WO2020249088A1 - 一种移动目标的追踪方法、装置及无人机 - Google Patents

一种移动目标的追踪方法、装置及无人机 Download PDF

Info

Publication number
WO2020249088A1
WO2020249088A1 PCT/CN2020/095841 CN2020095841W WO2020249088A1 WO 2020249088 A1 WO2020249088 A1 WO 2020249088A1 CN 2020095841 W CN2020095841 W CN 2020095841W WO 2020249088 A1 WO2020249088 A1 WO 2020249088A1
Authority
WO
WIPO (PCT)
Prior art keywords
moving target
moving
drone
display screen
control terminal
Prior art date
Application number
PCT/CN2020/095841
Other languages
English (en)
French (fr)
Inventor
黄欣
杜元源
Original Assignee
深圳市道通智能航空技术有限公司
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 深圳市道通智能航空技术有限公司 filed Critical 深圳市道通智能航空技术有限公司
Publication of WO2020249088A1 publication Critical patent/WO2020249088A1/zh
Priority to US17/643,696 priority Critical patent/US20220137648A1/en

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60Intended control result
    • G05D1/656Interaction with payloads or external entities
    • G05D1/686Maintaining a relative position with respect to moving targets, e.g. following animals or humans
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/12Target-seeking control
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0094Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots involving pointing a payload, e.g. camera, weapon, sensor, towards a fixed or moving target
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64CAEROPLANES; HELICOPTERS
    • B64C39/00Aircraft not otherwise provided for
    • B64C39/02Aircraft not otherwise provided for characterised by special use
    • B64C39/024Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64DEQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
    • B64D47/00Equipment not otherwise provided for
    • B64D47/08Arrangements of cameras
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U20/00Constructional aspects of UAVs
    • B64U20/80Arrangement of on-board electronics, e.g. avionics systems or wiring
    • B64U20/87Mounting of imaging devices, e.g. mounting of gimbals
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/101Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20Control system inputs
    • G05D1/22Command input arrangements
    • G05D1/221Remote-control arrangements
    • G05D1/222Remote-control arrangements operated by humans
    • G05D1/224Output arrangements on the remote controller, e.g. displays, haptics or speakers
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60Intended control result
    • G05D1/656Interaction with payloads or external entities
    • G05D1/689Pointing payloads towards fixed or moving targets
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/246Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/246Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G06T7/251Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/75Determining position or orientation of objects or cameras using feature-based methods involving models
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/17Terrestrial scenes taken from planes or by drones
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/67Focus control based on electronic image sensor signals
    • H04N23/675Focus control based on electronic image sensor signals comprising setting of focusing regions
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/695Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U10/00Type of UAV
    • B64U10/10Rotorcrafts
    • B64U10/13Flying platforms
    • B64U10/14Flying platforms with four distinct rotor axes, e.g. quadcopters
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00UAVs specially adapted for particular uses or applications
    • B64U2101/30UAVs specially adapted for particular uses or applications for imaging, photography or videography
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B64AIRCRAFT; AVIATION; COSMONAUTICS
    • B64UUNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2201/00UAVs characterised by their flight controls
    • B64U2201/10UAVs characterised by their flight controls autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10032Satellite or aerial image; Remote sensing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07Target detection

Definitions

  • This application relates to the technical field of drone tracking, in particular to a method, device and drone for tracking a moving target.
  • drones are widely used to track moving targets. They usually install wireless ranging sensors at different positions on the surface of the moving target. Each wireless ranging sensor forms a local positioning network fixed on the surface of the moving target. The wireless ranging sensor is installed on the aircraft. The wireless ranging sensor on the drone communicates and measures the distance with the wireless ranging sensor on the moving target. The drone is active in the local positioning network, and the drone is calculated by the ranging value Position in the local positioning system to achieve position lock and track moving targets.
  • the technical problem to be solved by the present invention is to provide a tracking method, device and unmanned aerial vehicle for a moving target, which solves the technical problems of poor stability and narrow application range when the related technology is tracking a moving target.
  • One aspect of the embodiments of the present invention provides a method for tracking a moving target, which is applied to a drone,
  • the drone includes a photographing device, the photographing device includes a pan/tilt and a camera mounted on the pan/tilt, and the method includes:
  • the motion state of the moving target adjust the motion state of the drone and/or the parameters of the photographing device so that the moving target is always located in the display screen of the control terminal, wherein the control terminal and The drone is in communication connection.
  • the identifying and locking the moving target includes:
  • the identifying and locking the moving target includes:
  • feature matching is performed on the moving target to identify and lock the moving target.
  • the method further includes:
  • the preprocessing of the images of the multiple moving targets includes:
  • the color of the image the brightness of the image, and the size of the image.
  • the motion state of the moving target includes the motion direction of the moving target
  • the parameters of the photographing device include the angle of the pan/tilt, then:
  • the adjusting the motion state of the drone and/or the parameters of the shooting device according to the motion state of the moving target so that the moving target is always located in the display screen of the control terminal includes :
  • the angle of the pan/tilt is adjusted according to the moving direction of the target so that the moving target is always located at
  • the preset position in the display screen of the control terminal includes:
  • the yaw angle of the pan/tilt is adjusted so that the moving target is always located at a preset position in the display screen of the control terminal.
  • the angle of the pan/tilt is adjusted according to the moving direction of the target so that the moving target is always located at
  • the display screen of the control terminal includes:
  • the pitch angle of the pan/tilt is adjusted so that the moving target is always located at a preset position in the display screen of the control terminal.
  • the method further includes:
  • the adjusting the motion state of the drone and/or the parameters of the shooting device So that the moving target is always located at the preset position in the display screen of the control terminal with the preset size, including:
  • the adjustment of the motion state of the drone and/or the parameters of the shooting device is performed to
  • the enabling the moving target to always be located at the preset position in the display screen of the control terminal at the preset size includes:
  • the focal length of the camera is adjusted so that the moving target is always located at the preset position in the display screen with the preset size.
  • the preset position is a central position of a display screen of the control terminal.
  • the method further includes:
  • a tracking device for a moving target which is applied to an unmanned aerial vehicle.
  • the unmanned aerial vehicle includes a photographing device, and the photographing device includes a pan-tilt and a camera mounted on the pan-tilt,
  • the device includes:
  • Recognition module used to identify and lock moving targets
  • the adjustment module is configured to adjust the movement state of the drone and/or the parameters of the shooting device according to the movement state of the moving target, so that the moving target is always located in the display screen of the control terminal, wherein, The control terminal is in communication connection with the drone.
  • the recognition module uses machine vision to recognize and lock the moving target.
  • the identification module is specifically configured to:
  • feature matching is performed on the moving target to identify and lock the moving target.
  • the device further includes a preprocessing module configured to preprocess the images of a plurality of the moving targets.
  • the preprocessing module is specifically used for:
  • the color of the image the brightness of the image, and the size of the image.
  • the motion state of the moving target includes the motion direction of the moving target
  • the parameters of the photographing device include the angle of the pan/tilt, then:
  • the adjustment module is specifically used for:
  • the adjustment module is specifically configured to:
  • the yaw angle of the pan/tilt is adjusted so that the moving target is always located at a preset position in the display screen of the control terminal.
  • the adjustment module is specifically configured to:
  • the pitch angle of the pan/tilt is adjusted so that the moving target is always located at a preset position in the display screen of the control terminal.
  • the adjustment module is further used for:
  • the adjustment module is specifically configured to:
  • the adjustment module is specifically configured to:
  • the focal length of the camera is adjusted so that the moving target is always located at the preset position in the display screen with the preset size.
  • the preset position is a central position of a display screen of the control terminal.
  • the identification module is further used for:
  • a drone including:
  • An arm connected to the fuselage
  • the power device is arranged on the arm and is used to provide power for the drone to fly;
  • a photographing device arranged in the body, the photographing device including a pan-tilt and a camera mounted on the pan-tilt;
  • a vision chip the vision chip is arranged in the body, and the vision chip is used to identify and lock a moving target;
  • a flight controller the flight controller is arranged on the fuselage and is in communication connection with the vision chip, and the flight controller is used for:
  • the motion state of the moving target adjust the motion state of the drone and/or the parameters of the photographing device so that the moving target is always located in the display screen of the control terminal, wherein the control terminal and The drone is in communication connection.
  • the vision chip recognizes and locks the moving target through machine vision.
  • the vision chip is specifically used for:
  • feature matching is performed on the moving target to identify and lock the moving target.
  • the vision chip is also used for:
  • the vision chip is also used for:
  • the color of the image the brightness of the image, and the size of the image.
  • the motion state of the moving target includes the motion direction of the moving target
  • the parameters of the photographing device include the angle of the pan/tilt, then:
  • the flight controller is used for:
  • the flight controller is specifically used for:
  • the yaw angle of the pan/tilt is adjusted so that the moving target is always located at a preset position in the display screen of the control terminal.
  • the flight controller is specifically used for:
  • the pitch angle of the pan/tilt is adjusted so that the moving target is always located at a preset position in the display screen of the control terminal.
  • the flight controller is also used for:
  • the flight controller is also used for:
  • the flight controller is also used for:
  • the focal length of the camera is adjusted so that the moving target is always located at the preset position in the display screen with the preset size.
  • the preset position is a central position of a display screen of the control terminal.
  • the vision chip is also used for:
  • the moving target to be tracked is first identified and locked, and then the motion state of the drone and/or the parameters of the shooting device are adjusted according to the motion state of the moving target, so as to control the movement during the tracking of the moving target
  • the target is in the display screen of the control terminal.
  • the mobile target tracking method, device and drone provided by the present invention can adjust the motion state of the drone and/or the parameters of the shooting equipment in real time according to the motion state of the mobile target, and can ensure that the mobile target is always located in the control terminal at a preset size Therefore, this embodiment improves the stability and reliability of the moving target tracking process, and has a wider application range.
  • FIG. 1 is a schematic diagram of the operating environment of a method for tracking a moving target provided by an embodiment of the present invention
  • Figure 2 is a schematic structural diagram of a drone provided by an embodiment of the present invention.
  • FIG. 3 is a flowchart of a method for tracking a moving target provided by an embodiment of the present invention.
  • step S10 is a flowchart of one embodiment of step S10 in the method for tracking a moving target provided by an embodiment of the present invention
  • step S20 is a flowchart of one embodiment of step S20 in the method for tracking a moving target provided by an embodiment of the present invention
  • FIG. 6 is a flowchart of another embodiment of a method for tracking a moving target provided by the present invention.
  • Fig. 7 is a structural block diagram of a moving target tracking device provided by an embodiment of the present invention.
  • FIG. 1 is a schematic diagram of an operating environment of a method and device for tracking a moving target according to an embodiment of the present invention.
  • the operating environment includes the control terminal 10, the drone 20, and the ground station 30.
  • the control terminal 10 communicates with the drone 20 through the ground station 30.
  • the user can control the terminal 10 to control the drone 20 to realize the tracking method of the moving target.
  • the method and device for tracking a moving target are applied to the drone 20.
  • the user can send the information of the moving target or the tracking instruction from the ground station 30 to the drone 20 by operating the control terminal 10, and the drone 20 executes the information of the moving target according to the information or the tracking instruction. Tracking method.
  • the drone 20 receives the tracking instruction of the moving target sent by the control terminal 10, the drone 20 is used to identify and lock the moving target, and adjust the unmanned vehicle according to the movement state of the moving target.
  • the drone 20 includes: a fuselage 201, four arms 202 extending from the fuselage 201, a power unit 203 respectively installed on each arm 202, and a shooting device arranged on the fuselage 201 (Not shown), a vision chip (not shown) provided on the fuselage 201, and a flight controller (not shown) provided on the fuselage 201.
  • the imaging device is connected to the vision chip and the flight controller respectively, and the vision chip is connected to the flight controller.
  • the body 201 and the arm 202 are fixedly connected, and preferably, the body 201 and the arm 202 are integrally formed.
  • the arm 202 may also be connected to the fuselage 201 in a manner of being expanded or folded relative to the fuselage 201.
  • the arm 202 can be connected to the body 201 through a rotating shaft mechanism, so that the arm 202 can be expanded or folded relative to the body 201.
  • the power device 203 is used to provide power for the drone 20 to fly.
  • the drone 20 shown in FIG. 2 is a quadrotor unmanned aerial vehicle.
  • the number of power devices 203 is four.
  • the drone 20 may be any other suitable type of unmanned aerial vehicle, such as a fixed-wing unmanned aerial vehicle.
  • the power unit 203 is applied to other types of unmanned aerial vehicles, the number of the power unit 203 can be changed according to actual needs, which is not limited in the present invention.
  • the power device 203 includes a driving device 2031 and a propeller assembly 2032 driven by the driving device 2031.
  • the propeller assembly 2032 is installed on the output shaft of the driving device 2031, and the propeller assembly 2032 is driven by the driving device 2031. It rotates to generate lift or thrust that makes the drone 20 fly.
  • the driving device 2031 may be any suitable type of motor, such as a brush motor, a brushless motor, a DC motor, a stepper motor, an AC induction motor, and so on.
  • the photographing equipment includes: a pan/tilt (not shown) and a camera (not shown) mounted on the pan/tilt.
  • the pan/tilt is installed at the bottom of the fuselage 201.
  • the pan/tilt is used to carry a high-definition digital camera or other imaging device to eliminate disturbances from the high-definition digital camera or other imaging device, and ensure the clarity and stability of the video captured by the camera or other imaging device.
  • the photographing device is used to photograph a moving target to be tracked.
  • the moving target includes, but is not limited to, other movable objects such as people, animals, and aircraft.
  • the moving target shot by the photographing device may be a video or picture containing the moving target, and the number of the video or picture is not limited.
  • the vision chip is connected to the shooting device and the flight controller.
  • the vision chip is used to identify and lock the moving target.
  • the vision chip can recognize and lock the moving target through machine vision.
  • Machine vision recognition of moving targets belongs to active recognition and does not rely on other external sensors. Therefore, it has high stability, wide application range and is not affected by the type of moving targets, and can improve the accuracy and reliability of target recognition.
  • the vision chip acquires a plurality of images containing the moving target from the shooting device, wherein the plurality of images may be images taken by the shooting device from different shooting angles and containing all the images. Describe the image of the moving target.
  • the features of the moving target include at least one of a texture feature, a shape feature, and a spatial feature
  • the texture feature is A feature of the surface of the moving target, which depicts the recurring local patterns in the image of the moving target and their arrangement rules
  • the shape feature refers to the shape of the moving target in the image, such as Circle, star, etc.
  • a feature classification model is established, wherein the feature classification model is used to characterize the category of the moving target.
  • a classification algorithm in machine learning may be used to establish the feature classification model.
  • the classification algorithm includes a support vector machine, a neural network, a Bayesian classification algorithm, and the like.
  • the main process of establishing the feature classification model includes collecting a large amount of sample data, extracting features of the sample data, and inputting the extracted features into a classification trainer for training to determine a classifier, which is the feature classification model.
  • the sample data is a model library related to the moving target to be identified.
  • feature matching is performed on the moving target to identify and lock the moving target.
  • the image of the moving target and the model library corresponding to the moving target can be input into the established feature classification model, and the moving target can be matched with features, thereby identifying and locking the moving target.
  • the information of the moving target can be output, where the information of the moving target includes the name, posture, position, shape, category, color, etc. of the moving target.
  • the vision chip is further used to preprocess the images of the multiple moving targets.
  • the vision chip is used to preprocess the performance characteristics of each of the multiple images of the moving target, so that the performance characteristics of each image remain consistent, wherein the performance The characteristics include at least one of the following: the color of the image, the brightness of the image, and the size of the image.
  • the process of preprocessing the image of the moving target by the vision chip may specifically be performed after the vision chip acquires multiple images containing the moving target from the shooting device, that is, the process of preprocessing the image of the moving target Multiple images are preprocessed.
  • the recognition accuracy of the moving target can be improved.
  • the flight controller tracks the moving target according to the moving target locked by the vision chip and the recognition result of the moving target.
  • the flight controller adjusts the motion state of the drone 20 and/or the parameters of the shooting device according to the motion state of the moving target, so that the moving target is always Located on the display screen of the control terminal 10.
  • the motion state of the moving target includes the motion direction of the moving target
  • the motion state of the drone 20 includes the motion direction of the drone 20
  • the parameters of the shooting device include a pan/tilt. Angle.
  • the flight controller determines whether the moving direction of the moving target is consistent with the moving direction of the UAV 20; if not, it adjusts the angle of the pan/tilt according to the moving direction of the moving target so that all The moving target is always located at a preset position in the display screen of the control terminal.
  • the flight controller determines whether the movement direction of the moving target is consistent with the movement direction of the drone 20, and can compare the acquired movement direction of the moving target with that of the drone 20.
  • the running direction of the UAV 20 is compared.
  • the parameters corresponding to the two moving directions are exactly the same or the error of the parameters is within the preset range, it is determined that the moving direction of the moving target is consistent with the moving direction of the UAV 20, otherwise, both The direction of movement is inconsistent.
  • the moving target when the moving direction of the moving target is left and right relative to the camera, the yaw angle of the pan/tilt is adjusted.
  • the pitch angle of the pan/tilt is adjusted. Therefore, the moving target is always located at the preset position in the display screen of the control terminal.
  • control terminal 10 includes a display module, and the image corresponding to the moving target is displayed through the display module.
  • the control terminal 10 may specifically be a smart phone, a notebook computer, a tablet computer, a smart bracelet, etc.,
  • the preset position is the center position of the display screen of the control terminal 10. In other possible embodiments, the preset position may also be a position other than the central position.
  • the flying The controller will timely adjust the motion state of the drone 20 and/the parameters of the photographing device so that the moving target is always located at the preset position in the display screen of the control terminal 10 at the preset size .
  • the preset size may be set by the flight controller according to the size of the display screen of the control terminal, or may be customized by the user according to personal preferences.
  • the preset size includes the height, width, volume, etc. of the moving target.
  • the movement state of the drone 20 includes the speed of the drone 20.
  • the flight controller determines whether the speed change rate of the moving target in the moving direction of the drone 20 is greater than the first threshold; if so, Then the speed of the drone 20 is adjusted so that the moving target is always located at the preset position in the display screen at the preset size.
  • the first threshold may be a speed change rate parameter set by the flight controller system, or a user-defined speed change rate parameter.
  • the parameters of the photographing device include the focal length of the camera.
  • the flight controller determines whether the difference between the speed of the moving target and the speed of the drone 20 is greater than the second threshold; if so, , The focal length of the camera is adjusted so that the moving target is always located at the preset position in the display screen at the preset size.
  • the second threshold may be a speed parameter set by the flight controller system, or a user-defined speed parameter.
  • the camera focal length of the drone 20 is adjusted.
  • the focal length of the camera of the drone 20 can be adjusted according to the size change of the moving target on the display screen of the control terminal 10, so that the camera focal length can be adjusted to ensure the control terminal The uniqueness of the size of the moving target on the display screen.
  • first level adjustment is performed by adjusting the angle of the pan/tilt, so that the moving target is always kept on the display screen of the control terminal.
  • second level adjustment is performed by adjusting the angle of the gimbal, if you find that the moving target is too close or too far from the drone, you can adjust the speed of the drone 20 for secondary adjustment to ensure that the moving target is displayed on the control terminal.
  • the size of the images in is basically the same. If at this time, there is still no way to ensure that the image size of the moving target in the display screen of the control terminal remains stable, three-level adjustment is performed by adjusting the camera focal length, thereby ensuring the stability and reliability of tracking to the greatest extent.
  • the vision chip is also used to determine whether the moving target is Lost; if it is lost, search for the moving target, and re-identify and lock the moving target.
  • the vision chip can determine whether the moving target is lost in the following manner: when the moving target cannot be identified from the images collected by the shooting device within a preset time, then It is considered that the moving target is lost. Or, the size of the moving target obtained from the display screen of the control terminal is less than the preset threshold. For example, the mobile terminal becomes very small in the display screen of the control terminal, or even can only be represented by one dot, then the moving target is considered lost . Or, determine whether the moving target is lost by other means.
  • the flight controller may search for the moving target according to the historical moving trajectory of the moving target, or use other methods to search for the moving target.
  • the flight controller may also send warning information to the control terminal 10 to remind the user to pay attention.
  • the process of the flight controller re-identifying and searching for the moving target may be displayed on the display screen of the control terminal 10.
  • the drone provided by the embodiment of the present invention collects image information of a moving target through a photographing device, and analyzes the image information of the moving target through a vision chip, thereby identifying and locking the moving target, and then the flight controller performs multiple identifications And the locked moving target is tracked.
  • the flight controller can adjust the motion state of the drone and/or the parameters of the shooting device so that the moving target can always be displayed in the control at a preset size.
  • the display interface of the terminal is always maintained at the preset position of the display interface.
  • the UAV can track moving targets more accurately, ensuring the stability and reliability of tracking to the greatest extent.
  • the following provides a method and device for tracking a moving target applied to the aforementioned UAV 20. Please refer to Figure 3.
  • the tracking method of the moving target includes:
  • step S10 may include:
  • S101 Collect multiple images of the moving target through the photographing device.
  • a camera on the drone can be used to take pictures of the moving target from multiple angles to obtain images of the moving target at different angles.
  • S102 Perform preprocessing on the images of the multiple moving targets.
  • the preprocessing of the images of the multiple moving targets includes:
  • the performance characteristics of each of the images of the multiple moving targets are preprocessed to keep the performance characteristics of each image consistent, wherein the performance characteristics include the color of the image, the image At least one of the brightness and the size of the image.
  • features include but are not limited to color features, texture features, shape features, and spatial features.
  • the specific process of performing feature extraction can refer to existing image recognition methods.
  • feature selection can be performed after feature extraction to find the feature that best matches the current application scenario.
  • S105 Perform feature matching on the moving target based on the feature classification model to identify and lock the moving target.
  • the tracking method of the moving target also includes:
  • the moving state of the moving target includes the moving direction of the moving target, and the parameters of the photographing device include the angle of the pan/tilt.
  • S201 Determine whether the moving direction of the moving target is consistent with the moving direction of the drone
  • step S202 If they are not consistent, perform the following step S202;
  • the yaw angle of the pan/tilt is adjusted so that the moving target is always located on the control terminal. Display the preset position in the screen.
  • the pitch angle of the pan/tilt is adjusted so that the moving target is always located on the display of the control terminal The preset position in the screen.
  • the method further includes:
  • S203 Determine whether the image size of the moving target in the display screen of the control terminal is smaller than a preset size
  • the motion state of the drone includes the speed of the drone.
  • the parameters of the shooting device also include the focal length of the camera.
  • the preset position is the central position of the display screen of the control terminal.
  • the image size of the moving target in the display screen of the control terminal is smaller than the preset size, it indicates that the tracking effect is not ideal. At this time, it is necessary to determine the speed of the moving target in the moving direction of the drone Whether the rate of change is greater than a first threshold; if so, adjust the speed of the drone so that the moving target is always located at the preset position in the display screen at the preset size.
  • the method further includes:
  • step S40 If it is lost, perform the following step S40;
  • the method first recognizes and locks the moving target to be tracked, and then adjusts the motion state of the drone and/or the parameters of the shooting device according to the motion state of the moving target.
  • the control moving target is located on the display screen of the control terminal.
  • the mobile target tracking method, device and drone provided by the present invention can adjust the motion state of the drone and/or the parameters of the shooting equipment in real time according to the motion state of the mobile target, and can ensure that the mobile target is always located in the control terminal at a preset size Therefore, this embodiment improves the stability and reliability of the moving target tracking process, and has a wider application range.
  • FIG. 7 is a schematic structural diagram of a moving target tracking device provided by an embodiment of the present invention.
  • the tracking device for moving targets is applied to an unmanned aerial vehicle.
  • the unmanned aerial vehicle includes a photographing device, the photographing device includes a pan-tilt and a camera mounted on the pan-tilt, and the device 40 includes: an identification module 41 and a preprocessing module 42 and adjustment module 43.
  • the identification module 41 is used to identify and lock the moving target.
  • the recognition module 41 uses machine vision to recognize and lock the moving target. Specifically, the recognition module 41 is configured to: collect images of the moving target from multiple angles through the shooting device to obtain images of multiple moving targets; and extract images of the moving targets based on the multiple images of the moving targets.
  • the characteristics of the moving target wherein the characteristics of the moving target include at least one of a texture feature, a shape feature, and a spatial feature; establishing a feature classification model, wherein the feature classification model is used to characterize the category of the moving target; Based on the feature classification model, feature matching is performed on the moving target to identify and lock the moving target.
  • the preprocessing module 42 is used to preprocess a plurality of images of the moving target.
  • the preprocessing module 42 is connected to the recognition module 41, and the preprocessing module 42 obtains the images of the multiple moving targets from the recognition module 41.
  • the preprocessing module 42 is specifically used for:
  • the performance characteristics include at least one of the following: The color of the image, the brightness of the image, and the size of the image.
  • the motion state of the moving target includes the moving direction of the moving target
  • the parameters of the photographing device include the angle of the pan/tilt
  • the adjustment module 43 is specifically configured to: determine the motion of the moving target Whether the direction is consistent with the moving direction of the drone; if not, adjust the angle of the pan/tilt according to the moving direction of the moving target so that the moving target is always located on the display screen of the control terminal Preset position.
  • the adjustment module 43 is specifically configured to adjust the yaw angle of the pan/tilt when the moving direction of the moving target is left and right relative to the camera, so that the moving target is always located in the control The preset position in the terminal's display screen.
  • the adjustment module 43 is specifically configured to: when the moving direction of the moving target is moving forward and backward relative to the camera, adjust the pitch angle of the pan/tilt so that the moving target is always located at the control terminal The preset position in the display screen of.
  • the adjustment module 43 is further configured to: determine whether the image size of the moving target in the display screen of the control terminal is smaller than a preset size; if so, adjust the movement state and/or the position of the drone. The parameters of the photographing device, so that the moving target is always located at the preset position in the display screen of the control terminal with the preset size.
  • the adjustment module 43 is specifically configured to: determine whether the rate of change of the speed of the moving target in the moving direction of the drone is greater than a first threshold; if so, adjust the speed of the drone so that all The moving target is always located at the preset position in the display screen with the preset size.
  • the adjustment module 43 is specifically configured to: determine whether the difference between the speed of the moving target and the speed of the drone is greater than a second threshold; if so, adjust the focal length of the camera to make the movement
  • the target is always located at the preset position in the display screen with the preset size.
  • the preset position is the central position of the display screen of the control terminal.
  • the identification module 41 is further configured to determine whether the moving target is lost; if it is lost, search for the moving target, and re-identify and lock the moving target.
  • the recognition module 41 and the preprocessing module 42 are the vision chips of the drone, and the adjustment module 43 is the flight controller of the drone.
  • the embodiment of the present invention provides a tracking device for a moving target.
  • the device first recognizes and locks the moving target to be tracked, and then adjusts the motion state of the drone and/or the parameters of the shooting equipment according to the motion state of the moving target.
  • the control moving target is located on the display screen of the control terminal.
  • the mobile target tracking method, device and drone provided by the present invention can adjust the motion state of the drone and/or the parameters of the shooting equipment in real time according to the motion state of the mobile target, and can ensure that the mobile target is always located in the control terminal at a preset size Therefore, this embodiment improves the stability and reliability of the moving target tracking process, and has a wider application range.
  • the device embodiments described above are merely illustrative.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each implementation manner can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware.
  • a person of ordinary skill in the art can understand that all or part of the processes in the method of the foregoing embodiments can be implemented by instructing relevant hardware through a computer program.
  • the program can be stored in a computer readable storage medium. When executed, it may include the processes of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Mechanical Engineering (AREA)
  • Studio Devices (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

本发明涉及无人机追踪技术领域,尤其涉及一种移动目标的追踪方法、装置及无人机。该方法包括:识别并锁定移动目标;根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中。本发明提供的移动目标追踪方法、装置及无人机能够根据移动目标的运动状态实时调整无人机的运动状态和/或拍摄设备的参数,能确保移动目标以预设尺寸大小始终位于控制终端的显示画面中,因此,该实施方式提高了移动目标追踪过程中的稳定性和可靠性,并且适用范围更广。

Description

一种移动目标的追踪方法、装置及无人机
本申请要求于2019年6月14日提交中国专利局、申请号为201910516768.7、申请名称为“一种移动目标的追踪方法、装置及无人机”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及无人机追踪技术领域,尤其涉及一种移动目标的追踪方法、装置及无人机。
背景技术
目前无人机被广泛的应用于移动目标的追踪,其通常是在移动目标的表面不同位置安装无线测距传感器,各个无线测距传感器组成一个固定在移动目标表面的局部定位网络,在无人机上安装无线测距传感器,无人机上的无线测距传感器与移动目标上的无线测距传感器进行通信和测距,无人机在局部定位网络中活动,并且通过测距值计算出无人机在局部定位系统中的位置,从而实现位置锁定并跟踪移动目标。
然而,上述这种移动目标的追踪方式需要依靠外界传感器,并且还要凭借移动目标上的通信模块用于数据的通信传输,从而造成无人机在追踪移动目标时存在稳定性差、适用范围窄的问题。
发明内容
本发明要解决的技术问题是提供一种移动目标的追踪方法、装置及无人机,解决相关技术在追踪移动目标时存在稳定性差、适用范围窄的技术问题。
本发明实施例的一个方面,提供一种移动目标的追踪方法,应用于无人机,
所述无人机包括拍摄设备,所述拍摄设备包括云台和搭载于所述云台的相机,所述方法包括:
识别并锁定移动目标;
根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
可选地,所述识别并锁定所述移动目标包括:
采用机器视觉识别并锁定所述移动目标。
可选地,所述识别并锁定所述移动目标包括:
通过所述拍摄设备采集多个所述移动目标的图像;
基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;
建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;
基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
可选地,所述方法还包括:
对所述多个所述移动目标的图像进行预处理。
可选地,所述对所述多个所述移动目标的图像进行预处理,包括:
对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:
图像的颜色、图像的明暗和图像的尺寸。
可选地,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:
所述根据所述移动目标的所述运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于所述控制终端的显示画面中,包括:
判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,当所述移动目标的运动方向与所述无人机的运动方向不一致时,所述根据所述目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置,包括:
当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,当所述移动目标的运动方向与所述无人机的运动方向不一致时,所述根据所述目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中,包括:
当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,该方法还包括:
判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;
若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
可选地,当所述移动目标在所述控制终端的显示画面中的图像尺寸小于所述预设尺寸时,所述调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置,包括:
判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;
若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
可选地,当所述移动目标在所述控制终端的画面中的图像尺寸小于所述预设尺寸时,所述调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置,包括:
判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;
若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
可选地,所述预设位置为所述控制终端的显示画面的中央位置。
可选地,该方法还包括:
判断所述移动目标是否丢失;
若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
本发明实施例的另一个方面,提供一种移动目标的追踪装置,应用于无人机,所述无人机包括拍摄设备,所述拍摄设备包括云台和搭载于所述云台的相机,所述装置包括:
识别模块,用于识别并锁定移动目标;
调整模块,用于根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
可选地,所述识别模块采用机器视觉识别并锁定所述移动目标。
可选地,所述识别模块具体用于:
通过所述拍摄设备多角度采集所述移动目标的图像,以获得多个所述移动目标的图像;
基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;
建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;
基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
可选地,所述装置还包括预处理模块,所述预处理模块用于对多个所述移动目标的图像进行预处理。
可选地,所述预处理模块具体用于:
对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:
图像的颜色、图像的明暗和图像的尺寸。
可选地,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:
所述调整模块具体用于:
判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,所述调整模块具体用于:
当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,所述调整模块具体用于:
当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,所述调整模块还用于:
判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;
若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
可选地,所述调整模块具体用于:
判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;
若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
可选地,所述调整模块具体用于:
判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;
若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
可选地,所述预设位置为所述控制终端的显示画面的中央位置。
可选地,所述识别模块还用于:
判断所述移动目标是否丢失;
若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
本发明实施例的又一个方面,提供一种无人机,包括:
机身;
机臂,与所述机身相连;
动力装置,设于所述机臂,用于给所述无人机提供飞行的动力;
拍摄设备,设于所述机身,所述拍摄设备包括云台和搭载于所述云台的相机;
视觉芯片,所述视觉芯片设于所述机身,所述视觉芯片用于识别并锁定移动目标;以及
飞行控制器,所述飞行控制器设于所述机身,并与所述视觉芯片通信连接,所述飞行控制器用于:
根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
可选地,所述视觉芯片通过机器视觉识别并锁定所述移动目标。
可选地,所述视觉芯片具体用于:
通过所述拍摄设备采集多个所述移动目标的图像;
基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;
建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;
基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
可选地,所述视觉芯片还用于:
对所述多个所述移动目标的图像进行预处理。
可选地,所述视觉芯片还用于:
对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:
图像的颜色、图像的明暗和图像的尺寸。
可选地,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:
所述飞行控制器用于:
判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,所述飞行控制器具体用于:
当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,所述飞行控制器具体用于:
当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
可选地,所述飞行控制器还用于:
判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;
若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
可选地,所述飞行控制器还用于:
判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;
若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
可选地,所述飞行控制器还用于:
判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;
若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
可选地,所述预设位置为所述控制终端的显示画面的中央位置。
可选地,所述视觉芯片还用于:
判断所述移动目标是否丢失;
若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
在本发明实施例中,首先对待追踪的移动目标进行识别和锁定,然后根据移动目标的运动状态调整无人机的运动状态和/或拍摄设备的参数,从而在追踪移动目标的过程中控制移动目标位于控制终端的显示画面中。本发明提供的移动目标追踪方法、装置及无人机能够根据移动目标的运动状态实时调整无人机的运动状态和/或拍摄设备的参数,能确保移动目标以预设尺寸大小始终位于控制终端的显示画面中,因此,该实施方式提高了移动目标追踪过程中的稳定性和可靠性,并且适用范围更广。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明,这些示例性说明并不构成对实施例的限定,附图中具有相同参考数字标号的元件表示为类似的元件,除非有特别申明,附图中的图不构成比例限制。
图1是本发明实施例提供的一种移动目标的追踪方法运行环境示意图;
图2是本发明实施例提供的一种无人机的结构示意图;
图3是本发明实施例提供的一种移动目标的追踪方法的流程图;
图4是本发明实施例提供的移动目标的追踪方法中步骤S10其中一实施例的的流程图;
图5是本发明实施例提供的移动目标的追踪方法中步骤S20其中一实施例的流程图;
图6是本发明提供的一种移动目标的追踪方法另一实施例的流程图;
图7是本发明实施例提供的一种移动目标的追踪装置的结构框图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。
请参阅图1,图1是本发明实施例提供的移动目标的追踪方法和装置的运行环境示意图。该运行环境包括控制终端10、无人机20以及地面站30。控制终端10通过地面站30与无人机20通讯。用户可以通过控制终端10操控无人机20来实现所述移动目标的追踪方法。在本实施例中,所述移动目标的追踪方法和装置应用于无人机20。其中,用户可以通过操作控制终端10由地面站30向无人机20发送移 动目标的信息或者发送追踪指令,无人机20根据所述移动目标的信息或者所述追踪指令执行所述移动目标的追踪方法。例如,无人机20接收到控制终端10发送的移动目标的追踪指令后,所述无人机20用于识别并锁定所述移动目标,根据所述移动目标的运动状态,调整所述无人机20的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于所述控制终端10的显示画面中。
下面结合具体的实施例来说明所述无人机20所执行的移动目标的追踪方法。
请参阅图2,无人机20包括:机身201、四个自机身201延伸的机臂202、分别装设在每个机臂202上的动力装置203、设于机身201的拍摄设备(图未示)、设于机身201的视觉芯片(图未示)以及设于机身201的飞行控制器(图未示)。其中,所述拍摄设备分别连接所述视觉芯片和所述飞行控制器,所述视觉芯片连接所述飞行控制器。
其中,机身201与机臂202固定连接,优选地,机身201与机臂202一体成型。在其他可能的实施例中,机臂202还可以相对于机身201展开或者折叠的方式与机身201相连。例如,机臂202可以通过一转轴机构与机身201相连,以实现机臂202可相对于机身201展开或折叠。
其中,所述动力装置203用于给所述无人机20提供飞行的动力,图2示出的无人机20为四旋翼无人飞行器,动力装置203的数量为四个,在其他可能的实施例中,无人机20可以是其他任何合适类型的无人飞行器,例如固定翼无人机飞行器等。在动力装置203应用于其他类型无人飞行器的场合,动力装置203的数量可以根据实际需要改变,本发明对此不作限定。
在其他可能的实施例中,动力装置203包括驱动装置2031和由驱动装置2031驱动的螺旋桨组件2032,螺旋桨组件2032装设于驱动装置2031的输出轴上,螺旋桨组件2032在驱动装置2031的驱动下旋转以产生使无人机20飞行的升力或推力。驱动装置2031可以是任何合适类型的电机,例如有刷电机、无刷电机、直流电机、步进电机、交流感应电机等。
其中,所述拍摄设备包括:云台(图未示)和搭载于所述云台的相机(图未示)。该云台安装于机身201的底部,云台用于搭载高清数码相机或者其他摄像装置以消除高清数码相机或其他摄像装置受到的扰动,保证相机或其他摄像装置拍摄的视频的清晰稳定。
所述拍摄设备用于拍摄待追踪的移动目标。所述移动目标包括但不限于人、动物、飞行器等其他可以移动的物体。拍摄设备所拍摄的移动目标可以是包含所述移动目标的视频或者图片,所述视频或者图片的数量不作限制。
其中,所述视觉芯片连接所述拍摄设备和飞行控制器。所述视觉芯片用于识别并锁定移动目标。所述视觉芯片可以通过机器视觉的方式识别并锁定所述移动目标。机器视觉方式识别移动目标属于主动识别,不依靠外界其他传感器,因此稳定性高,适用范围广且不受移动目标类型的影响,能够提高目标识别的准确度和可靠性。在本发明的一实施例中,所述视觉芯片从所述拍摄设备获取包含所述移动目标的多个图像,其中,所述多个图像可以是所述拍摄设备从不同拍摄角度拍摄的包含 所述移动目标的图像。其次,基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种,所述纹理特征是所述移动目标表面的一种特征,其刻画了移动目标的图像中重复出现的局部模式与他们的排列规则;所述形状特征指的是所述移动目标在图像中所反应出的形状,比如圆形、星形等。然后,建立特征分类模型,其中,所述特征分类模型用于表征所述移动目标的类别。在本发明的一实施例中,可以采用机器学习中的分类算法来建立所述特征分类模型,该分类算法包括支持向量机、神经网络、贝叶斯分类算法等。建立所述特征分类模型的主要过程包括,采集大量的样本数据,提取样本数据的特征,将提取的特征输入分类训练器中进行训练,以确定分类器,该分类器即所述特征分类模型。其中,所述样本数据是与要识别的移动目标相关的模型库。最后,基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。在本实施例中,可以向建立的特征分类模型中输入所述移动目标的图像以及所述移动目标对应的模型库,对所述移动目标进行特征匹配,从而识别并且锁定所述移动目标。特征匹配后可以输出所述移动目标的信息,其中,所述移动目标的信息包括所述移动目标的名称、姿态、位置、形状、类别、颜色等等。
在其他可能的实施例中,所述视觉芯片还用于对所述多个所述移动目标的图像进行预处理。具体的,所述视觉芯片用于对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:图像的颜色、图像的明暗和图像的尺寸。所述视觉芯片对移动目标的图像进行预处理的过程具体可以在所述视觉芯片从所述拍摄设备获取到包含所述移动目标的多个图像之后来进行,即是对包含所述移动目标的多个图像进行预处理。在这里,通过对移动目标的图像进行预处理,从而能提高所述移动目标的识别准确率。
上述在所述视觉芯片识别并锁定移动目标后,所述飞行控制器根据所述视觉芯片锁定的移动目标以及所述移动目标的识别结果对所述移动目标进行追踪。在本发明的一实施例中,所述飞行控制器根据所述移动目标的运动状态,调整所述无人机20的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端10的显示画面中。
在本发明的一实施例中,所述移动目标的运动状态包括移动目标的运动方向,所述无人机20的运动状态包括无人机20的运动方向,所述拍摄设备的参数包括云台的角度。所述飞行控制器判断所述移动目标的运动方向与所述无人机20的运动方向是否一致;若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
在本发明的一实施例中,所述飞行控制器判断所述移动目标的运动方向与所述无人机20的运动方向是否一致可以将获取到的所述移动目标的运动方向与无人机20的运行方向进行比较,当这两个运动方向对应的参数完全相同或者参数的误差在预设范围内时,则确定移动目标的运动方向与无人机20的运动方向一致,否则, 两者的运动方向不一致。
在本发明的一实施例中,当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角。当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角。由此,使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
在本发明的实施例中,所述控制终端10包括显示模块,通过所述显示模块显示所述移动目标对应的图像。所述控制终端10具体可以是智能手机、笔记本电脑、平板电脑、智能手环等,
在本发明的一实施例中,所述预设位置为所述控制终端10的显示画面的中央位置。在其他可能的实施例中,所述预设位置也可以是除了所述中央位置之外的其他位置。
在其他可能的实施例中,当移动目标在控制终端10的显示画面中的图像尺寸较小,例如,小于预设尺寸时,为了保证跟踪效果,更稳定的追踪所述移动目标,所述飞行控制器会及时调整所述无人机20的运动状态和/所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端10的显示画面中的预设位置。
其中,所述预设尺寸可以由所述飞行控制器根据控制终端显示画面的大小进行设置,也可以由用户根据个人喜好进行自定义。所述预设尺寸包括移动目标的高度、宽度、体积等。
在本发明的一实施例中,无人机20的运动状态包括无人机20的速度。当移动目标在控制终端10的显示画面中的图像尺寸小于预设尺寸时,飞行控制器判断所述移动目标在所述无人机20运动方向上的速度变化率是否大于第一阈值;若是,则调整所述无人机20的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。所述第一阈值可以是飞行控制器系统设置的速度变化率参数,也可以是用户自定义的速度变化率参数。在这里,通过调节无人机的速度,从而能够保证移动目标能始终维持为原始画面大小,保证了追踪的稳定性和可靠性。
在本发明的一实施例中,所述拍摄设备的参数包括所述相机的焦距。当移动目标在控制终端10的显示画面中的图像尺寸小于预设尺寸时,飞行控制器判断判断所述移动目标的速度与所述无人机20的速度的差值是否大于第二阈值;若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。所述第二阈值可以是飞行控制器系统设置的速度参数,也可以是用户自定义的速度参数。在这里,对无人机20的相机焦距进行调整,根据相机成像原理可以知道,1/U+1/V=1/F,其中,U表示物镜,V表示像距,F表示焦距。当移动目标距离镜头的距离变大,并且在焦距不变的情况下,控制终端10显示画面上所看到的移动目标的大小将变小;当移动目标距离镜头的距离变大,并且在焦距变小的情况下,控制终端10显示画面上所看到的移动目标的大小将变得更小;当移动目标距离镜头的距离变大,并且在焦距变大的情况下,控制终端10显示画面上所看到的移动目标的大小将变大。因此,在移动目标与镜头的距离发生改变时,可 以根据控制终端10显示画面上移动目标的大小变化情况来调节无人机20的相机的焦距,从而可以实现通过调节相机焦距大小来保障控制终端显示画面上移动目标的大小的唯一性。
上述分别通过调节云台角度、无人机20的速度以及相机焦距来确保追踪的移动目标始终能维持在预设的追踪范围内,并且保证了移动目标在控制终端显示画面中的图像大小的唯一性,值得说明的是,这三种调节方式可以是独立的,也可以是层层递进的。比如,首先通过调节云台角度来进行一级调节,使得移动目标始终保持在控制终端的显示画面中。在调整云台角度的过程中,如果发现移动目标距离无人机的距离过近或过远,则可以通过调节无人机20的速度来进行二级调节,以保证移动目标在控制终端显示画面中的图像大小基本保持一致。如果此时,仍然没有办法保证移动目标在控制终端的显示画面中的图像大小保持稳定,则通过调节相机焦距来进行三级调节,从而最大程度上保证了追踪的稳定性和可靠性。
可以理解的是,通过上述方式对移动目标进行追踪的过程中还是可能存在移动目标被追踪丢失的情况,因此,在其他可能的实施例中,所述视觉芯片还用于判断所述移动目标是否丢失;若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。在本发明的一实施例中,视觉芯片判断所述移动目标是否丢失可以通过以下方式进行判断:当预设时间内从所述拍摄设备采集的图像中都不能识别到所述移动目标时,则认为所述移动目标丢失。或者,从控制终端显示画面中获取的移动目标的尺寸小于预设阈值,比如移动终端在控制终端的显示画面中变得很小,甚至只能用一个点来表示,则认为所述移动目标丢失。或者,通过其他方式判断所述移动目标是否丢失。
其中,在移动目标丢失后,所述飞行控制器可以根据所述移动目标的历史移动轨迹来搜索所述移动目标,或者采用其他方法搜索所述移动目标。
在移动目标丢失后,所述飞行控制器还可以向控制终端10发送告警信息,以提示用户注意。并且,所述飞行控制器重新识别和搜索所述移动目标的过程可以显示于控制终端10的显示画面。
本发明实施例提供的无人机通过拍摄设备采集移动目标的图像信息,通过视觉芯片对移动目标的图像信息进行分析,从而识别并且锁定所述移动目标,然后再由飞行控制器多所述识别并且锁定的所述移动目标进行追踪,飞行控制器在追踪移动目标的过程中,可以通过调节无人机的运动状态和/或拍摄设备的参数,使移动目标能始终以预设尺寸显示于控制终端的显示界面,并且始终保持在显示界面的预设位置。所述无人机能够更精准的对移动目标进行追踪,最大程度的保证了追踪的稳定性和可靠性。
下面提供一种应用于上述无人机20的移动目标的追踪方法和装置。请参阅图3,该移动目标的追踪方法包括:
S10、识别并锁定移动目标;
所述识别并锁定所述移动目标包括:采用机器视觉识别并锁定所述移动目标。具体地,请参阅图4,在本发明的一实施例中,步骤S10可以包括:
S101、通过所述拍摄设备采集多个所述移动目标的图像。其中,可以通过无人机上的相机对移动目标进行多角度拍照,以获取不同角度位置的所述移动目标的图像。
S102、对所述多个所述移动目标的图像进行预处理。
其中,所述对所述多个所述移动目标的图像进行预处理,包括:
对所述多个所述移动目标的图像中的每一张图像的表现特征进行预处理,以使得所述每一张图像的表现特征保持一致,其中,所述表现特征包括图像的颜色、图像的明暗和图像的尺寸中的至少一种。
S103、基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种。
为了能有效的实现分类识别,需要对采集的原始图像数据进行变换,得到最能够反映分类本质的特征,这些特征包括但不限于颜色特征、纹理特征、形状特征、空间特征等。其中,进行特征提取的具体过程可以参考现有的图像识别方法。此外,当提取的特征种类很多或者待识别的移动目标的类别很多时,还可以在进行特征提取后进行特征选择,找到最匹配当前应用场景的特征。
S104、建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别。
S105、基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
关于移动目标的识别和锁定的具体内容可参见本发明提供的无人机实施例。
该移动目标的追踪方法还包括:
S20、根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
在本发明的一实施例中,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则,请参阅图5,上述步骤S20包括:
S201、判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
若不一致,则执行下述步骤S202;
S202、根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
在本发明的一实施例中,当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
在本发明的一实施例中,当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
在其他可能的实施例中,同样请参阅图5,所述方法还包括:
S203、判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预 设尺寸;
若是,则执行下述步骤S204;
S204、调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
在本发明的一实施例中,所述无人机的运动状态包括无人机的速度。所述拍摄设备的参数还包括相机的焦距。所述预设位置为所述控制终端的显示画面的中央位置。
当所述移动目标在所述控制终端的显示画面中的图像尺寸小于所述预设尺寸时,说明跟踪效果不理想,此时需要判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
在本发明的一实施例中,还可以判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
在其他可能的实施例中,请参阅图6,所述方法还包括:
S30、判断所述移动目标是否丢失;
若丢失,则执行下述步骤S40;
S40、搜索所述移动目标,并重新识别并锁定所述移动目标。
关于本发明的移动目标追踪方法的详细内容可以参见本发明提供的无人机实施例,在此不再详述。
本发明实施例提供的移动目标的追踪方法,该方法首先对待追踪的移动目标进行识别和锁定,然后根据移动目标的运动状态调整无人机的运动状态和/或拍摄设备的参数,从而在追踪移动目标的过程中控制移动目标位于控制终端的显示画面中。本发明提供的移动目标追踪方法、装置及无人机能够根据移动目标的运动状态实时调整无人机的运动状态和/或拍摄设备的参数,能确保移动目标以预设尺寸大小始终位于控制终端的显示画面中,因此,该实施方式提高了移动目标追踪过程中的稳定性和可靠性,并且适用范围更广。
请参阅图7,图7是本发明实施例提供的一种移动目标的追踪装置的结构示意图。该移动目标的追踪装置应用于无人机,所述无人机包括拍摄设备,所述拍摄设备包括云台和搭载于所述云台的相机,该装置40包括:识别模块41、预处理模块42以及调整模块43。
其中,所述识别模块41用于识别并锁定移动目标。所述识别模块41采用机器视觉识别并锁定所述移动目标。具体的,所述识别模块41用于:通过所述拍摄设备多角度采集所述移动目标的图像,以获得多个所述移动目标的图像;基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
其中,所述预处理模块42用于对多个所述移动目标的图像进行预处理。所述预处理模块42连接所述识别模块41,所述预处理模块42从所述识别模块41获取所述多个所述移动目标的图像。所述预处理模块42具体用于:
对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:图像的颜色、图像的明暗和图像的尺寸。
其中,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:所述调整模块43具体用于:判断所述移动目标的运动方向与所述无人机的运动方向是否一致;若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
其中,所述调整模块43具体用于:当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
其中,所述调整模块43具体用于:当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
其中,所述调整模块43还用于:判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
其中,所述调整模块43具体用于:判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
其中,所述调整模块43具体用于:判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
其中,所述预设位置为所述控制终端的显示画面的中央位置。
在其他可能的实施例中,所述识别模块41还用于:判断所述移动目标是否丢失;若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
值得说明的是,上述装置内的模块、单元之间的信息交互、执行过程等内容,由于与本发明的方法实施例基于同一构思,具体内容可以参考本发明方法实施例中的叙述,此处不再赘述。
在本发明的一实施例中,识别模块41和预处理模块42为无人机的视觉芯片,调整模块43为无人机的飞行控制器。
本发明实施例提供了一种移动目标的追踪装置,该装置首先对待追踪的移动目标进行识别和锁定,然后根据移动目标的运动状态调整无人机的运动状态和/或拍摄设备的参数,从而在追踪移动目标的过程中控制移动目标位于控制终端的显示画 面中。本发明提供的移动目标追踪方法、装置及无人机能够根据移动目标的运动状态实时调整无人机的运动状态和/或拍摄设备的参数,能确保移动目标以预设尺寸大小始终位于控制终端的显示画面中,因此,该实施方式提高了移动目标追踪过程中的稳定性和可靠性,并且适用范围更广。
以上所描述的装置实施例仅仅是示意性的,其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述,本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现,当然也可以通过硬件来实现。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成,所述的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
最后应说明的是:以上实施例仅用以说明本发明的技术方案,而非对其限制;在本发明的思路下,以上实施例或者不同实施例中的技术特征之间也可以进行组合,步骤可以以任意顺序实现,并存在如上所述的本发明的不同方面的许多其它变化,为了简明,它们没有在细节中提供;尽管参照前述实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (39)

  1. 一种移动目标的追踪方法,应用于无人机,所述无人机包括拍摄设备,所述拍摄设备包括云台和搭载于所述云台的相机,其特征在于,所述方法包括:
    识别并锁定移动目标;
    根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
  2. 根据权利要求1所述的方法,其特征在于,所述识别并锁定所述移动目标包括:
    采用机器视觉识别并锁定所述移动目标。
  3. 根据权利要求1或2所述的方法,其特征在于,所述识别并锁定所述移动目标,包括:
    通过所述拍摄设备采集多个所述移动目标的图像;
    基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;
    建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;
    基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
  4. 根据权利要求3所述的方法,其特征在于,该方法还包括:
    对所述多个所述移动目标的图像进行预处理。
  5. 根据权利要求4所述的方法,其特征在于,所述对所述多个所述移动目标的图像进行预处理,包括:
    对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:
    图像的颜色、图像的明暗和图像的尺寸。
  6. 根据权利要求1-5中任一项所述的方法,其特征在于,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:
    所述根据所述移动目标的所述运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于所述控制终端的显示画面中,包括:
    判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
    若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  7. 根据权利要求6所述的方法,其特征在于,当所述移动目标的运动方向与所述无人机的运动方向不一致时,所述根据所述目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置,包括:
    当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  8. 根据权利要求6所述的方法,其特征在于,当所述移动目标的运动方向与所述无人机的运动方向不一致时,所述根据所述目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中,包括:
    当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  9. 根据权利要求6-8中任一项所述的方法,其特征在于,该方法还包括:
    判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;
    若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
  10. 根据权利要求9所述的方法,其特征在于,当所述移动目标在所述控制终端的显示画面中的图像尺寸小于所述预设尺寸时,所述调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置,包括:
    判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;
    若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
  11. 根据权利要求9或10所述的方法,其特征在于,当所述移动目标在所述控制终端的画面中的图像尺寸小于所述预设尺寸时,所述调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置,包括:
    判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;
    若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
  12. 根据权利要求6-11中任一项所述的方法,其特征在于,所述预设位置为所述控制终端的显示画面的中央位置。
  13. 根据权利要求1-12中任一项所述的方法,其特征在于,该方法还包括:
    判断所述移动目标是否丢失;
    若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
  14. 一种移动目标的追踪装置,应用于无人机,所述无人机包括拍摄设备,所述拍摄设备包括云台和搭载于所述云台的相机,其特征在于,所述装置包括:
    识别模块,用于识别并锁定移动目标;
    调整模块,用于根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
  15. 根据权利要求14所述的装置,其特征在于,所述识别模块采用机器视觉识别并锁定所述移动目标。
  16. 根据权利要求14或15所述的装置,其特征在于,所述识别模块具体用于:
    通过所述拍摄设备多角度采集所述移动目标的图像,以获得多个所述移动目标的图像;
    基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;
    建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;
    基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
  17. 根据权利要求16所述的装置,其特征在于,所述装置还包括预处理模块,所述预处理模块用于对多个所述移动目标的图像进行预处理。
  18. 根据权利要求17所述的装置,其特征在于,所述预处理模块具体用于:
    对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:
    图像的颜色、图像的明暗和图像的尺寸。
  19. 根据权利要求14-18中任一项所述的装置,其特征在于,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:
    所述调整模块具体用于:
    判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
    若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  20. 根据权利要求19所述的装置,其特征在于,所述调整模块具体用于:
    当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  21. 根据权利要求19所述的装置,其特征在于,所述调整模块具体用于:
    当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  22. 根据权利要求19-21中任一项所述的装置,其特征在于,所述调整模块还用于:
    判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;
    若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
  23. 根据权利要求22所述的装置,其特征在于,所述调整模块具体用于:
    判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;
    若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
  24. 根据权利要求22或23所述的装置,其特征在于,所述调整模块具体用于:
    判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;
    若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
  25. 根据权利要求19-24中任一项所述的装置,其特征在于,所述预设位置为所述控制终端的显示画面的中央位置。
  26. 根据权利要求14-25中任一项所述的装置,其特征在于,所述识别模块还用于:
    判断所述移动目标是否丢失;
    若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
  27. 一种无人机,其特征在于,包括:
    机身;
    机臂,与所述机身相连;
    动力装置,设于所述机臂,用于给所述无人机提供飞行的动力;
    拍摄设备,设于所述机身,所述拍摄设备包括云台和搭载于所述云台的相机;
    视觉芯片,所述视觉芯片设于所述机身,所述视觉芯片用于识别并锁定移动目标;以及
    飞行控制器,所述飞行控制器设于所述机身,并与所述视觉芯片通信连接,所述飞行控制器用于:
    根据所述移动目标的运动状态,调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标始终位于控制终端的显示画面中,其中,所述控制终端与所述无人机通信连接。
  28. 根据权利要求27所述的无人机,其特征在于,所述视觉芯片通过机器视觉识别并锁定所述移动目标。
  29. 根据权利要求27或28所述的无人机,其特征在于,所述视觉芯片具体用于:
    通过所述拍摄设备采集多个所述移动目标的图像;
    基于所述多个所述移动目标的图像,提取所述移动目标的特征,其中,所述移动目标的特征包括纹理特征、形状特征和空间特征中的至少一种;
    建立特征分类模型,其中,所述特征分类模型用于表征移动目标的类别;
    基于所述特征分类模型,对所述移动目标进行特征匹配,以识别并锁定所述移动目标。
  30. 根据权利要求29所述的无人机,其特征在于,所述视觉芯片还用于:
    对所述多个所述移动目标的图像进行预处理。
  31. 根据权利要求30所述的无人机,其特征在于,所述视觉芯片还用于:
    对所述多个所述移动目标的图像中的每一个图像的表现特征进行预处理,以使得所述每一个图像的表现特征保持一致,其中,所述表现特征包括以下中的至少一种:
    图像的颜色、图像的明暗和图像的尺寸。
  32. 根据权利要求27-31中任一项所述的无人机,其特征在于,所述移动目标的运动状态包括所述移动目标的运动方向,所述拍摄设备的参数包括所述云台的角度,则:
    所述飞行控制器用于:
    判断所述移动目标的运动方向与所述无人机的运动方向是否一致;
    若不一致,则根据所述移动目标的运动方向,调整所述云台的角度,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  33. 根据权利要求32所述的无人机,其特征在于,所述飞行控制器具体用于:
    当所述移动目标的运动方向为相对于所述相机左右运动时,调整所述云台的偏航角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  34. 根据权利要求32所述的无人机,其特征在于,所述飞行控制器具体用于:
    当所述移动目标的运动方向为相对于所述相机前后运动时,调整所述云台的俯仰角,以使得所述移动目标始终位于所述控制终端的显示画面中的预设位置。
  35. 根据权利要求32-34中任一项所述的无人机,其特征在于,所述飞行控制器还用于:
    判断所述移动目标在所述控制终端的显示画面中的图像尺寸是否小于预设尺寸;
    若是,则调整所述无人机的运动状态和/或所述拍摄设备的参数,以使得所述移动目标以所述预设尺寸始终位于所述控制终端的显示画面中的预设位置。
  36. 根据权利要求35所述的无人机,其特征在于,所述飞行控制器还用于:
    判断所述移动目标在所述无人机运动方向上的速度变化率是否大于第一阈值;
    若是,则调整所述无人机的速度,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
  37. 根据权利要求35或36所述的无人机,其特征在于,所述飞行控制器还用于:
    判断所述移动目标的速度与所述无人机的速度的差值是否大于第二阈值;
    若是,则调整所述相机的焦距,以使得所述移动目标以所述预设尺寸始终位于所述显示画面中的预设位置。
  38. 根据权利要求32-37中任一项所述的无人机,其特征在于,所述预设位置为所述控制终端的显示画面的中央位置。
  39. 根据权利要求27-38中任一项所述的无人机,其特征在于,所述视觉芯片还用于:
    判断所述移动目标是否丢失;
    若丢失,则搜索所述移动目标,并重新识别并锁定所述移动目标。
PCT/CN2020/095841 2019-06-14 2020-06-12 一种移动目标的追踪方法、装置及无人机 WO2020249088A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/643,696 US20220137648A1 (en) 2019-06-14 2021-12-10 Method and apparatus for tracking moving target and unmanned aerial vehicle

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910516768.7 2019-06-14
CN201910516768.7A CN110147122A (zh) 2019-06-14 2019-06-14 一种移动目标的追踪方法、装置及无人机

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/643,696 Continuation US20220137648A1 (en) 2019-06-14 2021-12-10 Method and apparatus for tracking moving target and unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
WO2020249088A1 true WO2020249088A1 (zh) 2020-12-17

Family

ID=67591391

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/095841 WO2020249088A1 (zh) 2019-06-14 2020-06-12 一种移动目标的追踪方法、装置及无人机

Country Status (3)

Country Link
US (1) US20220137648A1 (zh)
CN (1) CN110147122A (zh)
WO (1) WO2020249088A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110147122A (zh) * 2019-06-14 2019-08-20 深圳市道通智能航空技术有限公司 一种移动目标的追踪方法、装置及无人机
JP7247904B2 (ja) * 2020-01-15 2023-03-29 トヨタ自動車株式会社 ドローンシステム及びドローンによる車両撮影方法
CN112640422A (zh) * 2020-04-24 2021-04-09 深圳市大疆创新科技有限公司 拍摄方法、可移动平台、控制设备和存储介质
CN112233141B (zh) * 2020-09-28 2022-10-14 国网浙江省电力有限公司杭州供电公司 电力场景下基于无人机视觉的运动目标追踪方法及系统
CN114489093B (zh) * 2020-10-27 2022-11-29 北京远度互联科技有限公司 姿态调整方法、装置、存储介质、图像采集设备及无人机
CN113867417B (zh) * 2021-12-06 2022-03-29 北京航空航天大学 一种无人机移动目标久航追踪方法
CN114821375B (zh) * 2022-06-27 2022-09-06 江西省地矿测绘有限公司 基于多源遥感数据的成图方法、装置、存储介质及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103149939A (zh) * 2013-02-26 2013-06-12 北京航空航天大学 一种基于视觉的无人机动态目标跟踪与定位方法
CN107209854A (zh) * 2015-09-15 2017-09-26 深圳市大疆创新科技有限公司 用于支持顺畅的目标跟随的系统和方法
US9930298B2 (en) * 2011-04-19 2018-03-27 JoeBen Bevirt Tracking of dynamic object of interest and active stabilization of an autonomous airborne platform mounted camera
US20180158197A1 (en) * 2016-12-01 2018-06-07 Skydio, Inc. Object tracking by an unmanned aerial vehicle using visual sensors
CN110147122A (zh) * 2019-06-14 2019-08-20 深圳市道通智能航空技术有限公司 一种移动目标的追踪方法、装置及无人机

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180365839A1 (en) * 2016-09-27 2018-12-20 SZ DJI Technology Co., Ltd. Systems and methods for initialization of target object in a tracking system
CN108537726B (zh) * 2017-03-03 2022-01-04 杭州海康威视数字技术股份有限公司 一种跟踪拍摄的方法、设备和无人机
CN113163118A (zh) * 2017-05-24 2021-07-23 深圳市大疆创新科技有限公司 拍摄控制方法及装置
EP3613208A4 (en) * 2017-06-02 2020-06-24 SZ DJI Technology Co., Ltd. SYSTEMS AND METHODS FOR TRACKING MULTIPLE OBJECTIVES AND AUTOFOCUSING BASED ON DEEP MACHINE LEARNING AND LASER RADAR
US10379545B2 (en) * 2017-07-03 2019-08-13 Skydio, Inc. Detecting optical discrepancies in captured images
CN109814588A (zh) * 2017-11-20 2019-05-28 深圳富泰宏精密工业有限公司 飞行器以及应用于飞行器的目标物追踪系统和方法
CN109828596A (zh) * 2019-02-28 2019-05-31 深圳市道通智能航空技术有限公司 一种目标跟踪方法、装置和无人机

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9930298B2 (en) * 2011-04-19 2018-03-27 JoeBen Bevirt Tracking of dynamic object of interest and active stabilization of an autonomous airborne platform mounted camera
CN103149939A (zh) * 2013-02-26 2013-06-12 北京航空航天大学 一种基于视觉的无人机动态目标跟踪与定位方法
CN107209854A (zh) * 2015-09-15 2017-09-26 深圳市大疆创新科技有限公司 用于支持顺畅的目标跟随的系统和方法
US20180158197A1 (en) * 2016-12-01 2018-06-07 Skydio, Inc. Object tracking by an unmanned aerial vehicle using visual sensors
CN110147122A (zh) * 2019-06-14 2019-08-20 深圳市道通智能航空技术有限公司 一种移动目标的追踪方法、装置及无人机

Also Published As

Publication number Publication date
US20220137648A1 (en) 2022-05-05
CN110147122A (zh) 2019-08-20

Similar Documents

Publication Publication Date Title
WO2020249088A1 (zh) 一种移动目标的追踪方法、装置及无人机
US11645765B2 (en) Real-time visual object tracking for unmanned aerial vehicles (UAVs)
US11748898B2 (en) Methods and system for infrared tracking
US20230360230A1 (en) Methods and system for multi-traget tracking
US11527105B2 (en) System and method for scalable cloud-robotics based face recognition and face analysis
KR101645722B1 (ko) 자동추적 기능을 갖는 무인항공기 및 그 제어방법
CN113038016B (zh) 无人机图像采集方法及无人机
Ashraf et al. Dogfight: Detecting drones from drones videos
US11443454B2 (en) Method for estimating the pose of a camera in the frame of reference of a three-dimensional scene, device, augmented reality system and computer program therefor
KR101769601B1 (ko) 자동추적 기능을 갖는 무인항공기
CN106973221B (zh) 基于美学评价的无人机摄像方法和系统
CN105979147A (zh) 一种无人机智能拍摄方法
CN110799921A (zh) 拍摄方法、装置和无人机
WO2017045326A1 (zh) 一种无人飞行器的摄像处理方法
MX2012010602A (es) Aparato para el reconocimiento de la cara y metodo para el reconocimiento de la cara.
US20210103299A1 (en) Obstacle avoidance method and device and movable platform
WO2019104641A1 (zh) 无人机、其控制方法以及记录介质
JP6696095B1 (ja) 画像処理装置、撮像装置、画像処理方法、及びプログラム
US20210009270A1 (en) Methods and system for composing and capturing images
CN110443247A (zh) 一种无人机地面运动小目标实时检测系统及方法
CN111046734A (zh) 基于膨胀卷积的多模态融合视线估计方法
US20190378290A1 (en) Information processing apparatus and non-transitory computer readable medium storing information processing program
KR102160128B1 (ko) 인공지능 기반 스마트 앨범 생성 방법 및 장치
Pu et al. Aerial face recognition and absolute distance estimation using drone and deep learning
WO2023197841A1 (zh) 一种对焦方法、摄像装置、无人机和存储介质

Legal Events

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

Ref document number: 20822927

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: 20822927

Country of ref document: EP

Kind code of ref document: A1