WO2022126415A1 - 追踪算法的运行方法、装置、电子设备及计算机可读存储介质 - Google Patents

追踪算法的运行方法、装置、电子设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2022126415A1
WO2022126415A1 PCT/CN2020/136744 CN2020136744W WO2022126415A1 WO 2022126415 A1 WO2022126415 A1 WO 2022126415A1 CN 2020136744 W CN2020136744 W CN 2020136744W WO 2022126415 A1 WO2022126415 A1 WO 2022126415A1
Authority
WO
WIPO (PCT)
Prior art keywords
tracking
tracking algorithm
calculation result
terminal device
photographing device
Prior art date
Application number
PCT/CN2020/136744
Other languages
English (en)
French (fr)
Inventor
郑伟
董庆堂
朱超
潘德燃
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2020/136744 priority Critical patent/WO2022126415A1/zh
Priority to CN202080074215.1A priority patent/CN114600445A/zh
Publication of WO2022126415A1 publication Critical patent/WO2022126415A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/66Remote control of cameras or camera parts, e.g. by remote control devices
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/12Target-seeking control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/695Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects

Definitions

  • the present application relates to the field of computer technology, and in particular, to a method, apparatus, electronic device, and computer-readable storage medium for running a tracking algorithm.
  • Tracking algorithms are used in the fields of autonomous driving, assisted driving, and automatic mapping. Tracking algorithms can track the location and motion parameters of target objects in the environment.
  • the tracking algorithm can be built into the shooting device used to track the target object.
  • the shooting device can shoot the environment where the target object is located, and based on the built-in tracking algorithm and the hardware resources of the shooting device, the The data such as the position and motion parameters of the target object are tracked and obtained.
  • the tracking algorithm has certain requirements on hardware resources. Therefore, a shooting device that supports the tracking algorithm has a high demand for its own hardware resources, which increases the hardware cost and power consumption of the shooting device.
  • the present application provides a method, device and computer-readable storage medium for running a tracking algorithm, which can solve the problems in the prior art that photographing equipment has high demands on its own hardware resources and increase the hardware cost and power consumption of photographing equipment .
  • an embodiment of the present application provides a method for running a tracking algorithm, which is applied to a terminal device, including:
  • the device operation information determine that the terminal device and/or the photographing device run the tracking algorithm
  • the photographing device In a case where it is determined that the tracking algorithm is run by the photographing device, the photographing device is notified to run the tracking algorithm.
  • an embodiment of the present application provides a method for running a tracking algorithm, which is applied to a photographing device, including:
  • the photographing device is controlled to perform a tracking operation.
  • an embodiment of the present application provides a method for running a tracking algorithm, which is applied to a photographing device, including:
  • the device operation information determine that the terminal device and/or the photographing device run the tracking algorithm
  • the photographing device is controlled to perform a tracking operation.
  • an embodiment of the present application provides a method for running a tracking algorithm, which is applied to a terminal device, including:
  • an embodiment of the present application provides a device for running a tracking algorithm, which is applied to a photographing device, including:
  • the memory is used to obtain equipment operation information of the terminal equipment and the photographing equipment;
  • the processor is configured to: determine, according to the device operation information, that the terminal device and/or the photographing device run a tracking algorithm;
  • the photographing device In a case where it is determined that the tracking algorithm is run by the photographing device, the photographing device is notified to run the tracking algorithm.
  • an embodiment of the present application provides a device for running a tracking algorithm, which is applied to a photographing device, including:
  • the processor is used to:
  • the photographing device is controlled to perform a tracking operation.
  • an embodiment of the present application provides a device for running a tracking algorithm, which is applied to a photographing device, including:
  • the memory is used to obtain equipment operation information of the terminal equipment and the photographing equipment;
  • the processor is used to:
  • the device operation information determine that the terminal device and/or the photographing device run the tracking algorithm
  • the photographing device is controlled to perform a tracking operation.
  • an embodiment of the present application provides an apparatus for running a tracking algorithm, which is applied to a terminal device, including:
  • the memory is configured to receive a notification for running the tracking algorithm sent by the photographing device;
  • the processor is used to:
  • the present application provides an electronic device, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor to achieve the above the method described in the aspect.
  • the present application provides a computer-readable storage medium, wherein the computer-readable storage medium includes instructions, which, when executed on a computer, cause the computer to perform the method described in the above aspects.
  • the present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method described in the above aspects.
  • the present application determines that the terminal equipment and/or the photographing equipment run tracking by analyzing the respective equipment operation information of the terminal equipment and the photographing equipment on the basis of not affecting the normal operation of the terminal equipment and the photographing equipment.
  • the algorithm ensures the operation stability of the terminal equipment and the shooting equipment, and then can use the hardware resources and computing power of the terminal equipment to assist in the realization of the tracking algorithm, so as to avoid attaching all the computing power pressure to the shooting equipment and avoid shooting.
  • the device greatly increases its own hardware cost and power consumption.
  • FIG. 1 is an architecture diagram of a running system of a tracking algorithm provided by an embodiment of the present application
  • FIG. 2 is a flowchart of steps of a method for running a tracking algorithm on a terminal device side provided by an embodiment of the present application;
  • FIG. 3 is a flowchart of steps of a method for running a tracking algorithm on a shooting device side provided by an embodiment of the present application;
  • FIG. 4 is a flow chart of interactive steps of a method for running a tracking algorithm provided by an embodiment of the present application
  • FIG. 5 is a flowchart of steps of another method for running a tracking algorithm on the shooting device side provided by an embodiment of the present application;
  • FIG. 6 is a flowchart of steps of another method for running a tracking algorithm on the terminal device side provided by an embodiment of the present application;
  • FIG. 7 is a block diagram of an apparatus for running a tracking algorithm on a terminal device side provided by an embodiment of the present application.
  • FIG. 8 is a block diagram of an apparatus for running a tracking algorithm on a photographing device side provided by an embodiment of the present application
  • Fig. 9 is the block diagram of the running device of the tracking algorithm of another kind of photographing equipment side provided by the embodiment of the present application.
  • FIG. 10 is a block diagram of an apparatus for running another tracking algorithm on the terminal device side provided by an embodiment of the present application.
  • FIG. 1 shows a framework diagram of a running system of a tracking algorithm provided by an embodiment of the present application.
  • the running system of the tracking algorithm includes a shooting device 10 and a terminal device 20, and the shooting device 10 and the terminal device 20 can be connected to each other in communication. , wherein, both the shooting device 10 and the terminal device 20 may have a built-in tracking algorithm.
  • the tracking algorithm is used to perceive and track the target object in the shooting scene.
  • the tracking algorithm can be implemented based on the image collected by the shooting device 10. Accurate labeling of objects to achieve the purpose of perceiving and tracking target objects.
  • the terminal device 20 can realize some operations such as the configuration of the tracking algorithm and the control of the tracking function.
  • the shooting device 10 and the terminal device 20 each have certain hardware resources and computing power, but The photographing device 10 has consumed a certain amount of hardware resources and computing power in the process of realizing image acquisition.
  • the photographing device 10 needs to increase the hardware resources and computing power accordingly, resulting in an increase in cost and power consumption. , it is difficult to meet the balance between cost and performance.
  • the hardware resources and computing power of the terminal device 20 can be used to transfer the tracking algorithm to the terminal device when the hardware resources and computing power of the shooting device 10 cannot satisfy its own normal shooting and tracking functions at the same time. 20, and according to the communication connection with the terminal device 20, the operation result of the terminal device 20 after the tracking algorithm is implemented is obtained, so that the tracking function can be realized by using the hardware resources and computing power of the terminal device itself, avoiding the shooting equipment. Costs and power consumption have risen dramatically.
  • the implementation of the tracking algorithm in the terminal device 20 also needs not to affect its own normal operation.
  • the tracking algorithm can also be transferred to the shooting device 10 for implementation.
  • the user can also choose to run the tracking algorithm by the photographing device 10 or the terminal device 20 according to actual needs, which is not limited in this embodiment of the present application.
  • FIG. 2 is a flowchart of a method for running a tracking algorithm provided by an embodiment of the present application, which is applied to a terminal device. As shown in FIG. 2 , the method may include:
  • Step 101 Acquire device operation information of the terminal device and the photographing device.
  • the terminal device and the photographing device each have corresponding device operation information, and the device operation information is used to reflect the operation status of the device, and is a kind of index data.
  • the device operation information may include the current hardware resources of the device. Load parameters, device-to-device communication status parameters, etc.
  • the terminal device may be a device that maintains a communication connection with the photographing device, may receive device operation information of the photographing device sent by the photographing device, and collect its own device operation information.
  • Step 102 According to the device operation information, determine that the terminal device and/or the photographing device run the tracking algorithm.
  • both the terminal device and the shooting device have built-in tracking algorithms, and the conditions that need to be satisfied during the implementation of the tracking algorithm include: further utilizing the hardware resources and computing power of the terminal device to assist in the realization of the tracking algorithm, The realization does not affect the normal operation of the terminal equipment and the shooting equipment, and avoids the shooting equipment greatly improving its own hardware foundation and power consumption due to the implementation of the tracking algorithm.
  • the terminal equipment can determine the respective operating conditions of the terminal equipment and the photographing equipment according to the equipment operation information of the terminal equipment and the photographing equipment, and according to the operating conditions, on the basis of satisfying the above conditions, decide whether to use the terminal equipment and/or the photographing equipment. Or the camera device runs the tracking algorithm.
  • the terminal equipment can determine the current load conditions of the terminal equipment and the photographing equipment by analyzing the equipment operation information, and when the load condition of the photographing equipment is too high , choose to run the tracking algorithm by the terminal device; when the load condition of the terminal device is too high, choose to run the tracking algorithm by the shooting device, which will prevent one party from affecting the normal operation of the device itself due to the high load condition.
  • the terminal equipment can determine the communication status between the terminal equipment and the photographing equipment by analyzing the equipment operation information.
  • the device runs the tracking algorithm, which will prevent the shooting device from being unable to achieve the tracking function due to the inability to communicate with the terminal device normally.
  • the terminal device can also determine that the terminal device and the shooting device run their respective tracking algorithms, and the terminal device can use the calculation result obtained first, so that the device can The competition between hardware resources and computing power can get the results of the tracking algorithm faster.
  • Step 103 If it is determined that the tracking algorithm is run by the terminal device, run the tracking algorithm to obtain a calculation result, and send the calculation result to the photographing device.
  • the hardware resources and computing power of the terminal device can be used to run the tracking algorithm, thereby reducing the computing power pressure of the shooting device.
  • the calculation result of the tracking algorithm needs to be returned to the shooting device for subsequent tracking operations, the calculation result can be returned to the shooting device after the terminal device obtains the calculation result;
  • the photographing device may be further controlled to perform the subsequent tracking operation according to the calculation result.
  • Step 104 In the case that it is determined that the tracking algorithm is run by the photographing device, notify the photographing device to run the tracking algorithm.
  • a notification instruction can be sent to the shooting device, so that the shooting device can run the tracking algorithm according to the notification instruction, and the calculation result of the tracking algorithm needs to be processed by the shooting device.
  • the shooting device can further control the subsequent tracking operations according to the calculation results; in addition, the results of the tracking algorithm need to be obtained by the terminal device for it to control the shooting.
  • the device performs a subsequent tracking operation after the photographing device obtains the calculation result, the calculation result can be returned to the terminal device, and the terminal device can control the subsequent tracking operation of the photographing device according to the calculation result.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • FIG. 3 is a flowchart of steps of a method for running a tracking algorithm provided by an embodiment of the present application, which is applied to a photographing device, and the method may include:
  • Step 201 Send device operation information of the photographing device to the terminal device.
  • the terminal device and the photographing device each have corresponding equipment operation information
  • the equipment operation information is used to reflect the operation status of the equipment
  • the photographing device can send the equipment operation information to the terminal after acquiring its own equipment operation information equipment, so that the terminal equipment can determine the operation status of the photographing equipment according to the equipment operation information.
  • Step 202 In the case of receiving the notification sent by the terminal device for running the tracking algorithm, run the tracking algorithm to obtain a calculation result, or receive the calculation result sent by the terminal device.
  • Step 203 Control the photographing device to perform a tracking operation according to the calculation result.
  • the photographing device in the case where the calculation result of the tracking algorithm needs to be processed by the photographing device so that it can perform subsequent tracking operations, after the photographing device runs the tracking algorithm and obtains the calculation result, the photographing device can further execute the tracking algorithm according to the calculation result.
  • the calculation result controls the subsequent tracking operation; or after the terminal device runs the tracking algorithm and obtains the calculation result, the photographing device receives the calculation result sent by the terminal device, and the photographing device controls the subsequent tracking operation according to the calculation result.
  • the result of the tracking algorithm needs to be acquired by the terminal device for it to control the shooting device to perform subsequent tracking operations
  • the shooting device obtains the calculation result
  • the calculation result can be returned to the terminal device, and the terminal device can calculate the result according to the calculation result.
  • the result controls the subsequent tracking operation of the photographing device.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • FIG. 4 is a flow chart of interactive steps of a method for running a tracking algorithm provided by an embodiment of the present application, and the method may include:
  • Step 301 The photographing device sends the device operation information of the photographing device to the terminal device.
  • Step 302 The terminal device acquires device operation information of the terminal device and the photographing device.
  • Step 303 The terminal device determines the type of the transmission channel with the photographing device.
  • a communication connection between a terminal device and a photographing device forms a data transmission channel.
  • the type of the transmission channel has a great influence on the quality of data transmission between the terminal device and the photographing device.
  • the shooting device needs to send the collected tracking data to the terminal device through the transmission channel. After the terminal device obtains the calculation result, it also needs to pass The transmission channel sends the calculation results to the shooting device. If the communication quality of the transmission channel is poor, there will be delays and packet loss in data transmission, which will greatly affect the experience of the tracking function.
  • the camera device runs a tracking algorithm.
  • the type of transmission channel may include a Universal Serial Bus (USB, Universal Serial Bus) connection channel, a 5G connection channel, and the like.
  • USB Universal Serial Bus
  • 5G 5th Generation
  • USB Universal Serial Bus
  • Step 304 in the case that the terminal device is of the first type, proceed to step 306 .
  • the first type includes: USB connection channel, 5G connection channel.
  • connection channel belonging to the first type has characteristics such as high stability and low transmission delay. Therefore, when the type of the transmission channel between the terminal device and the photographing device is the first type, it can be considered that The quality of the data transmission between the two is relatively high.
  • step 306 may be entered to realize that the terminal device and/or the photographing device run the tracking algorithm according to the device operation information.
  • the first type may also include other types of connection channels with characteristics of high stability and low transmission delay.
  • Step 305 In the case that the type is the second type, the terminal device determines that the tracking algorithm is run by the photographing device.
  • the second category includes: other connection channels except the USB connection channel and the 5G connection channel.
  • the connection channel belonging to the second type has relatively poor stability and high transmission delay.
  • ordinary wireless hotspot connection channels, 4G connection channels, etc. all have poor stability and transmission delay.
  • the characteristic of high delay is that under the second type of connection channel, the quality of data transmission between the terminal device and the shooting device is poor. Due to the high probability of high delay and high packet loss rate, it cannot satisfy the tracking algorithm for data. Therefore, in this case, the tracking algorithm can be run directly by the shooting device, that is, the shooting device obtains the tracking data, runs the tracking algorithm according to the tracking data, obtains the calculation result, and finally performs the tracking operation according to the calculation result. , so that in the whole process of implementing the tracking algorithm, the data transmission with the terminal device is minimized, so as to ensure the stability of the tracking algorithm implementation process.
  • Step 306 The terminal device determines, according to the device operation information, that the terminal device and/or the photographing device run the tracking algorithm.
  • the device operation information includes: current load information; step 306 may specifically include:
  • Sub-step 3061 In the case that the current load information of the terminal device does not meet the algorithm running condition, determine that the tracking algorithm is run by the photographing device.
  • the device operation information may include: current load information.
  • the current load information may reflect the current utilization rate of the hardware resources of the device. If the current load information of the device is too high, it will affect the device. The normal operation of the device will increase the power consumption of the device, causing the device to heat up seriously and reducing the battery life.
  • the preset threshold may be set according to actual requirements. For example, when the current load information is in the form of percentage usage, the preset threshold may be a percentage value such as 80% or 90%.
  • Sub-step 3062 In the case that the current load information of the photographing device does not meet the algorithm running condition, determine that the tracking algorithm is run by the terminal device.
  • the current load information of the terminal device is less than a preset threshold, it can be considered that the hardware resources of the terminal device are sufficient and the algorithm running conditions are met. At this time, it can be determined that the terminal device runs the tracking algorithm, so that the hardware resources of the terminal device can be utilized. and computing power to assist in the implementation of the tracking algorithm, avoiding adding all the computing power pressure to the shooting device, and avoiding the shooting device's substantial increase in hardware cost and power consumption in order to force the tracking algorithm.
  • step 306 may further include:
  • Sub-step 3063 when the current load information of the terminal device and the photographing device both satisfy the algorithm running condition, the terminal device determines that the tracking algorithm is run by the terminal device and the photographing device at the same time.
  • the terminal device may determine that the tracking algorithm is run by the terminal device and the photographing device at the same time, that is, the terminal device and the photographing device run the respectively stored tracking algorithms at the same time, and obtain their respective calculation results.
  • the hardware resources and computing power of the terminal device and the shooting device are different, so that the speed at which the two process the tracking algorithm to obtain the calculation result is different from each other.
  • the calculation results obtained by the first calculation can be used, so that the calculation results of the tracking algorithm can be obtained faster through the competition of hardware resources and computing power between devices, which improves the calculation efficiency.
  • the acquisition speed of the results improves the implementation effect of the tracking algorithm.
  • the terminal device when the computing power of the terminal device is stronger, the terminal device obtains the calculation result and sends the calculation result to the photographing device, so that the time when the photographing device calculates the calculation result by itself is later than the time when the photographing device receives the calculation result sent by the terminal device.
  • the time of the result enables the photographing device to use the calculation result sent by the terminal device to perform the tracking operation, so that the photographing device has a faster acquisition speed of the calculation result.
  • Sub-step 3064 the terminal device sends a simultaneous operation notification to the photographing device.
  • the terminal device can send a simultaneous operation notification to the photographing device for the photographing device to run the tracking algorithm in parallel with the terminal device according to the simultaneous operation notification.
  • the tracking algorithm includes: a first tracking algorithm deployed on the terminal device and a second tracking algorithm deployed on the photographing device, and after sub-step 3064, may also include:
  • Sub-step 3065 the terminal device runs the first tracking algorithm to obtain a first calculation result, and sends the first calculation result to the photographing device.
  • Sub-step 3066 the terminal device notifies the shooting device to run the second tracking algorithm.
  • different tracking algorithms may be deployed in the terminal device and the photographing device respectively, and when it is determined that the tracking algorithm is run by the terminal device and the photographing device at the same time, the terminal device runs the first tracking algorithm to obtain the first tracking algorithm. Calculate the result, send the first calculation result to the shooting device, and notify the shooting device to run the second tracking algorithm to obtain the second calculation result by the terminal device, so that the shooting device can obtain the second calculation result from the first calculation result and the second calculation result according to the actual demand. Select a calculation result from to control the tracking operation.
  • the first tracking algorithm may be an algorithm deployed for hardware resources and computing power characteristics of the terminal device
  • the second tracking algorithm may be an algorithm deployed for hardware resources and computing power characteristics of the photographing device.
  • the first tracking algorithm may be a tracking algorithm for human objects
  • the second tracking algorithm may be a tracking algorithm for building objects. Then, when the photographing device needs to track a human object, the first calculation result can be selected, and when the photographing device needs to track a building object, the second calculation result can be selected.
  • the device operation information includes current load information and network bandwidth; step 306 may specifically include:
  • Sub-step 3067 the terminal device determines the transmission delay of the transmission channel with the photographing device according to the current load information and the network bandwidth.
  • the tracking function if it is necessary to use the hardware resources and computing power of the terminal device to assist in the implementation of the tracking algorithm, data interaction between the terminal device and the shooting device needs to be performed.
  • the transmission delay of the transmission channel between the shooting devices is as low as possible to ensure the timeliness of the data.
  • the device operation information may further include the network bandwidth of the device on the basis of the current load information, and the terminal device may determine, according to the current load information and the network bandwidth, Transmission delay, so as to determine the data transmission quality between the terminal device and the shooting device according to the size of the transmission delay.
  • Sub-step 3068 the terminal device proceeds to step 306 when the transmission delay is less than or equal to the preset delay threshold.
  • the terminal device may consider that the data transmission quality between the terminal device and the photographing device is better, and at this time, step 306 may be entered to realize the The device determines, according to the device operation information, that the terminal device and/or the photographing device run the tracking algorithm.
  • Sub-step 3069 In the case that the transmission delay is greater than the preset delay threshold, the terminal device determines that the tracking algorithm is run by the photographing device.
  • the terminal device may consider that the quality of data transmission between the terminal device and the photographing device is poor, and the phenomenon of high delay and high packet loss rate is likely to occur.
  • the tracking algorithm can be run directly by the shooting device, that is, the tracking data is obtained by the shooting device, and the tracking algorithm is run according to the tracking data to obtain the calculation result.
  • the calculation result is tracked, so that in the whole process of implementing the tracking algorithm, the data transmission with the terminal device is minimized, so as to ensure the stability of the tracking algorithm implementation process.
  • Step 307 If it is determined that the tracking algorithm is run by the terminal device, the terminal device runs the tracking algorithm to obtain a calculation result, and sends the calculation result to the photographing device.
  • step 307 may specifically include:
  • Sub-step 3071 the terminal device determines the current target application scenario when it is determined that the tracking algorithm is run by the terminal device.
  • the terminal device since the terminal device itself has the characteristics of richness of hardware resources and computing power, this characteristic can be used to arrange more personalized functions for the tracking algorithm on the terminal device. Specifically, the terminal device can Based on the analysis of historical usage data or user requirements, a number of different application scenarios are determined, and the tracking algorithm applicable to each application scenario is determined, and the corresponding relationship between the application scenario and the tracking algorithm is established locally.
  • the terminal device can determine the current target application scenario by collecting the surrounding environment information or the user's designated operation.
  • Sub-step 3072 the terminal device determines a target tracking algorithm corresponding to the target application scenario according to the corresponding relationship.
  • the target tracking algorithm corresponding to the target application scenario can be further determined from the corresponding relationship.
  • Sub-step 3073 the terminal device runs the target tracking algorithm to obtain the calculation result.
  • the purpose of automatically selecting an adapted target tracking algorithm according to the current target application scenario of the terminal device can be achieved, and the target tracking algorithm corresponding to different application scenarios is provided.
  • Personalized definitions improve user experience.
  • step 307 may specifically include:
  • Sub-step 3074 In the case where it is determined that the tracking algorithm is run by the terminal device, the terminal device sends a tracking data acquisition request to the photographing device.
  • Sub-step 3075 in the case of receiving the tracking data sent by the photographing device according to the tracking data acquisition request, the terminal device calculates and obtains the calculation result according to the tracking data and the tracking algorithm.
  • the tracking algorithm may be calculated based on the tracking data collected by the photographing device to obtain corresponding calculation results.
  • the tracking data collected by the photographing device may include image data, point cloud data and other types of data.
  • the terminal device needs to send the tracking data acquisition request to the shooting device to obtain the tracking data collected by the shooting device, and calculate the calculation result according to the tracking data and the tracking algorithm.
  • the photographing device can calculate and obtain the calculation result according to the tracking data and the tracking algorithm.
  • sub-step 3075 may specifically include:
  • Sub-step 30751 the terminal device identifies the target entity object in the tracking image generated by the tracking data.
  • Sub-step 30752 After adding an object frame to the target entity object in the tracking image, the terminal device obtains the calculation result, where the object frame is used to reflect the location of the target entity object.
  • the implementation of the tracking algorithm is: in the calculation result of the tracking algorithm, it is necessary to realize the tracking of the target entity object in the scene, the terminal device can generate the tracking image according to the tracking data collected by the shooting device, and the tracking image reflects the scene, Further, the terminal device can identify the target entity object in the generated tracking image, and add an object frame to the target entity object to obtain a tracking image reflecting the scene, the target entity object in the tracking image, and reflect the location of the target entity object. The result of the calculation of the object frame. After obtaining the calculation result, the shooting device can further adjust the shooting angle and direction according to the position of the target physical object in the scene, so as to maintain the tracking shooting of the target physical object.
  • Step 308 In a case where it is determined that the tracking algorithm is run by the photographing device, the terminal device notifies the photographing device to run the tracking algorithm.
  • Step 309 The photographing device runs the tracking algorithm to obtain a calculation result when it receives the notification sent by the terminal device for running the tracking algorithm, or receives the calculation result sent by the terminal device.
  • Step 310 The photographing device controls the photographing device to perform a tracking operation according to the calculation result.
  • step 310 may specifically include:
  • Sub-step 3101 When receiving the simultaneous calculation notification sent by the terminal device, the photographing device determines to first receive the calculation result sent by the terminal device, or determines to first obtain the calculation result according to the simultaneous calculation notification.
  • the terminal device may determine that the tracking algorithm is run by the terminal device and the photographing device at the same time, that is, the terminal device and the photographing device run the respectively stored tracking algorithms at the same time, and obtain their respective calculation results. After obtaining the calculation result, the terminal device will send the calculation result to the photographing device.
  • the hardware resources and computing power of the terminal device and the shooting device are different, so that the speed at which the two process the tracking algorithm to obtain the calculation result is different from each other.
  • the calculation results obtained by the first calculation can be used, so that the calculation results of the tracking algorithm can be obtained faster through the competition of hardware resources and computing power between devices, which improves the calculation efficiency.
  • the acquisition speed of the results improves the implementation effect of the tracking algorithm.
  • the photographing device can determine that the calculation result obtained first is the calculation result sent by the terminal device, or the calculation result obtained by the photographing device according to the simultaneous operation notification. Therefore, the photographing device can have two judgment results.
  • Sub-step 3102 when the photographing device determines that the calculation result is obtained by calculating according to the simultaneous operation notification, the photographing device controls the photographing device to perform the tracking operation by using the calculation result obtained by the calculation by the photographing device.
  • the photographing device may consider that the computing power of the photographing device is stronger, so that the time for the photographing device to calculate the calculation result by itself is earlier than the time when the photographing device receives the calculation sent by the terminal device.
  • the time of the result enables the photographing device to use the calculation result calculated by itself to perform the tracking operation, so that the photographing device has a faster acquisition speed of the calculation result.
  • Sub-step 3103 In the case where the photographing device determines to receive the calculation result sent by the terminal device first, the photographing device uses the calculation result sent by the terminal device to control the photographing device to perform the tracking operation.
  • the photographing device may consider that the computing power of the terminal device is stronger, and the terminal device obtains the calculation result and sends the calculation result to the photographing device, so that the photographing device can obtain the calculation result by itself.
  • the time is later than the time when the photographing device receives the calculation result sent by the terminal device, so that the photographing device can use the calculation result sent by the terminal device to perform the tracking operation, so that the photographing device has a faster acquisition speed of the calculation result.
  • the tracking algorithm includes: a first tracking algorithm deployed on the terminal device and a second tracking algorithm deployed on the photographing device; step 310 may specifically include:
  • Sub-step 3104 The photographing device receives the first calculation result for the first tracking algorithm sent by the terminal device.
  • Sub-step 3105 The photographing device runs the second tracking algorithm to obtain a second calculation result when receiving the notification sent by the terminal device for running the second tracking algorithm.
  • Sub-step 3106 the photographing device selects one calculation result from the first calculation result and the second calculation result, and controls the photographing device to perform a tracking operation according to the selected calculation result.
  • different tracking algorithms may be deployed in the terminal device and the photographing device respectively, and when it is determined that the tracking algorithm is run by the terminal device and the photographing device at the same time, the terminal device runs the first tracking algorithm to obtain the first tracking algorithm. Calculate the result, send the first calculation result to the shooting device, and notify the shooting device to run the second tracking algorithm to obtain the second calculation result by the terminal device, so that the shooting device can obtain the second calculation result from the first calculation result and the second calculation result according to the actual demand. Select a calculation result from to control the tracking operation.
  • the first tracking algorithm may be an algorithm deployed for hardware resources and computing power characteristics of the terminal device
  • the second tracking algorithm may be an algorithm deployed for hardware resources and computing power characteristics of the photographing device.
  • sub-step 3106 may specifically include:
  • Sub-step 31061 The photographing device identifies the entity object in the tracking image captured by the photographing device, and the tracking image is generated from the tracking data collected by the photographing device.
  • the photographing device when it is determined that the tracking algorithm is run by the photographing device, the photographing device can identify the entity objects, such as human objects, building objects, etc., in the tracking images photographed by the photographing device.
  • Sub-step 31062 When the number of the first physical objects included in the tracking screen is greater than a first number threshold, the photographing device selects the first calculation result to control the photographing device to perform a tracking operation.
  • the shooting device may consider that the current shooting scene is more suitable for the first tracking algorithm for identifying the first physical object, and the shooting device may select the The first calculation result controls the shooting device to perform the tracking operation, thereby improving the adaptability of the tracking algorithm to the shooting scene containing more first physical objects.
  • Sub-step 31063 when the number of second physical objects contained in the tracking screen is greater than a second number threshold, the photographing device selects the second calculation result to control the photographing device to perform a tracking operation.
  • the shooting device may consider that the current shooting scene is more suitable for the second tracking algorithm for recognizing the second physical object, and the shooting device may select the The second calculation result controls the shooting device to perform the tracking operation, thereby improving the adaptability of the tracking algorithm to the shooting scene containing more second physical objects.
  • sub-step 3106 may further include:
  • Sub-step 31064 when the tracking screen contains both the first entity object and the second entity object, the shooting device fuses the first calculation result and the second calculation result to obtain the target calculation result.
  • Sub-step 31065 the photographing device controls the photographing device to perform a tracking operation according to the target calculation result.
  • the The device can fuse the first calculation result of identifying the first entity object and the second calculation result of identifying the second entity object to obtain the target calculation result, in which the positions of the first entity object and the second entity object are simultaneously calculated.
  • the labeling enables high-precision tracking of the first entity object and the second entity object in subsequent tracking operations of the photographing device.
  • the calculation result includes: in the tracking image generated by the tracking data collected by the photographing device, an object frame corresponding to the target entity object, where the object frame is used to reflect the location of the target entity object; the The photographing device has a PTZ; step 310 may specifically include:
  • the photographing device calculates the target movement vector value according to the position information of the object frame.
  • Sub-step 3108 the photographing device controls the movement of the pan/tilt according to the target movement vector value, so as to realize the tracking photographing of the target entity object by the photographing device.
  • the tracking algorithm may be calculated based on the tracking data collected by the photographing device to obtain corresponding calculation results.
  • the tracking data collected by the photographing device may include image data, point cloud data and other types of data.
  • the data and the calculation result obtained by the tracking algorithm include the tracking image reflecting the shooting scene, and the object frame corresponding to the target entity object in the tracking image, and the object frame can reflect the location of the target entity object.
  • the shooting device can calculate the target movement vector value required for the movement of the pan-tilt according to the position of the target entity object in the scene, and further adjust the movement of the pan-tilt according to the target movement vector value, so as to keep the target moving. Tracking shots of solid objects.
  • the method may also include:
  • Step A1 The terminal device receives a new tracking algorithm through a preset custom interface.
  • Step A2 The terminal device adds the new tracking algorithm locally, or replaces the local tracking algorithm with the new tracking algorithm.
  • the terminal device itself has the characteristics of rich hardware resources and computing power, this characteristic can be used to arrange more personalized functions for the tracking algorithm on the terminal device. Further, you can also preset custom functions on the terminal device. Interface, through this custom interface, the terminal device can receive the new tracking algorithm sent by the external device, so that the local storage of the terminal device has multiple tracking algorithms, or replace the original tracking algorithm with the new tracking algorithm, so as to satisfy the user's requirement for different tracking algorithms. The individual needs of the algorithm.
  • the method may also include:
  • Step B1 When receiving the tracking data acquisition request sent by the terminal device, the photographing device sends the tracking data collected by the photographing device to the terminal device.
  • the tracking algorithm may be calculated based on the tracking data collected by the photographing device to obtain corresponding calculation results.
  • the tracking data collected by the photographing device may include image data, point cloud data and other types of data.
  • the terminal device needs to obtain the tracking data collected by the shooting device by sending the tracking data acquisition request to the shooting device.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • Fig. 5 is the step flow chart of the operation method of a kind of tracking algorithm that the embodiment of the present application provides, is applied to photographing equipment, and this method can include:
  • Step 401 Acquire device operation information of the terminal device and the photographing device.
  • Step 402 According to the device operation information, determine that the terminal device and/or the photographing device run the tracking algorithm.
  • Step 403 In the case that it is determined that the tracking algorithm is run by the terminal device, notify the terminal device to run the tracking algorithm, and receive the calculation result sent by the terminal device.
  • Step 404 In the case where it is determined that the tracking algorithm is run by the photographing device, run the tracking algorithm to obtain a calculation result.
  • Step 405 Control the photographing device to perform a tracking operation according to the calculation result.
  • a function for deciding whether to run the tracking algorithm by the terminal device and/or the photographing device can also be set on the photographing device, so that the photographing device can make a decision by the terminal according to the terminal device and the device operation information of the photographing device.
  • the device and/or the photographing device runs the tracking algorithm, and the specific implementation details may refer to the descriptions of the foregoing embodiments, which will not be repeated here.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • FIG. 6 is a flowchart of steps of a method for running a tracking algorithm provided by an embodiment of the present application, which is applied to a terminal device, and the method may include:
  • Step 501 In the case of receiving a notification sent by the photographing device for running the tracking algorithm, run the tracking algorithm to obtain a calculation result.
  • Step 502 Send the calculation result to the photographing device.
  • the terminal device can run the tracking algorithm through its own Hardware resources and computing power are used to assist in the implementation of the tracking algorithm, so as to avoid adding all the computing power pressure to the shooting device.
  • the specific implementation details can refer to the description of the above embodiment, which will not be repeated here.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • an apparatus 600 for running a tracking algorithm may include: a memory 601 and a processor 602;
  • the memory 601 is used to obtain the device operation information of the terminal device and the photographing device;
  • the processor 602 is configured to: determine, according to the device operation information, that the terminal device and/or the photographing device run a tracking algorithm;
  • the photographing device In a case where it is determined that the tracking algorithm is run by the photographing device, the photographing device is notified to run the tracking algorithm.
  • the device operation information includes: current load information; the processor is specifically configured to:
  • the processor is also used for:
  • the tracking algorithm includes: a first tracking algorithm deployed on the terminal device and a second tracking algorithm deployed on the photographing device; the processor is further configured to:
  • the photographing device is notified to run the second tracking algorithm.
  • the device operation information includes current load information and network bandwidth; the processor is also used for:
  • the transmission delay is less than or equal to the preset delay threshold, enter the step of determining that the terminal device and/or the photographing device run the tracking algorithm according to the device operation information;
  • the transmission delay is greater than the preset delay threshold, it is determined that the tracking algorithm is run by the photographing device.
  • the processor is also used for:
  • the type is the first type, enter the step of determining that the terminal device and/or the photographing device run the tracking algorithm according to the device operation information;
  • the type is the second type, determining that the tracking algorithm is run by the photographing device;
  • the first type includes: a USB connection channel and a 5G connection channel
  • the second type includes: other connection channels except the USB connection channel and the 5G connection channel.
  • the processor is also used for:
  • the new tracking algorithm is added locally, or the local tracking algorithm is replaced with the new tracking algorithm.
  • a corresponding relationship between an application scenario and a tracking algorithm is established locally on the terminal device; the processor is specifically used for:
  • the calculation result is obtained by running the target tracking algorithm.
  • the processor is specifically used for:
  • the calculation result is obtained by calculation according to the tracking data and the tracking algorithm.
  • the processor is specifically used for:
  • the calculation result is obtained, and the object frame is used to reflect the location of the target entity object.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • an apparatus 700 for running a tracking algorithm may include: a memory 701 and a processor 702;
  • the processor is used 702 to:
  • the photographing device is controlled to perform a tracking operation.
  • the processor is also used for:
  • the processor is specifically used for:
  • the shooting device is controlled to perform the tracking operation by using the calculation result sent by the terminal device.
  • the tracking algorithm includes: a first tracking algorithm deployed on the terminal device and a second tracking algorithm deployed on the shooting device; the memory is used for:
  • the processor is also used to:
  • the processor is specifically used for:
  • One calculation result is selected from the first calculation result and the second calculation result, and the photographing device is controlled to perform a tracking operation according to the selected calculation result.
  • the first tracking algorithm is used to identify the first entity object
  • the second tracking algorithm is used to identify the second entity object
  • the processor is specifically used for:
  • the processor is also used for:
  • the first calculation result and the second calculation result are fused to obtain a target calculation result
  • the photographing device is controlled to perform a tracking operation according to the target calculation result.
  • the processor is also used for:
  • the tracking data collected by the photographing device is sent to the terminal device.
  • the calculation result includes: in the tracking image generated by the tracking data collected by the photographing device, an object frame corresponding to the target entity object, where the object frame is used to reflect the location of the target entity object;
  • the photographing device has a PTZ; the processor is specifically used for:
  • the movement of the pan/tilt is controlled according to the target movement vector value, so as to realize the tracking shooting of the target entity object by the shooting device.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • FIG. 9 is a block diagram of an apparatus for running a tracking algorithm provided by an embodiment of the present application, which is applied to a photographing device.
  • an apparatus 800 for running the tracking algorithm may include: a memory 801 and a processor 802;
  • the memory 801 is used to obtain device operation information of the terminal device and the photographing device;
  • the processor 802 is used to:
  • the device operation information determine that the terminal device and/or the photographing device run the tracking algorithm
  • the photographing device is controlled to perform a tracking operation.
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • FIG. 10 is a block diagram of an apparatus for running a tracking algorithm provided by an embodiment of the present application, which is applied to a photographing device.
  • an apparatus 900 for running the tracking algorithm may include: a memory 901 and a processor 902;
  • the memory 901 is configured to receive a notification for running the tracking algorithm sent by the photographing device;
  • the processor 902 is used to:
  • the present application determines the operation information of the terminal device and the photographing device respectively without affecting the normal operation of the terminal device and the photographing device.
  • the tracking algorithm is run by the terminal device and/or the shooting device, thus ensuring the operation stability of the terminal device and the shooting device, and then the hardware resources and computing power of the terminal device can be used to assist in the implementation of the tracking algorithm, avoiding all computing power pressure. All of them are attached to the shooting equipment, which avoids the shooting equipment from greatly increasing its own hardware cost and power consumption in order to force the tracking algorithm.
  • Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, each process of the above-mentioned method for running the tracking algorithm is implemented, and can achieve the same In order to avoid repetition, the technical effect will not be repeated here.
  • the computer-readable storage medium such as read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), magnetic disk or optical disk and so on.
  • the memory may be an interface between the external control terminal and the running device of the tracking algorithm.
  • the external control terminal may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a control terminal with an identification module, an audio input /Output (I/O) ports, video I/O ports, headphone ports, and more.
  • the memory may be used to receive input (eg, data information, power, etc.) from an external control terminal and transmit the received input to one or more elements within the execution device of the tracking algorithm or may be used in the execution of the tracking algorithm Data transfer between the device and an external control terminal.
  • At least one magnetic disk storage device For example at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • the processor is the control center of the control terminal. It uses various interfaces and lines to connect various parts of the entire control terminal, and executes control by running or executing the software programs and/or modules stored in the memory and calling the data stored in the memory. Various functions of the terminal and processing data, so as to carry out overall monitoring of the control terminal.
  • the processor may include one or more processing units; preferably, the processor may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor Mainly deals with wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor.
  • the embodiments of the present application may be provided as a method, a control terminal, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer readable memory result in an article of manufacture comprising the instruction to control the terminal,
  • the instruction controls the terminal to implement the function specified in one flow or multiple flows of the flowchart and/or one block or multiple blocks of the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Studio Devices (AREA)

Abstract

一种追踪算法的运行方法、装置及计算机可读存储介质,方法包括:获取终端设备和拍摄设备的设备运行信息(101);根据设备运行信息,确定由终端设备和/或拍摄设备运行追踪算法(102);在确定由终端设备运行追踪算法的情况下,运行追踪算法得到计算结果,并将计算结果发送至拍摄设备(103);在确定由拍摄设备运行追踪算法的情况下,通知拍摄设备运行追踪算法(104)。本申请可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。

Description

追踪算法的运行方法、装置、电子设备及计算机可读存储介质 技术领域
本申请涉及计算机技术领域,特别是涉及一种追踪算法的运行方法、装置、电子设备及计算机可读存储介质。
背景技术
在自动驾驶、辅助驾驶、自动测绘等领域都会运用追踪算法,追踪算法可以实现对环境中目标对象的位置、运动参数等数据的追踪。
在目前方案中,追踪算法可以内置在用于实现目标对象的追踪的拍摄设备内部,拍摄设备可以对目标对象所处的环境进行拍摄,并基于内置的追踪算法和拍摄设备自身的硬件资源,对目标对象的位置、运动参数等数据进行追踪获取。
但是,追踪算法对硬件资源具有一定的需求,因此支持追踪算法的拍摄设备对自身的硬件资源具有较高的需求,提高了拍摄设备的硬件成本和功耗。
发明内容
本申请提供一种追踪算法的运行方法、装置及计算机可读存储介质,可以解决现有技术中拍摄设备对自身的硬件资源具有较高的需求,提高了拍摄设备的硬件成本和功耗的问题。
第一方面,本申请实施例提供了一种追踪算法的运行方法,应用于终端设备,包括:
获取终端设备和拍摄设备的设备运行信息;
根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备;
在确定由所述拍摄设备运行所述追踪算法的情况下,通知所述拍摄设备运行所述追踪算法。
第二方面,本申请实施例提供了一种追踪算法的运行方法,应用于拍摄设备,包括:
发送所述拍摄设备的设备运行信息至所述终端设备;
在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果;
根据所述计算结果,控制所述拍摄设备执行追踪操作。
第三方面,本申请实施例提供了一种追踪算法的运行方法,应用于拍摄设备,包括:
获取终端设备和拍摄设备的设备运行信息;
根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
在确定由所述终端设备运行所述追踪算法的情况下,通知所述终端设备运行所述追踪算法,以及接收所述终端设备发送的计算结果;
在确定由所述拍摄设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果;
根据所述计算结果,控制所述拍摄设备执行追踪操作。
第四方面,本申请实施例提供了一种追踪算法的运行方法,应用于终端设备,包括:
在接收到所述拍摄设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果;
发送所述计算结果至所述拍摄设备。
第五方面,本申请实施例提供了一种追踪算法的运行装置,应用于拍摄设备,包括:
存储器和处理器;
所述存储器用于,获取终端设备和拍摄设备的设备运行信息;
所述处理器用于:根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备;
在确定由所述拍摄设备运行所述追踪算法的情况下,通知所述拍摄设备运行所述追踪算法。
第六方面,本申请实施例提供了一种追踪算法的运行装置,应用于拍摄 设备,包括:
存储器和处理器;
所述处理器用于:
发送所述拍摄设备的设备运行信息至所述终端设备;
在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果;
根据所述计算结果,控制所述拍摄设备执行追踪操作。
第七方面,本申请实施例提供了一种追踪算法的运行装置,应用于拍摄设备,包括:
存储器和处理器;
所述存储器用于,获取终端设备和拍摄设备的设备运行信息;
所述处理器用于:
根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
在确定由所述终端设备运行所述追踪算法的情况下,通知所述终端设备运行所述追踪算法,以及接收所述终端设备发送的计算结果;
在确定由所述拍摄设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果;
根据所述计算结果,控制所述拍摄设备执行追踪操作。
第八方面,本申请实施例提供了一种追踪算法的运行装置,应用于终端设备,包括:
存储器和处理器;
所述存储器用于,接收所述拍摄设备发送的针对运行追踪算法的通知;
所述处理器用于:
在接收到所述拍摄设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果;
发送所述计算结果至所述拍摄设备。
第九方面,本申请提供一种电子设备,包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的计算机程序,所述计算机程序被所述 处理器执行时实现上述方面所述的方法。
第十方面,本申请提供一种计算机可读存储介质,所述计算机可读存储介质包括指令,当其在计算机上运行时,使得计算机执行上述方面所述的方法。
第十一方面,本申请提供一种计算机程序产品,所述计算机程序产品包括指令,当其在计算机上运行时,使得计算机执行上述方面所述的方法。
在本申请实施例中,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
附图说明
图1是本申请实施例提供的一种追踪算法的运行***的架构图;
图2是本申请实施例提供的一种终端设备侧的追踪算法的运行方法的步骤流程图;
图3是本申请实施例提供的一种拍摄设备侧的追踪算法的运行方法的步骤流程图;
图4是本申请实施例提供的一种追踪算法的运行方法的交互步骤流程图;
图5是本申请实施例提供的另一种拍摄设备侧的追踪算法的运行方法的步骤流程图;
图6是本申请实施例提供的另一种终端设备侧的追踪算法的运行方法的步骤流程图;
图7是本申请实施例提供的一种终端设备侧的追踪算法的运行装置的框图;
图8是本申请实施例提供的一种拍摄设备侧的追踪算法的运行装置的框图;
图9是本申请实施例提供的另一种拍摄设备侧的追踪算法的运行装置的 框图;
图10是本申请实施例提供的另一种终端设备侧的追踪算法的运行装置的框图。
具体实施方式
为了使得本发明的目的、技术方案和优点更为明显,下面将参照附图详细描述根据本发明的示例实施例。显然,所描述的实施例仅仅是本发明的一部分实施例,而不是本发明的全部实施例,应理解,本发明不受这里描述的示例实施例的限制。基于本发明中描述的本发明实施例,本领域技术人员在没有付出创造性劳动的情况下所得到的所有其它实施例都应落入本发明的保护范围之内。
在下文的描述中,给出了大量具体的细节以便提供对本发明更为彻底的理解。然而,对于本领域技术人员而言显而易见的是,本发明可以无需一个或多个这些细节而得以实施。在其他的例子中,为了避免与本发明发生混淆,对于本领域公知的一些技术特征未进行描述。
应当理解的是,本发明能够以不同形式实施,而不应当解释为局限于这里提出的实施例。相反地,提供这些实施例将使公开彻底和完全,并且将本发明的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本发明的限制。在此使用时,单数形式的“一”、“一个”和“所述/该”也意图包括复数形式,除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”,当在该说明书中使用时,确定所述特征、整数、步骤、操作、元件和/或部件的存在,但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时,术语“和/或”包括相关所列项目的任何及所有组合。
为了彻底理解本发明,将在下列的描述中提出详细的结构,以便阐释本发明提出的技术方案。本发明的可选实施例详细描述如下,然而除了这些详细描述外,本发明还可以具有其他实施方式。
下面结合附图,对本申请的追踪算法的运行方法和装置、***进行详细说明。在不冲突的情况下,下述的实施例及实施方式中的特征可以相互组合。
参照图1,图1示出了本申请实施例提供的一种追踪算法的运行***框架图,追踪算法的运行***包括拍摄设备10和终端设备20,拍摄设备10 和终端设备20可以相互通信连接,其中,拍摄设备10和终端设备20中都可以内置有追踪算法,追踪算法用于对拍摄场景中目标对象进行感知和追踪,追踪算法可以基于拍摄设备10采集的图像实现,通过对图像中目标对象的准确标注,达到感知和追踪目标对象的目的。
在应用了追踪算法的辅助驾驶、自动测绘等场景中,在通过拍摄设备10进行图像采集的基础上,还可以具有与拍摄设备10连接的终端设备20,终端设备20可以为个人电脑、车载终端、手机、可穿戴设备等,终端设备20可以实现一些对追踪算法的配置以及对追踪功能的控制等操作,具体的,拍摄设备10和终端设备20各自都具备一定的硬件资源和算力,但是拍摄设备10在实现图像采集的过程中,已经消耗了一定的硬件资源和算力,进一步若要再实现追踪算法,拍摄设备10则需要相应的增加硬件资源和算力,导致成本和功耗上升,难以满足成本和性能的平衡。
在本申请实施例中,可以利用终端设备20的硬件资源和算力,在拍摄设备10的硬件资源和算力难以同时满足自身的正常拍摄和追踪功能的情况下,将追踪算法转移至终端设备20中进行实现,并根据与终端设备20的通信连接,获得终端设备20在实现了追踪算法后的运算结果,从而可以利用终端设备自身的硬件资源和算力实现追踪功能,避免了拍摄设备的成本和功耗大幅上升。
需要说明的是,在终端设备20实现追踪算法也需要不影响自身的正常运行,当追踪算法的实现影响到终端设备20自身的正常运行时,也可以将追踪算法转移至拍摄设备10中进行实现,另外,用户也可以根据实际需求,自行选择由拍摄设备10或是终端设备20运行追踪算法,本申请实施例对此不作限定。
图2是本申请实施例提供的一种追踪算法的运行方法的流程图,应用于终端设备,如图2所示,该方法可以包括:
步骤101、获取终端设备和拍摄设备的设备运行信息。
在本申请实施例中,终端设备和拍摄设备各自具有对应的设备运行信息,设备运行信息用于反映设备的运行状况,是一种指标型数据,如,设备运行信息可以包括设备当前硬件资源的负载参数、设备与设备之间的通信状况参数等。本申请实施例中,终端设备可以为拍摄设备保持通信连接的设备,可以接收拍摄设备发送的拍摄设备的设备运行信息,并采集自身的设备运行信息。
步骤102、根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法。
在本申请实施例中,终端设备和拍摄设备自身都内置有追踪算法,在追踪算法的实现过程中需要满足的条件包括:进一步利用终端设备自身硬件资源及算力辅助实现追踪算法,追踪算法的实现不影响终端设备和拍摄设备的正常运行,避免因为了实现追踪算法而使得拍摄设备大幅提升自身的硬件基础和功耗。
因此,基于上述条件,终端设备可以根据终端设备和拍摄设备的设备运行信息,确定终端设备和拍摄设备各自的运行状况,并根据运行状况,在满足上述条件的基础上,决定由终端设备和/或拍摄设备运行追踪算法。
例如,若设备运行信息反映了设备当前的硬件负载,则终端设备可以通过对设备运行信息的分析,确定终端设备和拍摄设备各自当前的负载状况,并在拍摄设备的负载状况过高的情况下,选择由终端设备运行追踪算法;在终端设备的负载状况过高的情况下,选择由拍摄设备运行追踪算法,这样会避免一方因负载状况过高的情况下影响到设备自身的正常运行。
若设备运行信息反映了设备与设备之间的通信状况,则终端设备可以通过对设备运行信息的分析,确定终端设备和拍摄设备之间通信状况,在通信状况过差的情况下,选择由拍摄设备运行追踪算法,这样会避免拍摄设备因无法与终端设备正常通信而导致无法实现追踪功能的情况发生。
另外,为了更快的获取得到追踪算法的结果,终端设备也可以确定由终端设备和拍摄设备都运行各自的追踪算法,终端设备则可以将最先得出的计算结果进行运用,使得可以通过设备之间的硬件资源和算力的竞争,更快的获得追踪算法的结果。
步骤103、在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备。
针对终端设备侧,在确定了由终端设备运行追踪算法的情况下,则可以利用终端设备自身的硬件资源和算力,运行追踪算法,从而降低了拍摄设备的算力压力。在追踪算法的计算结果需要返回至拍摄设备以供其进行后续的追踪操作的情况下,可以在终端设备获得计算结果后,将计算结果返回至拍摄设备;另外,在追踪算法的结果需要由终端设备获取以供其指导拍摄设备进行后续的追踪操作的情况下,则可以在终端设备获得计算结果后,进一步根据计算结果控制拍摄设备进行后续的追踪操作。
步骤104、在确定由所述拍摄设备运行所述追踪算法的情况下,通知所 述拍摄设备运行所述追踪算法。
针对终端设备侧,在确定了由拍摄设备运行追踪算法的情况下,可以发送通知指令至拍摄设备,以供拍摄设备根据通知指令运行追踪算法,在追踪算法的计算结果需要由拍摄设备处理,以供其进行后续的追踪操作的情况下,可以在拍摄设备获得计算结果后,进一步由拍摄设备根据计算结果控制后续的追踪操作;另外,在追踪算法的结果需要由终端设备获取以供其控制拍摄设备进行后续的追踪操作的情况下,则可以在拍摄设备获得计算结果后,将计算结果返回至终端设备,由终端设备根据计算结果控制拍摄设备后续的追踪操作。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图3是本申请实施例提供的一种追踪算法的运行方法的步骤流程图,应用于拍摄设备,该方法可以包括:
步骤201、发送所述拍摄设备的设备运行信息至所述终端设备。
在本申请实施例中,终端设备和拍摄设备各自具有对应的设备运行信息,设备运行信息用于反映设备的运行状况,拍摄设备可以在获取自身的设备运行信息后,将设备运行信息发送至终端设备,以供终端设备根据设备运行信息确定拍摄设备的运行状况。
步骤202、在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果。
步骤203、根据所述计算结果,控制所述拍摄设备执行追踪操作。
在本申请实施例中,在追踪算法的计算结果需要由拍摄设备处理,以供其进行后续的追踪操作的情况下,可以在拍摄设备运行了追踪算法并获得计算结果后,进一步由拍摄设备根据计算结果控制后续的追踪操作;也可以在终端设备运行了追踪算法并获得计算结果后,由拍摄设备接收终端设备发送 的计算结果,并由拍摄设备根据计算结果控制后续的追踪操作。
另外,在追踪算法的结果需要由终端设备获取以供其控制拍摄设备进行后续的追踪操作的情况下,则可以在拍摄设备获得计算结果后,将计算结果返回至终端设备,由终端设备根据计算结果控制拍摄设备后续的追踪操作。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图4是本申请实施例提供的一种追踪算法的运行方法的交互步骤流程图,该方法可以包括:
步骤301、拍摄设备发送所述拍摄设备的设备运行信息至所述终端设备。
该步骤具体可以参照上述步骤201,此处不再赘述。
步骤302、终端设备获取终端设备和拍摄设备的设备运行信息。
该步骤具体可以参照上述步骤101,此处不再赘述。
步骤303、终端设备确定与所述拍摄设备之间的传输通道的类型。
在本申请实施例中,终端设备和拍摄设备之间通信连接,形成数据的传输通道,该传输通道的类型对终端设备和拍摄设备之间的数据传输质量具有较大影响,例如,在终端设备运行追踪算法,并在拍摄设备上根据追踪算法的计算结果控制进行追踪操作的情况下,拍摄设备需要将采集的追踪数据通过传输通道发送至终端设备,终端设备在得到计算结果后,也需要通过传输通道将计算结果发送至拍摄设备,若传输通道的通信质量较差,则会在数据传输上产生延迟和丢包等现象,这将大大影响到追踪功能的体验。
因此,本申请实施例需要针对终端设备和拍摄设备之间的传输通道的类型,确定终端设备和拍摄设备之间的数据传输质量,并进一步根据该数据质量的考量,确定由终端设备和/或拍摄设备运行追踪算法。
其中,传输通道的类型可以包括通用串行总线(USB,Universal Serial Bus)连接通道、5G连接通道等。
步骤304、终端设备在所述类型为第一类型的情况下,进入步骤306。
其中,第一类型包括:USB连接通道、5G连接通道。
在本申请实施例中,属于第一类型的连接通道具备稳定性高、低传输延迟等特性,因此,在终端设备和拍摄设备之间的传输通道的类型为第一类型的情况下,可以认为二者间数据传输质量较高,此时可以进入步骤306,以实现由终端设备根据设备运行信息,确定由终端设备和/或拍摄设备运行追踪算法。
需要说明的是,根据实际需求的不同,第一类型还可以包括其他具备稳定性高、低传输延迟特性的连接通道的类型。
步骤305、终端设备在所述类型为第二类型的情况下,确定由所述拍摄设备运行所述追踪算法。
其中,第二类别包括:除所述USB连接通道、所述5G连接通道之外的其他连接通道。
在本申请实施例中,属于第二类型的连接通道的稳定性相对较差、且传输延迟较高,如,普通的无线热点连接通道、4G连接通道等,都存在稳定性较差,且传输延迟较高的特性,在第二类型的连接通道下,终端设备和拍摄设备之间的数据传输质量较差,由于出现高延迟、高丢包率现象的几率较高,无法满足追踪算法对数据的高时效性需求,因此,在这种情况下,可以直接由拍摄设备运行追踪算法,即由拍摄设备获取追踪数据,并根据追踪数据运行追踪算法,得到计算结果,最后根据计算结果进行追踪操作,使得在实现追踪算法的整个过程中,尽量减少与终端设备之间的数据传输,从而保证追踪算法实现过程的稳定性。
步骤306、终端设备根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法。
该步骤具体可以参照上述步骤102,此处不再赘述。
可选的,在一种实现方式中,所述设备运行信息包括:当前负载信息;步骤306具体可以包括:
子步骤3061、在所述终端设备的当前负载信息不满足算法运行条件的情况下,确定由所述拍摄设备运行所述追踪算法。
在本申请实施例的一种实现方式中,设备运行信息可以包括:当前负载信息,当前负载信息可以反映设备的硬件资源的当前的使用率,若设备的当前负载信息过高,会影响到设备的正常工作,并会增大设备的功耗,使得设备发热严重,续航降低。
因此,在终端设备的当前负载信息大于或等于一个预设阈值时,可以认 为终端设备的硬件资源不足,不满足算法运行条件,此时可以确定由拍摄设备运行所述追踪算法,避免在因在终端设备上强行运行追踪算法而影响到终端设备的正常工作。其中,该预设阈值可以根据实际需求进行设定,如,在当前负载信息为百分比的使用率形式下,该预设阈值可以为80%,90%等百分比数值。
子步骤3062、在所述拍摄设备的当前负载信息不满足所述算法运行条件的情况下,确定由所述终端设备运行所述追踪算法。
在终端设备的当前负载信息小于一个预设阈值时,可以认为终端设备的硬件资源充裕,满足算法运行条件,此时可以确定由终端设备运行所述追踪算法,从而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
可选的,步骤306具体还可以包括:
子步骤3063、终端设备在所述终端设备和所述拍摄设备的当前负载信息都满足所述算法运行条件的情况下,确定同时由所述终端设备和所述拍摄设备运行所述追踪算法。
在本申请实施例中,在终端设备和拍摄设备的当前负载信息都满足算法运行条件的情况下,终端设备和拍摄设备的硬件资源都很充裕,则进一步为了提高追踪算法的计算结果获取速度,终端设备可以确定同时由终端设备和拍摄设备运行追踪算法,即同时由终端设备和拍摄设备各自运行各自存储的追踪算法,并得到各自的计算结果。
在实际应用中,终端设备和拍摄设备各自的硬件资源和算力存在差异,使得二者处理追踪算法得到计算结果的速度互不相同,则在终端设备和拍摄设备各自运行各自存储的追踪算法,并得到各自的计算结果的情况下,可以将最先计算得到的计算结果进行采用,这样便通过设备之间的硬件资源和算力的竞争,更快的获得追踪算法的计算结果,提高了计算结果的获取速度,从而提高了追踪算法的实现效果。
例如,在终端设备的算力更强的情况下,终端设备获得计算结果并将计算结果发送至拍摄设备,使得拍摄设备自身计算得到计算结果的时间,晚于拍摄设备接收到终端设备发送的计算结果的时间,使得拍摄设备可以采用终 端设备发送的计算结果进行追踪操作,这样拍摄设备具备更快的计算结果获取速度。
子步骤3064、终端设备发送同时运算通知至所述拍摄设备。
在确定同时由终端设备和拍摄设备运行追踪算法,终端设备可以发送同时运算通知至拍摄设备,以供拍摄设备根据同时运算通知与终端设备并行进行追踪算法的运行。
可选的,追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算法,在子步骤3064之后,还可以包括:
子步骤3065、终端设备运行所述第一追踪算法得到第一计算结果,并将所述第一计算结果发送至所述拍摄设备。
子步骤3066、终端设备通知所述拍摄设备运行所述第二追踪算法。
在本申请实施例中,可以在终端设备和拍摄设备中分别部署不同的追踪算法,并在确定同时由终端设备和拍摄设备运行追踪算法的情况下,由终端设备运行第一追踪算法得到第一计算结果,并将第一计算结果发送至拍摄设备,并由终端设备通知拍摄设备运行第二追踪算法得到第二计算结果,使得拍摄设备可以根据实际需求,从第一计算结果和第二计算结果中选取一个计算结果控制追踪操作。
其中,第一追踪算法可以为针对终端设备的硬件资源和算力特性所部署的算法,第二追踪算法可以为针对拍摄设备的硬件资源和算力特性所部署的算法。例如,假设终端设备的人物识别能力较强,拍摄设备的建筑物识别能力较强,则第一追踪算法可以为针对人物对象的追踪算法,第二追踪算法可以为针对建筑物对象的追踪算法,则在拍摄设备需要追踪人物对象时,可以选取第一计算结果,在拍摄设备需要追踪建筑物对象时,可以选取第二计算结果。
可选的,在另一种实现方式中,所述设备运行信息包括当前负载信息和网络带宽;步骤306具体可以包括:
子步骤3067、终端设备根据所述当前负载信息和网络带宽,确定与所述拍摄设备之间的传输通道的传输延迟。
在追踪功能的实现过程中,若需要利用终端设备的硬件资源和算力辅助实现追踪算法,则终端设备和拍摄设备之间需要进行数据交互,为了提供更优的追踪功能体验,需要终端设备与拍摄设备之间的传输通道的传输延迟尽可能低,以保证数据的时效性。
因此,在本申请实施例中,设备运行信息可以在包括当前负载信息的基础上,进一步包括设备的网络带宽,终端设备可以根据当前负载信息和网络带宽,确定与拍摄设备之间的传输通道的传输延迟,从而根据传输延迟的大小,确定终端设备和拍摄设备之间的数据传输质量。
子步骤3068、终端设备在所述传输延迟小于或等于预设延迟阈值的情况下,进入步骤306。
在本申请实施例中,在传输延迟小于或等于预设延迟阈值的情况下,终端设备可以认为终端设备和拍摄设备之间的数据传输质量较佳,此时可以进入步骤306,以实现由终端设备根据设备运行信息,确定由终端设备和/或拍摄设备运行追踪算法。
子步骤3069、终端设备在所述传输延迟大于所述预设延迟阈值的情况下,确定由所述拍摄设备运行所述追踪算法。
在本申请实施例中,在传输延迟大于预设延迟阈值的情况下,终端设备可以认为终端设备和拍摄设备之间的数据传输质量较差,易出现高延迟、高丢包率的现象,无法满足追踪算法对数据的高时效性需求,因此,在这种情况下,可以直接由拍摄设备运行追踪算法,即由拍摄设备获取追踪数据,并根据追踪数据运行追踪算法,得到计算结果,最后根据计算结果进行追踪操作,使得在实现追踪算法的整个过程中,尽量减少与终端设备之间的数据传输,从而保证追踪算法实现过程的稳定性。
步骤307、在确定由所述终端设备运行所述追踪算法的情况下,终端设备运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备。
该步骤具体可以参照上述步骤103,此处不再赘述。
可选的,所述终端设备的本地建立有应用场景和追踪算法的对应关系;步骤307具体可以包括:
子步骤3071、终端设备在确定由所述终端设备运行所述追踪算法的情况下,确定当前的目标应用场景。
在本申请实施例中,由于终端设备自身具备硬件资源和算力的丰富性特性,因此可以利用这种特性,在终端设备上布置针对追踪算法的更多个性化功能,具体的,终端设备可以针对历史使用数据或用户需求的分析,确定多个不同的应用场景,并确定每个应用场景适用的追踪算法,在本地建立有应用场景和追踪算法的对应关系。
例如,城市应用场景与适配的追踪算法1的对应关系;野外应用场景与适配的追踪算法2的对应关系;室内应用场景与适配的追踪算法3的对应关系等。
在该步骤中,在确定由终端设备运行追踪算法的情况下,终端设备可以通过采集周围环境信息或用户的指定操作,确定当前的目标应用场景。
子步骤3072、终端设备根据所述对应关系,确定所述目标应用场景对应的目标追踪算法。
在该步骤中,由于终端设备的本地存在应用场景与追踪算法之间的对应关系,因此在确定了目标应用场景之后,可以从对应关系中进一步确定标应用场景对应的目标追踪算法。
子步骤3073、终端设备运行所述目标追踪算法得到计算结果。
在该步骤中,通过运行目标应用场景对应的目标追踪算法,可以达到终端设备自动根据当前所处的目标应用场景选取适配的目标追踪算法的目的,提供了对不同应用场景对应的追踪算法的个性化定义,提高了用户体验度。
可选的,步骤307具体可以包括:
子步骤3074、在确定由所述终端设备运行所述追踪算法的情况下,终端设备向所述拍摄设备发送追踪数据获取请求。
子步骤3075、终端设备在接收到所述拍摄设备根据所述追踪数据获取请求发送的追踪数据的情况下,根据所述追踪数据和所述追踪算法,计算得到所述计算结果。
在本申请实施例中,追踪算法可以基于拍摄设备采集的追踪数据进行计算,从而得到对应的计算结果,如,拍摄设备采集的追踪数据可以包括图像数据、点云数据等类型的数据,在确定由终端设备运行追踪算法的情况下,终端设备需要通过向拍摄设备发送追踪数据获取请求,从而获取拍摄设备采集的追踪数据,并根据追踪数据和追踪算法,计算得到计算结果。在确定由拍摄设备运行追踪算法的情况下,拍摄设备在采集追踪数据之后,可以根据追踪数据和追踪算法,计算得到计算结果。
可选的,子步骤3075具体可以包括:
子步骤30751、终端设备在由所述追踪数据生成的追踪图像中,识别目 标实体对象。
子步骤30752、终端设备在为所述追踪图像中的目标实体对象添加了物体框之后,得到所述计算结果,所述物体框用于反映所述目标实体对象的所处位置。
在本申请实施例中,追踪算法的实现在于:追踪算法的计算结果中需要实现对场景中目标实体对象的追踪,终端设备根据拍摄设备采集的追踪数据可以生成追踪图像,追踪图像反映了场景,则进一步终端设备可以在生成的追踪图像中,识别目标实体对象,并对目标实体对象添加物体框,得到具有反映场景的追踪图像、追踪图像中的目标实体对象,反映目标实体对象的所处位置的物体框的计算结果。拍摄设备在得到计算结果后,可以根据场景中目标实体对象的所处位置,进一步调整拍摄角度和方向,保持对目标实体对象的追踪拍摄。
步骤308、在确定由所述拍摄设备运行所述追踪算法的情况下,终端设备通知所述拍摄设备运行所述追踪算法。
该步骤具体可以参照上述步骤104,此处不再赘述。
步骤309、拍摄设备在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果。
该步骤具体可以参照上述步骤202,此处不再赘述。
步骤310、拍摄设备根据所述计算结果,控制所述拍摄设备执行追踪操作。
该步骤具体可以参照上述步骤203,此处不再赘述。
可选的,步骤310具体可以包括:
子步骤3101、拍摄设备在接收到所述终端设备发送的同时运算通知的情况下,确定先接收到终端设备发送的计算结果,或确定先根据所述同时运算通知计算得到计算结果。
在本申请实施例中,在终端设备和拍摄设备的当前负载信息都满足算法运行条件的情况下,终端设备和拍摄设备的硬件资源都很充裕,则进一步为了提高追踪算法的计算结果获取速度,终端设备可以确定同时由终端设备和 拍摄设备运行追踪算法,即同时由终端设备和拍摄设备各自运行各自存储的追踪算法,并得到各自的计算结果。终端设备在得到计算结果后,会将计算结果发送至拍摄设备。
在实际应用中,终端设备和拍摄设备各自的硬件资源和算力存在差异,使得二者处理追踪算法得到计算结果的速度互不相同,则在终端设备和拍摄设备各自运行各自存储的追踪算法,并得到各自的计算结果的情况下,可以将最先计算得到的计算结果进行采用,这样便通过设备之间的硬件资源和算力的竞争,更快的获得追踪算法的计算结果,提高了计算结果的获取速度,从而提高了追踪算法的实现效果。
在该步骤中,拍摄设备可以确定最先获得的计算结果是终端设备发送的计算结果,或是拍摄设备根据同时运算通知计算得到的计算结果,因此,拍摄设备可以具有两种判断结果。
子步骤3102、拍摄设备在确定先根据所述同时运算通知计算得到计算结果的情况下,采用所述拍摄设备计算得到计算结果控制所述拍摄设备执行追踪操作。
在确定先根据同时运算通知计算得到计算结果的情况下,拍摄设备可以认为拍摄设备的算力更强,使得拍摄设备自身计算得到计算结果的时间,要早于拍摄设备接收到终端设备发送的计算结果的时间,使得拍摄设备可以采用自身计算得到的计算结果进行追踪操作,这样拍摄设备具备更快的计算结果获取速度。
子步骤3103、拍摄设备在确定先接收到终端设备发送的计算结果的情况下,采用所述终端设备发送的计算结果控制所述拍摄设备执行追踪操作。
在确定先接收到终端设备发送的计算结果的情况下,拍摄设备可以认为终端设备的算力更强,终端设备获得计算结果并将计算结果发送至拍摄设备,使得拍摄设备自身计算得到计算结果的时间,要晚于拍摄设备接收到终端设备发送的计算结果的时间,使得拍摄设备可以采用终端设备发送的计算结果进行追踪操作,这样拍摄设备具备更快的计算结果获取速度。
可选的,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算法;步骤310具体可以包括:
子步骤3104、拍摄设备接收所述终端设备发送的针对所述第一追踪算法的第一计算结果。
子步骤3105、拍摄设备在接收到所述终端设备发送的针对运行所述第二追踪算法的通知的情况下,运行所述第二追踪算法得到第二计算结果。
子步骤3106、拍摄设备从所述第一计算结果和所述第二计算结果中选取一个计算结果,并根据选取的计算结果控制所述拍摄设备执行追踪操作。
在本申请实施例中,可以在终端设备和拍摄设备中分别部署不同的追踪算法,并在确定同时由终端设备和拍摄设备运行追踪算法的情况下,由终端设备运行第一追踪算法得到第一计算结果,并将第一计算结果发送至拍摄设备,并由终端设备通知拍摄设备运行第二追踪算法得到第二计算结果,使得拍摄设备可以根据实际需求,从第一计算结果和第二计算结果中选取一个计算结果控制追踪操作。其中,第一追踪算法可以为针对终端设备的硬件资源和算力特性所部署的算法,第二追踪算法可以为针对拍摄设备的硬件资源和算力特性所部署的算法。
可选的,所述第一追踪算法用于识别第一实体对象,所述第二追踪算法用于识别第二实体对象;子步骤3106具体可以包括:
子步骤31061、拍摄设备识别所述拍摄设备拍摄的追踪图像中的实体对象,所述追踪图像由所述拍摄设备采集的追踪数据生成。
在本申请实施例中,在确定由拍摄设备运行追踪算法的情况下,拍摄设备可以识别拍摄设备拍摄的追踪图像中的实体对象,如人物对象、建筑物对象等。
子步骤31062、拍摄设备在所述追踪画面中包含的第一实体对象的数量大于第一数量阈值的情况下,选取所述第一计算结果控制所述拍摄设备执行追踪操作。
在追踪画面中包含的第一实体对象的数量大于第一数量阈值的情况下,拍摄设备可以认为当前拍摄场景更适用于用于识别第一实体对象的第一追踪算法,则拍摄设备可以选取所述第一计算结果控制所述拍摄设备执行追踪操作,从而提高了追踪算法对包含更多第一实体对象的拍摄场景的适配性。
子步骤31063、拍摄设备在所述追踪画面中包含的第二实体对象的数量大于第二数量阈值的情况下,选取所述第二计算结果控制所述拍摄设备执行 追踪操作。
在追踪画面中包含的第二实体对象的数量大于第二数量阈值的情况下,拍摄设备可以认为当前拍摄场景更适用于用于识别第二实体对象的第二追踪算法,则拍摄设备可以选取所述第二计算结果控制所述拍摄设备执行追踪操作,从而提高了追踪算法对包含更多第二实体对象的拍摄场景的适配性。
可选的,子步骤3106还可以包括:
子步骤31064、拍摄设备在所述追踪画面中同时包含所述第一实体对象和所述第二实体对象的情况下,将所述第一计算结果和所述第二计算结果融合,得到目标计算结果。
子步骤31065、拍摄设备根据所述目标计算结果控制所述拍摄设备执行追踪操作。
进一步的,在另一种实现方式中,若追踪画面中同时包含第一实体对象和第二实体对象,则为了在追踪操作中同时保证对第一实体对象和第二实体对象的追踪精度,拍摄设备可以将识别第一实体对象的第一计算结果和识别第二实体对象的第二计算结果融合,得到目标计算结果,目标计算结果中同时对第一实体对象和第二实体对象的位置进行了标注,使得拍摄设备后续的追踪操作中,可以实现对第一实体对象和第二实体对象高精度追踪。
可选的,计算结果包括:由所述拍摄设备采集的追踪数据生成的追踪图像中,目标实体对象对应的物体框,所述物体框用于反映所述目标实体对象的所处位置;所述拍摄设备具有云台;步骤310具体可以包括:
子步骤3107、拍摄设备根据所述物体框的位置信息,计算目标移动向量值。
子步骤3108、拍摄设备根据所述目标移动向量值控制所述云台移动,以实现所述拍摄设备对所述目标实体对象的追踪拍摄。
在本申请实施例中,追踪算法可以基于拍摄设备采集的追踪数据进行计算,从而得到对应的计算结果,如,拍摄设备采集的追踪数据可以包括图像数据、点云数据等类型的数据,根据追踪数据和追踪算法计算得到的计算结果中,包含有反映拍摄场景的追踪图像,以及追踪图像中目标实体对象对应的物体框,物体框可以反映所述目标实体对象的所处位置。
进一步的,拍摄设备在得到计算结果后,可以根据场景中目标实体对象的所处位置,计算云台移动所需的目标移动向量值,并进一步根据目标移动向量值调整云台移动,保持对目标实体对象的追踪拍摄。
可选的,所述方法还可以包括:
步骤A1、终端设备通过预设的自定义接口,接收新的追踪算法。
步骤A2、终端设备在本地增加所述新的追踪算法,或用所述新的追踪算法替换所述本地的追踪算法。
由于终端设备自身具备硬件资源和算力的丰富性特性,因此可以利用这种特性,在终端设备上布置针对追踪算法的更多个性化功能,进一步的,还可以在终端设备上预设自定义接口,通过该自定义接口,终端设备可以接收外界设备发送的新的追踪算法,使得终端设备的本地存储有多种追踪算法,或将新的追踪算法替换原始的追踪算法,满足用户对不同追踪算法的个性化需求。
可选的,所述方法还可以包括:
步骤B1、拍摄设备在接收到所述终端设备发送的追踪数据获取请求的情况下,将所述拍摄设备采集到的追踪数据发送至所述终端设备。
在本申请实施例中,追踪算法可以基于拍摄设备采集的追踪数据进行计算,从而得到对应的计算结果,如,拍摄设备采集的追踪数据可以包括图像数据、点云数据等类型的数据,在确定由终端设备运行追踪算法的情况下,终端设备需要通过向拍摄设备发送追踪数据获取请求,从而获取拍摄设备采集的追踪数据。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图5是本申请实施例提供的一种追踪算法的运行方法的步骤流程图,应 用于拍摄设备,该方法可以包括:
步骤401、获取终端设备和拍摄设备的设备运行信息。
步骤402、根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法。
步骤403、在确定由所述终端设备运行所述追踪算法的情况下,通知所述终端设备运行所述追踪算法,以及接收所述终端设备发送的计算结果。
步骤404、在确定由所述拍摄设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果。
步骤405、根据所述计算结果,控制所述拍摄设备执行追踪操作。
在本申请实施例中,也可以将用于决策由终端设备和/或拍摄设备运行追踪算法的功能设置在拍摄设备上,使得拍摄设备可以根据终端设备和拍摄设备的设备运行信息,决策由终端设备和/或拍摄设备运行追踪算法,具体实现细节可以参照上述实施例的描述,此处不再赘述。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图6是本申请实施例提供的一种追踪算法的运行方法的步骤流程图,应用于终端设备,该方法可以包括:
步骤501、在接收到所述拍摄设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果。
步骤502、发送所述计算结果至所述拍摄设备。
针对图5所示的实施例,在将用于决策由终端设备和/或拍摄设备运行追踪算法的功能设置在拍摄设备上之后,终端设备可以在被允许进行追踪算法的运行时,通过自身的硬件资源和算力,来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,具体实现细节可以参照上述实施例的描述,此处不再赘述。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从 而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图7是本申请实施例提供的一种追踪算法的运行装置的框图,应用于终端设备,如图7所示,该追踪算法的运行装置600可以包括:存储器601和处理器602;
所述存储器601用于,获取终端设备和拍摄设备的设备运行信息;
所述处理器602用于:根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备;
在确定由所述拍摄设备运行所述追踪算法的情况下,通知所述拍摄设备运行所述追踪算法。
可选的,所述设备运行信息包括:当前负载信息;所述处理器具体用于:
在所述终端设备的当前负载信息不满足算法运行条件的情况下,确定由所述拍摄设备运行所述追踪算法;
在所述拍摄设备的当前负载信息不满足所述算法运行条件的情况下,确定由所述终端设备运行所述追踪算法。
可选的,所述处理器还用于:
在所述终端设备和所述拍摄设备的当前负载信息都满足所述算法运行条件的情况下,确定同时由所述终端设备和所述拍摄设备运行所述追踪算法;
发送同时运算通知至所述拍摄设备。
可选的,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算法;所述处理器还用于:
运行所述第一追踪算法得到第一计算结果,并将所述第一计算结果发送至所述拍摄设备;
通知所述拍摄设备运行所述第二追踪算法。
可选的,所述设备运行信息包括当前负载信息和网络带宽;所述处理器 还用于:
根据所述当前负载信息和网络带宽,确定与所述拍摄设备之间的传输通道的传输延迟;
在所述传输延迟小于或等于预设延迟阈值的情况下,进入所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法的步骤;
在所述传输延迟大于所述预设延迟阈值的情况下,确定由所述拍摄设备运行所述追踪算法。
可选的,所述处理器还用于:
确定与所述拍摄设备之间的传输通道的类型;
在所述类型为第一类型的情况下,进入所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法的步骤;
在所述类型为第二类型的情况下,确定由所述拍摄设备运行所述追踪算法;
其中,所述第一类型包括:USB连接通道、5G连接通道;所述第二类别包括:除所述USB连接通道、所述5G连接通道之外的其他连接通道。
可选的,所述处理器还用于:
通过预设的自定义接口,接收新的追踪算法;
在本地增加所述新的追踪算法,或用所述新的追踪算法替换所述本地的追踪算法。
可选的,所述终端设备的本地建立有应用场景和追踪算法的对应关系;所述处理器具体用于:
在确定由所述终端设备运行所述追踪算法的情况下,确定当前的目标应用场景;
根据所述对应关系,确定所述目标应用场景对应的目标追踪算法;
运行所述目标追踪算法得到计算结果。
可选的,所述处理器具体用于:
在确定由所述终端设备运行所述追踪算法的情况下,向所述拍摄设备发送追踪数据获取请求;
在接收到所述拍摄设备根据所述追踪数据获取请求发送的追踪数据的 情况下,根据所述追踪数据和所述追踪算法,计算得到所述计算结果。
可选的,所述处理器具体用于:
在由所述追踪数据生成的追踪图像中,识别目标实体对象;
在为所述追踪图像中的目标实体对象添加了物体框之后,得到所述计算结果,所述物体框用于反映所述目标实体对象的所处位置。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图8是本申请实施例提供的一种追踪算法的运行装置的框图,应用于拍摄设备,如图8所示,该追踪算法的运行装置700可以包括:存储器701和处理器702;
所述处理器用702于:
发送所述拍摄设备的设备运行信息至所述终端设备;
在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果;
根据所述计算结果,控制所述拍摄设备执行追踪操作。
可选的,所述处理器还用于:
在接收到所述终端设备发送的同时运算通知的情况下,确定先接收到终端设备发送的计算结果,或确定先根据所述同时运算通知计算得到计算结果;
所述处理器具体用于:
在确定先根据所述同时运算通知计算得到计算结果的情况下,采用所述拍摄设备计算得到计算结果控制所述拍摄设备执行追踪操作;
在确定先接收到终端设备发送的计算结果的情况下,采用所述终端设备发送的计算结果控制所述拍摄设备执行追踪操作。
可选的,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部 署在所述拍摄设备的第二追踪算法;所述存储器用于:
接收所述终端设备发送的针对所述第一追踪算法的第一计算结果;
所述处理器还用于:
在接收到所述终端设备发送的针对运行所述第二追踪算法的通知的情况下,运行所述第二追踪算法得到第二计算结果;
所述处理器具体用于:
从所述第一计算结果和所述第二计算结果中选取一个计算结果,并根据选取的计算结果控制所述拍摄设备执行追踪操作。
可选的,所述第一追踪算法用于识别第一实体对象,所述第二追踪算法用于识别第二实体对象;所述处理器具体用于:
识别所述拍摄设备拍摄的追踪图像中的实体对象,所述追踪图像由所述拍摄设备采集的追踪数据生成;
在所述追踪画面中包含的第一实体对象的数量大于第一数量阈值的情况下,选取所述第一计算结果控制所述拍摄设备执行追踪操作;
在所述追踪画面中包含的第二实体对象的数量大于第二数量阈值的情况下,选取所述第二计算结果控制所述拍摄设备执行追踪操作。
可选的,所述处理器还用于:
在所述追踪画面中同时包含所述第一实体对象和所述第二实体对象的情况下,将所述第一计算结果和所述第二计算结果融合,得到目标计算结果;
根据所述目标计算结果控制所述拍摄设备执行追踪操作。
可选的,所述处理器还用于:
在接收到所述终端设备发送的追踪数据获取请求的情况下,将所述拍摄设备采集到的追踪数据发送至所述终端设备。
可选的,所述计算结果包括:由所述拍摄设备采集的追踪数据生成的追踪图像中,目标实体对象对应的物体框,所述物体框用于反映所述目标实体对象的所处位置;所述拍摄设备具有云台;所述处理器具体用于:
根据所述物体框的位置信息,计算目标移动向量值;
根据所述目标移动向量值控制所述云台移动,以实现所述拍摄设备对所述目标实体对象的追踪拍摄。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图9是本申请实施例提供的一种追踪算法的运行装置的框图,应用于拍摄设备,如图9所示,该追踪算法的运行装置800可以包括:存储器801和处理器802;
所述存储器801用于,获取终端设备和拍摄设备的设备运行信息;
所述处理器802用于:
根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
在确定由所述终端设备运行所述追踪算法的情况下,通知所述终端设备运行所述追踪算法,以及接收所述终端设备发送的计算结果;
在确定由所述拍摄设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果;
根据所述计算结果,控制所述拍摄设备执行追踪操作。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
图10是本申请实施例提供的一种追踪算法的运行装置的框图,应用于拍摄设备,如图10所示,该追踪算法的运行装置900可以包括:存储器901和处理器902;
所述存储器901用于,接收所述拍摄设备发送的针对运行追踪算法的通 知;
所述处理器902用于:
在接收到所述拍摄设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果;
发送所述计算结果至所述拍摄设备。
综上,本申请实施例提供的一种追踪算法的运行方法,本申请通过对终端设备和拍摄设备各自的设备运行信息的分析,在不影响终端设备和拍摄设备各自正常运行的基础上,确定由终端设备和/或拍摄设备运行追踪算法,从而保证了终端设备和拍摄设备的运行稳定性,进而可以利用终端设备自身的硬件资源和算力来辅助实现追踪算法,避免将所有的算力压力都附加在拍摄设备上,避免了拍摄设备为了强行实现追踪算法而大幅提升自身的硬件成本和功耗。
本申请实施例还提供一种计算机可读存储介质,计算机可读存储介质上存储有计算机程序,该计算机程序被处理器执行时实现上述追踪算法的运行方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。其中,所述的计算机可读存储介质,如只读存储器(Read-Only Memory,简称ROM)、随机存取存储器(Random Access Memory,简称RAM)、磁碟或者光盘等。
存储器可以为外部控制终端与追踪算法的运行装置连接的接口。例如,外部控制终端可以包括有线或无线头戴式耳机端口、外部电源(或电池充电器)端口、有线或无线数据端口、存储卡端口、用于连接具有识别模块的控制终端的端口、音频输入/输出(I/O)端口、视频I/O端口、耳机端口等等。存储器可以用于接收来自外部控制终端的输入(例如,数据信息、电力等等)并且将接收到的输入传输到追踪算法的运行装置内的一个或多个元件或者可以用于在追踪算法的运行装置和外部控制终端之间传输数据。
例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
处理器是控制终端的控制中心,利用各种接口和线路连接整个控制终端的各个部分,通过运行或执行存储在存储器内的软件程序和/或模块,以及调用存储在存储器内的数据,执行控制终端的各种功能和处理数据,从而对控制终端进行整体监控。处理器可包括一个或多个处理单元;优选的,处理器可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作***、用户界面和应用程序等,调制解调处理器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器中。
本说明书中的各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似的部分互相参见即可。
本领域内的技术人员应明白,本申请的实施例可提供为方法、控制终端、或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、终端设备(***)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的控制终端。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令控制终端的制造品,该指令控制终端实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上,使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例做出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。
最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素, 而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。
以上对本申请进行了详细介绍,本文中应用了具体个例对本申请的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本申请的方法及其核心思想;同时,对于本领域的一般技术人员,依据本申请的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本申请的限制。

Claims (40)

  1. 一种追踪算法的运行方法,应用于终端设备,其特征在于,所述方法包括:
    获取终端设备和拍摄设备的设备运行信息;
    根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
    在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备;
    在确定由所述拍摄设备运行所述追踪算法的情况下,通知所述拍摄设备运行所述追踪算法。
  2. 根据权利要求1所述的方法,其特征在于,所述设备运行信息包括:当前负载信息;所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法,包括:
    在所述终端设备的当前负载信息不满足算法运行条件的情况下,确定由所述拍摄设备运行所述追踪算法;
    在所述拍摄设备的当前负载信息不满足所述算法运行条件的情况下,确定由所述终端设备运行所述追踪算法。
  3. 根据权利要求2所述的方法,其特征在于,所述方法还包括:
    在所述终端设备和所述拍摄设备的当前负载信息都满足所述算法运行条件的情况下,确定同时由所述终端设备和所述拍摄设备运行所述追踪算法;
    发送同时运算通知至所述拍摄设备。
  4. 根据权利要求3所述的方法,其特征在于,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算法;
    在所述确定同时由所述终端设备和所述拍摄设备运行所述追踪算法之后,所述方法还包括:
    运行所述第一追踪算法得到第一计算结果,并将所述第一计算结果发送至所述拍摄设备;
    通知所述拍摄设备运行所述第二追踪算法。
  5. 根据权利要求1所述的方法,其特征在于,所述设备运行信息包括 当前负载信息和网络带宽;在所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法之前,所述方法还包括:
    根据所述当前负载信息和网络带宽,确定与所述拍摄设备之间的传输通道的传输延迟;
    在所述传输延迟小于或等于预设延迟阈值的情况下,进入所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法的步骤;
    在所述传输延迟大于所述预设延迟阈值的情况下,确定由所述拍摄设备运行所述追踪算法。
  6. 根据权利要求1所述的方法,其特征在于,在所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法之前,所述方法还包括:
    确定与所述拍摄设备之间的传输通道的类型;
    在所述类型为第一类型的情况下,进入所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法的步骤;
    在所述类型为第二类型的情况下,确定由所述拍摄设备运行所述追踪算法;
    其中,所述第一类型包括:USB连接通道、5G连接通道;所述第二类别包括:除所述USB连接通道、所述5G连接通道之外的其他连接通道。
  7. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    通过预设的自定义接口,接收新的追踪算法;
    在本地增加所述新的追踪算法,或用所述新的追踪算法替换所述本地的追踪算法。
  8. 根据权利要求1所述的方法,其特征在于,所述终端设备的本地建立有应用场景和追踪算法的对应关系;
    所述在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,包括:
    在确定由所述终端设备运行所述追踪算法的情况下,确定当前的目标应用场景;
    根据所述对应关系,确定所述目标应用场景对应的目标追踪算法;
    运行所述目标追踪算法得到计算结果。
  9. 根据权利要求1所述的方法,其特征在于,所述在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,包括:
    在确定由所述终端设备运行所述追踪算法的情况下,向所述拍摄设备发送追踪数据获取请求;
    在接收到所述拍摄设备根据所述追踪数据获取请求发送的追踪数据的情况下,根据所述追踪数据和所述追踪算法,计算得到所述计算结果。
  10. 根据权利要求9所述的方法,其特征在于,所述根据所述追踪数据和所述追踪算法,计算得到所述计算结果,包括:
    在由所述追踪数据生成的追踪图像中,识别目标实体对象;
    在为所述追踪图像中的目标实体对象添加了物体框之后,得到所述计算结果,所述物体框用于反映所述目标实体对象的所处位置。
  11. 一种追踪算法的运行方法,应用于拍摄设备,其特征在于,所述方法包括:
    发送所述拍摄设备的设备运行信息至所述终端设备;
    在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果;
    根据所述计算结果,控制所述拍摄设备执行追踪操作。
  12. 根据权利要求11所述的方法,其特征在于,所述方法还包括:
    在接收到所述终端设备发送的同时运算通知的情况下,确定先接收到终端设备发送的计算结果,或确定先根据所述同时运算通知计算得到计算结果;
    所述根据所述计算结果,控制所述拍摄设备执行追踪操作,包括:
    在确定先根据所述同时运算通知计算得到计算结果的情况下,采用所述拍摄设备计算得到计算结果控制所述拍摄设备执行追踪操作;
    在确定先接收到终端设备发送的计算结果的情况下,采用所述终端设备发送的计算结果控制所述拍摄设备执行追踪操作。
  13. 根据权利要求11所述的方法,其特征在于,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算 法;所述方法还包括:
    接收所述终端设备发送的针对所述第一追踪算法的第一计算结果;
    在接收到所述终端设备发送的针对运行所述第二追踪算法的通知的情况下,运行所述第二追踪算法得到第二计算结果;
    所述根据所述计算结果,控制所述拍摄设备执行追踪操作,包括:
    从所述第一计算结果和所述第二计算结果中选取一个计算结果,并根据选取的计算结果控制所述拍摄设备执行追踪操作。
  14. 根据权利要求13所述的方法,其特征在于,所述第一追踪算法用于识别第一实体对象,所述第二追踪算法用于识别第二实体对象;
    所述从所述第一计算结果和所述第二计算结果中选取一个计算结果,并根据选取的计算结果控制所述拍摄设备执行追踪操作,包括:
    识别所述拍摄设备拍摄的追踪图像中的实体对象,所述追踪图像由所述拍摄设备采集的追踪数据生成;
    在所述追踪画面中包含的第一实体对象的数量大于第一数量阈值的情况下,选取所述第一计算结果控制所述拍摄设备执行追踪操作;
    在所述追踪画面中包含的第二实体对象的数量大于第二数量阈值的情况下,选取所述第二计算结果控制所述拍摄设备执行追踪操作。
  15. 根据权利要求14所述的方法,其特征在于,所述方法还包括:
    在所述追踪画面中同时包含所述第一实体对象和所述第二实体对象的情况下,将所述第一计算结果和所述第二计算结果融合,得到目标计算结果;
    根据所述目标计算结果控制所述拍摄设备执行追踪操作。
  16. 根据权利要求11所述的方法,其特征在于,所述方法还包括:
    在接收到所述终端设备发送的追踪数据获取请求的情况下,将所述拍摄设备采集到的追踪数据发送至所述终端设备。
  17. 根据权利要求11所述的方法,其特征在于,所述计算结果包括:由所述拍摄设备采集的追踪数据生成的追踪图像中,目标实体对象对应的物体框,所述物体框用于反映所述目标实体对象的所处位置;所述拍摄设备具有云台;
    所述根据所述计算结果,控制所述拍摄设备执行追踪操作,包括:
    根据所述物体框的位置信息,计算目标移动向量值;
    根据所述目标移动向量值控制所述云台移动,以实现所述拍摄设备对所述目标实体对象的追踪拍摄。
  18. 一种追踪算法的运行方法,应用于拍摄设备,其特征在于,所述方法包括:
    获取终端设备和拍摄设备的设备运行信息;
    根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
    在确定由所述终端设备运行所述追踪算法的情况下,通知所述终端设备运行所述追踪算法,以及接收所述终端设备发送的计算结果;
    在确定由所述拍摄设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果;
    根据所述计算结果,控制所述拍摄设备执行追踪操作。
  19. 一种追踪算法的运行方法,应用于终端设备,其特征在于,所述方法包括:
    在接收到所述拍摄设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果;
    发送所述计算结果至所述拍摄设备。
  20. 一种追踪算法的运行装置,应用于终端设备,其特征在于,所述装置包括:存储器和处理器;
    所述存储器用于,获取终端设备和拍摄设备的设备运行信息;
    所述处理器用于:根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
    在确定由所述终端设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果,并将所述计算结果发送至所述拍摄设备;
    在确定由所述拍摄设备运行所述追踪算法的情况下,通知所述拍摄设备运行所述追踪算法。
  21. 根据权利要求20所述的装置,其特征在于,所述设备运行信息包 括:当前负载信息;所述处理器具体用于:
    在所述终端设备的当前负载信息不满足算法运行条件的情况下,确定由所述拍摄设备运行所述追踪算法;
    在所述拍摄设备的当前负载信息不满足所述算法运行条件的情况下,确定由所述终端设备运行所述追踪算法。
  22. 根据权利要求21所述的装置,其特征在于,所述处理器还用于:
    在所述终端设备和所述拍摄设备的当前负载信息都满足所述算法运行条件的情况下,确定同时由所述终端设备和所述拍摄设备运行所述追踪算法;
    发送同时运算通知至所述拍摄设备。
  23. 根据权利要求22所述的装置,其特征在于,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算法;所述处理器还用于:
    运行所述第一追踪算法得到第一计算结果,并将所述第一计算结果发送至所述拍摄设备;
    通知所述拍摄设备运行所述第二追踪算法。
  24. 根据权利要求20所述的装置,其特征在于,所述设备运行信息包括当前负载信息和网络带宽;所述处理器还用于:
    根据所述当前负载信息和网络带宽,确定与所述拍摄设备之间的传输通道的传输延迟;
    在所述传输延迟小于或等于预设延迟阈值的情况下,进入所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法的步骤;
    在所述传输延迟大于所述预设延迟阈值的情况下,确定由所述拍摄设备运行所述追踪算法。
  25. 根据权利要求20所述的装置,其特征在于,所述处理器还用于:
    确定与所述拍摄设备之间的传输通道的类型;
    在所述类型为第一类型的情况下,进入所述根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法的步骤;
    在所述类型为第二类型的情况下,确定由所述拍摄设备运行所述追踪算法;
    其中,所述第一类型包括:USB连接通道、5G连接通道;所述第二类别包括:除所述USB连接通道、所述5G连接通道之外的其他连接通道。
  26. 根据权利要求20所述的装置,其特征在于,所述处理器还用于:
    通过预设的自定义接口,接收新的追踪算法;
    在本地增加所述新的追踪算法,或用所述新的追踪算法替换所述本地的追踪算法。
  27. 根据权利要求20所述的装置,其特征在于,所述终端设备的本地建立有应用场景和追踪算法的对应关系;所述处理器具体用于:
    在确定由所述终端设备运行所述追踪算法的情况下,确定当前的目标应用场景;
    根据所述对应关系,确定所述目标应用场景对应的目标追踪算法;
    运行所述目标追踪算法得到计算结果。
  28. 根据权利要求20所述的装置,其特征在于,所述处理器具体用于:
    在确定由所述终端设备运行所述追踪算法的情况下,向所述拍摄设备发送追踪数据获取请求;
    在接收到所述拍摄设备根据所述追踪数据获取请求发送的追踪数据的情况下,根据所述追踪数据和所述追踪算法,计算得到所述计算结果。
  29. 根据权利要求28所述的装置,其特征在于,所述处理器具体用于:
    在由所述追踪数据生成的追踪图像中,识别目标实体对象;
    在为所述追踪图像中的目标实体对象添加了物体框之后,得到所述计算结果,所述物体框用于反映所述目标实体对象的所处位置。
  30. 一种追踪算法的运行装置,应用于拍摄设备,其特征在于,所述装置包括:存储器和处理器;
    所述处理器用于:
    发送所述拍摄设备的设备运行信息至所述终端设备;
    在接收到所述终端设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果,或接收所述终端设备发送的计算结果;
    根据所述计算结果,控制所述拍摄设备执行追踪操作。
  31. 根据权利要求30所述的装置,其特征在于,所述处理器还用于:
    在接收到所述终端设备发送的同时运算通知的情况下,确定先接收到终端设备发送的计算结果,或确定先根据所述同时运算通知计算得到计算结果;
    所述处理器具体用于:
    在确定先根据所述同时运算通知计算得到计算结果的情况下,采用所述拍摄设备计算得到计算结果控制所述拍摄设备执行追踪操作;
    在确定先接收到终端设备发送的计算结果的情况下,采用所述终端设备发送的计算结果控制所述拍摄设备执行追踪操作。
  32. 根据权利要求30所述的装置,其特征在于,所述追踪算法包括:部署在所述终端设备的第一追踪算法和部署在所述拍摄设备的第二追踪算法;所述存储器用于:
    接收所述终端设备发送的针对所述第一追踪算法的第一计算结果;
    所述处理器还用于:
    在接收到所述终端设备发送的针对运行所述第二追踪算法的通知的情况下,运行所述第二追踪算法得到第二计算结果;
    所述处理器具体用于:
    从所述第一计算结果和所述第二计算结果中选取一个计算结果,并根据选取的计算结果控制所述拍摄设备执行追踪操作。
  33. 根据权利要求32所述的装置,其特征在于,所述第一追踪算法用于识别第一实体对象,所述第二追踪算法用于识别第二实体对象;所述处理器具体用于:
    识别所述拍摄设备拍摄的追踪图像中的实体对象,所述追踪图像由所述拍摄设备采集的追踪数据生成;
    在所述追踪画面中包含的第一实体对象的数量大于第一数量阈值的情况下,选取所述第一计算结果控制所述拍摄设备执行追踪操作;
    在所述追踪画面中包含的第二实体对象的数量大于第二数量阈值的情况下,选取所述第二计算结果控制所述拍摄设备执行追踪操作。
  34. 根据权利要求33所述的装置,其特征在于,所述处理器还用于:
    在所述追踪画面中同时包含所述第一实体对象和所述第二实体对象的 情况下,将所述第一计算结果和所述第二计算结果融合,得到目标计算结果;
    根据所述目标计算结果控制所述拍摄设备执行追踪操作。
  35. 根据权利要求30所述的装置,其特征在于,所述处理器还用于:
    在接收到所述终端设备发送的追踪数据获取请求的情况下,将所述拍摄设备采集到的追踪数据发送至所述终端设备。
  36. 根据权利要求30所述的装置,其特征在于,所述计算结果包括:由所述拍摄设备采集的追踪数据生成的追踪图像中,目标实体对象对应的物体框,所述物体框用于反映所述目标实体对象的所处位置;所述拍摄设备具有云台;所述处理器具体用于:
    根据所述物体框的位置信息,计算目标移动向量值;
    根据所述目标移动向量值控制所述云台移动,以实现所述拍摄设备对所述目标实体对象的追踪拍摄。
  37. 一种追踪算法的运行装置,应用于拍摄设备,其特征在于,所述装置包括:存储器和处理器;
    所述存储器用于,获取终端设备和拍摄设备的设备运行信息;
    所述处理器用于:
    根据所述设备运行信息,确定由所述终端设备和/或所述拍摄设备运行追踪算法;
    在确定由所述终端设备运行所述追踪算法的情况下,通知所述终端设备运行所述追踪算法,以及接收所述终端设备发送的计算结果;
    在确定由所述拍摄设备运行所述追踪算法的情况下,运行所述追踪算法得到计算结果;
    根据所述计算结果,控制所述拍摄设备执行追踪操作。
  38. 一种追踪算法的运行装置,应用于终端设备,其特征在于,所述装置包括:存储器和处理器;
    所述存储器用于,接收所述拍摄设备发送的针对运行追踪算法的通知;
    所述处理器用于:
    在接收到所述拍摄设备发送的针对运行追踪算法的通知的情况下,运行所述追踪算法得到计算结果;
    发送所述计算结果至所述拍摄设备。
  39. 一种电子设备,其特征在于,包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的计算机程序,所述计算机程序被所述处理器执行时实现如权利要求1至19中任一项所述的追踪算法的运行方法。
  40. 一种计算机可读存储介质,其特征在于,包括指令,当其在计算机上运行时,使得所述计算机执行权利要求1至19中任一项所述的追踪算法的运行方法。
PCT/CN2020/136744 2020-12-16 2020-12-16 追踪算法的运行方法、装置、电子设备及计算机可读存储介质 WO2022126415A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/136744 WO2022126415A1 (zh) 2020-12-16 2020-12-16 追踪算法的运行方法、装置、电子设备及计算机可读存储介质
CN202080074215.1A CN114600445A (zh) 2020-12-16 2020-12-16 追踪算法的运行方法、装置、电子设备及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/136744 WO2022126415A1 (zh) 2020-12-16 2020-12-16 追踪算法的运行方法、装置、电子设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022126415A1 true WO2022126415A1 (zh) 2022-06-23

Family

ID=81814554

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/136744 WO2022126415A1 (zh) 2020-12-16 2020-12-16 追踪算法的运行方法、装置、电子设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN114600445A (zh)
WO (1) WO2022126415A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117956264A (zh) * 2024-03-26 2024-04-30 荣耀终端有限公司 拍摄方法、电子设备、存储介质和程序产品

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN205750541U (zh) * 2016-04-19 2016-11-30 天津城建大学 一种多旋翼飞行器的控制***
WO2017164753A1 (en) * 2016-03-24 2017-09-28 Motorola Solutions, Inc. Methods and apparatus for continuing a zoom of a stationary camera utilizing a drone
CN108513696A (zh) * 2017-03-21 2018-09-07 深圳市大疆创新科技有限公司 无人机控制方法及控制设备、无人机监管方法及监管设备
CN108881706A (zh) * 2017-05-16 2018-11-23 北京三星通信技术研究有限公司 控制多媒体设备工作的方法及装置
CN111279690A (zh) * 2019-01-30 2020-06-12 深圳市大疆创新科技有限公司 多负载图传方法、控制***、控制终端、无人机和服务器

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110099395B (zh) * 2018-01-30 2022-04-15 ***通信有限公司研究院 一种信息处理方法、设备、终端和计算机存储介质
CN109218612B (zh) * 2018-09-17 2022-04-22 东莞市丰展电子科技有限公司 一种追踪拍摄***及拍摄方法
KR20200094444A (ko) * 2019-01-30 2020-08-07 한국전자통신연구원 지능형 영상 촬영 장치, 그리고 이를 이용하는 객체 추적 장치 및 방법
CN109996039B (zh) * 2019-04-04 2021-06-25 中南大学 一种基于边缘计算的目标追踪方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017164753A1 (en) * 2016-03-24 2017-09-28 Motorola Solutions, Inc. Methods and apparatus for continuing a zoom of a stationary camera utilizing a drone
CN205750541U (zh) * 2016-04-19 2016-11-30 天津城建大学 一种多旋翼飞行器的控制***
CN108513696A (zh) * 2017-03-21 2018-09-07 深圳市大疆创新科技有限公司 无人机控制方法及控制设备、无人机监管方法及监管设备
CN108881706A (zh) * 2017-05-16 2018-11-23 北京三星通信技术研究有限公司 控制多媒体设备工作的方法及装置
CN111279690A (zh) * 2019-01-30 2020-06-12 深圳市大疆创新科技有限公司 多负载图传方法、控制***、控制终端、无人机和服务器

Also Published As

Publication number Publication date
CN114600445A (zh) 2022-06-07

Similar Documents

Publication Publication Date Title
US20230232213A1 (en) Information transmission methods and apparatuses, and communication devices and storage medium
JP2019186931A (ja) カメラ撮影制御方法、装置、インテリジェント装置およびコンピュータ記憶媒体
EP2724343B1 (en) Video remixing system
EP2892205B1 (en) Method and device for determining a sharing terminal
EP3125525A1 (en) Method and system for enabling camera of mobile terminal to automatically adapt to scene
CN108696911B (zh) 一种物联网数据传输方式的选择方法和装置
CN107146623B (zh) 基于人工智能的语音识别方法、装置和***
KR102159045B1 (ko) 네트워크 정책 업데이트를 트리거하는 방법, 관리 기능 엔티티 및 코어 네트워크 기기
WO2021189650A1 (zh) 实时视频流的显示方法、头戴设备、存储介质及电子设备
CN106331569A (zh) 即时视频画面中人物脸部变换方法以及***
WO2022126415A1 (zh) 追踪算法的运行方法、装置、电子设备及计算机可读存储介质
CN114172809B (zh) 一种基于目标追踪的视频计算云边协同任务调度方法
CN113485842B (zh) 一种基于设备集群进行数据分析的方法及设备
WO2016192467A1 (zh) 一种播放视频的方法及装置
CN108600691B (zh) 图像采集方法、装置及***
CN110868747B (zh) 一种可应用于多网络模式检测延时并自动切换的方法
CN113784052B (zh) 超高清多摄输入切换装置、方法及***
CN108206940B (zh) 视频串流的接合与传输方法、网关装置及观看装置
CN111245878A (zh) 一种基于混合云计算和雾计算的计算卸载通信网络的方法
CN105812835A (zh) 一种信息处理方法和电子设备
CN112911132B (zh) 拍照控制方法、拍照控制装置、电子设备及存储介质
CN114500129A (zh) 一种信息处理方法及电子设备
CN112866729A (zh) 一种降低网络直播时延的方法及网络直播***
CN113014961A (zh) 视频推送及传输方法、视角同步方法及装置、存储介质
CN210221843U (zh) 输电线设备的蜂窝缺陷检测***

Legal Events

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

Ref document number: 20965433

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20965433

Country of ref document: EP

Kind code of ref document: A1