WO2022061615A1 - 待跟随目标的确定方法、装置、系统、设备及存储介质 - Google Patents

待跟随目标的确定方法、装置、系统、设备及存储介质 Download PDF

Info

Publication number
WO2022061615A1
WO2022061615A1 PCT/CN2020/117223 CN2020117223W WO2022061615A1 WO 2022061615 A1 WO2022061615 A1 WO 2022061615A1 CN 2020117223 W CN2020117223 W CN 2020117223W WO 2022061615 A1 WO2022061615 A1 WO 2022061615A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
image
followed
recognition result
specific
Prior art date
Application number
PCT/CN2020/117223
Other languages
English (en)
French (fr)
Inventor
施泽浩
聂谷洪
王栋
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 CN202080007463.4A priority Critical patent/CN113273174A/zh
Priority to PCT/CN2020/117223 priority patent/WO2022061615A1/zh
Publication of WO2022061615A1 publication Critical patent/WO2022061615A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/667—Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user

Definitions

  • the present application relates to the technical field of target following, and in particular, to a method, apparatus, system, device and storage medium for determining a target to be followed.
  • the target to be followed needs to be determined.
  • the target detection algorithm is used to identify specific targets such as people, cars and ships, and the specific target is used as the target to be followed.
  • the number of categories that can be detected by the target detection algorithm is limited. , which cannot cover the user's usage scenarios.
  • the user selects other targets to be followed through the human-computer interaction interface, which is cumbersome and requires high precision for the target to be followed.
  • the embodiments of the present application provide a method, apparatus, system, device and storage medium for determining a target to be followed, aiming to accurately and quickly determine the target to be followed and improve user experience.
  • an embodiment of the present application provides a method for determining a target to be followed, which is applied to a target determining device, where the target determining device is configured to communicate with a photographing device, and the method includes:
  • a target to be followed is determined from the image according to the first recognition result and the second recognition result.
  • an embodiment of the present application further provides a target determination apparatus, where the target determination apparatus is configured to communicate with a photographing device, and the target determination apparatus includes a memory and a processor;
  • the memory is used to store computer programs
  • the processor is configured to execute the computer program and implement the following steps when executing the computer program:
  • a target to be followed is determined from the image according to the first recognition result and the second recognition result.
  • an embodiment of the present application further provides a target following system, where the target following system includes a gimbal, a photographing device mounted on the gimbal, and the above-mentioned target determination device.
  • an embodiment of the present application further provides a handheld pan/tilt, the handheld pan/tilt includes a handle portion, a pan/tilt connected to the handle portion, and the above target determination device, the pan/tilt is used for A photographing device is mounted, and the target determination device is provided on the handle portion.
  • an embodiment of the present application further provides a movable platform, the movable platform includes a platform body, a pan/tilt mounted on the platform body, and the above-mentioned target determination device, the pan/tilt is used for A photographing device is mounted, and the target determination device is arranged on the platform body.
  • an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the above-mentioned The steps of the method for determining the target to be followed.
  • the embodiments of the present application provide a method, device, system, device, and storage medium for determining a target to be followed.
  • a first recognition result of the specific target and a salient target are obtained.
  • the second recognition result of the salient target, and according to the first recognition result and the second recognition result, the target to be followed is determined from the image, and the whole process does not require the user to select other targets or specific targets as the target to be followed through the human-computer interaction interface.
  • the target can be accurately and quickly determined to be followed, which greatly improves the user experience.
  • FIG. 1 is a schematic diagram of a scenario for implementing the method for determining a target to be followed provided by an embodiment of the present application;
  • FIG. 2 is a schematic diagram of another scenario for implementing the method for determining a target to be followed provided by an embodiment of the present application;
  • FIG. 3 is a schematic flowchart of steps of a method for determining a target to be followed provided by an embodiment of the present application;
  • Fig. 4 is a schematic flow chart of a sub-step of the method for determining the target to be followed in Fig. 3;
  • Fig. 5 is a sub-step schematic flow chart of the method for determining the target to be followed in Fig. 3;
  • Fig. 6 is a sub-step schematic flow chart of the method for determining the target to be followed in Fig. 3;
  • FIG. 7 is a schematic flowchart of steps of another method for determining a target to be followed provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of an image collected by a photographing device displayed by a display device in an embodiment of the present application.
  • FIG. 9 is another schematic diagram of an image captured by a photographing device displayed by a display device in an embodiment of the present application.
  • FIG. 10 is another schematic diagram of an image captured by a photographing device displayed by a display device in an embodiment of the present application.
  • FIG. 11 is another schematic diagram of an image captured by a photographing device displayed by a display device in an embodiment of the present application.
  • FIG. 12 is another schematic diagram of an image captured by a photographing device displayed by a display device in an embodiment of the present application.
  • FIG. 13 is another schematic diagram of an image captured by a photographing device displayed by a display device in an embodiment of the present application.
  • FIG. 14 is a schematic block diagram of the structure of an apparatus for determining a target provided by an embodiment of the present application.
  • 15 is a schematic block diagram of the structure of a target following system provided by an embodiment of the present application.
  • 16 is a schematic block diagram of the structure of a handheld cloud platform provided by an embodiment of the present application.
  • FIG. 17 is a schematic structural block diagram of a movable platform provided by an embodiment of the present application.
  • the target to be followed needs to be determined.
  • the target detection algorithm is used to identify specific targets such as people, cars and ships, and the specific target is used as the target to be followed.
  • the number of categories that can be detected by the target detection algorithm is limited. , which cannot cover the user's usage scenarios.
  • the user selects other targets to be followed through the human-computer interaction interface, which is cumbersome and requires high precision for the target to be followed.
  • the embodiments of the present application provide a method, device, system, device and storage medium for determining a target to be followed.
  • the first recognition result and the second recognition result of the salient target, and according to the first recognition result and the second recognition result, the target to be followed is determined from the image, and the whole process does not require the user to select other targets or
  • the specific target is used as the target to be followed, and the target to be followed can be determined accurately and quickly, which greatly improves the user experience.
  • FIG. 1 is a schematic diagram of a scenario for implementing the method for determining a target to be followed provided by an embodiment of the present application.
  • the scene includes a handheld gimbal 100 and a photographing device 200 mounted on the handheld gimbal 100 .
  • the handheld gimbal 100 includes a handle portion 101 and a gimbal 102 disposed on the handle portion 101 .
  • the gimbal 102 uses When the photographing device 200 is mounted, the photographing device 200 may be integrated with the pan/tilt 102 , or may be externally connected to the pan/tilt 102 .
  • the photographing device 200 may be a smartphone, or a camera, such as a single-lens reflex camera, or a camera.
  • the handheld platform 100 can carry the photographing device 200 for fixing the photographing device 200 and changing the height, inclination and/or direction of the photographing device 200, or for stably keeping the photographing device 200 in a certain posture and controlling the photographing device 200 to shoot.
  • the handheld pan/tilt 100 is communicatively connected to the photographing device 200, and the handheld pan/tilt 100 may be connected to the photographing device 200 through a control line, such as a shutter release cable.
  • a control line such as a shutter release cable.
  • the type of the shutter release cable is not limited here, for example, the shutter release cable may be a Universal Serial Bus (Universal Serial Bus, USB).
  • the handheld gimbal 100 can also be connected to the photographing device 200 in a wireless manner. communication connection between.
  • the pan/tilt head 102 includes three-axis motors, and the three-axis motors are a pitch (pitch) axis motor 1021, a yaw (yaw) axis motor 1022, and a roll (roll) axis motor (not shown in FIG. 1 ), respectively.
  • the three-axis motor is used to adjust the balance posture of the photographing device 200 mounted on the gimbal 102 so as to photograph a stable and smooth picture.
  • the gimbal 102 is also provided with an inertial measurement unit (Inertial measurement unit, IMU), which may be at least one of an accelerometer or a gyroscope, which can be used to measure the attitude and acceleration of the gimbal 102, so as to measure the attitude and acceleration of the gimbal 102 according to the attitude Adjust the posture of the gimbal 102 .
  • IMU inertial measurement unit
  • the handle portion 101 is also provided with an inertial measurement unit (Inertial measurement unit, IMU), for example including at least one of an accelerometer or a gyroscope, which can be used to measure the attitude and acceleration of the handle portion 101, etc., In order to adjust the posture of the pan/tilt head 102 according to the posture of the handle part 101 and the posture of the pan/tilt head 102 .
  • IMU inertial measurement unit
  • the handheld pan-tilt 100 includes a processor, and the processor is configured to process input control instructions, or send and receive signals.
  • the processor may be provided inside the handle portion 101 .
  • the processor may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (application specific integrated circuits) circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the handheld gimbal 100 includes multiple working modes, including, for example, a follow mode, a target tracking mode, a lock mode, a motion mode, and/or a sleep mode, and the like.
  • the handheld gimbal 100 performs different actions in different working modes.
  • the following mode is used to control the shooting device 200 to follow the shooting, and the following mode may refer to the shooting mode in which the gimbal 102 follows the movement of the handle part 101; if the handheld gimbal 100 is in target tracking mode, after the target to be followed is determined, the pan/tilt 102 starts to automatically rotate so that the angle of the photographing device 200 always follows the target to be followed and keeps the target to be followed in the captured image.
  • the lock mode means that the three axes of the gimbal 102 are locked, and the three axes of the gimbal do not follow;
  • the motion mode means that the gimbal 102 follows at a preset speed, such as the maximum speed of the three axes of the gimbal;
  • sleep mode Mode means to control the handheld gimbal to enter the sleep state.
  • the following object of the gimbal may be the handle part 101, the target to be followed, or others, which can be set as required, which is not specifically limited here.
  • the determination method of the target to be followed may be as follows: the processor of the handheld platform 100 obtains the image collected by the photographing device 200, and recognizes the specific target and the salient target in the image, and obtains the first target of the specific target. A recognition result and a second recognition result of the salient target, and according to the first recognition result and the second recognition result, the target to be followed is determined from the image.
  • the determination method of the target to be followed can also be determined by the user after performing an operation such as frame selection or click selection on the hand-held platform 100, or it can also be determined according to a specific posture in the image captured by the photographing device 200, It may also be determined according to the position of a specific target or a salient target in the image captured by the photographing device 200 . There is no specific limitation here.
  • the handle portion 101 is further provided with a control key, so that the user can operate the control key to control the pan/tilt head 102 or the photographing device 200 .
  • the control key may be, for example, a key, a trigger, a knob or a joystick, etc., of course, other forms of physical keys or virtual keys are also included.
  • the virtual keys may be virtual buttons provided on the touch screen for interacting with the user.
  • the joystick can be used to control the movement of at least one rotating shaft, and then control the movement of the photographing device 200 . It will be appreciated that the joystick can also be used for other functions. It can be understood that the number of control keys may be one or more.
  • control keys When the number of control keys is one, different operation modes can be used to generate different control instructions for the control key, for example, the number of times of pressing is different; when the number of control keys is multiple, for example, the first control key, second control key, third control key, etc., different control keys are used to generate different control instructions.
  • the control key includes a follow control key, and the follow control key is used to control the handheld gimbal 100 to start or exit the target tracking mode.
  • One pressing operation if the handheld pan/tilt 100 is not in the target tracking mode, control the handheld pan/tilt 100 to be in the target tracking mode, and acquire the image captured by the photographing device 200; the first recognition result, and identify the salient target in the image to obtain the second recognition result of the salient target; according to the first recognition result and the second recognition result, determine the target to be followed from the image, so that the user can
  • the handheld pan/tilt 100 can be quickly controlled to enter the target tracking mode by following the control buttons, so that the target to be followed can be tracked.
  • the handheld platform 100 further includes a display device, and the display device is used to display the image captured by the photographing device 200 .
  • the processor controls the display device to display the image collected by the photographing device 200, and identifies the target to be followed in the image displayed by the display device; according to the first The identification result and the second identification result determine the following priority of each candidate target in the image; in response to the second pressing operation of the following control button, according to the following priority of the target to be followed and the following of each candidate target priority, re-determine the target to be followed, and mark the re-determined target to be followed in the image. It is convenient for the user to switch the target to be followed through the follow control button.
  • FIG. 2 is a schematic diagram of another scenario for implementing the method for determining a target to be followed provided by an embodiment of the present application.
  • the scene includes a control terminal 300 and a movable platform 400 , the control terminal 300 is connected in communication with the movable platform 400 , the control terminal 300 includes a display device 310 , and the display device 310 is used to display an image sent by the movable platform 400 .
  • the display device 310 includes a display screen disposed on the control terminal 300 or a display independent of the control terminal 300, and the display independent of the control terminal 300 may include a mobile phone, a tablet computer, a personal computer, etc., or may also be a Other electronic equipment with a display screen.
  • the display screen includes an LED display screen, an OLED display screen, an LCD display screen, and the like.
  • the movable platform 400 includes a platform body 410, a pan/tilt 420 mounted on the platform body, and a power system 430.
  • the pan/tilt 420 is used to carry the photographing device 500
  • the power system 430 includes a motor 431 and a propeller 432. 431 is used to drive the propeller 432 to rotate, so as to provide moving power for the movable platform.
  • the pan/tilt 420 includes three-axis motors, which are a translation axis motor 421, a pitch axis motor 422, and a roll axis motor 423, which are used to adjust the balance posture of the photographing device 500 mounted on the pan/tilt 420, so as to capture images anytime, anywhere. High-precision stable picture.
  • the movable platform 400 further includes a processor, and the processor is configured to process the input control instructions, or to send and receive signals.
  • the processor may be located inside the movable platform 400 .
  • the processor may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (application specific integrated circuits) circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • control terminal 300 includes a follow-up control button, and the follow-up control button is used to control the movable platform 400 to start or exit the target tracking mode.
  • the movable platform 400 can control the PTZ. 420 moves, so that the angle of the photographing device 500 always follows the target to be followed and keeps the target to be followed in the captured picture.
  • control terminal 300 generates a target following start instruction in response to the user's first pressing operation on the follow control button, and sends the target follow start instruction to the movable platform 400; the movable platform 400 receives the target follow start instruction, and It is transmitted to the processor, and the processor controls the movable platform 400 to be in the target tracking mode according to the target following the start instruction, and obtains the image collected by the shooting device 500, and then identifies the specific target in the image to obtain the first target of the specific target.
  • the salient target in the image is recognized, and the second recognition result of the salient target is obtained, and then the target to be followed is determined from the image according to the first recognition result and the second recognition result, and according to the shooting
  • the image collected by the device 500 controls the movement of the pan/tilt 420, so that the angle of the photographing device 500 always follows the target to be followed and keeps the target to be followed in the captured image.
  • the movable platform includes movable robots, unmanned aerial vehicles and unmanned vehicles, etc.
  • the movable platform 400 is an unmanned aerial vehicle, and the power system 430 can make the unmanned aerial vehicle take off vertically from the ground, or land vertically on the ground, Without the need for any horizontal movement of the drone (eg no taxiing on the runway).
  • the power system 430 may allow the drone to preset positions and/or turn the steering wheel in the air.
  • One or more of the power systems 430 may be controlled independently of the other power systems 430 .
  • one or more power systems 430 may be controlled simultaneously.
  • the drone may have multiple horizontally oriented power systems 430 to track the lift and/or push of the target.
  • the horizontally oriented power system 430 can be actuated to provide the drone with the ability to take off vertically, land vertically, and hover.
  • one or more of the horizontally oriented power systems 430 may rotate in a clockwise direction, while one or more of the other horizontally oriented power systems may rotate in a counter-clockwise direction.
  • the rotational rate of each power system 430 in the horizontal direction can be varied independently to achieve lift and/or push operations caused by each power system 430 to adjust the spatial orientation, speed and/or acceleration of the drone (eg, relative to multiple rotation and translation up to three degrees of freedom).
  • the drone may also include a sensing system, which may include one or more sensors to sense the spatial orientation, velocity, and/or acceleration of the drone (eg, relative to up to three Degree of freedom rotation and translation), angular acceleration, attitude, position (absolute position or relative position), etc.
  • the one or more sensors include GPS sensors, motion sensors, inertial sensors, proximity sensors, or image sensors.
  • the sensing system can also be used to collect data on the environment in which the UAV is located, such as climatic conditions, potential obstacles to be approached, locations of geographic features, locations of man-made structures, and the like.
  • the drone may include a tripod
  • the tripod is a contact piece between the drone and the ground when the drone lands
  • the tripod can be received by the unmanned aerial vehicle in a flying state (for example, when the unmanned aerial vehicle is cruising). It can only be put down when landing; it can also be fixedly installed on the drone and kept in the state of being put down all the time.
  • the movable platform 400 can communicate with the control terminal 300, and can realize data interaction between the control terminal 300 and the movable platform 400, such as the movement control of the movable platform 400, the control of the load (when When the payload is the photographing device 500, the control terminal 300 can control the photographing device 500), wherein the control terminal 300 can communicate with the movable platform 400 and/or the payload, and the communication between the movable platform 400 and the control terminal 300 can be Wireless communication can provide direct communication between the movable platform 400 and the control terminal 300 . This direct communication can occur without any intermediary devices or networks.
  • indirect communication may be provided between the movable platform 400 and the control terminal 300 .
  • Such indirect communication may take place by means of one or more intermediaries or networks.
  • indirect communication may utilize a telecommunications network.
  • Indirect communication may take place by means of one or more routers, communication towers, satellites, or any other intermediary device or network.
  • Examples of types of communication may include, but are not limited to, communication via the Internet, Local Area Network (LAN), Wide Area Network (WAN), Bluetooth, Near Field Communication (NFC) technology, based on technologies such as General Packet Radio Service (GPRS), GSM Enhanced Data GSM Environment (EDGE), 3G, 4G, or Long Term Evolution (LTE) protocols for mobile data protocols, infrared (IR) communication technology, and/or Wi-Fi, and may be wireless, wired, or its combination.
  • GPRS General Packet Radio Service
  • EDGE GSM Enhanced Data GSM Environment
  • 3G Third Generation
  • 4G Long Term Evolution
  • LTE Long Term Evolution
  • control terminal 300 may include but not limited to: smart phone/mobile phone, tablet computer, personal digital assistant (PDA), desktop computer, media content player, video game station/system, virtual reality system, augmented reality system, wearable devices (eg, watches, glasses, gloves, headwear (eg, hats, helmets, virtual reality headsets, augmented reality headsets, head mounted devices (HMDs), headbands), pendants, armbands, leg loops, shoes, vest), gesture recognition device, microphone, any electronic device capable of providing or rendering image data, or any other type of device.
  • the control terminal 300 may be a handheld terminal, and the control terminal 300 may be portable.
  • the control terminal 300 may be carried by a human user. In some cases, the control terminal 300 may be remote from the human user, and the user may control the control terminal 300 using wireless and/or wired communication.
  • FIG. 1 or FIG. 2 is only used to explain the method for determining the target to be followed provided by the embodiment of the present application, but does not constitute a limitation on the application scenario of the method for determining the target to be followed provided by the embodiment of the present application.
  • FIG. 3 is a schematic flowchart of steps of a method for determining a target to be followed provided by an embodiment of the present application.
  • the method for determining the target to be followed includes steps S101 to S103 .
  • Step S101 identifying a specific target in the image collected by the photographing device, and obtaining a first identification result of the specific target, wherein the category of the specific target is located in a first preset category library;
  • Step S102 Identify a salient target in the image collected by the photographing device, and obtain a second identification result of the salient target, wherein the salient target is based on the image collected by the target object to determine the degree of significance in;
  • Step S103 Determine the target to be followed from the image according to the first recognition result and the second recognition result.
  • the image collected by the photographing device is acquired, and the specific target and the salient target are identified in the image collected by the photographing device, and the first recognition result of the specific target and the second recognition result of the salient target are obtained. , and then, based on the first recognition result and the second recognition result, the target to be followed is determined from the images collected by the photographing device.
  • the categories in the first preset category library include categories of objects that can be identified by the target detection algorithm, such as pedestrians, vehicles, and ships.
  • the target detection algorithm can be used to identify in the images collected by the shooting device.
  • the first recognition result of the specific target can be obtained, and the salient target can be identified in the image collected by the photographing device through the salient target detection algorithm, and the second recognition result of the salient target can be obtained.
  • the class of saliency targets is different from the class of specific targets.
  • the saliency target is determined according to the saliency of the target object in the captured image. For example, when the saliency of the target object in the captured image is greater than or equal to a preset saliency It is determined that the target object is a saliency target, and when the salience degree of the target object in the captured image is less than a preset salience degree, it can be determined that the target object is not a salient target.
  • the preset significance level may be set based on the actual situation, which is not specifically limited in this embodiment of the present application.
  • the salience of the target object in the captured image may be determined according to the duration of stay of the target object at a preset position in the image. And/or can be determined according to the saliency value between the image area where the target object is located in the acquired image and the adjacent image area. It can be understood that the longer the stay time of the target object in the preset position in the image, the higher the salience of the target object in the collected image, and the shorter the stay time of the target object in the preset position in the image. , the lower the salience of the target object in the collected image.
  • the target to be followed includes any one of a saliency target and a specific target
  • the salience target includes an object located at a preset position in the image, and the object is at a preset position and/or, the saliency target is located in a foreground image in the image; and/or, the saliency target is in the image area in the image and the image area in the image
  • the saliency value between adjacent image regions of is greater than or equal to the preset saliency value.
  • the saliency value between the image area where the saliency target is located and the adjacent image area is determined according to the color difference and/or contrast between the image area where the saliency target is located and the adjacent image area.
  • the preset position, preset dwell time and preset significance value can be set based on the actual situation or set by the user. For example, the preset position can be the center of the image, the preset dwell time is 10 seconds, and the preset significance value is 50. .
  • the method of determining the target to be followed from the image may be: if the first recognition result is that there is a specific target in the image, then according to the first recognition result, the image The specific target in the image is determined as the target to be followed; if the first recognition result is that there is no specific target in the image, then according to the second recognition result, the salient target in the image is determined as the target to be followed.
  • the specific target When a specific target is recognized, the specific target is used as the target to be followed, but the specific target is not recognized, and when a salient target is recognized, the salient target is used as the target to be followed, and the user does not need to make a box selection through the human-computer interaction page
  • the target to be followed can also be determined accurately and quickly, which greatly improves the user experience.
  • the step of determining a specific target in the image as the target to be followed may include: sub-steps S1031 to S1032 .
  • Sub-step S1031 if there are multiple specific targets in the image, determine the first follow-up priority of each specific target according to the first identification result;
  • Sub-step S1032 Determine the target to be followed from a plurality of the specific targets according to the first following priority of each of the specific targets.
  • the first follow-up priority of each specific target determines the first follow-up priority of each specific target, and determine the specific target corresponding to the highest first follow-up priority as To be followed target.
  • the first following priorities of specific target A, specific target B, and specific target C are level 1, level 2, and level 3, respectively, and level 1 corresponds to the highest priority, so specific target A is selected as the target to be followed.
  • the first following priority is used to describe the probability of selecting a specific target as the target to be followed. The higher the specific target of the first following priority, the higher the probability of selecting the specific target as the target to be followed.
  • the first following priority The lower the level of a specific target, the lower the probability of selecting the specific target as the target to be followed.
  • the manner of determining the first following priority of each specific target may be: obtaining the following probability of each specific target from the first identification result, wherein the following The probability is the probability that the output object is a specific target when the object in the image is identified according to the target detection algorithm; and/or, the position of each specific target in the image is obtained from the first recognition result; and/or , obtain the position information of each specific target in the image from the first recognition result, and determine the frame ratio of each specific target in the image according to the position information of each specific target in the image; The following probability of the target, the position in the image and/or the frame proportion of the image determines the first following priority of each specific target.
  • the following probabilities of specific target A, specific target B and specific target C are 95%, 82% and 85%, respectively, since 95%>85%>82%, therefore, by the magnitude of 95%>85%>82% relationship, it can be determined that the first follow-up priority of specific target A is level 1, the first follow-up priority of specific target C is level 2, and the first follow-up priority of specific target B is level 3.
  • the proportions of the specific target A, the specific target B and the specific target C in the image are 8%, 12% and 15% respectively. Since 15%>12%>8%, through 15%>12%> 8%, it can be determined that the first follow-up priority of specific target A is level three, the first follow-up priority of specific target B is level two, and the first follow-up priority of specific object C is level one.
  • the method of determining the first follow-up priority of each specific target can be: The position in the image and the center position of the image, determine the distance between the position of each specific target and the center position; according to the distance between the position of each specific target and the center position, determine the first follow-up priority of each specific target class.
  • the distances between the positions of a specific target A, a specific target B and a specific target C in the image and the center position are a, b and c, respectively, and a>b>c, therefore, by a>b>c
  • the size relationship can determine that the first follow-up priority of specific target A is level three, the first follow-up priority of specific target B is level two, and the first follow-up priority of specific object C is level one.
  • the method of determining the first following priority of each specific target may be: according to each specific target The following probability of a specific target is determined, and the first following index of each specific target is determined; the distance between the position of each specific target and the central position of the image is determined, and the distance between the position of each specific target and the central position of the image is determined according to the difference between the position of each specific target and the central position of the image.
  • the second follow index of each specific target is determined; according to the frame ratio of each specific target to the image, the third follow index is determined, and according to the first follow index, second follow index and /or a third follow-up index, determining a target follow-up index of each specific target; determining a first follow-up priority of each specific target according to the target follow-up index of each specific target.
  • the first following index of the specific target may be determined according to the first preset mapping relationship and the following probability of the specific target, and the first preset mapping relationship includes the following indexes corresponding to different following probabilities, for example, the following probability is 60%, 70%
  • the following indices corresponding to %, 90%, and 95% are 60, 70, 90, and 95 points, respectively. Therefore, if the following probability of a specific target is 95%, the first following index of a specific target is 95%.
  • the second following index of the specific target can be determined according to the second preset mapping relationship and the distance between the position of the specific target and the center position of the image, and the second preset relationship includes the following indexes corresponding to different distances, for example, the distance is 0.5
  • the following indices corresponding to centimeters, 1 centimeters, and 1.5 centimeters are 90, 80, and 70 points, respectively. Therefore, if the distance between the position of a specific target and the center of the image is 0.5 centimeters, the second following index of the specific target is 0.5 centimeters. 90 points.
  • the third following index of the specific target may be determined according to the third preset mapping relationship and the frame ratio of the specific target in the image, and the third preset mapping relationship includes the following indices corresponding to different frame ratios, for example, the frame ratio is 5%, 10%
  • the following indices corresponding to % and 12% are 60, 65, and 70 points, respectively. Therefore, if the proportion of the image frame of the specific target is 12%, the third following index of the specific target is 70 points.
  • the first preset mapping relationship, the second preset mapping relationship, and the third preset mapping relationship may be set based on actual conditions, which are not specifically limited in this embodiment of the present application.
  • the method of determining the target follow index of the specific target may be: if only the follow probability of the specific target is considered, the first follow The index is determined as the target following index of the specific target; if only the position of the specific target in the image is considered, the second following index is determined as the target following index of the specific target; if only the frame ratio of the specific target in the image is considered, then The third following index is determined as the target following index of the specific target; if the following probability of the specific target and the position in the image are considered, the sum of the first following index and the second following index is determined as the target following index of the specific target ; If considering the following probability of a specific target and the frame ratio of the image, the sum of the first following index and the third following index is determined as the target following index of the specific target; If considering the position and the proportion of the specific target in the image, The frame ratio of the image, the sum of the second following index and the third following index is determined as the target following index of the specific target; If considering the position and the proportion of the specific target in the
  • the product of the first preset weight and the first following index of the specific target is calculated, and the second preset weight and the specific target are calculated.
  • the product of the second following index of the target calculate the sum of the above two products, and determine the sum of the above two products as the target following index of the specific target, wherein the sum of the first preset weight and the second preset weight is 1.
  • the product of the first preset weight and the first following index of the specific target is calculated, and the third preset weight and the third following index of the specific target are calculated. Calculate the sum of the above two products, and determine the sum of the above two products as the target following index of the specific target, wherein the sum of the first preset weight and the third preset weight is 1.
  • the product of the second preset weight and the second follow index of the specific target is calculated, and the third preset weight and the specific target are calculated.
  • the product of the first preset weight and the first following index of the specific target is calculated, and the second preset weight and the specific target are calculated.
  • the method of determining the specific target in the image as the target to be followed may be: if there are multiple specific targets in the image collected by the photographing device, then according to the first identification of the specific target As a result, the category of each specific target is determined; the target to be followed is determined from a plurality of specific targets according to the second preset category library corresponding to the current shooting mode of the shooting device and the category of each specific target.
  • the shooting modes of the shooting device include portrait shooting mode, pet shooting mode, plant shooting mode, vehicle shooting mode, panorama shooting mode, etc., and different shooting modes correspond to different second preset category libraries. For example, in portrait shooting mode, Identify the person in the image as the target to follow.
  • the target to be followed is determined based on the second preset category library corresponding to the current shooting mode of the shooting device and the category of each specific target, so that the determined target to be followed better meets the user's needs and greatly improves the user experience.
  • the method of determining the target to be followed from the plurality of specific targets may be: Whether there is a specific object whose category is located in the second preset category library, if there is only one specific object whose category is located in the second preset category library, the specific object whose category is located in the second preset category library is determined as to be followed target; if the number of specific targets whose category is located in the second preset category library is at least two, then according to the first identification result, determine the follow-up priority of each specific object whose category is located in the second preset category library, and The specific target corresponding to the highest following priority is determined as the target to be followed.
  • the step of determining the salient target in the image as the target to be followed may include: sub-steps S1033 to S1034 .
  • Sub-step S1033 If there are multiple salient objects in the image, determine the second following priority of each salient object according to the second identification result;
  • Sub-step S1034 Determine the target to be followed from a plurality of the salient targets according to the second following priority of each of the salient targets in the image.
  • the second identification result of the saliency objects determines the second follow-up priority of each saliency object, and assign the saliency object corresponding to the highest second follow-up priority
  • Sexual targets are identified as to-be-followed targets.
  • the first following priorities of saliency target D, salient target E, and salient target F are first, second, and third, respectively, and the first priority corresponds to the highest priority, so the salient target D is selected as the to-be-followed Target.
  • the second following priority is used to describe the probability of selecting a salient target as the target to be followed.
  • the higher the salient target of the second following priority the higher the probability of selecting the salient target as the target to be followed.
  • the manner of determining the second following priority of each salient target may be: obtaining the following probability of each salient target from the second identification result, wherein , the following probability is the probability that the output object is the salient target when the salient target recognition is performed on the object in the image according to the target detection algorithm; and/or, each salient target in the image is obtained from the second recognition result and/or, obtain the position information of each salient target in the image from the second recognition result, and determine that each salient target occupies the position according to the position information of each salient target in the image
  • the frame ratio of the image according to the following probability of each saliency target, the position in the image and/or the frame ratio of the image, the second following priority of each saliency target is determined.
  • the following probabilities of salient target D, salient target E, and salient target F are 90%, 80%, and 85%, respectively, since 90%>85%>80%, so by 90%>85%>80 %, it can be determined that the second follow-up priority of the saliency target D is the first level, the second follow-up priority of the saliency target F is the second level, and the second follow-up priority of the salient target E is the third level.
  • the saliency target D, saliency target E and saliency target F account for 8%, 12% and 15% of the frame of the image respectively.
  • the second follow-up priority of salient target D is level 3
  • the second follow-up priority of salient target E is level 2
  • the second follow-up priority of salient target F is level one.
  • the method of determining the second follow-up priority of each salient object may be: At the position in the image and the center position of the image, determine the distance between the position of each saliency target and the center position; according to the distance between the position of each saliency target and the center position, determine each saliency The second following priority for the target.
  • the distances between the positions of saliency target D, saliency target E and saliency target F in the image and the center position are d, e and f respectively, and d>e>f, therefore, by d>e > f, it can be determined that the second follow-up priority of saliency target D is level three, the second follow-up priority of saliency target E is level two, and the second follow-up priority of salience target F is level one.
  • the method of determining the second following priority of each salient target may be: according to The following probability of each salient object is determined, the first following index of each salient object is determined; the distance between the position of each salient object and the center position of the image is determined, and according to the position and The distance between the center positions of the image is to determine the second following index of each salient object; the third following index is determined according to the proportion of each salient object in the image, and the third following index is determined according to the proportion of each salient object in the image.
  • a follow-up index, a second follow-up index and/or a third follow-up index determine the target follow-up index of each salient target; according to the target follow-up index of each salient target, determine the second follow-up priority of each salient target .
  • the first following index of the salient target may be determined according to the first preset mapping relationship and the following probability of the salient target.
  • the first preset mapping relationship includes the following indexes corresponding to different following probabilities, for example, the following probability is 60% , 70%, 90%, and 95% are corresponding to the following indices of 60, 70, 90, and 95, respectively. Therefore, the following probability of a salient target is 90%, and the first following index of a salient target is 90. .
  • the second following index of the saliency target can be determined according to a second preset mapping relationship and the distance between the position of the salient target and the center position of the image, and the second preset relationship includes the following indices corresponding to different distances, for example, the distance
  • the following indices corresponding to 0.5 cm, 1 cm, and 1.5 cm are 90, 80, and 70 points, respectively. Therefore, if the distance between the position of the salient target and the center of the image is 1 cm, then the The second follow index is 80 points.
  • the manner of determining the second follow-up priority of each salient object may be: specifying a predetermined position in the image, and according to each salient object The position of each salient target in the image and the predetermined position of the image, determine the distance between the position of each salient target and the predetermined position; according to the distance between the position of each salient target and the predetermined position, determine The second following priority for each salience target.
  • the third following index of the saliency target may be determined according to the third preset mapping relationship and the frame ratio of the saliency target in the image, and the third preset mapping relationship includes the following indices corresponding to different frame ratios, for example, the frame ratio is 5%.
  • the following indices corresponding to , 10%, and 12% are 60, 65, and 70 points, respectively. Therefore, if the saliency target accounts for 10% of the frame of the image, the third following index for a specific target is 65 points.
  • the method of determining the target following index of the salient target may be: if only the following probability of the salient target is considered, then The first following index is determined as the target following index of the salient target; if only the position of the salient target in the image is considered, the second following index is determined as the target following index of the salient target; The frame ratio of the image, the third following index is determined as the target following index of the saliency target; if the following probability of the salient target and its position in the image are considered, the sum of the first following index and the second following index Determined as the target following index of the saliency target; if considering the following probability of the salient target and the proportion of the image in the image, the sum of the first following index and the third following index is determined as the target following index of the salient target; if Considering the position of the saliency target in the image and the frame ratio of the image, the sum of the second following index and the third following index is determined as the target following index of the salient target; if Considering the position of the
  • the product of the first preset weight and the first following index of the saliency target is calculated, and the second preset weight is calculated.
  • the product of the weight and the second following index of the saliency target calculate the sum of the above two products, and determine the sum of the above two products as the target following index of the salient target, wherein the first preset weight and the second Let the sum of the weights be 1.
  • the product of the first preset weight and the first following index of the saliency target is calculated, and the third preset weight and the saliency target are calculated.
  • the product of the three following indices; the sum of the above two products is calculated, and the sum of the above two products is determined as the target following index of the saliency target, wherein the sum of the first preset weight and the third preset weight is 1.
  • the position of the saliency target in the image and the frame ratio of the saliency target in the image are considered, then calculate the product of the second preset weight and the second follow index of the saliency target, and calculate the third preset weight The product of the third following index of the saliency target; calculate the sum of the above two products, and determine the sum of the above two products as the target following index of the salient target, wherein the second preset weight and the third preset weight are The sum of the weights is 1.
  • the product of the first preset weight and the first following index of the saliency target is calculated, and the second preset weight is calculated. Multiplying the product with the second following index of the saliency target and calculating the product of the third preset weight and the third following index of the saliency target; calculating the sum of the above three products, and determining the sum of the above three products as the saliency
  • the target following index of the target wherein the sum of the first preset weight, the second preset weight and the third preset weight is 1.
  • the method of determining the salient target in the image as the target to be followed may be: if there are multiple salient targets in the image collected by the photographing device, according to the salient target
  • the category of each salient target is determined; according to the third preset category library corresponding to the current shooting mode of the photographing device and the category of each salient target, the target to be followed is determined from the multiple salient targets.
  • the shooting modes of the shooting device include portrait shooting mode, pet shooting mode, plant shooting mode, vehicle shooting mode, panorama shooting mode, etc., and different shooting modes correspond to different third preset category libraries.
  • the target to be followed is determined based on the third preset category library corresponding to the current shooting mode of the shooting device and the category of each salient target, so that the determined target to be followed better meets the user's needs and greatly improves the user experience.
  • the method of determining the target to be followed from the plurality of salient targets may be: determining a plurality of salient targets; Whether there is a saliency target whose category is located in the third preset category library, if there is only one saliency target whose category is located in the third preset category library, the saliency object whose category is located in the third preset category library is set to The saliency target is determined as the target to be followed; if the number of saliency targets whose category is located in the third preset category library is at least two, then according to the second recognition result, determine each saliency object whose category is located in the third preset category library.
  • the following priority of the sexual target is determined, and the salient target corresponding to the highest following priority is determined as the target to be followed.
  • the step of determining the target to be followed from the image may include: sub-steps S1035 to S1037 .
  • Sub-step S1035 determine the first follow-up priority of the specific target in the image
  • Sub-step S1037 Determine the target to be followed from the specific target and the salience target according to the first following priority and the second following priority.
  • the target to be followed is determined from the specific target and the salient target, that is, if the first following priority of the specific target is higher than the second following priority of the salient target, Then the specific target is determined as the target to be followed; or if the second follow-up priority of the salient target is higher than the first follow-up priority of the specific target, the salient target is determined as the target to be followed.
  • the specific target or salient target with a higher following priority is determined as the target to be followed, so that the determined target to be followed is more in line with the needs of the user, which greatly improves the user experience. experience.
  • the method for determining the target to be followed provided by the above-mentioned embodiment, by identifying the specific target and the salient target in the image collected by the shooting device, the first recognition result of the specific target and the second recognition result of the salient target are obtained, and according to the first recognition result of the salient target.
  • the first recognition result and the second recognition result, the target to be followed is determined from the image.
  • the whole process does not require the user to select other targets or specific targets as the target to be followed through the human-computer interaction interface, which can accurately and quickly determine the target to be followed. Greatly improved user experience.
  • FIG. 7 is a schematic flowchart of steps of another method for determining a target to be followed provided by an embodiment of the present application.
  • the method for determining the target to be followed includes steps S201 to S207.
  • Step S201 in response to a first pressing operation of the follow-up control button by the user, acquire the image collected by the photographing device, and display the image through the display device.
  • the target determination device includes a following control button and a display device, and the following control button is used to control the target determination device to determine the target to be followed.
  • the following control button is used to control the target determination device to determine the target to be followed.
  • the first pressing operation includes a single-click operation, a double-click operation, a long-press operation, and the like.
  • Step S202 Identify a specific target in the image collected by the photographing device, and obtain a first identification result of the specific target, wherein the category of the specific target is located in a first preset category library.
  • the categories in the first preset category library include categories of objects that can be identified by the target detection algorithm, such as pedestrians, vehicles, and ships.
  • the target detection algorithm can be used to identify in the images collected by the shooting device.
  • the first recognition result of the specific target is obtained.
  • Step S203 Identify a salient target in the image collected by the photographing device, and obtain a second identification result of the salient target, wherein the salient target is based on the image collected by the target object to determine the degree of significance.
  • a salient target detection algorithm can be used to identify a salient target in an image collected by a photographing device, and a second identification result of the salient target can be obtained, and the category of the salient target is different from the category of the specific target.
  • the target to be followed includes any one of a saliency target and a specific target, the salient target includes an object located at a preset position in the image, and the object stays at the preset position for longer than a preset time and/or, the saliency target is located in a foreground image in the image; and/or, the saliency target is between an image area in the image and an image area adjacent to the image area. The significance value between them is greater than or equal to the preset significance value.
  • Step S204 Determine the target to be followed from the image according to the first recognition result and the second recognition result.
  • the specific target in the image is determined as the target to be followed; if the first recognition result is that there is no specific target in the image, then according to the second recognition result , and determine the salient target in the image as the target to be followed.
  • the specific target is used as the target to be followed, but the specific target is not recognized, and when a salient target is recognized, the salient target is used as the target to be followed, and the user does not need to make a box selection through the human-computer interaction page
  • the target to be followed can also be determined accurately and quickly, which greatly improves the user experience.
  • Step S205 Identify the target to be followed in the displayed image, and determine the follow priority of each candidate target in the image according to the first recognition result and the second recognition result.
  • the target to be followed is identified in the image displayed by the display device, and the following priority of each candidate target in the image is determined according to the first recognition result and the second recognition result, that is, if only If there is a specific target, then according to the first recognition result, determine the following priority of each specific target in the image, if there is only a salient target in the image, then according to the second recognition result, determine each salient target in the image.
  • the following priority of the sexual target if both the specific target and the salient target exist in the image, the following priority of the specific target and the salient target is determined according to the first recognition result and the second recognition result.
  • the candidate target includes a specific target and a salient target, and the method for determining the follow-up priority of the candidate target may refer to the foregoing embodiment, which will not be repeated here.
  • the way of identifying the target to be followed in the image displayed by the display device includes displaying a rectangular frame and/or an identification icon in an area where the target to be followed is located.
  • the image displayed by the display device includes a specific target 10, a specific target 20 and a salient target 30. Since the specific target 10 is the target to be followed, the area where the specific target 10 is located is displayed with Rectangular frame 40 . As shown in FIG. 9 , a rectangular frame 40 and an identification icon 50 are displayed in the area where the specific target 10 is located.
  • an identification icon may be used to indicate a candidate target to follow.
  • the image displayed by the display device includes a specific target 10 , a specific target 20 and a salient target 30 , and the regions where the specific target 10 , the specific target 20 and the salient target 30 are located are marked with signs.
  • FIG. 11 when the user selects the saliency target 30 as the target to be followed, a rectangular frame 40 is displayed in the area where the saliency target 30 is located.
  • Step S206 in response to the second pressing operation of the following control button by the user, re-determine the to-be-followed according to the following priority of the target to be followed and the following priority of each candidate target Target.
  • Step S207 marking the re-determined target to be followed in the image.
  • the target to be followed is re-determined according to the following priority of the target to be followed and the following priority of each candidate target, and displayed on the display device A target to be followed with a determined gravity is identified in the displayed image.
  • the following priority of the target to be followed before the re-determination is higher than the following priority of the target to be followed after the re-determination, or the following priority of the target to be followed before the re-determination is lower than that of the target to be followed after the re-determination Priority, the second pressing operation includes a single-click operation, a double-click operation, and a long-press operation.
  • the following priorities of the specific target 10, the specific target 20, and the salient target 30 be level 1, level 2, and level 3, respectively.
  • the following priorities of 20 and salient target 30 are first, second and third, respectively, so the specific target 20 is determined as the new target to be followed.
  • the area where the specific target 20 is located is displayed with a rectangle.
  • Block 40 when the user continues to press the following control button, the salient target 30 is determined as a new target to be followed.
  • a rectangular frame 40 is displayed in the area where the salient target 30 is located.
  • the specific target 10 is determined as the target to be followed again.
  • the method for determining the target to be followed provided by the above-mentioned embodiment, by identifying the determined target to be followed in the image displayed by the display device, and in response to the user's pressing operation on the following control button, the target to be followed in the displayed image is changed.
  • the earth facilitates the user to switch the target to be followed and improves the user experience.
  • FIG. 14 is a schematic block diagram of the structure of an apparatus for determining a target provided by an embodiment of the present application.
  • the target determination apparatus 600 includes a processor 601 and a memory 602, and the processor 601 and the memory 602 are connected through a bus 603, such as an I2C (Inter-integrated Circuit) bus.
  • the target determination apparatus 600 is used for communicating with the photographing device.
  • the processor 601 may be a micro-controller unit (Micro-controller Unit, MCU), a central processing unit (Central Processing Unit, CPU), or a digital signal processor (Digital Signal Processor, DSP) or the like.
  • MCU Micro-controller Unit
  • CPU Central Processing Unit
  • DSP Digital Signal Processor
  • the memory 602 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) magnetic disk, an optical disk, a U disk, a mobile hard disk, and the like.
  • ROM Read-Only Memory
  • the memory 602 may be a Flash chip, a read-only memory (ROM, Read-Only Memory) magnetic disk, an optical disk, a U disk, a mobile hard disk, and the like.
  • the processor 601 is used for running the computer program stored in the memory 602, and implements the following steps when executing the computer program:
  • a target to be followed is determined from the image according to the first recognition result and the second recognition result.
  • the target to be followed includes any one of the saliency target and the specific target
  • the salience target includes an object located at a preset position in the image
  • the object The staying time at the preset position is longer than the preset staying time
  • the saliency target is located in a foreground image in the image.
  • a saliency value of the saliency target between an image area in the image and an image area adjacent to the image area is greater than or equal to a preset saliency value.
  • the processor when determining the target to be followed from the image according to the first recognition result and the second recognition result, is configured to:
  • the specific target in the image is determined as the target to be followed according to the first recognition result.
  • the processor when determining the specific target in the image as the target to be followed according to the first recognition result, is configured to:
  • the to-be-followed target is determined from a plurality of the specific targets according to the first following priority of each of the specific targets.
  • the processor when determining the specific target in the image as the target to be followed according to the first recognition result, is configured to:
  • the target to be followed is determined from a plurality of the specific targets according to the second preset category library corresponding to the current shooting mode of the shooting device and the category of each specific target.
  • the processor when the processor determines the target to be followed from the image according to the first recognition result and the second recognition result, the processor is configured to:
  • the salient target in the image is determined as the target to be followed.
  • the processor determines the salient target in the image as the target to be followed according to the second recognition result, it is used to realize:
  • the to-be-followed object is determined from a plurality of the saliency objects according to the second following priority of each of the saliency objects in the image.
  • the processor when the processor determines the second follow-up priority of each of the salience targets according to the second identification result, the processor is configured to:
  • the second following priority of each of the saliency objects is determined according to the following probability of each of the saliency objects, the frame proportion of the image, and/or the position in the image.
  • the processor when determining the salient target in the image as the target to be followed according to the second recognition result, is configured to:
  • the target to be followed is determined from a plurality of the salient targets according to the third preset category library corresponding to the current shooting mode of the shooting device and the category of each of the saliency targets.
  • the processor when the processor determines the target to be followed from the image according to the first recognition result and the second recognition result, the processor is configured to:
  • the target to be followed is determined from the specific target and the salience target.
  • the salient target is determined as the target to be followed.
  • the target determination device includes a follow-up control button and a display device, and before the processor realizes the recognition of a specific target in the image collected by the shooting device and obtains the first recognition result of the specific target , also used to implement:
  • the processor determines the target to be followed from the image according to the first recognition result and the second recognition result, the processor is further configured to:
  • the re-determined target to follow is identified in the image.
  • the following priority of the target to be followed before re-determination is higher than the following priority of the target to be followed after the re-determination.
  • FIG. 15 is a schematic structural block diagram of a target following system provided by an embodiment of the present application.
  • the target following system 700 includes a target determination device 710 , a pan/tilt 720 , and a photographing device 730 mounted on the pan/tilt 720 , and the target determining device 710 is connected to the photographing device 730 in communication.
  • the pan/tilt head 720 is connected to the handle portion, and the target determination device 710 is disposed on the handle portion.
  • the PTZ 720 is mounted on the movable platform, and the target determination device 710 is further used to control the movement of the movable platform.
  • FIG. 6 is a schematic block diagram of the structure of a handheld gimbal provided by an embodiment of the present application.
  • the handheld pan/tilt 800 includes a target determination device 810 , a handle, and a pan/tilt 820 connected to the handle.
  • the pan/tilt 820 is used to mount a photographing device, and the target determination device 810 is provided on the handle.
  • the target determination device 810 is connected to the pan/tilt 820 .
  • FIG. 17 is a schematic structural block diagram of a movable platform provided by an embodiment of the present application.
  • the movable platform 900 includes a platform body, a pan/tilt 910 mounted on the platform body, and a target determination device 920 .
  • the pan/tilt 910 is used for carrying a photographing device, and the target determination device 920 is provided on the platform body.
  • Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program includes program instructions, and the processor executes the program instructions to realize the provision of the above embodiments.
  • the computer-readable storage medium may be the control terminal described in any of the foregoing embodiments or an internal storage unit of the unmanned aerial vehicle, such as a hard disk or memory of the control terminal or the unmanned aerial vehicle.
  • the computer-readable storage medium can also be an external storage device of the control terminal or the unmanned aerial vehicle, such as a plug-in hard disk equipped on the control terminal or the unmanned aerial vehicle, a smart memory card (Smart Media Card, SMC) , Secure Digital (Secure Digital, SD) card, flash memory card (Flash Card) and so on.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Studio Devices (AREA)

Abstract

一种待跟随目标的确定方法、装置、系统、设备及存储介质，该方法包括：在拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库(S101)；在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的(S102)；根据第一识别结果和第二识别结果，从所述图像中确定待跟随目标(S103)。该方法能够准确快速地确定待跟随目标。

Description

待跟随目标的确定方法、装置、系统、设备及存储介质 技术领域
本申请涉及目标跟随技术领域，尤其涉及一种待跟随目标的确定方法、装置、系统、设备及存储介质。
背景技术
在目标智能跟随场景下，需要确定待跟随目标，一般是通过目标检测算法对人、汽车和船舶等特定目标进行识别，将特定目标作为待跟随目标，但目标检测算法能够检测到的类别数量有限，无法覆盖用户的使用场景。目前，用户通过人机交互界面框选其他目标作为待跟随目标，操作较为繁琐，并且对框选得到的待跟随目标的精度要求较高，无法快速准确地确定待跟随目标，用户体验不好。
发明内容
基于此，本申请实施例提供了一种待跟随目标的确定方法、装置、系统、设备及存储介质，旨在准确快速地确定待跟随目标，提高用户体验。
第一方面，本申请实施例提供了一种待跟随目标的确定方法，应用于目标确定装置，所述目标确定装置用于与拍摄设备通信连接，所述方法包括：
在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库；
在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的；
根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
第二方面，本申请实施例还提供了一种目标确定装置，所述目标确定装置用于与拍摄设备通信连接，所述目标确定装置包括存储器和处理器；
所述存储器用于存储计算机程序；
所述处理器，用于执行所述计算机程序并在执行所述计算机程序时，实现如下步骤：
在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库；
在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的；
根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
第三方面，本申请实施例还提供了一种目标跟随系统，所述目标跟随系统包括云台、搭载于所述云台上的拍摄设备和如上所述的目标确定装置。
第四方面，本申请实施例还提供了一种手持云台，所述手持云台包括手柄部、连接于所述手柄部的云台和如上所述的目标确定装置，所述云台用于搭载拍摄设备，所述目标确定装置设置在所述手柄部上。
第五方面，本申请实施例还提供了一种可移动平台，所述可移动平台包括平台本体、搭载于所述平台本体的云台和如上所述的目标确定装置，所述云台用于搭载拍摄设备，所述目标确定装置设置在所述平台本体上。
第六方面，本申请实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时使所述处理器实现如上所述的待跟随目标的确定方法的步骤。
本申请实施例提供了一种待跟随目标的确定方法、装置、系统、设备及存储介质，通过在拍摄设备采集到的图像中识别特定目标和显著性目标，得到特定目标的第一识别结果和显著性目标的第二识别结果，并根据第一识别结果和第二识别结果，从该图像中确定待跟随目标，整个过程不需要用户通过人机交互界面框选其他目标或特定目标作为待跟随目标，能够准确快速地确定待跟随目标，极大地提高了用户体验。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本申请。
附图说明
为了更清楚地说明本申请实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是实施本申请实施例提供的待跟随目标的确定方法的一场景示意图；
图2是实施本申请实施例提供的待跟随目标的确定方法的另一场景示意图；
图3是本申请实施例提供的一种待跟随目标的确定方法的步骤示意流程图；
图4是图3中的待跟随目标的确定方法的一子步骤示意流程图；
图5是图3中的待跟随目标的确定方法的一子步骤示意流程图；
图6是图3中的待跟随目标的确定方法的一子步骤示意流程图；
图7是本申请实施例提供的另一种待跟随目标的确定方法的步骤示意流程图；
图8是本申请实施例中显示装置显示的拍摄设备采集到的图像的一示意图；
图9是本申请实施例中显示装置显示的拍摄设备采集到的图像的另一示意图；
图10是本申请实施例中显示装置显示的拍摄设备采集到的图像的另一示意图；
图11是本申请实施例中显示装置显示的拍摄设备采集到的图像的另一示意图；
图12是本申请实施例中显示装置显示的拍摄设备采集到的图像的另一示意图；
图13是本申请实施例中显示装置显示的拍摄设备采集到的图像的另一示意图；
图14是本申请实施例提供的一种目标确定装置的结构示意性框图；
图15是本申请实施例提供的一种目标跟随系统的结构示意性框图；
图16是本申请实施例提供的一种手持云台的结构示意性框图；
图17是本申请实施例提供的一种可移动平台的结构示意性框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
附图中所示的流程图仅是示例说明，不是必须包括所有的内容和操作/步骤，也不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解、组合或部分合并，因此实际执行的顺序有可能根据实际情况改变。
下面结合附图，对本申请的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
在目标智能跟随场景下，需要确定待跟随目标，一般是通过目标检测算法对人、汽车和船舶等特定目标进行识别，将特定目标作为待跟随目标，但目标检测算法能够检测到的类别数量有限，无法覆盖用户的使用场景。目前，用户通过人机交互界面框选其他目标作为待跟随目标，操作较为繁琐，并且对框选得到的待跟随目标的精度要求较高，无法快速准确地确定待跟随目标，用户体验不好。
为解决上述问题，本申请实施例提供了一种待跟随目标的确定方法、装置、系统、设备及存储介质，通过在拍摄设备采集到的图像中识别特定目标和显著性目标，得到特定目标的第一识别结果和显著性目标的第二识别结果，并根据第一识别结果和第二识别结果，从该图像中确定待跟随目标，整个过程不需要用户通过人机交互界面框选其他目标或特定目标作为待跟随目标，能够准确快速地确定待跟随目标，极大地提高了用户体验。
请参阅图1，图1是实施本申请实施例提供的待跟随目标的确定方法的一场景示意图。如图1所示，该场景包括手持云台100和搭载于手持云台100上的拍摄设备200，手持云台100包括手柄部101和设于手柄部101上的云台102，云台102用于搭载拍摄设备200，拍摄设备200可以与云台102一体设置，也可以外接于云台102。示例性的，拍摄设备200可以为智能手机，也可以为相机，例如为单反相机，还可以为摄像头。手持云台100可以承载拍摄设备200，用于固定拍摄设备200以及改变拍摄设备200的高度、倾角和/或方向，或者用于将拍摄设备200稳定地保持在某一姿态上，并控制拍摄设备200进行拍摄。
在一实施例中，手持云台100与拍摄设备200通信连接，手持云台100可以通过控制线与拍摄设备200连接，该控制线例如为快门线。此处不限定快门线的种类，例如，该快门线可以是通用串行总线(Universal Serial Bus，USB)。手持云台100也可以通过无线的方式与拍摄设备200连接，例如，通过手持云台100内置的第一蓝牙模块与拍摄设备200内置的第二蓝牙模块，建立手持云台100与拍摄设备200之间的通信连接。
在一实施例中，云台102包括三轴电机，三轴电机分别为俯仰(pitch)轴电机1021、平移(yaw)轴电机1022和横滚(roll)轴电机(图1中未示出)，所述三轴电机用于调整搭载于云台102上的拍摄设备200的平衡姿态，以便拍摄稳定流畅的画面。其中，云台102上还设置有惯性测量单元(Inertial  measurement unit，IMU)，可例如为加速度计或陀螺仪中的至少一种，可以用于测量云台102的姿态和加速度等，以便根据姿态调整云台102的姿态。在一实施例中，手柄部101上也设置有惯性测量单元(Inertial measurement unit，IMU)，例如包括加速度计或陀螺仪中的至少一种，可以用于测量手柄部101的姿态和加速度等，以便根据手柄部101的姿态和云台102的姿态调整云台102的姿态。
在一实施例中，手持云台100包括处理器，处理器用于对输入的控制指令进行处理，或者收发信号等。处理器可以设置在手柄部101的内部。可选地，该处理器可以是中央处理单元(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在一实施例中，手持云台100包括多种工作模式，比如包括：跟随模式、目标跟踪模式、锁定模式、运动模式和/或休眠模式等。手持云台100处于不同的工作模式执行不同的动作。例如，若手持云台100处于跟随模式，则采用跟随模式控制拍摄设备200进行跟随拍摄，所述跟随模式可以是指云台102跟随手柄部101运动的拍摄模式；若手持云台100处于目标跟踪模式，则在确定待跟随目标后，云台102开始自动旋转使得拍摄设备200的角度始终跟随待跟随目标转动，保持待跟随目标在采集的画面中。
例如，锁定模式是指对云台102的三轴进行锁定，云台的三轴不跟随；运动模式是指云台102以预设速度跟随，比如以云台的三轴的最大速度跟随；休眠模式是指控制手持云台进入休眠状态。其中，在锁定模式或运动模式，云台的跟随对象可以是手柄部101，也可以是待跟随目标，还可以是其它，具体可以根据需要设定，此处不做具体限定。
在一实施例中，待跟随目标的确定方式可以为：手持云台100的处理器获取拍摄设备200采集到的图像，并识别该图像中的识别特定目标和显著性目标，得到特定目标的第一识别结果和显著性目标的第二识别结果，并根据第一识别结果和第二识别结果，从该图像中确定待跟随目标。可以理解的是，待跟随目标的确定方式也可以由用户在手持云台100侧进行诸如框选或点选的操作后确定，也可以是根据拍摄设备200采集到的图像中的特定姿势确定，还可以是利用根据拍摄设备200采集到的图像中的特定目标或显著性目标在画面中的位置 确定。此处不做具体限定。
在一实施例中，手柄部101上还设置有控制键，以便用户操作该控制键以控制云台102或拍摄设备200。该控制键可例如为按键、扳机、旋钮或者摇杆等，当然也包括其他形式的物理按键或者虚拟按键。其中，虚拟按键可以为设置于触摸屏上的用于和用户交互的虚拟按钮。摇杆可以用于控制至少一个转轴的运动，进而控制拍摄设备200的运动。可以理解的是，遥杆也可以用于其他功能。可以理解的是，控制键的数量可以为一个或多个。当控制键的数量为一个时，可以针对该控制键采用不同的操作方式产生不同的控制指令，不同的操作方式比如为按压次数不同；当控制键的数量为多个时，比如包括第一控制键、第二控制键和第三控制键等，不同控制键用于产生不同的控制指令。
在一实施例中，该控制键包括跟随控制按键，该跟随控制按键用于控制手持云台100启动或退出目标跟踪模式，例如，手持云台100的处理器响应于用户对跟随控制按键的第一按压操作，若手持云台100不处于目标跟踪模式，则控制手持云台100处于目标跟踪模式，并获取拍摄设备200采集到的图像；对该图像中的特定目标进行识别，得到特定目标的第一识别结果，并对该图像中的显著性目标进行识别，得到显著性目标的第二识别结果；根据第一识别结果和第二识别结果，从该图像中确定待跟随目标，使得用户能够通过跟随控制按键快速地控制手持云台100进入目标跟踪模式，能够对待跟随目标进行跟踪。
在一实施例中，手持云台100还包括显示装置，该显示装置用于显示拍摄设备200采集到的图像。在手持云台100处于目标跟踪模式，且对待跟随目标进行跟踪的过程中，处理器控制显示装置显示拍摄设备200采集到的图像，并在显示装置显示的图像中标识待跟随目标；根据第一识别结果和第二识别结果确定该图像中的每个候选目标的跟随优先级；响应于对该跟随控制按键的第二按压操作，根据该待跟随目标的跟随优先级和每个候选目标的跟随优先级，重新确定待跟随目标，并在该图像中标识重新确定的待跟随目标。通过跟随控制按键方便用户切换待跟随目标。
请参阅图2，图2是实施本申请实施例提供的待跟随目标的确定方法的另一场景示意图。如图2所示，该场景包括控制终端300和可移动平台400，控制终端300与可移动平台400通信连接，控制终端300包括显示装置310，显示装置310用于显示可移动平台400发送的图像。需要说明的是，显示装置310包括设置在控制终端300上的显示屏或者独立于控制终端300的显示器，独立于控制终端300的显示器可以包括手机、平板电脑或者个人电脑等，或者也可 以是带有显示屏的其他电子设备。其中，该显示屏包括LED显示屏、OLED显示屏、LCD显示屏等等。
在一实施例中，可移动平台400包括平台本体410、搭载于平台本体上的云台420和动力系统430，云台420用于搭载拍摄设备500，动力系统430包括电机431和螺旋桨432，电机431用于驱动螺旋桨432旋转，从而为可移动平台提供移动动力。其中，云台420包括三轴电机，分别为平移轴电机421、俯仰轴电机422和横滚轴电机423，用于调整搭载于云台420上的拍摄设备500的平衡姿态，以便随时随地拍摄出高精度的稳定画面。
在一实施例中，可移动平台400还包括处理器，处理器用于对输入的控制指令进行处理，或者收发信号等。处理器可以设置可移动平台400内部。可选地，该处理器可以是中央处理单元(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在一实施例中，控制终端300包括跟随控制按键，该跟随控制按键用于控制可移动平台400启动或退出目标跟踪模式，可移动平台400处于目标跟踪模式时，可移动平台400能够控制云台420运动，使得拍摄设备500的角度始终跟随待跟随目标转动，保持待跟随目标在采集的画面中。例如，控制终端300响应于用户对该跟随控制按键的第一按压操作，生成目标跟随启动指令，并向可移动平台400发送该目标跟随启动指令；可移动平台400接收该目标跟随启动指令，并传输给处理器，处理器根据该目标跟随启动指令，控制可移动平台400处于目标跟踪模式，并获取拍摄设备500采集到的图像，然后对该图像中的特定目标进行识别，得到特定目标的第一识别结果，并对该图像中的显著性目标进行识别，得到显著性目标的第二识别结果，然后根据第一识别结果和第二识别结果，从该图像中确定待跟随目标，并根据拍摄设备500采集到的图像控制云台420运动，使得拍摄设备500的角度始终跟随待跟随目标转动，保持待跟随目标在采集的画面中。
其中，可移动平台包括可移动机器人、无人机和无人车等，可移动平台400为无人机，动力系统430能够使无人机垂直地从地面起飞，或者垂直地降落在地面上，而不需要无人机任何水平运动(如不需要在跑道上滑行)。可选的， 动力系统430可以允许无人机在空中预设位置和/或方向盘旋。一个或者多个动力系统430在受到控制时可以独立于其它的动力系统430。可选的，一个或者多个动力系统430可以同时受到控制。例如，无人机可以有多个水平方向的动力系统430，以追踪目标的提升及/或推动。水平方向的动力系统430可以被致动以提供无人机垂直起飞、垂直降落、盘旋的能力。
在一实施例中，水平方向的动力系统430中的一个或者多个可以顺时针方向旋转，而水平方向的动力系统中的其它一个或者多个可以逆时针方向旋转。例如，顺时针旋转的动力系统430与逆时针旋转的动力系统430的数量一样。每一个水平方向的动力系统430的旋转速率可以独立变化，以实现每个动力系统430导致的提升及/或推动操作，从而调整无人机的空间方位、速度及/或加速度(如相对于多达三个自由度的旋转及平移)。
在一实施例中，无人机还可以包括传感系统，传感系统可以包括一个或者多个传感器，以感测无人机的空间方位、速度及/或加速度(如相对于多达三个自由度的旋转及平移)、角加速度、姿态、位置(绝对位置或者相对位置)等。所述一个或者多个传感器包括GPS传感器、运动传感器、惯性传感器、近程传感器或者影像传感器。可选的，传感系统还可以用于采集无人飞行器所处的环境数据，如气候条件、要接近的潜在的障碍、地理特征的位置、人造结构的位置等。另外，无人机可以包括脚架，所述脚架是无人机降落时，无人机与地面的接触件，脚架可以是无人飞行器在飞行状态(例如无人飞行器在巡航时)收起，在降落时才放下；也可以固定安装在无人机上，一直处于放下的状态。
在一实施例中，可移动平台400能够与控制终端300进行通信，可以实现控制终端300与可移动平台400之间的数据交互，例如对可移动平台400的移动控制、对负载的控制(当负载为拍摄设备500时，控制终端300可以控制该拍摄设备500)，其中，控制终端300可以与可移动平台400和/或负载进行通信，可移动平台400与控制终端300之间的通信可以是无线通信，可以在可移动平台400和控制终端300之间提供直接通信。这种直接通信可以无需任何中间装置或网络地发生的。
在一实施例中，可以在可移动平台400与控制终端300之间提供间接通信。这种间接通信可以借助于一个或多个中间装置或网络来发生。例如，间接通信可以利用电信网络。间接通信可以借助于一个或多个路由器、通信塔、卫星、或任何其他的中间装置或网络来进行。通信类型的实例可以包括但不限于经由以下方式的通信：因特网，局域网(LAN)，广域网(WAN)，蓝牙，近场通信 (NFC)技术，基于诸如通用分组无线电服务(GPRS)、GSM增强型数据GSM环境(EDGE)、3G、4G、或长期演进(LTE)协议的移动数据协议的网络，红外线(IR)通信技术，和/或Wi-Fi，并且可以是无线式、有线式、或其组合。
其中，控制终端300可以包括但不限于：智能电话/手机、平板电脑、个人数字助理(PDA)、台式计算机、媒体内容播放器、视频游戏站/系统、虚拟现实系统、增强现实系统、可穿戴式装置(例如，手表、眼镜、手套、头饰(例如，帽子、头盔、虚拟现实头戴耳机、增强现实头戴耳机、头装式装置(HMD)、头带)、挂件、臂章、腿环、鞋子、马甲)、手势识别装置、麦克风、能够提供或渲染图像数据的任意电子装置、或者任何其他类型的装置。该控制终端300可以是手持终端，控制终端300可以是便携式的。该控制终端300可以由人类用户携带。在一些情况下，控制终端300可以远离人类用户，并且用户可以使用无线和/或有线通信来控制控制终端300。
以下，将结合图1或图2中的场景对本申请的实施例提供的待跟随目标的确定方法进行详细介绍。需知，图1或图2中的场景仅用于解释本申请实施例提供的待跟随目标的确定方法，但并不构成对本申请实施例提供的待跟随目标的确定方法应用场景的限定。
请参阅图3，图3是本申请实施例提供的一种待跟随目标的确定方法的步骤示意流程图。
如图3所示，该待跟随目标的确定方法包括步骤S101至步骤S103。
步骤S101、在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库；
步骤S102、在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的；
步骤S103、根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
在需要确定待跟随目标时，获取拍摄设备采集到的图像，并在拍摄设备采集到的图像中识别特定目标和显著性目标，得到特定目标的第一识别结果和显著性目标的第二识别结果，然后基于第一识别结果和第二识别结果，从拍摄设备采集到的图像中确定待跟随目标。其中，第一预设类别库中的类别包括能够通过目标检测算法识别到的对象的类别，例如，行人、车辆和船舶等，对此，可以通过目标检测算法在拍摄设备采集到的图像中识别特定目标，得到特定目 标的第一识别结果，可以通过显著性目标检测算法在拍摄设备采集到的图像中识别显著性目标，得到显著性目标的第二识别结果。可选的，显著性目标的类别与特定目标的类别不同。
在一实施例中，显著性目标是依据目标对象在采集到的图像中的显著程度来确定的，例如，当目标对象在采集到的图像中的显著程度大于或等于预设显著程度时，可以确定该目标对象为显著性目标，而当目标对象在采集到的图像中的显著程度小于预设显著程度时，可以确定该目标对象不为显著性目标。其中，预设显著程度可基于实际情况进行设置，本申请实施例对此不做具体限定。
在一实施例中，目标对象在采集到的图像中的显著程度可以根据目标对象在图像中的预设位置的停留时长确定。和/或可以根据目标对象在采集到的图像中所处的图像区域与相邻图像区域之间的显著性值确定。可以理解的是，目标对象在图像中的预设位置的停留时长越长，则目标对象在采集到的图像中的显著程度越高，而目标对象在图像中的预设位置的停留时长越短，则目标对象在采集到的图像中的显著程度越低。目标对象在采集到的图像中所处的图像区域与相邻图像区域之间的显著性值越大，则目标对象在采集到的图像中的显著程度越高，而目标对象在采集到的图像中所处的图像区域与相邻图像区域之间的显著性值越小，则目标对象在采集到的图像中的显著程度越低。
在一实施例中，所述待跟随目标包括显著性目标和特定目标中的任一项，所述显著性目标包括位于所述图像中的预设位置的对象，且所述对象在预设位置的停留时长大于预设停留时长；和/或，所述显著性目标位于所述图像中的前景图像中；和/或，所述显著性目标在所述图像中的图像区域与所述图像区域的相邻图像区域之间的显著性值大于或等于预设显著性值。
其中，显著性目标所在的图像区域与相邻图像区域之间的显著性值是根据显著性目标所在的图像区域与相邻图像区域之间的色差和/或对比度确定的，色差越大，则显著性值越大，色差越小，则显著性值越小，对比度越大，则显著性值越大，对比度越小，则显著性值越小。预设位置、预设停留时长和预设显著性值可基于实际情况进行设置或由用户自行设置，例如预设位置可以图像的中心位置，预设停留时长为10秒，预设显著值为50。
在一实施例中，根据第一识别结果和第二识别结果，从图像中确定待跟随目标的方式可以为：若第一识别结果为图像中存在特定目标，则根据第一识别结果，将图像中的特定目标确定为待跟随目标；若第一识别结果为图像中不存在特定目标，则根据第二识别结果，将图像中的显著性目标确定为待跟随目标。 通过在识别到特定目标时，将特定目标作为待跟随目标，而未识别到特定目标，且识别到显著性目标时，将显著性目标作为待跟随目标，不需要用户通过人机交互页面框选待跟随目标，也能够准确快速地确定待跟随目标，极大地提高了用户体验。
在一实施例中，如图4所示，根据第一识别结果，将图像中的特定目标确定为待跟随目标的步骤可以包括：子步骤S1031至S1032。
子步骤S1031、若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的第一跟随优先级；
子步骤S1032、根据每个所述特定目标的所述第一跟随优先级，从多个所述特定目标中确定所述待跟随目标。
如果拍摄设备采集到的图像中存在多个特定目标，则根据特定目标的第一识别结果，确定每个特定目标的第一跟随优先级，并将第一跟随优先级最高对应的特定目标确定为待跟随目标。例如，特定目标A、特定目标B和特定目标C的第一跟随优先级分别为一级、二级和三级，一级对应的优先级最高，因此选择特定目标A作为待跟随目标。其中，第一跟随优先级用于描述选择特定目标作为待跟随目标的概率高低，第一跟随优先级越高的特定目标，则选择该特定目标作为待跟随目标的概率越高，第一跟随优先级越低的特定目标，则选择该特定目标作为待跟随目标的概率越低。通过确定每个特定目标的第一跟随优先级，并将第一跟随优先级最高对应的特定目标确定为待跟随目标，使得确定的待跟随目标更加符合用户的需求，提高用户体验。
在一实施例中，根据特定目标的第一识别结果，确定每个特定目标的第一跟随优先级的方式可以为：从第一识别结果中获取每个特定目标的跟随概率，其中，该跟随概率为根据目标检测算法对图像中的对象进行特定目标识别时输出的对象为特定目标的概率；和/或，从第一识别结果中获取每个特定目标在该图像中的位置；和/或，从第一识别结果中获取每个特定目标在该图像中的位置信息，并根据每个特定目标在该图像中的位置信息，确定每个特定目标占该图像的画幅比例；根据每个特定目标的跟随概率、在该图像中的位置和/或占该图像的画幅比例，确定每个特定目标的第一跟随优先级。
例如，特定目标A、特定目标B和特定目标C的跟随概率分别为95％、82％和85％，由于95％>85％>82％，因此，通过95％>85％>82％的大小关系，可以确定特定目标A的第一跟随优先级为一级、特定目标C的第一跟随优先级为二级，特定目标B的第一跟随优先级为三级。又例如，特定目标A、特定目标B 和特定目标C占该图像的画幅比例分别为8％、12％和15％，由于15％>12％>8％，因此，通过15％>12％>8％的大小关系，可以确定特定目标A的第一跟随优先级为三级、特定目标B的第一跟随优先级为二级，特定目标C的第一跟随优先级为一级。
在一实施例中，根据每个特定目标在该图像中的位置，确定每个特定目标的第一跟随优先级的方式可以为：获取该图像的中心位置，并根据每个特定目标在该图像中的位置和该图像的中心位置，确定每个特定目标的位置与中心位置之间的距离；根据每个特定目标的位置与中心位置之间的距离，确定每个特定目标的第一跟随优先级。例如，特定目标A、特定目标B和特定目标C在该图像中的位置与中心位置之间的距离分别为a、b和c，且a>b>c，因此，通过a>b>c的大小关系，可以确定特定目标A的第一跟随优先级为三级、特定目标B的第一跟随优先级为二级，特定目标C的第一跟随优先级为一级。
在一实施例中，根据每个特定目标的跟随概率、在该图像中的位置和/或占该图像的画幅比例，确定每个特定目标的第一跟随优先级的方式可以为：根据每个特定目标的跟随概率，确定每个特定目标的第一跟随指数；确定每个特定目标的位置与该图像的中心位置之间的距离，并根据每个特定目标的位置与该图像的中心位置之间的距离，确定每个特定目标的第二跟随指数；根据每个特定目标占该图像的画幅比例，确定第三跟随指数，并根据每个特定目标的第一跟随指数、第二跟随指数和/或第三跟随指数，确定每个特定目标的目标跟随指数；根据每个特定目标的目标跟随指数，确定每个特定目标的第一跟随优先级。
其中，特定目标的第一跟随指数可以根据第一预设映射关系和特定目标的跟随概率确定，第一预设映射关系包括不同跟随概率各自对应的跟随指数，例如，跟随概率为60％、70％、90％、95％对应的跟随指数分别为60分、70分、90分、95分，因此，特定目标的跟随概率为95％，则特定目标的第一跟随指数为95％。
特定目标的第二跟随指数可以根据第二预设映射关系和特定目标的位置与该图像的中心位置之间的距离确定，第二预设关系包括不同距离对应的跟随指数，例如，距离为0.5厘米、1厘米、1.5厘米对应的跟随指数分别为90分、80分和70分，因此，特定目标的位置与该图像的中心位置之间的距离为0.5厘米，则特定目标的第二跟随指数为90分。
特定目标的第三跟随指数可以根据第三预设映射关系和特定目标占该图像的画幅比例确定，第三预设映射关系包括不同画幅比例对应的跟随指数，例如， 画幅比例为5％、10％、12％对应的跟随指数分别为60分、65分和70分，因此，特定目标占该图像的画幅比例为12％，则特定目标的第三跟随指数为70分。第一预设映射关系、第二预设映射关系和第三预设映射关系可基于实际情况进行设置，本申请实施例对此不做具体限定。
在一实施例中，根据第一跟随指数、第二跟随指数和/或第三跟随指数，确定特定目标的目标跟随指数的方式可以为：若仅考虑特定目标的跟随概率，则将第一跟随指数确定为特定目标的目标跟随指数；若仅考虑特定目标在该图像中的位置，则将第二跟随指数确定为特定目标的目标跟随指数；若仅考虑特定目标占该图像的画幅比例，则将第三跟随指数确定为特定目标的目标跟随指数；若考虑特定目标的跟随概率和在该图像中的位置，则将第一跟随指数和第二跟随指数之和确定为特定目标的目标跟随指数；若考虑特定目标的跟随概率和占该图像的画幅比例，则将第一跟随指数和第三跟随指数之和确定为特定目标的目标跟随指数；若考虑特定目标在该图像中的位置和占该图像的画幅比例，则将第二跟随指数和第三跟随指数之和确定为特定目标的目标跟随指数；若考虑特定目标的跟随概率、在该图像中的位置和占该图像的画幅比例，则将第一跟随指数、第二跟随指数和第三跟随指数之和确定为特定目标的目标跟随指数。
在一实施例中，若考虑特定目标的跟随概率和特定目标在该图像中的位置，则计算第一预设权重与特定目标的第一跟随指数的乘积，并计算第二预设权重与特定目标的第二跟随指数的乘积；计算上述两个乘积的和，并将上述两个乘积的和确定为特定目标的目标跟随指数，其中，第一预设权重与第二预设权重之和为1。
或者，若考虑特定目标的跟随概率和占该图像的画幅比例，则计算第一预设权重与特定目标的第一跟随指数的乘积，并计算第三预设权重与特定目标的第三跟随指数的乘积；计算上述两个乘积的和，并将上述两个乘积的和确定为特定目标的目标跟随指数，其中，第一预设权重与第三预设权重之和为1。
或者，若考虑特定目标在该图像中的位置和特定目标占该图像的画幅比例，则计算第二预设权重与特定目标的第二跟随指数的乘积，并计算第三预设权重与特定目标的第三跟随指数的乘积；计算上述两个乘积的和，并将上述两个乘积的和确定为特定目标的目标跟随指数，其中，第二预设权重与第三预设权重之和为1。
或者，若考虑特定目标的跟随概率、在该图像中的位置和占该图像的画幅比例，则计算第一预设权重与特定目标的第一跟随指数的乘积、计算第二预设 权重与特定目标的第二跟随指数的乘积以及计算第三预设权重与特定目标的第三跟随指数的乘积；计算上述三个乘积的和，并将上述三个乘积的和确定为特定目标的目标跟随指数，其中，第一预设权重、第二预设权重与第三预设权重之和为1。
在一实施例中，根据第一识别结果，将图像中的特定目标确定为待跟随目标的方式可以为：若拍摄设备采集到的图像中存在多个特定目标，则根据特定目标的第一识别结果，确定每个特定目标的类别；根据拍摄设备的当前拍摄模式对应的第二预设类别库和每个特定目标的类别，从多个特定目标中确定待跟随目标。其中，拍摄设备的拍摄模式包括人像拍摄模式、宠物拍摄模式、植物拍摄模式、车辆拍摄模式和全景拍摄模式等，不同拍摄模式对应不同的第二预设类别库，例如，在人像拍摄模式下，将图像中的人确定为待跟随目标。通过基于拍摄设备的当前拍摄模式对应的第二预设类别库和每个特定目标的类别，确定待跟随目标，使得确定的待跟随目标更加符合用户的需求，极大地提高了用户体验。
在一实施例中，根据拍摄设备的当前拍摄模式对应的第二预设类别库和每个特定目标的类别，从多个特定目标中确定待跟随目标的方式可以为：确定多个特定目标中是否存在类别位于第二预设类别库内的特定目标，若类别位于第二预设类别库内的特定目标仅有一个，则将类别位于第二预设类别库内的特定目标确定为待跟随目标；若类别位于第二预设类别库内的特定目标的数量至少为两个，则根据第一识别结果，确定类别位于第二预设类别库内的每个特定目标的跟随优先级，并将该跟随优先级最高对应的特定目标确定为待跟随目标。
在一实施例中，如图5所示，根据第二识别结果，将图像中的显著性目标确定为待跟随目标的步骤可以包括：子步骤S1033至S1034。
子步骤S1033、若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级；
子步骤S1034、根据所述图像中的每个所述显著性目标的所述第二跟随优先级，从多个所述显著性目标中确定所述待跟随目标。
如果拍摄设备采集到的图像中存在多个显著性目标，则根据显著性目标的第二识别结果，确定每个显著性目标的第二跟随优先级，并将第二跟随优先级最高对应的显著性目标确定为待跟随目标。例如，显著性目标D、显著性目标E和显著性目标F的第一跟随优先级分别为一级、二级和三级，一级对应的优先级最高，因此选择显著性目标D作为待跟随目标。其中，第二跟随优先级用 于描述选择显著性目标作为待跟随目标的概率高低，第二跟随优先级越高的显著性目标，则选择该显著性目标作为待跟随目标的概率越高，第二跟随优先级越低的显著性目标，则选择该显著性目标作为待跟随目标的概率越低。通过确定每个显著性目标的第二跟随优先级，并将第二跟随优先级最高对应的显著性目标确定为待跟随目标，使得确定的待跟随目标更加符合用户的需求，提高用户体验。
在一实施例中，根据显著性目标的第二识别结果，确定每个显著性目标的第二跟随优先级的方式可以为：从第二识别结果中获取每个显著性目标的跟随概率，其中，该跟随概率为根据目标检测算法对图像中的对象进行显著性目标识别时输出的对象为显著性目标的概率；和/或，从第二识别结果中获取每个显著性目标在该图像中的位置；和/或，从第二识别结果中获取每个显著性目标在该图像中的位置信息，并根据每个显著性目标在该图像中的位置信息，确定每个显著性目标占该图像的画幅比例；根据每个显著性目标的跟随概率、在该图像中的位置和/或占该图像的画幅比例，确定每个显著性目标的第二跟随优先级。
例如，显著性目标D、显著性目标E和显著性目标F的跟随概率分别为90％、80％和85％，由于90％>85％>80％，因此，通过90％>85％>80％的大小关系，可以确定显著性目标D的第二跟随优先级为一级、显著性目标F的第二跟随优先级为二级，显著性目标E的第二跟随优先级为三级。又例如，显著性目标D、显著性目标E和显著性目标F占该图像的画幅比例分别为8％、12％和15％，由于15％>12％>8％，因此，通过15％>12％>8％的大小关系，可以确定显著性目标D的第二跟随优先级为三级、显著性目标E的第二跟随优先级为二级，显著性目标F的第二跟随优先级为一级。
在一实施例中，根据每个显著性目标在该图像中的位置，确定每个显著性目标的第二跟随优先级的方式可以为：获取该图像的中心位置，并根据每个显著性目标在该图像中的位置和该图像的中心位置，确定每个显著性目标的位置与中心位置之间的距离；根据每个显著性目标的位置与中心位置之间的距离，确定每个显著性目标的第二跟随优先级。例如，显著性目标D、显著性目标E和显著性目标F在该图像中的位置与中心位置之间的距离分别为d、e和f，且d>e>f，因此，通过d>e>f的大小关系，可以确定显著性目标D的第二跟随优先级为三级、显著性目标E的第二跟随优先级为二级，显著性目标F的第二跟随优先级为一级。
在一实施例中，根据每个显著性目标的跟随概率、在该图像中的位置和/ 或占该图像的画幅比例，确定每个显著性目标的第二跟随优先级的方式可以为：根据每个显著性目标的跟随概率，确定每个显著性目标的第一跟随指数；确定每个显著性目标的位置与该图像的中心位置之间的距离，并根据每个显著性目标的位置与该图像的中心位置之间的距离，确定每个显著性目标的第二跟随指数；根据每个显著性目标占该图像的画幅比例，确定第三跟随指数，并根据每个显著性目标的第一跟随指数、第二跟随指数和/或第三跟随指数，确定每个显著性目标的目标跟随指数；根据每个显著性目标的目标跟随指数，确定每个显著性目标的第二跟随优先级。
其中，显著性目标的第一跟随指数可以根据第一预设映射关系和显著性目标的跟随概率确定，第一预设映射关系包括不同跟随概率各自对应的跟随指数，例如，跟随概率为60％、70％、90％、95％对应的跟随指数分别为60分、70分、90分、95分，因此，显著性目标的跟随概率为90％，则显著性目标的第一跟随指数为90。
显著性目标的第二跟随指数可以根据第二预设映射关系和显著性目标的位置与该图像的中心位置之间的距离确定，第二预设关系包括不同距离对应的跟随指数，例如，距离为0.5厘米、1厘米、1.5厘米对应的跟随指数分别为90分、80分和70分，因此，显著性目标的位置与该图像的中心位置之间的距离为1厘米，则显著性目标的第二跟随指数为80分。
本申请并非限于此。根据本申请的另一实施方式，根据每个显著性目标在该图像中的位置，确定每个显著性目标的第二跟随优先级的方式可以为：在图像中指定一预定位置，并根据每个显著性目标在该图像中的位置和该图像的预定位置，确定每个显著性目标的位置与预定位置之间的距离；根据每个显著性目标的位置与预定位置之间的距离，确定每个显著性目标的第二跟随优先级。
显著性目标的第三跟随指数可以根据第三预设映射关系和显著性目标占该图像的画幅比例确定，第三预设映射关系包括不同画幅比例对应的跟随指数，例如，画幅比例为5％、10％、12％对应的跟随指数分别为60分、65分和70分，因此，显著性目标占该图像的画幅比例为10％，则特定目标的第三跟随指数为65分。
在一实施例中，根据第一跟随指数、第二跟随指数和/或第三跟随指数，确定显著性目标的目标跟随指数的方式可以为：若仅考虑显著性目标的跟随概率，则将第一跟随指数确定为显著性目标的目标跟随指数；若仅考虑显著性目标在该图像中的位置，则将第二跟随指数确定为显著性目标的目标跟随指数；若仅 考虑显著性目标占该图像的画幅比例，则将第三跟随指数确定为显著性目标的目标跟随指数；若考虑显著性目标的跟随概率和在该图像中的位置，则将第一跟随指数和第二跟随指数之和确定为显著性目标的目标跟随指数；若考虑显著性目标的跟随概率和占该图像的画幅比例，则将第一跟随指数和第三跟随指数之和确定为显著性目标的目标跟随指数；若考虑显著性目标在该图像中的位置和占该图像的画幅比例，则将第二跟随指数和第三跟随指数之和确定为显著性目标的目标跟随指数；若考虑显著性目标的跟随概率、在该图像中的位置和占该图像的画幅比例，则将第一跟随指数、第二跟随指数和第三跟随指数之和确定为显著性目标的目标跟随指数。
在一实施例中，若考虑显著性目标的跟随概率和显著性目标在该图像中的位置，则计算第一预设权重与显著性目标的第一跟随指数的乘积，并计算第二预设权重与显著性目标的第二跟随指数的乘积；计算上述两个乘积的和，并将上述两个乘积的和确定为显著性目标的目标跟随指数，其中，第一预设权重与第二预设权重之和为1。
或者，若考虑显著性目标的跟随概率和占该图像的画幅比例，则计算第一预设权重与显著性目标的第一跟随指数的乘积，并计算第三预设权重与显著性目标的第三跟随指数的乘积；计算上述两个乘积的和，并将上述两个乘积的和确定为显著性目标的目标跟随指数，其中，第一预设权重与第三预设权重之和为1。
或者，若考虑显著性目标在该图像中的位置和显著性目标占该图像的画幅比例，则计算第二预设权重与显著性目标的第二跟随指数的乘积，并计算第三预设权重与显著性目标的第三跟随指数的乘积；计算上述两个乘积的和，并将上述两个乘积的和确定为显著性目标的目标跟随指数，其中，第二预设权重与第三预设权重之和为1。
或者，若考虑显著性目标的跟随概率、在该图像中的位置和占该图像的画幅比例，则计算第一预设权重与显著性目标的第一跟随指数的乘积、计算第二预设权重与显著性目标的第二跟随指数的乘积以及计算第三预设权重与显著性目标的第三跟随指数的乘积；计算上述三个乘积的和，并将上述三个乘积的和确定为显著性目标的目标跟随指数，其中，第一预设权重、第二预设权重与第三预设权重之和为1。
在一实施例中，根据第二识别结果，将图像中的显著性目标确定为待跟随目标的方式可以为：若拍摄设备采集到的图像中存在多个显著性目标，则根据 显著性目标的第二识别结果，确定每个显著性目标的类别；根据拍摄设备的当前拍摄模式对应的第三预设类别库和每个显著性目标的类别，从多个显著性目标中确定待跟随目标。其中，拍摄设备的拍摄模式包括人像拍摄模式、宠物拍摄模式、植物拍摄模式、车辆拍摄模式和全景拍摄模式等，不同拍摄模式对应不同的第三预设类别库。通过基于拍摄设备的当前拍摄模式对应的第三预设类别库和每个显著性目标的类别，确定待跟随目标，使得确定的待跟随目标更加符合用户的需求，极大地提高了用户体验。
在一实施例中，根据拍摄设备的当前拍摄模式对应的第三预设类别库和每个显著性目标的类别，从多个显著性目标中确定待跟随目标的方式可以为：确定多个显著性目标中是否存在类别位于第三预设类别库内的显著性目标，若类别位于第三预设类别库内的显著性目标仅有一个，则将类别位于第三预设类别库内的显著性目标确定为待跟随目标；若类别位于第三预设类别库内的显著性目标的数量至少为两个，则根据第二识别结果，确定类别位于第三预设类别库内的每个显著性目标的跟随优先级，并将该跟随优先级最高对应的显著性目标确定为待跟随目标。
在一实施例中，如图6所示，根据第一识别结果和第二识别结果，从图像中确定待跟随目标的步骤可以包括：子步骤S1035至S1037。
子步骤S1035、根据所述第一识别结果，确定所述图像中的特定目标的第一跟随优先级；
子步骤S1036、根据所述第二识别结果，确定所述图像中的显著性目标的第二跟随优先级；
子步骤S1037、根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标。
如果图像中存在特定目标和显著性目标，则根据第一识别结果确定图像中的特定目标的第一跟随优先级，并根据第二识别结果确定图像中的显著性目标的第二跟随优先级，然后根据第一跟随优先级和第二跟随优先级，从该特定目标和显著性目标中确定待跟随目标，即若特定目标的第一跟随优先级高于显著性目标的第二跟随优先级，则将该特定目标确定为待跟随目标；或者若显著性目标的第二跟随优先级高于特定目标的第一跟随优先级，则将该显著性目标确定为待跟随目标。通过在图像中同时存在特定目标和显著性目标时，将跟随优先级较高的特定目标或显著性目标确定为待跟随目标，使得确定的待跟随目标更加符合用户的需求，极大地提高了用户体验。
上述实施例提供的待跟随目标的确定方法，通过在拍摄设备采集到的图像中识别特定目标和显著性目标，得到特定目标的第一识别结果和显著性目标的第二识别结果，并根据第一识别结果和第二识别结果，从该图像中确定待跟随目标，整个过程不需要用户通过人机交互界面框选其他目标或特定目标作为待跟随目标，能够准确快速地确定待跟随目标，极大地提高了用户体验。
请参阅图7，图7是本申请实施例提供的另一种待跟随目标的确定方法的步骤示意流程图。
如图7所示，该待跟随目标的确定方法包括步骤S201至S207。
步骤S201、响应于用户对所述跟随控制按键的第一按压操作，获取所述拍摄设备采集到的所述图像，并通过所述显示装置显示所述图像。
其中，目标确定装置包括跟随控制按键和显示装置，该该跟随控制按键用于控制目标确定装置确定待跟随目标。例如，响应于用户对该跟随控制按键的第一按压操作，获取拍摄设备采集到的图像，并通过显示装置显示图像，使得目标确定装置能够从该图像中确定待跟随目标。其中，第一按压操作包括单击操作、双击操作和长按操作等。
步骤S202、在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库。
其中，第一预设类别库中的类别包括能够通过目标检测算法识别到的对象的类别，例如，行人、车辆和船舶等，对此，可以通过目标检测算法在拍摄设备采集到的图像中识别特定目标，得到特定目标的第一识别结果。
步骤S203、在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的。
其中，可以通过显著性目标检测算法在拍摄设备采集到的图像中识别显著性目标，得到显著性目标的第二识别结果，显著性目标的类别与特定目标的类别不同。所述待跟随目标包括显著性目标和特定目标中的任一项，所述显著性目标包括位于所述图像中的预设位置的对象，且所述对象在预设位置的停留时长大于预设停留时长；和/或，所述显著性目标位于所述图像中的前景图像中；和/或，所述显著性目标在所述图像中的图像区域与所述图像区域的相邻图像区域之间的显著性值大于或等于预设显著性值。
步骤S204、根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
若第一识别结果为图像中存在特定目标，则根据第一识别结果，将图像中的特定目标确定为待跟随目标；若第一识别结果为图像中不存在特定目标，则根据第二识别结果，将图像中的显著性目标确定为待跟随目标。通过在识别到特定目标时，将特定目标作为待跟随目标，而未识别到特定目标，且识别到显著性目标时，将显著性目标作为待跟随目标，不需要用户通过人机交互页面框选待跟随目标，也能够准确快速地确定待跟随目标，极大地提高了用户体验。
步骤S205、在显示的所述图像中标识所述待跟随目标，并根据所述第一识别结果和所述第二识别结果确定所述图像中的每个候选目标的跟随优先级。
在确定待跟随目标后，在显示装置显示的图像中标识待跟随目标，并根据第一识别结果和第二识别结果确定该图像中的每个候选目标的跟随优先级，即若该图像中仅存在特定目标，则根据第一识别结果，确定该图像中的每个特定目标的跟随优先级，若该图像中仅存在显著性目标，则根据第二识别结果，确定该图像中的每个显著性目标的跟随优先级，若该图像中同时存在特定目标和显著性目标，则根据第一识别结果和第二识别结果，确定特定目标和显著性目标的跟随优先级。其中，候选目标包括特定目标和显著性目标，候选目标的跟随优先级的确定方式可以参照前述实施例，此处不做赘述。
其中，在显示装置显示的图像中标识待跟随目标的方式包括在待跟随目标所处的区域显示矩形框和/或标识图标。示例性的，如图8所示，显示装置显示的图像中包括特定目标10、特定目标20和显著性目标30，由于特定目标为10为待跟随目标，则特定目标10所处的区域显示有矩形框40。如图9所示，特定目标10所处的区域显示有矩形框40和标识图标50。
在一实施例中，标识图标可以用于指示候选的待跟随目标。示例性的，如图10所示，显示装置显示的图像中包括特定目标10、特定目标20和显著性目标30，且特定目标10、特定目标20和显著性目标30所处的区域显示有标识图标51、标识图标52和标识图标53，以指示特定目标10、特定目标20和显著性目标30为可选的待跟随目标。如图11所示，当用户选择显著性目标30作为待跟随目标时，在显著性目标30所处的区域显示矩形框40。通过在候选的待跟随目标所处的区域上显示标识图标，便于用户从候选的待跟随目标中切换实际跟随的待跟随目标。
步骤S206、响应于用户对所述跟随控制按键的第二按压操作，根据所述待跟随目标的所述跟随优先级和每个所述候选目标的所述跟随优先级，重新确定所述待跟随目标。
步骤S207、在所述图像中标识重新确定的所述待跟随目标。
在需要切换待跟随目标时，响应于用户对该跟随控制按键的第二按压操作，根据待跟随目标的跟随优先级和每个候选目标的跟随优先级，重新确定待跟随目标，并在显示装置显示的图像中标识重性确定的待跟随目标。其中，重新确定前的待跟随目标的跟随优先级高于重新确定后的待跟随目标的跟随优先级，或者重新确定前的待跟随目标的跟随优先级低于重新确定后的待跟随目标的跟随优先级，第二按压操作包括单击操作、双击操作和长按操作。
示例性的，设特定目标10、特定目标20和显著性目标30的跟随优先级分别为一级、二级和三级，当用户对该跟随控制按键进行按压后，由于特定目标10、特定目标20和显著性目标30的跟随优先级分别为一级、二级和三级，因此将特定目标20确定为新的待跟随目标，如图12所示，特定目标20所处的区域显示有矩形框40，当用户继续对该跟随控制按键进行按压，则将显著性目标30确定为新的待跟随目标，如图13所示，显著性目标30所处的区域显示有矩形框40。当用户继续对该跟随控制按键进行按压，则再次将特定目标10确定为待跟随目标。
上述实施例提供的待跟随目标的确定方法，通过在显示装置显示的图像中标识确定的待跟随目标，并响应于用户对跟随控制按键的按压操作，改变显示的图像中的待跟随目标，极大地方便用户切换待跟随目标，提高用户体验。
请参阅图14，图14是本申请实施例提供的一种目标确定装置的结构示意性框图。
如图14所示，目标确定装置600包括处理器601和存储器602，处理器601和存储器602通过总线603连接，该总线603比如为I2C(Inter-integrated Circuit)总线。目标确定装置600用于与拍摄设备通信连接。
具体地，处理器601可以是微控制单元(Micro-controller Unit，MCU)、中央处理单元(Central Processing Unit，CPU)或数字信号处理器(Digital Signal Processor，DSP)等。
具体地，存储器602可以是Flash芯片、只读存储器(ROM，Read-Only Memory)磁盘、光盘、U盘或移动硬盘等。
其中，所述处理器601用于运行存储在存储器602中的计算机程序，并在执行所述计算机程序时实现如下步骤：
在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库；
在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的；
根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
在一实施例中，所述待跟随目标包括所述显著性目标和所述特定目标中的任一项，所述显著性目标包括位于所述图像中的预设位置的对象，且所述对象在所述预设位置的停留时长大于预设停留时长。
在一实施例中，所述显著性目标位于所述图像中的前景图像中。
在一实施例中，所述显著性目标在所述图像中的图像区域与所述图像区域的相邻图像区域之间的显著性值大于或等于预设显著性值。
在一实施例中，所述处理器在实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标时，用于实现：
若所述第一识别结果为所述图像中存在所述特定目标，则根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标时，用于实现：
若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的第一跟随优先级；
根据每个所述特定目标的所述第一跟随优先级，从多个所述特定目标中确定所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标时，用于实现：
若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的类别；
根据所述拍摄设备的当前拍摄模式对应的第二预设类别库和每个所述特定目标的类别，从多个所述特定目标中确定所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标时，用于实现：
若所述第一识别结果为所述图像中不存在所述特定目标，则根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第二识别结果，将所述图像中 的所述显著性目标确定为所述待跟随目标时，用于实现：
若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级；
根据所述图像中的每个所述显著性目标的所述第二跟随优先级，从多个所述显著性目标中确定所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级时，用于实现：
根据所述第二识别结果，确定每个所述显著性目标的跟随概率、占所述图像的画幅比例和/或在所述图像中的位置；
根据每个所述显著性目标的跟随概率、占所述图像的画幅比例和/或在所述图像中的位置，确定每个所述显著性目标的所述第二跟随优先级。
在一实施例中，所述处理器在实现根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标时，用于实现：
若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的类别；
根据所述拍摄设备的当前拍摄模式对应的第三预设类别库和每个所述显著性目标的类别，从多个所述显著性目标中确定所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标时，用于实现：
根据所述第一识别结果，确定所述图像中的特定目标的第一跟随优先级；
根据所述第二识别结果，确定所述图像中的显著性目标的第二跟随优先级；
根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标。
在一实施例中，所述处理器在实现根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标时，用于实现：
若所述第一跟随优先级高于所述第二跟随优先级，则将所述特定目标确定为所述待跟随目标；或者
若所述第二跟随优先级高于所述第一跟随优先级，则将所述显著性目标确定为所述待跟随目标。
在一实施例中，所述目标确定装置包括跟随控制按键和显示装置，所述处理器在实现在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标 的第一识别结果之前，还用于实现：
响应于用户对所述跟随控制按键的第一按压操作，获取所述拍摄设备采集到的所述图像，并通过所述显示装置显示所述图像；
所述处理器实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标之后，还用于实现：
在显示的所述图像中标识所述待跟随目标，并根据所述第一识别结果和所述第二识别结果确定所述图像中的每个候选目标的跟随优先级；
响应于用户对所述跟随控制按键的第二按压操作，根据所述待跟随目标的所述跟随优先级和每个所述候选目标的所述跟随优先级，重新确定所述待跟随目标；
在所述图像中标识重新确定的所述待跟随目标。
在一实施例中，重新确定前的所述待跟随目标的所述跟随优先级高于重新确定后的所述待跟随目标的所述跟随优先级。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的目标确定装置的具体工作过程，可以参考前述待跟随目标的确定方法实施例中的对应过程，在此不再赘述。
请参阅图15，图15是本申请实施例提供的一种目标跟随系统的结构示意性框图。
如图15所示，目标跟随系统700包括目标确定装置710、云台720、搭载于云台720上的拍摄设备730，该目标确定装置710与拍摄设备730通信连接。在一实施例中，云台720连接于手柄部，目标确定装置710设置在手柄部上。在另一实施例中，云台720搭载在可移动平台上，目标确定装置710还用于控制可移动平台移动。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的目标跟随系统的具体工作过程，可以参考前述待跟随目标的确定方法实施例中的对应过程，在此不再赘述。
请参阅图16，图6是本申请实施例提供的一种手持云台的结构示意性框图。
如图16所示，手持云台800包括目标确定装置810、手柄部、连接于手柄部的云台820，云台820用于搭载拍摄设备，目标确定装置810设置在手柄部上。目标确定装置810与云台820连接。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的手持云台的具体工作过程，可以参考前述待跟随目标的确 定方法实施例中的对应过程，在此不再赘述。
请参阅图17，图17是本申请实施例提供的一种可移动平台的结构示意性框图。
如图17所示，可移动平台900包括平台本体、搭载于平台本体的云台910和目标确定装置920，云台910用于搭载拍摄设备，目标确定装置920设置在平台本体上。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的可移动平台的具体工作过程，可以参考前述待跟随目标的确定方法实施例中的对应过程，在此不再赘述。
本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序中包括程序指令，所述处理器执行所述程序指令，实现上述实施例提供的待跟随目标的确定方法的步骤。
其中，所述计算机可读存储介质可以是前述任一实施例所述的控制终端或无人飞行器的内部存储单元，例如所述控制终端或无人飞行器的硬盘或内存。所述计算机可读存储介质也可以是所述控制终端或无人飞行器的外部存储设备，例如所述控制终端或无人飞行器上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。
应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (36)

  1. 一种待跟随目标的确定方法，其特征在于，应用于目标确定装置，所述目标确定装置用于与拍摄设备通信连接，所述方法包括：
    在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库；
    在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的；
    根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
  2. 根据权利要求1所述的待跟随目标的确定方法，其特征在于，所述待跟随目标包括所述显著性目标和所述特定目标中的任一项，所述显著性目标包括位于所述图像中的预设位置的对象，且所述对象在所述预设位置的停留时长大于预设停留时长。
  3. 根据权利要求1所述的待跟随目标的确定方法，其特征在于，所述显著性目标位于所述图像中的前景图像中。
  4. 根据权利要求1所述的待跟随目标的确定方法，其特征在于，所述显著性目标在所述图像中的图像区域与所述图像区域的相邻图像区域之间的显著性值大于或等于预设显著性值。
  5. 根据权利要求1所述的待跟随目标的确定方法，其特征在于，所述根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标，包括：
    若所述第一识别结果为所述图像中存在所述特定目标，则根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标。
  6. 根据权利要求5所述的待跟随目标的确定方法，其特征在于，所述根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标，包括：
    若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的第一跟随优先级；
    根据每个所述特定目标的所述第一跟随优先级，从多个所述特定目标中确定所述待跟随目标。
  7. 根据权利要求5所述的待跟随目标的确定方法，其特征在于，所述根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标，包括：
    若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的类别；
    根据所述拍摄设备的当前拍摄模式对应的第二预设类别库和每个所述特定目标的类别，从多个所述特定目标中确定所述待跟随目标。
  8. 根据权利要求1-7中任一项所述的待跟随目标的确定方法，其特征在于，所述根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标，包括：
    若所述第一识别结果为所述图像中不存在所述特定目标，则根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标。
  9. 根据权利要求8所述的待跟随目标的确定方法，其特征在于，所述根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标，包括：
    若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级；
    根据所述图像中的每个所述显著性目标的所述第二跟随优先级，从多个所述显著性目标中确定所述待跟随目标。
  10. 根据权利要求9所述的待跟随目标的确定方法，其特征在于，所述根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级，包括：
    根据所述第二识别结果，确定每个所述显著性目标的跟随概率、占所述图像的画幅比例和/或在所述图像中的位置；
    根据每个所述显著性目标的跟随概率、占所述图像的画幅比例和/或在所述图像中的位置，确定每个所述显著性目标的所述第二跟随优先级。
  11. 根据权利要求8所述的待跟随目标的确定方法，其特征在于，所述根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标，包括：
    若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的类别；
    根据所述拍摄设备的当前拍摄模式对应的第三预设类别库和每个所述显著性目标的类别，从多个所述显著性目标中确定所述待跟随目标。
  12. 根据权利要求1-7中任一项所述的待跟随目标的确定方法，其特征在于，所述根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标，包括：
    根据所述第一识别结果，确定所述图像中的特定目标的第一跟随优先级；
    根据所述第二识别结果，确定所述图像中的显著性目标的第二跟随优先级；
    根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标。
  13. 根据权利要求12所述的待跟随目标的确定方法，其特征在于，所述根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标，包括：
    若所述第一跟随优先级高于所述第二跟随优先级，则将所述特定目标确定为所述待跟随目标；或者
    若所述第二跟随优先级高于所述第一跟随优先级，则将所述显著性目标确定为所述待跟随目标。
  14. 根据权利要求1-7中任一项所述的待跟随目标的确定方法，其特征在于，所述目标确定装置包括跟随控制按键和显示装置，所述在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果之前，还包括：
    响应于用户对所述跟随控制按键的第一按压操作，获取所述拍摄设备采集到的所述图像，并通过所述显示装置显示所述图像；
    所述根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标之后，还包括：
    在显示的所述图像中标识所述待跟随目标，并根据所述第一识别结果和所述第二识别结果确定所述图像中的每个候选目标的跟随优先级；
    响应于用户对所述跟随控制按键的第二按压操作，根据所述待跟随目标的所述跟随优先级和每个所述候选目标的所述跟随优先级，重新确定所述待跟随目标；
    在所述图像中标识重新确定的所述待跟随目标。
  15. 根据权利要求14所述的待跟随目标的确定方法，其特征在于，重新确定前的所述待跟随目标的所述跟随优先级高于重新确定后的所述待跟随目标的所述跟随优先级。
  16. 一种目标确定装置，其特征在于，所述目标确定装置用于与拍摄设备通信连接，所述目标确定装置包括存储器和处理器；
    所述存储器用于存储计算机程序；
    所述处理器，用于执行所述计算机程序并在执行所述计算机程序时，实现如下步骤：
    在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果，其中，所述特定目标的类别位于第一预设类别库；
    在所述拍摄设备采集到的所述图像中识别显著性目标，得到所述显著性目标的第二识别结果，其中，所述显著性目标是依据目标对象在采集到的所述图像中的显著程度来确定的；
    根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标。
  17. 根据权利要求16所述的目标确定装置，其特征在于，所述待跟随目标包括所述显著性目标和所述特定目标中的任一项，所述显著性目标包括位于所述图像中的预设位置的对象，且所述对象在所述预设位置的停留时长大于预设停留时长。
  18. 根据权利要求16所述的目标确定装置，其特征在于，所述显著性目标位于所述图像中的前景图像中。
  19. 根据权利要求16所述的目标确定装置，其特征在于，所述显著性目标在所述图像中的图像区域与所述图像区域的相邻图像区域之间的显著性值大于或等于预设显著性值。
  20. 根据权利要求16所述的目标确定装置，其特征在于，所述处理器在实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定待跟随目标时，用于实现：
    若所述第一识别结果为所述图像中存在所述特定目标，则根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标。
  21. 根据权利要求20所述的目标确定装置，其特征在于，所述处理器在实现根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标时，用于实现：
    若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的第一跟随优先级；
    根据每个所述特定目标的所述第一跟随优先级，从多个所述特定目标中确定所述待跟随目标。
  22. 根据权利要求20所述的目标确定装置，其特征在于，所述处理器在实 现根据所述第一识别结果，将所述图像中的所述特定目标确定为所述待跟随目标时，用于实现：
    若所述图像中存在多个所述特定目标，则根据所述第一识别结果，确定每个所述特定目标的类别；
    根据所述拍摄设备的当前拍摄模式对应的第二预设类别库和每个所述特定目标的类别，从多个所述特定目标中确定所述待跟随目标。
  23. 根据权利要求16-22中任一项所述的目标确定装置，其特征在于，所述处理器在实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标时，用于实现：
    若所述第一识别结果为所述图像中不存在所述特定目标，则根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标。
  24. 根据权利要求23所述的目标确定装置，其特征在于，所述处理器在实现根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标时，用于实现：
    若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级；
    根据所述图像中的每个所述显著性目标的所述第二跟随优先级，从多个所述显著性目标中确定所述待跟随目标。
  25. 根据权利要求24所述的目标确定装置，其特征在于，所述处理器在实现根据所述第二识别结果，确定每个所述显著性目标的所述第二跟随优先级时，用于实现：
    根据所述第二识别结果，确定每个所述显著性目标的跟随概率、占所述图像的画幅比例和/或在所述图像中的位置；
    根据每个所述显著性目标的跟随概率、占所述图像的画幅比例和/或在所述图像中的位置，确定每个所述显著性目标的所述第二跟随优先级。
  26. 根据权利要求23所述的目标确定装置，其特征在于，所述处理器在实现根据所述第二识别结果，将所述图像中的所述显著性目标确定为所述待跟随目标时，用于实现：
    若所述图像中存在多个所述显著性目标，则根据所述第二识别结果，确定每个所述显著性目标的类别；
    根据所述拍摄设备的当前拍摄模式对应的第三预设类别库和每个所述显著性目标的类别，从多个所述显著性目标中确定所述待跟随目标。
  27. 根据权利要求16-22中任一项所述的目标确定装置，其特征在于，所述处理器在实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标时，用于实现：
    根据所述第一识别结果，确定所述图像中的特定目标的第一跟随优先级；
    根据所述第二识别结果，确定所述图像中的显著性目标的第二跟随优先级；
    根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标。
  28. 根据权利要求27所述的目标确定装置，其特征在于，所述处理器在实现根据所述第一跟随优先级和所述第二跟随优先级，从所述特定目标和所述显著性目标中确定所述待跟随目标时，用于实现：
    若所述第一跟随优先级高于所述第二跟随优先级，则将所述特定目标确定为所述待跟随目标；或者
    若所述第二跟随优先级高于所述第一跟随优先级，则将所述显著性目标确定为所述待跟随目标。
  29. 根据权利要求16-22中任一项所述的目标确定装置，其特征在于，所述目标确定装置包括跟随控制按键和显示装置，所述处理器在实现在所述拍摄设备采集到的图像中识别特定目标，得到所述特定目标的第一识别结果之前，还用于实现：
    响应于用户对所述跟随控制按键的第一按压操作，获取所述拍摄设备采集到的所述图像，并通过所述显示装置显示所述图像；
    所述处理器实现根据所述第一识别结果和所述第二识别结果，从所述图像中确定所述待跟随目标之后，还用于实现：
    在显示的所述图像中标识所述待跟随目标，并根据所述第一识别结果和所述第二识别结果确定所述图像中的每个候选目标的跟随优先级；
    响应于用户对所述跟随控制按键的第二按压操作，根据所述待跟随目标的所述跟随优先级和每个所述候选目标的所述跟随优先级，重新确定所述待跟随目标；
    在所述图像中标识重新确定的所述待跟随目标。
  30. 根据权利要求29所述的目标确定装置，其特征在于，重新确定前的所述待跟随目标的所述跟随优先级高于重新确定后的所述待跟随目标的所述跟随优先级。
  31. 一种目标跟随系统，其特征在于，所述目标跟随系统包括云台、搭载 于所述云台上的拍摄设备和如权利要求16-30中任一项所述的目标确定装置。
  32. 根据权利要求31所述的目标跟随系统，其特征在于，所述云台连接于手柄部，所述目标确定装置设置在所述手柄部上。
  33. 根据权利要求31所述的目标跟随系统，其特征在于，所述云台搭载在可移动平台上，所述目标确定装置还用于控制所述可移动平台移动。
  34. 一种手持云台，其特征在于，所述手持云台包括手柄部、连接于所述手柄部的云台和如权利要求16-30中任一项所述的目标确定装置，所述云台用于搭载拍摄设备，所述目标确定装置设置在所述手柄部上。
  35. 一种可移动平台，其特征在于，所述可移动平台包括平台本体、搭载于所述平台本体的云台和如权利要求16-30中任一项所述的目标确定装置，所述云台用于搭载拍摄设备，所述目标确定装置设置在所述平台本体上。
  36. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时使所述处理器实现如权利要求1-15中任一项所述的待跟随目标的确定方法的步骤。
PCT/CN2020/117223 2020-09-23 2020-09-23 待跟随目标的确定方法、装置、系统、设备及存储介质 WO2022061615A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080007463.4A CN113273174A (zh) 2020-09-23 2020-09-23 待跟随目标的确定方法、装置、系统、设备及存储介质
PCT/CN2020/117223 WO2022061615A1 (zh) 2020-09-23 2020-09-23 待跟随目标的确定方法、装置、系统、设备及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/117223 WO2022061615A1 (zh) 2020-09-23 2020-09-23 待跟随目标的确定方法、装置、系统、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022061615A1 true WO2022061615A1 (zh) 2022-03-31

Family

ID=77227956

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/117223 WO2022061615A1 (zh) 2020-09-23 2020-09-23 待跟随目标的确定方法、装置、系统、设备及存储介质

Country Status (2)

Country Link
CN (1) CN113273174A (zh)
WO (1) WO2022061615A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112279A (zh) * 2013-04-19 2014-10-22 浙江大华技术股份有限公司 一种目标检测方法及装置
CN106651901A (zh) * 2015-07-24 2017-05-10 株式会社理光 对象跟踪方法和设备
CN106650630A (zh) * 2016-11-11 2017-05-10 纳恩博（北京）科技有限公司 一种目标跟踪方法及电子设备
CN109889727A (zh) * 2019-03-14 2019-06-14 睿魔智能科技（深圳）有限公司 无人拍摄目标切换方法及系统、无人摄像机及存储介质
CN110580053A (zh) * 2019-08-13 2019-12-17 深圳市道通智能航空技术有限公司 一种目标追踪方法、飞行器及飞行系统
CN111127518A (zh) * 2019-12-24 2020-05-08 深圳火星探索科技有限公司 基于无人机的目标跟踪方法及装置
CN111527463A (zh) * 2018-01-22 2020-08-11 深圳市大疆创新科技有限公司 用于多目标跟踪的方法和系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103984955B (zh) * 2014-04-23 2017-02-22 浙江工商大学 基于显著性特征和迁移增量学习的多摄像机目标识别方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112279A (zh) * 2013-04-19 2014-10-22 浙江大华技术股份有限公司 一种目标检测方法及装置
CN106651901A (zh) * 2015-07-24 2017-05-10 株式会社理光 对象跟踪方法和设备
CN106650630A (zh) * 2016-11-11 2017-05-10 纳恩博（北京）科技有限公司 一种目标跟踪方法及电子设备
CN111527463A (zh) * 2018-01-22 2020-08-11 深圳市大疆创新科技有限公司 用于多目标跟踪的方法和系统
CN109889727A (zh) * 2019-03-14 2019-06-14 睿魔智能科技（深圳）有限公司 无人拍摄目标切换方法及系统、无人摄像机及存储介质
CN110580053A (zh) * 2019-08-13 2019-12-17 深圳市道通智能航空技术有限公司 一种目标追踪方法、飞行器及飞行系统
CN111127518A (zh) * 2019-12-24 2020-05-08 深圳火星探索科技有限公司 基于无人机的目标跟踪方法及装置

Also Published As

Publication number Publication date
CN113273174A (zh) 2021-08-17

Similar Documents

Publication Publication Date Title
US11644832B2 (en) User interaction paradigms for a flying digital assistant
US11914370B2 (en) System and method for providing easy-to-use release and auto-positioning for drone applications
US11573562B2 (en) Magic wand interface and other user interaction paradigms for a flying digital assistant
US11288767B2 (en) Course profiling and sharing
US20180181119A1 (en) Method and electronic device for controlling unmanned aerial vehicle
WO2019242553A1 (zh) 控制拍摄装置的拍摄角度的方法、控制装置及可穿戴设备
KR101790592B1 (ko) 관광드론을 이용한 증강현실 관광 시스템 및 방법
WO2021127888A1 (zh) 控制方法、智能眼镜、可移动平台、云台、控制系统及计算机可读存储介质
KR102190743B1 (ko) 로봇과 인터랙션하는 증강현실 서비스 제공 장치 및 방법
WO2022082440A1 (zh) 确定目标跟随策略的方法、装置、系统、设备及存储介质
WO2022061615A1 (zh) 待跟随目标的确定方法、装置、系统、设备及存储介质
WO2020042186A1 (zh) 可移动平台的控制方法、可移动平台、终端设备和系统
WO2022188151A1 (zh) 影像拍摄方法、控制装置、可移动平台和计算机存储介质
WO2022061934A1 (zh) 图像处理方法、装置、系统、平台及计算机可读存储介质
WO2022021028A1 (zh) 目标检测方法、装置、无人机及计算机可读存储介质
WO2023065126A1 (zh) 拍摄控制方法、设备、拍摄系统及存储介质
US12007763B2 (en) Magic wand interface and other user interaction paradigms for a flying digital assistant
US20230280742A1 (en) Magic Wand Interface And Other User Interaction Paradigms For A Flying Digital Assistant
TWI682878B (zh) 使用無人機的旅遊系統與方法

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: 20954468

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: 20954468

Country of ref document: EP

Kind code of ref document: A1