrupt pin.
Preferably, the control module is further configured to start the camera to acquire the first image data at a low frequency after detecting that the main control module enters a standby state.
The embodiment of the invention has the following beneficial effects:
after the processor awakening method is adopted, the processor in the AR equipment reduces invalid energy consumption, the system energy consumption of the processor in continuous operation can be effectively reduced, the system load pressure of the processor is greatly reduced, and the endurance time of the processor of the AR equipment is prolonged.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Wherein:
FIG. 1 is a flowchart illustrating a wake-up method of a processor according to an embodiment;
FIG. 2 is a flowchart illustrating another processor wake-up method according to an embodiment;
FIG. 3 is a flowchart illustrating a wake-up method of a processor according to an embodiment;
FIG. 4 is a diagram illustrating an embodiment of a wake-up unit;
FIG. 5 is a block diagram of a wake-up system of a processor according to an embodiment;
fig. 6 is a schematic structural diagram of an AR glasses according to an embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the process of collecting video data by the camera shooting assembly, whether the video data containing specific behaviors are collected or not, the processor serving as the main control end can perform data operation in real time and can enter an invalid identification or invalid data processing state. However, the invalid video data identification increases the system load pressure of the processor and also generates a large amount of power consumption, thereby affecting the endurance time of the processor, and the embodiment of the invention provides a processor wake-up method, as shown in fig. 1, which comprises the following steps:
101. acquiring first image data acquired by the camera shooting assembly at a low frequency.
In the embodiment of the invention, the camera shooting assembly is assembly equipment for collecting image data, collects front-end images in real time, and comprises, but is not limited to, cameras of any model. At this time, the current execution end and the camera component (e.g., a camera) form a camera module, and the camera module is configured at the front end of the AR device (e.g., AR glasses) to process the acquired image data in combination with the virtual scene through the AR technology, which is not specifically limited in the embodiment of the present invention. The first image data is image content acquired by driving the camera shooting assembly at a low frequency, that is, after the user wears the started AR device, the camera shooting assembly acquires the first image data of the front end of the user at a low frequency, so as to perform the image recognition processing in step 102.
102. And carrying out image recognition processing on the first image data to obtain an image recognition result.
In the embodiment of the present invention, after acquiring the first image data, the current execution end performs image recognition processing, specifically, whether a target recognition object exists in the first image data is recognized, including but not limited to based on a machine learning algorithm or based on specific image content comparison, so as to obtain an image recognition result. For example, the comparison based on the specific image content may identify the image data of the image for the pre-configuration target, and then search for and identify whether or not the specific image content exists from the first image data to determine the image identification result. For another example, the first image data is subjected to image recognition processing based on the neural network model after model training is completed, so as to obtain a recognition result including different recognition objects, where the recognition objects include, but are not limited to, objects such as hands, faces, and feet, and the embodiment of the present invention is not limited in particular.
It should be noted that the target recognition object is a target object for waking up the processor, such as a human hand (or a human hand containing a specific gesture), a specific human face, and so on, so that the step in step 103 is executed when the target recognition object appears. The target recognition objects can be pre-recorded or configured, so that the processor is awakened for different target recognition objects.
103. And if the image recognition result comprises the target recognition object, sending a wake-up signal to a processor in a standby state.
In the embodiment of the present invention, the current execution end performs data communication with the processor in the standby state, and the processor in the standby state can be used as a main control end to provide an image data processing function for the AR device, at this time, the processor in the standby state is a state in which the processor does not acquire image data acquired by the camera shooting assembly for image processing, including but not limited to a state in which the processor is in a low power state, a state in which the processor is in a low power consumption and low frequency data processing state, and the like. Therefore, if the image recognition result includes the target recognition object, it indicates that the processor needs to be awakened at this time, so that the processor enters a normal processing state to process the image data, and further sends an awakening model to the processor in a standby state to drive the processor to perform image processing based on the second image data acquired by the camera module at high frequency.
It should be noted that, in the embodiment of the present invention, the current execution end is in data communication connection with the processor, and the camera module is in data communication connection with the processor, so that after the current execution end sends the wake-up signal to the processor in the standby state, the processor may acquire the second data acquired by the camera module at high frequency to perform image data. In addition, in this embodiment of the present invention, one or more processors in the standby state may be used to wake up and then execute the processing function of the corresponding processor, which is not limited in this embodiment of the present invention.
In another embodiment of the present invention, for further limitation and description, the step of performing image recognition processing on the image data to obtain an image recognition result includes: and carrying out image recognition processing on the first image data based on the image recognition model after model training is completed to obtain an image recognition result.
In order to reduce power consumption based on processor precision image processing and achieve a pre-recognition effect of a target recognition object, image recognition processing is firstly carried out on first image data based on an image recognition model which is trained on the model in a current execution end so as to obtain an image recognition result serving as rough recognition. The image recognition model is obtained by training based on an image training sample set containing a pre-configured target recognition object, namely, before model training of the image recognition model, the target recognition object used for waking up a processor is pre-configured or defined to be used as a mark specific construction image training sample set for model training. Specifically, the image recognition model may perform model training for a machine learning model with an image recognition function, including but not limited to Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), and the like, so as to improve the recognition accuracy of the target recognition object.
It should be noted that, since the first image data may include a plurality of recognition objects, for accurately waking up the processor, a target recognition object is configured or defined in advance, and image data corresponding to the target recognition object is used as a labeled feature image data to construct an image training sample set, so as to train the image recognition model based on the image training sample set. At this time, the obtained recognition result may include the target recognition object, and may also include recognition objects corresponding to other marked feature image data, which is not specifically limited in the embodiment of the present invention. In addition, the current execution end is in data communication connection with the processor, and the camera shooting assembly is in data communication connection with the processor, so that the image recognition model after model training can be loaded and acquired from the processor, and the data processing pressure of the current execution end is reduced.
Furthermore, if there are multiple processors in data communication with the current execution end, multiple target identification objects may be configured in advance, and a processor awakened by each target identification object may be defined, so as to achieve the purpose of awakening a processor with multiple identification effects. For example, gesture 1 corresponds to waking up processor 1 and gesture 2 corresponds to waking up processor 2, so that data processing functions in the corresponding processors can be performed for different gestures.
In another embodiment of the present invention, for further definition and explanation, as shown in fig. 2, before the step of acquiring the first image data acquired by the camera assembly at the low frequency, the method further includes:
201. detecting whether the processor is in a standby state;
202. if the processor is not in a standby state, sending a standby instruction to the processor;
specifically, the step of obtaining first image data acquired by the camera shooting assembly at low frequency comprises: 203. and if the processor is in a standby state, starting the camera shooting assembly to acquire first image data according to a preset low-frequency.
In order to wake up a standby state processor and reduce continuous power consumption of the processor, before the image data is collected by the camera shooting assembly at a low frequency, whether the processor is in a standby state is detected, and the camera shooting assembly is started to collect the first image data according to a preset low frequency when the processor is in the standby state. The detecting whether the processor is in the standby state may be performed by sending a state confirmation request to the processor, so as to determine whether the processor is in the standby state according to a state confirmation response fed back by the processor. To ensure that the processor is in a low power state when it is not in a standby state, a standby instruction is sent to the processor instructing the processor to enter a standby state if the processor is not in a standby state. Correspondingly, if the processor is in a standby state, the current execution end starts the camera shooting assembly to collect first image data according to the preset low-frequency. The preset low-frequency is a frequency relatively lower than the preset high-frequency, for example, the preset high-frequency is 100 times per second, and the corresponding preset low-frequency may be 1 time per second, which is not specifically limited in the embodiment of the present invention.
In another embodiment of the present invention, for further definition and explanation, as shown in fig. 3, the steps further include:
301. establishing a data communication connection with the processor based on a wake-up interface;
specifically, the step of sending the wake-up signal to the processor in the standby state includes: 301. sending a wake-up signal to the processor in a standby state based on the wake-up interface;
specifically, the step of sending the standby instruction to the processor includes: 303. sending a standby instruction to the processor in an unsStandby state based on the wake-up interface.
In order to effectively send the wake-up signal to the processor, thereby reducing the continuous power consumption of the processor, a data communication connection with the processor is established based on the wake-up interface of the current execution end, so that when the wake-up signal is sent, transmission is performed through the special wake-up interface. The wake-up signal sent to the processor in the standby state through the wake-up interface may be a level signal, such as a transition from an initial high level to a low level or a transition from an initial low level to a high level, so that the processor is started from the standby state to the normal operation state based on the wake-up signal. Meanwhile, if the processor is in a normal running state, namely in a non-standby state, a standby instruction can be sent to the processor through the wake-up interface, so that the processor enters a standby state, and the system power consumption of the processor is reduced.
In another embodiment of the present invention, for further definition and illustration, after the step of sending the wake-up signal to the processor in the standby state, the method further comprises:
and if the processor is detected to enter the standby state again, starting the camera shooting assembly to acquire first image data according to a preset low-frequency.
In order to ensure that a processor in the AR equipment is still in low power consumption when not performing data processing, and therefore the endurance effect of the processor is improved, after a wake-up signal is sent to the processor in a standby state, whether the processor enters the standby state again is detected, and if the processor is detected to enter the standby state again, a camera shooting component is started to collect first image data according to a preset low-frequency. The processor is awakened, then processes second image data acquired by the camera shooting assembly at a high frequency, and the processor enters an operating state at the moment, whether the processor is in a standby state or not can be triggered manually, or a standby timer is configured in the processor in advance, when the duration of the processor not running any data processing matches with the standby time, the processor is triggered to enter the standby state, and the processor can be configured to directly enter the standby state after completing processing the second image data.
It should be noted that, for the detection of whether the processors enter the standby state, the detection may be performed by sending a standby state confirmation request to the processors and receiving a standby state confirmation response, or may be performed based on a standby state signal fed back between the processors, which is not specifically limited in the embodiment of the present invention.
In another embodiment of the present invention, for further limitation and explanation, after performing an image recognition process on the first image data and obtaining an image recognition result, the method further includes:
and if the image recognition result does not comprise the target recognition object, re-executing the step of acquiring the first image data acquired by the camera shooting assembly at the low frequency so as to re-perform image recognition processing on the first image data.
In order to ensure that the processor can still realize the power consumption operation of the processor system when the processor does not recognize the target recognition object, when the image recognition result recognized in the current execution end does not include the target recognition object, it is indicated that the recognition object for waking up the processor does not appear, and the processor is not required to process the image data, at this time, the first image data acquired by the camera shooting component at low frequency is obtained again, and the step of performing the image recognition processing on the first image data is executed.
The embodiment of the invention provides a processor awakening method, which comprises the steps of acquiring first image data acquired by a camera shooting assembly at a low frequency; carrying out image recognition processing on the first image data to obtain an image recognition result; and if the image recognition result comprises a target recognition object, sending a wake-up signal to a processor in a standby state to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency, so that invalid energy consumption of the processor in the AR equipment is reduced, the system energy consumption of the processor in continuous operation can be effectively reduced, the system load pressure of the processor is greatly reduced, and the endurance time of the processor of the AR equipment is prolonged.
Further, as an implementation of the method shown in fig. 1, an embodiment of the present invention provides a processor wake-up apparatus, as shown in fig. 4, the apparatus includes:
the acquisition module 41 is configured to acquire first image data acquired by the camera shooting assembly at a low frequency;
the processing module 42 is configured to perform image recognition processing on the first image data to obtain an image recognition result;
a sending module 43, configured to send a wake-up signal to a processor in a standby state if the image recognition result includes a target recognition object, so as to drive the processor to perform image processing based on the second image data acquired by the camera component at high frequency.
Preferably, the processing module is specifically configured to perform image recognition processing on the first image data based on an image recognition model that has been trained to obtain an image recognition result, where the image recognition model is obtained by training based on an image training sample set that includes a pre-configured target recognition object, and the target recognition object is a target object for waking up the processor.
Preferably, the apparatus further comprises: a detection module for detecting the position of the optical fiber,
the detection module is used for detecting whether the processor is in a standby state;
the sending module is further configured to send a standby instruction to the processor to instruct the processor to enter a standby state;
the acquisition module is further used for starting the camera shooting assembly to acquire first image data according to a preset low-frequency if the processor is in a standby state.
Preferably, the apparatus further comprises: a module is established, and the module is used for establishing the module,
the establishing module is used for establishing data communication connection with the processor based on the awakening interface;
the sending module is further configured to send a wake-up signal to the processor in a standby state based on the wake-up interface;
the sending module is further configured to send a standby instruction to the processor in an unsafety state based on the wake-up interface.
Preferably, the apparatus further comprises:
and the starting module is used for starting the camera shooting assembly to acquire first image data according to a preset low-frequency if the processor is detected to reenter the standby state.
Preferably, the apparatus further comprises:
and the execution module is used for re-executing the step of acquiring the first image data acquired by the camera shooting assembly at the low frequency if the image recognition result does not include the target recognition object so as to re-perform image recognition processing on the first image data.
The embodiment of the invention provides a processor awakening device, which is characterized in that first image data acquired by a camera shooting assembly at a low frequency is acquired; carrying out image recognition processing on the first image data to obtain an image recognition result; and if the image recognition result comprises a target recognition object, sending a wake-up signal to a processor in a standby state to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency, so that invalid energy consumption of the processor in the AR equipment is reduced, the system energy consumption of the processor in continuous operation can be effectively reduced, the system load pressure of the processor is greatly reduced, and the endurance time of the processor of the AR equipment is prolonged.
According to an embodiment of the present invention, there is provided a processor wake-up system, as shown in fig. 5, including: a camera module 53 consisting of a camera module 51 and a first processor 52, a second processor 54,
the camera assembly 51 is in data communication with the first processor 52 and the second processor 54 respectively, and is used for acquiring image data;
the first processor 52 is in data communication with the second processor 54, and is configured to acquire first image data acquired by the camera module 51 at a low frequency; carrying out image recognition processing on the first image data to obtain an image recognition result; if the image recognition result includes the target recognition object, sending a wake-up signal to the second processor 54 in the standby state;
the second processor 54 is configured to perform image processing based on the second image data acquired by the camera module 51 at a high frequency after receiving the wake-up signal.
According to an embodiment of the present invention, a storage medium is provided, where the storage medium stores at least one executable instruction, and the computer executable instruction may execute the processor wake-up method in any of the method embodiments described above.
Fig. 6 is a schematic structural diagram of AR glasses according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the terminal.
The AR glasses may include: a camera module 63 composed of a camera 61 and a control module 62, and a main control module 64,
the camera 61 is in data communication with the control module 62 and the main control module 64 respectively, and the control module 62 is in data communication with the main control module 64;
the control module 62 is configured to acquire first image data acquired by the camera 61 at a low frequency, and identify the first image data based on the trained deep neural network model; if the recognized result is a target gesture or a target face, sending a wake-up signal to the main control module 64 in a standby state;
the main control module 64 is configured to collect second image data collected by the camera 61 at a high frequency after receiving the wake-up signal, so as to perform data processing based on the second image data.
Preferably, an interrupt pin is configured on the camera module, and the control module and the main control module perform data communication through the interrupt pin;
the control module is specifically configured to send a wake-up signal to the main control module through the interrupt pin.
Preferably, the control module is further configured to send a standby instruction to the main control module through the interrupt pin when it is detected that the main control module is not in a standby state;
the main control module is further configured to enter a standby state based on the standby instruction received by the interrupt pin.
Preferably, the control module is further configured to start the camera to acquire the first image data at a low frequency after detecting that the main control module enters a standby state.
Based on a specific application scenario, the method for waking up the main control module implemented in the AR glasses in the embodiment of the present invention is the same as the method for waking up the processor shown in fig. 1, and details are not repeated here.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (13)
1. A processor wake-up method, comprising:
acquiring first image data acquired by a camera shooting assembly at a low frequency;
performing image recognition processing on the first image data to obtain an image recognition result;
and if the image recognition result comprises a target recognition object, sending a wake-up signal to a processor in a standby state so as to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency.
2. The method according to claim 1, wherein the performing image recognition processing on the image data to obtain an image recognition result comprises:
and performing image recognition processing on the first image data based on an image recognition model which is trained by the model to obtain an image recognition result, wherein the image recognition model is obtained by training based on an image training sample set containing a pre-configured target recognition object, and the target recognition object is a target object for awakening a processor.
3. The method of claim 2, wherein prior to acquiring the first image data acquired by the camera assembly at the low frequency, the method further comprises:
detecting whether the processor is in a standby state;
if the processor is not in the standby state, sending a standby instruction to the processor to indicate the processor to enter the standby state;
the acquiring of the first image data acquired by the camera shooting assembly at low frequency comprises:
and if the processor is in a standby state, starting the camera shooting assembly to acquire first image data according to a preset low-frequency.
4. The method of claim 3, further comprising:
establishing a data communication connection with the processor based on a wake-up interface;
the sending of the wake-up signal to the processor in the standby state includes:
sending a wake-up signal to the processor in a standby state based on the wake-up interface;
the sending a standby instruction to the processor comprises:
sending a standby instruction to the processor in an unsawaited state based on the wake-up interface.
5. The method of claim 1, wherein after sending the wake-up signal to the processor in the standby state, the method further comprises:
and if the processor is detected to enter the standby state again, starting the camera shooting assembly to acquire first image data according to the preset low-frequency.
6. The method according to any one of claims 1 to 5, wherein after the image recognition processing is performed on the first image data to obtain an image recognition result, the method further comprises:
and if the image recognition result does not comprise the target recognition object, re-executing the step of acquiring the first image data acquired by the camera shooting assembly at the low frequency so as to re-perform image recognition processing on the first image data.
7. A processor wake-up device, comprising:
the acquisition module is used for acquiring first image data acquired by the camera shooting assembly at a low frequency;
the processing module is used for carrying out image identification processing on the first image data to obtain an image identification result;
and the sending module is used for sending a wake-up signal to a processor in a standby state if the image recognition result comprises a target recognition object so as to drive the processor to perform image processing based on second image data acquired by the camera shooting assembly at high frequency.
8. A processor wake-up system, comprising: a camera module consisting of a camera component and a first processor, a second processor,
the camera shooting assembly is in data communication with the first processor and the second processor respectively and is used for collecting image data;
the first processor is in data communication with the second processor and is used for acquiring first image data acquired by the camera shooting assembly at a low frequency; carrying out image recognition processing on the first image data to obtain an image recognition result; if the image recognition result comprises a target recognition object, sending a wake-up signal to a second processor in a standby state;
and the second processor is used for carrying out image processing based on second image data acquired by the camera shooting assembly at high frequency after receiving the wake-up signal.
9. A storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the processor wake-up method as claimed in any one of claims 1 to 6.
10. AR eyewear, comprising: a camera module group consisting of a camera and a control module, and a main control module,
the camera is in data communication with the control module and the main control module respectively, and the control module is in data communication with the main control module;
the control module is used for acquiring first image data acquired by the camera at low frequency and identifying the first image data based on the trained deep neural network model; if the recognized result is a target gesture or a target face, sending a wake-up signal to the main control module in a standby state;
and the main control module is used for acquiring second image data acquired by the camera at high frequency after receiving the wake-up signal so as to perform data processing based on the second image data.
11. The AR glasses according to claim 10, wherein the camera module is configured with an interrupt pin, and the control module and the main control module perform data communication through the interrupt pin;
the control module is specifically configured to send a wake-up signal to the main control module through the interrupt pin.
12. The AR glasses according to claim 11,
the control module is further configured to send a standby instruction to the main control module through the interrupt pin when it is detected that the main control module is not in a standby state;
the main control module is further configured to enter a standby state based on the standby instruction received by the interrupt pin.
13. The AR glasses according to any one of claims 10-12,
the control module is further used for starting the camera to acquire the first image data at a low frequency after the master control module is detected to enter a standby state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210459577.3A CN114785954A (en) | 2022-04-27 | 2022-04-27 | Processor wake-up method, device, system, storage medium and AR glasses |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210459577.3A CN114785954A (en) | 2022-04-27 | 2022-04-27 | Processor wake-up method, device, system, storage medium and AR glasses |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114785954A true CN114785954A (en) | 2022-07-22 |
Family
ID=82432550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210459577.3A Pending CN114785954A (en) | 2022-04-27 | 2022-04-27 | Processor wake-up method, device, system, storage medium and AR glasses |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114785954A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170353699A1 (en) * | 2016-06-01 | 2017-12-07 | Pixart Imaging Inc. | Surveillance system and operation method thereof |
| CN109448198A (en) * | 2018-12-18 | 2019-03-08 | 深圳市铁证科技有限公司 | A kind of face fingerprint recognition intelligent door lock control system |
| CN109917922A (en) * | 2019-03-28 | 2019-06-21 | 更藏多杰 | A kind of exchange method and wearable interactive device |
| CN112578893A (en) * | 2020-12-11 | 2021-03-30 | Oppo广东移动通信有限公司 | Data processing system, chip, method and storage medium |
| WO2022011986A1 (en) * | 2020-07-14 | 2022-01-20 | 浙江宇视科技有限公司 | Wake-up method for surveillance camera, device, surveillance camera, and medium |
| CN114202000A (en) * | 2020-08-31 | 2022-03-18 | 华为技术有限公司 | Service processing method and device |
-
2022
- 2022-04-27 CN CN202210459577.3A patent/CN114785954A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170353699A1 (en) * | 2016-06-01 | 2017-12-07 | Pixart Imaging Inc. | Surveillance system and operation method thereof |
| CN109448198A (en) * | 2018-12-18 | 2019-03-08 | 深圳市铁证科技有限公司 | A kind of face fingerprint recognition intelligent door lock control system |
| CN109917922A (en) * | 2019-03-28 | 2019-06-21 | 更藏多杰 | A kind of exchange method and wearable interactive device |
| WO2022011986A1 (en) * | 2020-07-14 | 2022-01-20 | 浙江宇视科技有限公司 | Wake-up method for surveillance camera, device, surveillance camera, and medium |
| CN114202000A (en) * | 2020-08-31 | 2022-03-18 | 华为技术有限公司 | Service processing method and device |
| CN112578893A (en) * | 2020-12-11 | 2021-03-30 | Oppo广东移动通信有限公司 | Data processing system, chip, method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103906A (en) | It is a kind of to wake up method, smart machine and medium that smart machine carries out speech recognition | |
| CN113778663B (en) | Scheduling method of multi-core processor and electronic equipment | |
| CN107622246B (en) | Face recognition method and related product | |
| CN112860169B (en) | Interaction method and device, computer readable medium and electronic equipment | |
| CN112634895A (en) | Voice interaction wake-up-free method and device | |
| CN114333774B (en) | Speech recognition method, device, computer equipment and storage medium | |
| CN111783674A (en) | Face recognition method and system based on AR glasses | |
| CN112367486B (en) | Video processing method and device | |
| CN113766127A (en) | Control method and device of mobile terminal, storage medium and electronic equipment | |
| CN114785954A (en) | Processor wake-up method, device, system, storage medium and AR glasses | |
| CN113014830A (en) | Video blurring method, device, equipment and storage medium | |
| CN109856800B (en) | Display control method and device of split AR glasses and split AR glasses | |
| CN112363861A (en) | Voice interaction method and device for subway ticket purchasing | |
| CN112150444A (en) | Method and device for identifying attribute features of face image and electronic equipment | |
| CN112333439B (en) | Face cleaning equipment control method and device and electronic equipment | |
| CN112232287A (en) | Face recognition method and device | |
| CN112580472A (en) | Rapid and lightweight face recognition method and device, machine readable medium and equipment | |
| CN110866488A (en) | Image processing method and device | |
| CN115797412B (en) | Dynamic object outlier parallel detection method, device, system, equipment and medium | |
| WO2023197887A1 (en) | Intelligent control method for starting washing machine and device thereof | |
| CN115859252B (en) | Authentication information processing method, device, electronic equipment and storage medium | |
| CN116744102B (en) | Ball machine tracking method and device based on feedback adjustment | |
| CN114356275B (en) | Interactive control method and device, intelligent voice equipment and storage medium | |
| CN110622498B (en) | Photographing composition method and device and electronic equipment | |
| CN116486058A (en) | Image shooting storage method and device, intelligent watch and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |