Task scheduling method, image acquisition device and storage medium

Abstract

The invention discloses a task scheduling method, an image acquisition device and a storage medium, and relates to the technical field of image processing, the task scheduling method is applied to the image acquisition device, the image acquisition device is in communication connection with a cloud computing module, and the task scheduling method comprises the following steps: if an analysis task is triggered, according to the video complexity corresponding to the analysis task, determining the video complexity corresponding to the analysis task; determining task complexity corresponding to the analysis task; determining a processing object of the analysis task according to the task complexity, wherein the processing object is an image acquisition device and / or a cloud computing module; and controlling the processing object to execute the analysis task. Based on this, the local and / or cloud end of the image acquisition device is intelligently selected according to the complexity of task processing to perform scheduling processing on the image tasks, and the situation that all tasks are sent to the cloud end, so that communication energy consumption is high, and task processing efficiency is affected is avoided.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a task scheduling method, an image acquisition device, and a storage medium. Background Art

[0002] Smart cameras are widely used in smart homes, security surveillance, and other fields, performing computational tasks such as object detection, facial recognition, behavior analysis, and motion tracking. They typically utilize both local and cloud computing modes. Due to hardware limitations, cameras struggle to handle data-intensive computational tasks. Therefore, smart cameras typically send these tasks to the cloud for processing.

[0003] However, when based on cloud computing, smart cameras need to upload a large amount of data to the cloud, and continuous video streaming will significantly increase the communication energy consumption of the device, resulting in high communication energy consumption of smart cameras.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a task scheduling method, an image acquisition device and a storage medium, aiming to solve the technical problem of high communication energy consumption of current smart devices.

[0006] To achieve the above objectives, the present application proposes a task scheduling method, which is applied to an image acquisition device, wherein the image acquisition device is communicatively connected to a cloud computing module, and the method includes:

[0007] If an analysis task is triggered, determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task;

[0008] Determining a processing object of the analysis task according to the task complexity, the processing object being the image acquisition device and / or the cloud computing module;

[0009] The processing object is controlled to execute the analysis task.

[0010] In one embodiment, the step of determining the processing object of the analysis task according to the task complexity, wherein the processing object is the image acquisition device and / or the cloud computing module, includes:

[0011] If the task complexity is lower than a preset threshold, determining that the processing object is the image acquisition device;

[0012] If the task complexity is greater than or equal to a preset threshold, the processing object is determined to be the cloud computing module.

[0013] In one embodiment, the step of determining the processing object of the analysis task according to the task complexity, wherein the processing object is the image acquisition device and / or the cloud computing module, includes:

[0014] If the task complexity is greater than or equal to the preset threshold, determining the device state of the image acquisition device;

[0015] If the device status meets the cloud computing requirements, the processing object is determined to be the cloud computing module; otherwise, the processing object is determined to be the cloud computing module and the image acquisition device.

[0016] In one embodiment, the task scheduling method further includes:

[0017] Acquire device status information of the image acquisition device, and update the preset threshold according to the device status information.

[0018] In one embodiment, the step of controlling the processing object to perform the analysis task includes:

[0019] Determining a first subtask and a second subtask corresponding to the processing object;

[0020] The image acquisition device is controlled to execute the first subtask, and the task requirements and basic data corresponding to the second subtask are sent to the cloud computing module.

[0021] In one embodiment, if the analysis task is triggered, the step of determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task includes:

[0022] If an analysis task is triggered, obtain the video data volume and video content corresponding to the analysis task;

[0023] Determining the video complexity according to the video data amount and the video content;

[0024] The task complexity associated with the video complexity is determined.

[0025] In one embodiment, before the step of determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task if the analysis task is triggered, the step further includes:

[0026] If the state of the image acquisition device changes, the analysis task is triggered; wherein the state change includes but is not limited to:

[0027] The image information changes within a preset period of time;

[0028] The time point at which the cache information of the image acquisition device is cleared is reached;

[0029] It is detected that the remaining power of the image acquisition device is less than a preset power.

[0030] In one embodiment, before the step of controlling the processing object to perform the analysis task, the method further includes:

[0031] Acquiring a power consumption operation mode of the image acquisition device;

[0032] If the power consumption operation mode is the first power consumption operation mode, determining a maximum frame rate of the image information or a maximum data upload amount in the analysis task, wherein the power consumption of the first power consumption operation mode is less than a preset power consumption;

[0033] The step of controlling the processing object to perform the analysis task includes:

[0034] controlling the image acquisition device to perform the analysis task based on the maximum frame rate; or

[0035] The image information collected by the image acquisition device is uploaded to the cloud module based on the maximum data upload amount, so that the cloud module performs the analysis task.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes an image acquisition device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the task scheduling method described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and stores a computer program on the storage medium. When the computer program is executed by the processor, the steps of the task scheduling method described above are implemented.

[0038] One or more technical solutions proposed in this application have at least the following technical effects:

[0039] When triggering an analysis task on an image acquisition device, the system first calculates the video complexity corresponding to the current analysis task. The system then determines the task complexity of the analysis task based on the video complexity. The system then controls the processing object, which includes the image acquisition device and / or the cloud computing module, to execute the analysis task. This intelligently selects the image acquisition device (i.e., a local device) and / or the cloud computing module (i.e., a cloud-based module) to execute the analysis task based on the task complexity of the analysis task. This avoids the high communication energy consumption caused by uploading all tasks to the cloud computing module for processing, which affects task processing efficiency. This optimizes the processing performance of the task scheduling device and reduces the energy consumption of task processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 A flowchart of the first embodiment of the task scheduling method of this application is provided;

[0043] Figure 2 A flowchart of the second embodiment of the task scheduling method of this application is provided;

[0044] Figure 3 This is an optional flowchart of the task scheduling method provided in the second embodiment of the present application;

[0045] Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the task scheduling method in the embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0048] Smart cameras are widely used in smart homes, security surveillance, and other fields, performing computational tasks such as object detection, facial recognition, behavior analysis, and motion tracking. They typically utilize both local and cloud computing modes. Due to hardware limitations, cameras struggle to handle data-intensive computational tasks. Therefore, smart cameras typically send these tasks to the cloud for processing.

[0049] However, when based on cloud computing, smart cameras need to upload a large amount of data to the cloud, and continuous video streaming will significantly increase the communication energy consumption of the device, resulting in high communication energy consumption of smart cameras.

[0050] The main solution of the embodiment of the present application is: if an analysis task is triggered, the task complexity corresponding to the analysis task is determined according to the video complexity corresponding to the analysis task;

[0051] Determining a processing object of the analysis task according to the task complexity, the processing object being the image acquisition device and / or the cloud computing module;

[0052] The processing object is controlled to execute the analysis task.

[0053] Specifically, in this embodiment, based on the task complexity of the analysis task, the image acquisition device, i.e., the local and / or cloud computing module, i.e., the cloud, is intelligently selected to perform the analysis task, so as to avoid uploading all tasks to the cloud computing module for processing, which would result in high communication energy consumption and affect the task processing efficiency, thereby optimizing the device processing performance of task scheduling and reducing the energy consumption of task processing.

[0054] It should be noted that the execution subject of this embodiment can be an image acquisition device equipped with a camera module, such as a smart camera or infrared camera. The image acquisition device can capture visible light images, infrared images, or other common images. The following uses the image acquisition device as an example to illustrate this embodiment and the following embodiments.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] The embodiment of the present application provides a task scheduling method applied to an image acquisition device, wherein the image acquisition device is connected to a cloud computing module for communication. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the task method of this application.

[0057] In this embodiment, the task scheduling method includes steps S10 to S30:

[0058] Step S10: If an analysis task is triggered, the task complexity corresponding to the analysis task is determined according to the video complexity corresponding to the analysis task.

[0059] An analysis task refers to a task that the image acquisition device and / or cloud computing module needs to perform based on the current video data. For example, the analysis task can be a simple motion detection, that is, detecting whether an object is moving in the video, or a more complex object recognition detection. In addition, the analysis task can also be a processing task in the common field of image processing, such as object tracking and simple face recognition. The specific category of the analysis task is not limited in this application. Among them, the analysis task is associated with real-time video data.

[0060] In this embodiment, after the analysis task is triggered, the complexity index of the video data corresponding to the analysis task in the time dimension, space dimension and content dimension can be determined, specifically including the video data volume and video content. The video data volume includes the bit rate, resolution, frame rate and encoding format of the video stream, and the video content includes the number of moving objects in the video, the action type (such as pedestrians walking / vehicles changing lanes), the semantic level features of the scene semantic category (such as traffic intersections / indoor monitoring), etc. The video complexity is then converted into an evaluation index of the computing resource requirement level, namely the task complexity, through a quantization model. Among them, the quantization model can be a pre-trained artificial intelligence model or a pre-trained neural network model. These models are set locally in the image acquisition device. Compared with the analysis task of executing video data, the amount of computation required to calculate the complexity of the analysis task is less.

[0061] In addition, the video complexity and task complexity can be associated by associating a parameter table. That is, when the video complexity is a certain parameter or a certain quantitative indicator, the task complexity is determined based on the data of the parameter or indicator in the pre-stored comparison table.

[0062] Specifically, after the analysis task is triggered, the video data volume and video content corresponding to the analysis task can be obtained, and then the video complexity can be determined based on the video data volume and video content, such as by fusing the video data volume feature (Q) and the video content feature (C), based on a dual-channel fully connected network, inputting Q and C features, outputting the video complexity level, and finally obtaining the task complexity associated with the video complexity level, or based on a random forest regression model, inputting the video complexity, and outputting the task complexity of the computing resource requirements.

[0063] Optionally, when the state of the image acquisition device changes, an analysis task is triggered. The state changes include, but are not limited to, changes in image information within a preset period, reaching the time point when the cached information of the image acquisition device is cleared, and detecting that the remaining power of the image acquisition device is less than the preset power. Specifically, in a simple scenario such as a smart home scenario, anti-theft recognition is performed through the image acquisition device. Under normal circumstances, the image information on the screen remains unchanged for a long time. Therefore, when the image information changes within the preset period, it indicates that someone may have broken in. At this time, the state of the image acquisition device changes, and then the analysis task is triggered to analyze and process the current image information. When the image acquisition device processes a large number of tasks, it will cache redundant data locally. These cached data affect the processing performance of the image acquisition device. Therefore, when reaching the time point when the cached information of the image acquisition device is cleared, since the cached information is cleared, the image acquisition device is in a better operating state and can analyze the current video content in real time. Some image acquisition devices are powered by built-in batteries. Therefore, when the remaining power is lower than a certain threshold, an analysis task is triggered to reallocate the processing object of the current task. For example, when the power is greater than 30%, the analysis task is usually executed by the cloud computing module, and when the power is less than 30%, it needs to be executed by the local module of the image acquisition device to reduce energy consumption and improve battery life.

[0064] Step S20: Determine the processing object of the analysis task according to the task complexity.

[0065] In this embodiment, the processing object selection mechanism can reasonably allocate resources for the image acquisition device, avoiding the situation of computational congestion and high energy consumption caused by blindly sending resources to the cloud computing module. The processing object can be the image acquisition device and / or the cloud computing module.

[0066] As an optional implementation manner for determining the processing object, if the task complexity is lower than the preset threshold, the processing object is determined to be the image acquisition device; if the task complexity is greater than or equal to the preset threshold, the processing object is determined to be the cloud computing module. Further, multiple thresholds can also be divided. That is, when the task complexity is greater than the first threshold and less than the second threshold, the processing object is determined to be the cloud computing module and the image acquisition device. Specifically, a complexity-resource mapping table can be established first. When the task complexity level T≤T1, local computing is used; when T1<T≤T2, local preprocessing + cloud fine processing is adopted; when T>T2, full-scale cloud processing is performed, where T1, T2, and T3 are preset parameters. The preset threshold can be dynamically updated based on the device state of the image acquisition device in addition to being set in advance.

[0067] Optionally, the historical task scheduling information of the image acquisition device can also be obtained, and then the processing object of the analysis task is determined based on the historical task scheduling information.

[0068] Optionally, the processing object can be dynamically calculated based on a dynamic load balancing algorithm. This algorithm monitors the available computing power Fe of the local computing unit and the transmission bandwidth B of the cloud computing module in real time. The decision function is Obj = argmin{α(1 / F_e) + β(1 / B)}, where α and β are preset weight coefficients. For example, when the task complexity level is C3, Fe = 0.8, and B = 50 Mbps, the analysis task is assigned to the image acquisition device, while the semantic segmentation task is assigned to the cloud computing module.

[0069] By flexibly selecting the processing objects of analysis tasks based on task complexity, resource utilization can be improved while improving task processing efficiency, avoiding the situation where tasks are stranded locally or in the cloud, resulting in low task processing efficiency and waste of power.

[0070] Step S30: Control the processing object to execute the analysis task.

[0071] In this embodiment, after the processing object is determined, the analysis task is performed by the processing object, that is, when the processing object is an image acquisition device, the analysis task is directly executed, such as performing motion detection on images with low data volume through the image acquisition device, and realizing low-resolution face recognition by comparing with the local database.

[0072] When the processing target is a cloud computing module, the data is sent to the cloud computing module so that the cloud computing module can perform analysis tasks based on the received data. For example, a 4K / 8K high-definition video and a task requirement (such as object recognition) can be sent to the cloud computing module so that the cloud computing module can perform object recognition processing through a deep learning network.

[0073] Furthermore, in a hybrid computing mode, that is, when the processing objects are an image acquisition device and a cloud computing module, the first subtask and the second subtask corresponding to the processing object can be determined separately, and then the image acquisition device can be controlled to execute the first subtask, and the task requirements and basic data corresponding to the second subtask can be sent to the cloud computing module. The basic data includes at least video data and data corresponding to the task requirements. For example, in the hybrid computing mode, the image acquisition device extracts feature data such as facial feature vectors, performs simple facial recognition based on these feature vectors, and uploads the recognition results and high-definition video data to the cloud computing module for calculation by the cloud computing module, effectively reducing the amount of data transmission.

[0074] For example, in the smart home field, if an intruder is detected (low complexity), a local alarm is immediately triggered, and this task is handled by the image acquisition device. When identifying the intruder (high complexity face comparison), the video data needs to be uploaded to the cloud computing module and identification analysis is performed based on the cloud computing module. In the field of industrial production, the image acquisition device can monitor the equipment in real time for abnormal vibration (low data volume). If abnormal vibration occurs, the video stream of the entire production line is sent to the cloud computing module, and the cloud computing module performs equipment failure analysis and prediction (requiring a high complexity prediction model).

[0075] This embodiment provides a task scheduling method, which realizes the intelligent allocation of analysis tasks between the image acquisition device and the cloud computing module by establishing a precise mapping model between video complexity and computing resources. Compared with the traditional method of allocating all tasks to the cloud, this application can reduce continuous video streaming transmission, reduce the communication energy consumption of the image acquisition device, avoid the low task processing efficiency caused by continuous video streaming transmission, and avoid the situation where computing resource utilization and real-time performance are difficult to balance, thereby improving resource utilization and real-time performance of task processing.

[0076] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be described in detail later. Figure 2 , step S20 further includes steps S21 to S22:

[0077] Step S21: If the task complexity is greater than or equal to a preset threshold, determine the device status of the image acquisition device.

[0078] In this embodiment, in addition to intelligently selecting the processing object of the analysis task based on task complexity, the allocation strategy of the analysis task can also be dynamically adjusted by combining parameters reflecting the device status, such as device computing power, bandwidth status, and power consumption. When the task complexity is greater than or equal to the preset threshold, the cloud computing module is usually required to perform calculations and processing. At this time, if the bandwidth status of the image acquisition device is poor, processing based on the cloud computing module may result in low overall task processing efficiency due to network congestion. Therefore, it is necessary to obtain the device status of the image acquisition device, wherein the current device status can be calculated by obtaining the bandwidth status of the image acquisition device, the current remaining computing power and the remaining power, etc.

[0079] For example, the CPU / GPU / NPU utilization of the image acquisition device is first calculated to calculate the current remaining computing power indicator. At the same time, the data upload rate of the current bandwidth is obtained to determine the bandwidth status. If the image acquisition device is powered by a built-in power supply, its remaining power is also required to calculate the battery life in different modes based on the remaining power. After obtaining these parameters, the weight values corresponding to these parameters are determined. Then, based on the weight values and parameters, the status of the device is calculated. The device status is divided into four levels (AD), and each parameter of the calculation result is associated with a unique level.

[0080] Step S22: If the device status meets the cloud computing requirement, the processing object is determined to be the cloud computing module; otherwise, the processing object is determined to be the cloud computing module and the image acquisition device.

[0081] In this embodiment, the device status includes multiple states, such as A, B, C and D levels corresponding to the idle, normal, busy and congested states of the device respectively. In the idle and normal states, it is considered that the image acquisition device meets the cloud computing requirements, and the processing object is directly determined to be the cloud computing module. If it does not meet the requirements, the processing object is determined to be the cloud computing module and the image acquisition device. Therefore, when processing highly complex analysis tasks, the image acquisition device can process simpler subtasks locally, reducing the amount of data uploaded and thus improving resource utilization.

[0082] It is understood that if the task complexity is low and the image acquisition device's device status is good, the processing target can also be determined to be the cloud computing module, or the cloud computing module and the image acquisition device. Specifically, the preset threshold can be updated based on the device status information of the image acquisition device. That is, after obtaining the device status information of the image acquisition device, the preset threshold is updated based on the device status information. For example, if the current status information of the image acquisition device is good, the preset threshold can be dynamically lowered to allow the cloud computing module to process more low-complexity tasks. If the current device status information indicates network congestion, the preset threshold parameters can be increased, thereby improving the screening criteria for task processing through the cloud computing module and avoiding high power consumption due to continuous data transmission.

[0083] Furthermore, the computing task load can be monitored in real time. If the temperature of the image acquisition device is too high when performing a task, the task will automatically switch to the cloud to avoid overheating. If the task is performed through the cloud computing module, the task will fall back to local processing after the delay increases.

[0084] Furthermore, the system can automatically optimize computing modes by learning user habits. For example, in nighttime mode, it reduces computational workload and lowers power consumption. In peak mode, it intelligently schedules tasks to reduce bandwidth consumption. If the user is dissatisfied with the results, the system automatically adjusts the computing strategy to improve accuracy and response speed.

[0085] For example, in order to help understand the implementation process of the task scheduling method obtained by combining this embodiment with the above first embodiment, please refer to Figure 3 , Figure 3 An optional flow chart of a task scheduling method is provided. Specifically, after the start, the camera is started and initialized, and parameters that can characterize the device status, such as the device computing power, network and power consumption status, are monitored. At the same time, the data volume of the current task is calculated, and the complexity of the processing task is analyzed. When the complexity is lower than the threshold, that is, lightweight computing, local computing is performed based on the image acquisition device, that is, local computing mode. When the complexity is higher, the data is sent to the cloud computing module to complete the calculation through the cloud computing mode. In addition, the current computing mode can be determined based on the device status (not shown in the figure). After completing the task calculation, the calculation results can be stored locally or pushed to the user. At the same time, during the calculation process, the computing mode and optimization strategy of the current analysis task can be dynamically adjusted through the parameters of the monitored device status to reduce power consumption and improve resource utilization.

[0086] This embodiment provides a task scheduling method. When processing analysis tasks with high task complexity, the device status of the image acquisition device is obtained, and the computing strategy of the analysis task is dynamically adjusted based on the device status. This avoids blindly sending data to the cloud computing module when the device status is poor, such as when the bandwidth is busy, which leads to resource congestion, increased energy consumption and low computing efficiency.

[0087] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to above and will not be described in detail. On this basis, before step S30, the power consumption operation mode of the image acquisition device can also be obtained. If the power consumption operation mode is the first power consumption operation mode, the maximum frame rate of the image information or the maximum data upload amount in the analysis task is determined, wherein the power consumption of the first power consumption operation mode is less than the preset power consumption, and the preset power consumption is a low power consumption mode, including low computing power, busy bandwidth, and remaining power less than the preset power.

[0088] Based on this, step S30 includes: controlling the image acquisition device to perform the analysis task based on the maximum frame rate; or uploading the image information collected by the image acquisition device to the cloud module based on the maximum data upload amount, so that the cloud module performs the analysis task.

[0089] For example, when the image acquisition device is processing analysis tasks such as target detection, object tracking, simple face recognition and other analysis subtasks, the results can be stored on the device side or pushed to the user application. In low-power mode, that is, in the first power consumption operation mode, the computing energy consumption can be reduced by reducing the frame rate or computing frequency, that is, the analysis task is performed based on the maximum frame rate. When the cloud computing module performs tasks, in a low network speed environment, the image acquisition device reduces resource congestion and communication energy consumption by uploading only key frames and reducing the amount of data. That is, the image acquisition device uploads image information to the cloud based on the maximum data upload amount, so that the cloud uploads data based on the current uploadable data amount, avoiding congestion during data transmission and increasing communication energy consumption.

[0090] The present application provides an image acquisition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the task scheduling method in the first embodiment above.

[0091] Reference below Figure 4 , which shows a structural schematic diagram of an image acquisition device suitable for implementing an embodiment of the present application. Figure 4 The image acquisition device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0092] like Figure 4As shown, the image acquisition device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the image acquisition device are also stored in the random access memory 1004. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the image acquisition device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an image acquisition device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0093] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0094] The image acquisition device provided in this application utilizes the task scheduling method described in the aforementioned embodiment to address the current technical issue of high communication energy consumption in intelligent devices. Compared to the prior art, the image acquisition device provided in this application achieves the same beneficial effects as the task scheduling method described in the aforementioned embodiment. Other technical features of this image acquisition device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0095] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0096] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0097] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, wherein the computer-readable program instructions are used to execute the task scheduling method in the above embodiment.

[0098] The computer-readable storage medium provided in this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM, Erasable Programmable ReadOnly Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM, CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequency (RF, Radio Frequency), etc., or any suitable combination thereof.

[0099] The computer-readable storage medium may be included in the image acquisition device, or may exist independently without being assembled into the image acquisition device.

[0100] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the image acquisition device, the image acquisition device:

[0101] If an analysis task is triggered, determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task;

[0102] Determining a processing object of the analysis task according to the task complexity, the processing object being the image acquisition device and / or the cloud computing module;

[0103] The processing object is controlled to execute the analysis task.

[0104] Computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0106] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0107] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned task scheduling method, thereby resolving the current technical issue of high communication energy consumption in smart devices. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the task scheduling method provided in the aforementioned embodiments, and are not further elaborated here.

[0108] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A task scheduling method, characterized in that: Applied to an image acquisition device, the image acquisition device is communicatively connected to a cloud computing module, and the task scheduling method includes: If an analysis task is triggered, determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task; Determining a processing object of the analysis task according to the task complexity, the processing object being the image acquisition device and / or the cloud computing module; The processing object is controlled to execute the analysis task.

2. The task scheduling method according to claim 1, wherein: The step of determining the processing object of the analysis task according to the task complexity, wherein the processing object is the image acquisition device and / or the cloud computing module, comprises: If the task complexity is lower than a preset threshold, determining that the processing object is the image acquisition device; If the task complexity is greater than or equal to a preset threshold, the processing object is determined to be the cloud computing module.

3. The task scheduling method according to claim 1, wherein: The step of determining the processing object of the analysis task according to the task complexity, wherein the processing object is the image acquisition device and / or the cloud computing module, comprises: If the task complexity is greater than or equal to the preset threshold, determining the device state of the image acquisition device; If the device status meets the cloud computing requirements, the processing object is determined to be the cloud computing module; otherwise, the processing object is determined to be the cloud computing module and the image acquisition device.

4. The task scheduling method according to any one of claims 1 to 3, characterized in that: The task scheduling method further includes: Acquire device status information of the image acquisition device, and update the preset threshold according to the device status information.

5. The task scheduling method according to claim 1, wherein: The step of controlling the processing object to perform the analysis task includes: Determining a first subtask and a second subtask corresponding to the processing object; The image acquisition device is controlled to execute the first subtask, and the task requirements and basic data corresponding to the second subtask are sent to the cloud computing module.

6. The task scheduling method according to claim 1, wherein: If the analysis task is triggered, the step of determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task includes: If an analysis task is triggered, obtain the video data volume and video content corresponding to the analysis task; Determining the video complexity according to the video data amount and the video content; The task complexity associated with the video complexity is determined.

7. The task scheduling method according to claim 1, wherein: Before the step of determining the task complexity corresponding to the analysis task according to the video complexity corresponding to the analysis task if the analysis task is triggered, the method further includes: If the state of the image acquisition device changes, the analysis task is triggered; wherein the state change includes but is not limited to: The image information changes within a preset period of time; The time point at which the cache information of the image acquisition device is cleared is reached; It is detected that the remaining power of the image acquisition device is less than a preset power.

8. The task scheduling method according to claim 1, wherein: Before the step of controlling the processing object to perform the analysis task, the method further includes: Acquiring a power consumption operation mode of the image acquisition device; If the power consumption operation mode is the first power consumption operation mode, determining a maximum frame rate of the image information or a maximum data upload amount in the analysis task, wherein the power consumption of the first power consumption operation mode is less than a preset power consumption; The step of controlling the processing object to perform the analysis task includes: controlling the image acquisition device to perform the analysis task based on the maximum frame rate; or The image information collected by the image acquisition device is uploaded to the cloud module based on the maximum data upload amount, so that the cloud module performs the analysis task.

9. An image acquisition device, characterized in that: The image acquisition device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the task scheduling method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the task scheduling method according to any one of claims 1 to 8 are implemented.

Images