WO2020220158A1 - 一种无人机的控制方法、无人机及计算机可读存储介质 - Google Patents

一种无人机的控制方法、无人机及计算机可读存储介质 Download PDF

Info

Publication number
WO2020220158A1
WO2020220158A1 PCT/CN2019/084759 CN2019084759W WO2020220158A1 WO 2020220158 A1 WO2020220158 A1 WO 2020220158A1 CN 2019084759 W CN2019084759 W CN 2019084759W WO 2020220158 A1 WO2020220158 A1 WO 2020220158A1
Authority
WO
WIPO (PCT)
Prior art keywords
line
information
reference marking
marking line
reference identification
Prior art date
Application number
PCT/CN2019/084759
Other languages
English (en)
French (fr)
Inventor
关雁铭
钱杰
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2019/084759 priority Critical patent/WO2020220158A1/zh
Priority to CN201980005063.7A priority patent/CN111247792B/zh
Publication of WO2020220158A1 publication Critical patent/WO2020220158A1/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
    • H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
    • G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle

Definitions

  • the present invention relates to the field of control technology, in particular to a control method of an unmanned aerial vehicle, an unmanned aerial vehicle and a computer-readable storage medium.
  • Line patrol control has a wide range of applications in the robotics industry.
  • Line patrol control usually requires an identification line set in space as a reference.
  • a set of detection equipment is needed to detect the identification line and the current position of the robot to calculate the control output according to the relationship between the robot and the identification line, so as to achieve The purpose of making the robot move along a given marking line.
  • the line inspection system needs to be supplemented by a set of road marking system.
  • the road sign system is used to mark information about intersections and lines through road signs, and road signs can usually be set in the form of Near Field Communication (NFC) induction loops, QR codes, and special patterns.
  • NFC Near Field Communication
  • QR codes QR codes
  • special patterns special patterns.
  • the robot obtains information about the road ahead by detecting the road signs ahead, and then executes corresponding actions.
  • adding a road sign system to the line patrol system will increase the cost and complexity of the line patrol system; and the road signs are confusing, which may easily lead to misjudgments by the robot due to issues such as observation angle and observation distance.
  • the embodiment of the present invention discloses a control method of a drone, a drone, and a computer-readable storage medium, which can not only accurately obtain the action task by identifying the characteristic information of the marking line, but also by combining the action task with the characteristic of the marking line Information fusion effectively reduces the cost and complexity of the line inspection system layout.
  • the first aspect of the embodiments of the present invention discloses a method for controlling a drone, wherein the drone includes a camera, and the method includes:
  • control the drone When the characteristic information meets the preset first characteristic condition, control the drone to perform the action task indicated by the characteristic information.
  • the second aspect of the embodiments of the present invention discloses an unmanned aerial vehicle, wherein the unmanned aerial vehicle includes a photographing device, and the unmanned aerial vehicle further includes a memory and a processor,
  • the memory is used to store program instructions
  • the processor is configured to execute program instructions stored in the memory, and when the program instructions are executed, the processor is configured to:
  • control the drone When the characteristic information meets the preset first characteristic condition, control the drone to perform the action task indicated by the characteristic information.
  • a third aspect of the embodiments of the present invention discloses a computer-readable storage medium in which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented .
  • the characteristic information of the reference marking line is recognized according to the image of the reference marking line during the process of the drone moving along the reference marking line, and the characteristic information of the reference marking line is controlled when the characteristic information meets preset characteristic conditions.
  • the action task indicated by the information can not only accurately obtain the action task by identifying the characteristic information of the marking line, but also by fusing the action task with the characteristic information of the marking line, effectively reducing the cost and complexity of the arrangement of the line inspection system.
  • Figure 1 is a schematic diagram of the structure of an unmanned aerial vehicle disclosed in an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of a scene patrolling control of a drone disclosed in an embodiment of the present invention
  • FIG. 3 is a schematic flowchart of a method for controlling a drone disclosed in an embodiment of the present invention
  • FIG. 4 is a schematic diagram of a drone moving along a reference marking line disclosed in an embodiment of the present invention.
  • Fig. 5 is a schematic structural diagram of another unmanned aerial vehicle disclosed in an embodiment of the present invention.
  • the drone may include a camera, wherein the camera can be carried on the body of the drone.
  • the photographing device may be directly carried on the body of the drone.
  • the drone further includes a pan/tilt, wherein the photographing device is installed on the pan/tilt, and the photographing device The device can be carried on the fuselage of the drone via the pan/tilt.
  • the photographing device may be a camera, a video camera, a mobile phone with a photographing function, and the like.
  • the pan/tilt head drives the camera to rotate around one or more of the yaw axis, roll axis and pitch axis to adjust the shooting attitude of the camera.
  • the relationship between the drone's fuselage, pan/tilt and camera is shown.
  • the pan/tilt 102 is installed on the drone's fuselage. 101, and the camera 103 is fixed on the platform 102.
  • the unmanned aerial vehicle described in the embodiment of the present invention may include unmanned aerial vehicles, unmanned vehicles, and unmanned ships.
  • the user can set a reference marking line 201 in the space in advance.
  • the preset reference marking line is used to indicate the trajectory of the drone 202; the preset reference marking line may have one or more types of characteristic information.
  • the characteristic information of the marking line may indicate the action task to be completed to the drone.
  • the reference identification line may be set on the ground or in the air; the characteristic information includes at least one of line type information, color information, line width information, bifurcation information, texture information, and stereo information.
  • the drone controls its configured camera to take pictures of the reference marking line to obtain an image of the reference marking line.
  • the drone obtains the image of the reference marking line output by the photographing device, and recognizes the characteristic information of the reference marking line according to the image of the reference marking line.
  • the drone is controlled to execute the action task indicated by the characteristic information.
  • the action task can be accurately obtained by identifying the characteristic information of the marking line.
  • the drone can determine the action that the drone needs to perform by detecting the characteristic information of the reference marking line Tasks can eliminate the need to set up road signs instructing drones to perform action tasks, which can effectively reduce the cost and complexity of the layout of the line inspection system.
  • FIG. 3 is a schematic flowchart of a method for controlling a drone according to an embodiment of the present invention.
  • the control method of the drone described in the embodiment of the present invention includes the following steps:
  • S301 During the process of the drone moving along the reference marking line preset in the space, identify the characteristic information of the reference marking line according to the image of the reference marking line output by the photographing device.
  • the user sets a reference marking line in the space in advance, and the preset reference marking line is used to indicate the trajectory of the drone; the preset reference marking line may have one or more kinds of characteristic information to pass
  • the characteristic information of the reference marking line indicates to the drone the action task to be completed.
  • the characteristic information includes at least one of line type information, color information, line width information, bifurcation information, texture information, and stereo information.
  • the drone controls its configured camera to take pictures of the reference marking line preset in the space to obtain the image of the reference marking line.
  • the drone acquires the image of the reference marking line output by the camera, and determines the target path of the drone according to the image of the reference marking line.
  • the drone determines the position of the reference marking line in the image, and determines the target path of the drone according to the position of the reference marking line in the image. Furthermore, the drone controls the movement of the drone according to the target path so that the drone moves along a preset reference marking line.
  • the drone controls its configured camera to take pictures of the reference marking line to obtain an image of the reference marking line. Further, the drone obtains the image of the reference marking line output by the photographing device, and recognizes the characteristic information of the reference marking line according to the image of the reference marking line.
  • the drone may be a photographing device that controls its configuration at preset time intervals to take pictures of the reference marking line to obtain an image of the reference marking line.
  • the unmanned aerial vehicle may also control its configured photographing device to take a picture of the reference marking line after receiving a photographing instruction sent by the control terminal to obtain an image of the reference marking line.
  • the feature information includes line type information
  • the way for the drone to recognize the feature information of the reference identification line according to the image of the reference identification line may be: performing connected domain detection processing on the image of the reference identification line to obtain all the information.
  • the connected domain detection result of the reference identification line in the image and then the line type information of the reference identification line is identified according to the connected domain detection result of the reference identification line in the image.
  • the connected domain detection result of the reference marking line in the image may be used to indicate whether the reference marking line in the image is connected, and the connected domain detection result of the reference marking line in the image may be used to determine the reference marking within the shooting range of the photographing device Line type information of the line.
  • the drone determines that the line type information of the reference marking line is a solid line, that is, the line type of the reference marking line within the shooting range of the camera is Solid line; when the connected domain detection result of the reference marking line in the image indicates that the reference marking line is not connected, the drone determines that the line type information of the reference marking line is a dashed line, that is, the reference marking line within the shooting range of the camera The line type is a dashed line.
  • the drone acquires the reference marking line in a plurality of discontinuous reference marking line segments in the image; and then acquiring the plurality of discontinuous reference marking line segments
  • the distance between adjacent reference marking line segments, and/or determining the shape of one or more reference marking line segments in the plurality of discontinuous reference marking line segments, the shape may be used to indicate the geometric shape of the reference marking line segment and Size information, etc.; finally according to the distance between adjacent reference identification line segments in the plurality of discontinuous reference identification line segments, and/or one or more reference identification line segments in the plurality of discontinuous reference identification line segments
  • the shape determines the dashed type of the reference marking line.
  • the reference marking line is a dotted dotted line. If it is detected that the shape of each of the multiple discontinuous reference marking line segments is linear, the reference marking line can be determined to be a line segment dashed line; when it is determined that the reference marking line is a line segment dashed line, if the detection is If the distance between each reference identification line segment is the same, it can be further determined that the reference identification line is an equally spaced line segment dashed line.
  • the characteristic information of the reference marking line includes color information for indicating the color of the reference marking line.
  • the drone obtains the gray information of the reference marking line in the image, and determines the color information of the reference marking line according to the gray information.
  • the color indicated by the color information of the reference marking line may be yellow, red, green, or blue.
  • the characteristic information of the reference marking line includes line width information for indicating the width of the reference marking line. The drone obtains the number of pixels of the reference marking line in the target direction in the image, and determines the line width information of the reference marking line according to the number of pixels.
  • the target direction may refer to the direction of the short side of the reference marking line in the image.
  • the characteristic information of the reference identification line includes bifurcation information
  • the bifurcation information includes indication information of whether the reference identification line has a bifurcation, the number of reference identification branches branched from the reference identification line, and the reference At least one of the feature information of each reference identification branch branched from the identification line.
  • the drone after the drone recognizes the characteristic information of the reference marking line according to the image of the reference marking line, it determines whether the characteristic information of the reference marking line satisfies the first characteristic condition, and after determining that the characteristic information of the reference marking line satisfies Under the first characteristic condition, the drone is controlled to execute the action task indicated by the characteristic information of the reference marking line.
  • the characteristic information of the reference marking line meeting the preset first characteristic condition includes: the line type information of the reference marking line meeting the preset first line type condition, the color information of the reference marking line meeting the preset first color condition, The line width information of the reference marking line satisfies the preset first line width condition, and the bifurcation information of the reference marking line indicates that the reference marking line diverges from at least one of a plurality of reference marking branch lines.
  • the action tasks indicated by the characteristic information of the reference marking line include: speed or acceleration adjustment task, U-turn task, task of moving the target reference marking branch line among the multiple reference marking branch lines branching off the reference marking line, stop moving task, and taking photo Or at least one of a video recording task, a shooting task, a shooting device adjustment task, and a task of sending prompt information to the control terminal.
  • the stop movement task includes controlling the drone to stop moving or controlling the drone to stop moving after moving to a target position.
  • the adjustment tasks of the camera include adjusting the posture of the camera or adjusting the shooting parameters of the camera.
  • the drone determines that the line type information of the reference marking line satisfies the preset first line type condition and meets the preset first line type condition. Set the first characteristic condition; and control the drone to perform the action task indicated by the line type of the target type. For example, when it is recognized that the line type of the reference marking line is a solid line, it is determined that the preset first line type condition is satisfied, and the drone is controlled to perform the photographing or video recording task indicated by the reference marking line with the line type being solid.
  • the drone is controlled to perform the task of adjusting the camera indicated by the reference marking line having the line type of the dotted line.
  • the drone determines that the color information of the reference marking line satisfies the preset first color condition and satisfies the preset first color condition.
  • a characteristic condition ; and control the drone to perform the action task indicated by the target color. For example, when it is recognized that the color of the reference marking line is red, it is determined that the preset first color condition is satisfied, and the drone is controlled to perform the stop movement task indicated by the red reference marking line. Or, when it is recognized that the color of the reference marking line is yellow, it is determined that the preset first color condition is satisfied, and the drone is controlled to perform the shooting task indicated by the yellow reference marking line.
  • the drone determines that the line width information of the reference marking line satisfies the preset first line width condition, and Satisfy the preset first characteristic condition; and control the drone to perform the action task indicated by the target line width.
  • the target line width can be a specific line width value or a line width range. For example, when it is recognized that the line width of the reference marking line is 25cm, it is determined that the preset first line width condition is satisfied, and the drone is controlled to perform the task of increasing the moving speed or acceleration indicated by the reference marking line with a line width of 25cm .
  • the drone determines that the line type information of the reference marking line meets the preset first line type condition; When the color information of the marking line indicates that the color of the reference marking line is the target color, the drone determines that the color information of the reference marking line meets the preset first color condition; when the line type information of the reference marking line meets the preset first line When the color information of the reference identification line meets the preset first color condition, the drone determines that the feature information of the reference identification line meets the preset first feature condition; and controls the drone to execute the color as the target color and
  • the line type is the action task indicated by the reference identification line of the target type.
  • the drone is controlled to perform the reference with the color blue and the line type being solid
  • the U-turn task indicated by the marking line when it is recognized that the line type of the reference marking line is a solid line and the color is blue, it is determined that the preset first characteristic condition is satisfied, and the drone is controlled to perform the reference with the color blue and the line type being solid
  • the U-turn task indicated by the marking line when it is recognized that the line type of the reference marking line is a solid line and the color is blue, it is determined that the preset first characteristic condition is satisfied, and the drone is controlled to perform the reference with the color blue and the line type being solid The U-turn task indicated by the marking line.
  • the drone determines that the bifurcation information of the reference identification line meets the preset first characteristic condition; After determining that the bifurcation information of the reference marking line satisfies the preset first characteristic condition, the drone determines the target reference marking branch line from the multiple reference marking branch lines according to the preset line patrol rule, and controls the drone to follow The target reference identifies the branch line movement.
  • the manner in which the drone determines the target reference identification branch line from the multiple reference identification branch lines according to the preset line tracking rule may be: determining each reference mark of the multiple reference identification branch lines according to the image of the reference identification line The feature information of the line, and the reference identification branch line whose feature information meets the preset second feature condition is determined as the target reference identification branch line.
  • the characteristic information includes at least one of line type information, color information, and line width information.
  • the characteristic information of the reference marking branch line meeting the preset second characteristic condition includes: the line type information of the reference marking branch line meeting the preset second line type condition, the color information of the reference marking branch line meeting the preset second color condition, and the reference marking
  • the line width information of the branch line satisfies at least one of the preset second line width conditions.
  • the way for the drone to determine the target reference identification branch from the multiple reference identification branches according to the preset line patrol rule may be: sending a prompt message requesting the selection of the reference identification branch to the control terminal; and The reference identification branch line indication information sent by the control terminal is received, and the reference identification branch line indicated by the reference identification branch line indication information is determined as a target reference identification branch line, wherein the reference identification branch line indication information is that the control terminal passes the user detection
  • the reference mark is generated by the branch selection operation.
  • FIG. 4 is a schematic diagram of a reference mark line movement provided by an embodiment of the present invention.
  • 401 represents the preset reference marking lines in the space, including the first reference marking line indicated by 4011, the second reference marking line indicated by 4012, the third reference marking line indicated by 4013, and the reference marking line 4014.
  • the line type of the first reference marking line indicated by 4011 is solid line, the color is gray, and the line width is the first width
  • the line type of the second reference marking line indicated by 4012 is the dashed line, the color is gray, and the line width is Is the first width
  • the line type of the third reference marking line indicated by 4013 is solid line, the color is black, and the line width is the first width
  • the line type of the fourth reference marking line indicated by 4014 is solid line, the color is Black
  • line width is the second width.
  • 402 is the movement trajectory of the drone moving along the part of the reference marking line indicated by 401 in the air.
  • the gray dots 4021, 4022, 4023, 4024, etc. in the figure indicate that the drone moves along the movement trajectory 402 for the reference
  • the marking line 401 is a shooting position point where shooting is performed.
  • the human-machine can recognize that the characteristic information of the reference marking line includes: the line type is a solid line, the color is gray, and the line width is the first width. Assuming that the reference identification line whose line type is a solid line meets the first characteristic condition, and the action task indicated by the solid line type is a photographing task, the drone controls its configured photographing device to take photographs of its environment.
  • the photographing device used by the drone to take pictures of the reference marking line may be the same or different from the photographing device used to take pictures of the environment in which the drone is located.
  • the drone can be equipped with at least two camera devices at the same time, and the at least two camera devices can be installed in different positions of the drone. If the drone controls its configured camera at the shooting position point 4024 to take pictures of the reference marking line 401, an image of the fourth reference marking line 4011 will be obtained; the drone will follow the fourth reference marking line 4011 output by the camera
  • the characteristic information that can identify the reference marking line includes: the line type is a solid line, the color is black, and the line width is the second width.
  • the action task of the drone is a shooting task, and the drone controls its equipped BB bullet launching device to launch BB bullets to target other unmanned equipment in the environment where the drone is located.
  • the characteristic information of the reference marking line is recognized according to the image of the reference marking line during the process of the drone moving along the reference marking line, and the characteristic information of the reference marking line is controlled when the characteristic information meets preset characteristic conditions.
  • the action task indicated by the information can not only accurately obtain the action task by identifying the characteristic information of the marking line, but also by fusing the action task with the characteristic information of the marking line, effectively reducing the cost and complexity of the arrangement of the line inspection system.
  • FIG. 5 is a schematic structural diagram of an unmanned aerial vehicle according to an embodiment of the present invention.
  • the drone described in the embodiment of the present invention includes: a processor 501, a communication interface 502, and a memory 503.
  • the processor 501, the communication interface 502, and the memory 503 may be connected through a bus or in other ways.
  • the embodiment of the present invention takes the connection through a bus as an example.
  • the processor 501 may be a central processing unit (CPU), or may be a core used to implement communication identification binding in a multi-core CPU.
  • the processor 501 may be a hardware chip.
  • the hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
  • the PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (generic array logic, GAL) or any combination thereof.
  • the communication interface 502 may be used for the interaction of sending and receiving information or signaling, as well as the reception and transmission of signals.
  • the communication interface 502 may optionally include a standard wireless interface (such as Wi-Fi, mobile communication interface, etc.).
  • the memory 503 may mainly include a storage program area and a storage data area.
  • the storage program area may store an operating system and a storage program required by at least one function (such as a text storage function, a location storage function, etc.); the storage data area may store Data (such as image data, text data) created according to the use of the device, etc., and may include application storage programs, etc.
  • the memory 403 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 503 is also used to store program instructions.
  • the processor 501 is configured to execute program instructions stored in the memory 503, and when the program instructions are executed, the processor 501 is configured to:
  • control the drone When the characteristic information meets the preset first characteristic condition, control the drone to perform the action task indicated by the characteristic information.
  • the characteristic information includes at least one of line type information, color information, line width information, and bifurcation information.
  • the characteristic information meeting the preset first characteristic condition includes the line type information meeting the preset first line type condition, the color information meeting the preset first color condition, the line type information
  • the width information satisfies the preset first line width condition and the bifurcation information indicates that the reference identification line diverges from at least one of a plurality of reference identification branch lines.
  • the action task includes a speed or acceleration adjustment task, a U-turn task, a task in which a target among a plurality of reference identification branches branching off along a reference identification line moves with a reference identification branch, a movement stop task, a photo or video recording At least one of a task, a shooting task, an adjustment task of the camera, and a task of sending prompt information to the control terminal.
  • the characteristic information includes line type information, and when the processor 501 recognizes the characteristic information of the reference marking line according to the image of the reference marking line output by the photographing device, it is specifically used to:
  • the feature information includes line type information, and when the processor 401 identifies the line type information of the reference marking line according to the connected domain detection result of the reference marking line in the image, it is specifically used for :
  • the connected domain detection result of the reference identification line in the image indicates that the reference identification line is not connected, it is determined that the line type information of the reference identification line is a dotted line.
  • the processor 501 when it is determined that the line type information of the reference marking line is a dotted line, the processor 501 is further configured to:
  • the dashed line type of the reference marking line is determined.
  • the characteristic information includes bifurcation information, and when the characteristic information satisfies a preset first characteristic condition, the processor 501 controls the drone to execute the characteristic information indicated by the characteristic information.
  • the action task is specifically used for:
  • a target reference identification branch line is determined from the multiple reference identification branch lines according to a preset line patrol rule
  • the processor 501 determines a target reference identification branch line from the plurality of reference identification branch lines according to a preset line tracking rule, it is specifically configured to:
  • the reference identification branch line whose characteristic information meets the preset second characteristic condition is determined as the target reference identification branch line.
  • the processor 501 determines a target reference identification branch line from the plurality of reference identification branch lines according to a preset line tracking rule, it is specifically configured to:
  • the reference identification branch line indication information sent by the control terminal is received through the communication interface 502, and the reference identification branch line indicated by the reference identification branch line indication information is determined as a target reference identification branch line, wherein the reference identification branch line indication information is all
  • the control terminal is generated by detecting the user's reference identification branch selection operation.
  • the processor 501 is further configured to:
  • the movement of the drone is controlled according to the target path to make the drone move along the reference marking line.
  • the drone is an unmanned ground robot, and the reference marking line is set on the ground.
  • the processor 501, the communication interface 502, and the memory 503 described in the embodiment of the present invention can execute the implementation described in the method for controlling a drone provided in the embodiment of the present invention, and will not be repeated here. .
  • An embodiment of the present invention also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the drone control method described in the above method embodiment is implemented .
  • the embodiment of the present invention also provides a computer program product containing instructions, which when running on a computer, causes the computer to execute the drone control method described in the foregoing method embodiment.
  • the program can be stored in a computer-readable storage medium, and the storage medium can include: Flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), magnetic disk or optical disk, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种无人机的控制方法、无人机及计算机可读存储介质，其中，所述无人机包括拍摄装置，所述方法包括：在所述无人机沿空间中预置的参考标识线移动的过程中，根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息；当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。本发明实施例不仅可以通过识别标识线的特征信息准确获取动作任务，还可以通过将动作任务与标识线的特征信息融合，有效降低巡线系统布置的成本和复杂度。

Description

一种无人机的控制方法、无人机及计算机可读存储介质 技术领域
本发明涉及控制技术领域，尤其涉及一种无人机的控制方法、无人机及计算机可读存储介质。
背景技术
巡线控制在机器人行业中具有广泛的应用。巡线控制通常需要一条在空间设置的标识线作为参考，同时需要一套检测设备对标识线和机器人当前的位置进行检测，以根据机器人和标识线两者之间的关系计算控制输出，从而达到使机器人沿给定标识线运动的目的。
目前，为实现机器人在巡线控制中执行不同动作，例如掉头、转弯等，巡线系统需要辅以一套路标系统。路标系统用于通过路标来标记路口、线的有关信息，通常可以采用近场通信(Near Field Communication，NFC)感应圈、二维码、特殊图案等形式来设置路标。机器人通过检测行进前方的路标来获取前方道路信息，从而执行相应动作。但是，在巡线系统中增设路标系统，会增加巡线系统布置的成本和复杂度；并且路标具有混淆性，容易导致机器人因为观察角度、观察距离等问题产生误判。
发明内容
本发明实施例公开了一种无人机的控制方法、无人机及计算机可读存储介质，不仅可以通过识别标识线的特征信息准确获取动作任务，还可以通过将动作任务与标识线的特征信息融合，有效降低巡线系统布置的成本和复杂度。
本发明实施例第一方面公开了一种无人机的控制方法，其中，所述无人机包括拍摄装置，所述方法包括：
在所述无人机沿空间中预置的参考标识线移动的过程中，根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息；
当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。
本发明实施例第二方面公开了一种无人机，其中，所述无人机包括拍摄装置，所述无人机还包括：存储器和处理器，
所述存储器，用于存储程序指令；
所述处理器，用于执行所述存储器存储的程序指令，当所述程序指令被执行时，所述处理器用于：
在所述无人机沿空间中预置的参考标识线移动的过程中，根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息；
当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。
本发明实施例第三方面公开了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，所述计算机程序被处理器执行时实现如上述第一方面所述方法的步骤。
本发明实施例通过在无人机沿参考标识线移动的过程中，根据参考标识线的图像识别参考标识线的特征信息，并在特征信息满足预设的特征条件时，控制无人机执行特征信息所指示的动作任务，不仅可以通过识别标识线的特征信息准确获取动作任务，还可以通过将动作任务与标识线的特征信息融合，有效降低巡线系统布置的成本和复杂度。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例公开的一种无人机的结构示意图；
图2是本发明实施例公开的一种无人机的巡线控制的场景示意图；
图3是本发明实施例公开的一种无人机的控制方法的流程示意图；
图4是本发明实施例公开的一种无人机沿参考标识线移动的示意图；
图5是本发明实施例公开的另一种无人机的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
下面结合附图，对本发明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。
本发明实施例中，无人机可以包括拍摄装置，其中，拍摄装置可以承载在无人机的机身上。所述拍摄装置可以直接承载在无人机的机身上，另外，在某些实施例中，所述无人机还包括云台，其中，所述拍摄装置安装在云台上，所述拍摄装置可以通过云台承载无人机的机身上。拍摄装置可以是相机、摄像机、具有拍照功能的手机等。所述云台带动所述拍摄装置绕偏航轴、横滚轴和俯仰轴中的一个或者多个轴线进行旋转以调整拍摄装置的拍摄姿态。如图1所示，示出了无人机的机身、云台和拍摄装置三者之间的关系，在图1所示的无人机中，云台102安装于无人机的机身101上，而拍摄装置103固定在云台102上。其中，本发明实施例中所述的无人机可以包括无人飞行器、无人车和无人船等。
如图2所示，用户可以预先在空间中设置参考标识线201，预置的参考标识线用于指示无人机202移动的轨迹；预置的参考标识线可以具有一种或者多种特征信息，以通过参考标识线的特征信息向无人机指示需要完成的动作任务。其中，参考标识线可以是设置在地面上，也可以是设置在空中；所述特征信息包括线型信息、颜色信息、线宽信息、分叉信息、纹理信息和立体信息中的至少一种。在无人机沿预置的参考标识线移动的过程中，无人机控制其配置的拍摄装置针对参考标识线进行拍照，得到参考标识线的图像。进一步地，无人机获取所述拍摄装置输出的参考标识线的图像，并根据参考标识线的图像识别参考标识线的特征信息。当参考标识线的特征信息满足预设的第一特征条件时，控制无人机执行所述特征信息所指示的动作任务。采用上述方式，通过识别标识线的特征信息可以准确获取动作任务，通过将动作任务与标识线的特征信息融合，无人机通过检测参考标识线的特征信息便能确定无人机需要执行的动作任务，可以免除设置指示无人机执行动作任务的路标，可以有效降低巡线系统 布置的成本和复杂度。
请参阅图3，为本发明实施例提供的一种无人机的控制方法的流程示意图。本发明实施例中所描述的无人机的控制方法包括如下步骤：
S301、在无人机沿空间中预置的参考标识线移动的过程中，根据拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息。
本发明实施例中，用户预先在空间中设置参考标识线，预置的参考标识线用于指示无人机移动的轨迹；预置的参考标识线可以具有一种或者多种特征信息，以通过参考标识线的特征信息向无人机指示需要完成的动作任务。其中，所述特征信息包括线型信息、颜色信息、线宽信息、分叉信息、纹理信息和立体信息中的至少一种。无人机控制其配置的拍摄装置针对空间中预置的参考标识线进行拍照，得到参考标识线的图像。无人机获取所述拍摄装置输出的参考标识线的图像，并根据参考标识线的图像确定所述无人机的目标路径。具体地，无人机确定参考标识线在所述图像中的位置，并根据参考标识线在所述图像中的位置确定无人机的目标路径。进而，无人机根据所述目标路径控制无人机移动以使无人机沿预置的参考标识线移动。
在无人机沿预置的参考标识线移动的过程中，无人机控制其配置的拍摄装置针对参考标识线进行拍照，得到参考标识线的图像。进一步地，无人机获取所述拍摄装置输出的参考标识线的图像，并根据参考标识线的图像识别参考标识线的特征信息。其中，无人机可以是每隔预设时间间隔控制其配置的拍摄装置针对参考标识线进行拍照，得到参考标识线的图像。无人机也可以是在接收到控制终端发送的拍照指令之后，控制其配置的拍摄装置针对参考标识线进行拍照，得到参考标识线的图像。
在一实施例中，所述特征信息包括线型信息，无人机根据参考标识线的图像识别参考标识线的特征信息的方式可以为：对参考标识线的图像进行连通域检测处理以获取所述图像中参考标识线的连通域检测结果；然后根据所述图像中参考标识线的连通域检测结果识别参考标识线的线型信息。其中，所述图像中参考标识线的连通域检测结果可以用于指示图像中的参考标识线是否连通，图像中参考标识线的连通域检测结果可以用于确定拍摄装置的拍摄范围内的参考标识线的线型信息。当所述图像中参考标识线的连通域检测结果指示参考 标识线连通时，无人机确定参考标识线的线型信息为实线，即拍摄装置的拍摄范围内的参考标识线的线型为实线；当所述图像中参考标识线的连通域检测结果指示参考标识线不连通时，无人机确定参考标识线的线型信息为虚线，即拍摄装置的拍摄范围内的参考标识线的线型为虚线。
进一步地，当确定参考标识线的线型信息为虚线时，无人机获取参考标识线在所述图像中多个不连续的参考标识线段；然后获取所述多个不连续的参考标识线段中相邻的参考标识线段之间的距离，和/或确定所述多个不连续的参考标识线段中一个或多个参考标识线段的形状，所述形状可以用于指示参考标识线段的几何形状以及尺寸信息等；最后根据所述多个不连续的参考标识线段中相邻的参考标识线段之间的距离，和/或所述多个不连续的参考标识线段中一个或多个参考标识线段的形状确定出参考标识线的虚线类型。其中，若检测出所述多个不连续的参考标识线段中各个参考标识线段的形状均为点状，则可以确定参考标识线为点虚线。若检测出所述多个不连续的参考标识线段中各个参考标识线段的形状均为线状，则可以确定参考标识线为线段虚线；在确定参考标识线为线段虚线时，若检测出所述各个参考标识线段之间的距离相同，则可以进一步确定参考标识线为等间隔线段虚线。
在另一实施例中，参考标识线的特征信息包括颜色信息，用于指示参考标识线的颜色。无人机获取参考标识线在所述图像中的灰度信息，并根据所述灰度信息确定参考标识线的颜色信息。参考标识线的颜色信息所指示的颜色可以是黄色、红色、绿色或者蓝色等。在另一实施例中，参考标识线的特征信息包括线宽信息，用于指示参考标识线的宽度。无人机获取参考标识线在所述图像中的目标方向上的像素点数量，并根据所述像素点数量确定参考标识线的线宽信息。所述目标方向可以是指参考标识线的短边在所述图像中的方向。在另一实施例中，参考标识线的特征信息包括分叉信息，所述分叉信息包括参考标识线是否存在分叉的指示信息、参考标识线分叉出的参考标识支线的数量，以及参考标识线分叉出的每条参考标识支线的特征信息等中的至少一种。
S302、当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。
本发明实施例中，无人机根据参考标识线的图像识别出参考标识线的特征 信息之后，判断参考标识线的特征信息是否满足第一特征条件，并在判断出参考标识线的特征信息满足第一特征条件时，控制无人机执行参考标识线的特征信息所指示的动作任务。其中，参考标识线的特征信息满足预设的第一特征条件包括：参考标识线的线型信息满足预设的第一线型条件、参考标识线的颜色信息满足预设的第一颜色条件、参考标识线的线宽信息满足预设的第一线宽条件、以及参考标识线的分叉信息指示参考标识线分叉出多条参考标识支线中的至少一种。参考标识线的特征信息所指示的动作任务包括：速度或者加速度调节任务、掉头任务、沿参考标识线分叉出的多条参考标识支线中的目标参考标识支线移动的任务、停止移动任务、拍照或者录像任务、射击任务、拍摄装置的调整任务、向控制终端发送提示信息的任务中的至少一种。需要说明的是，所述停止移动任务包括控制无人机停止移动或者控制无人机移动到目标位置后停止移动。所述拍摄装置的调整任务包括调整拍摄装置的姿态或者调整拍摄装置的拍摄参数等。
在一实施例中，当参考标识线的线型信息指示参考标识线的线型为目标类型时，无人机确定参考标识线的线型信息满足预设的第一线型条件，以及满足预设的第一特征条件；并控制无人机执行所述目标类型的线型所指示的动作任务。例如，当识别出参考标识线的线型为实线时，确定满足预设的第一线型条件，并控制无人机执行线型为实线的参考标识线所指示的拍照或者录像任务。或者，当识别出参考标识线的线型为虚线时，确定满足预设的第一线型条件，并控制无人机执行线型为虚线的参考标识线所指示的调整拍摄装置的任务。
在另一实施例中，当参考标识线的颜色信息指示参考标识线的颜色为目标颜色时，无人机确定参考标识线的颜色信息满足预设的第一颜色条件，以及满足预设的第一特征条件；并控制无人机执行所述目标颜色所指示的动作任务。例如，当识别出参考标识线的颜色为红色时，确定满足预设的第一颜色条件，并控制无人机执行红色参考标识线所指示的停止移动任务。或者，当识别出参考标识线的颜色为黄色时，确定满足预设的第一颜色条件，并控制无人机执行黄色参考标识线所指示的射击任务。
在另一实施例中，当参考标识线的线宽信息指示参考标识线的线宽为目标线宽时，无人机确定参考标识线的线宽信息满足预设的第一线宽条件，以及满 足预设的第一特征条件；并控制无人机执行所述目标线宽所指示的动作任务。其中，目标线宽可以是一个具体的线宽值，也可以是一个线宽范围。例如，当识别出参考标识线的线宽为25cm时，确定满足预设的第一线宽条件，并控制无人机执行线宽为25cm的参考标识线所指示的提高移动速度或者加速度的任务。或者，当识别出参考标识线的线宽处于线宽范围[10cm，20cm]内时，确定满足预设的第一线宽条件，并控制无人机执行线宽处于线宽范围[10cm,20cm]的参考标识线所指示的降低移动速度或者加速度的任务。
在另一实施例中，当参考标识线的线型信息指示参考标识线的线型为目标类型时，无人机确定参考标识线的线型信息满足预设的第一线型条件；当参考标识线的颜色信息指示参考标识线的颜色为目标颜色时，无人机确定参考标识线的颜色信息满足预设的第一颜色条件；当参考标识线的线型信息满足预设的第一线型条件，且参考标识线的颜色信息满足预设的第一颜色条件时，无人机确定参考标识线的特征信息满足预设的第一特征条件；并控制无人机执行颜色为目标颜色且线型为目标类型的参考标识线所指示的动作任务。例如，当识别出参考标识线的线型为实线，且颜色为蓝色时，确定满足预设的第一特征条件，并控制无人机执行颜色为蓝色且线型为实线的参考标识线所指示的掉头任务。
在另一实施例中，当参考标识线的分叉信息指示参考标识线分叉出多条参考标识支线时，无人机确定参考标识线的分叉信息满足预设的第一特征条件；在确定出参考标识线的分叉信息满足预设的第一特征条件之后，无人机按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线，并控制无人机沿所述目标参考标识支线移动。
其中，无人机按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线的方式可以为：根据参考标识线的图像确定所述多条参考标识支线中每一条参考标识线的特征信息，并将特征信息满足预设的第二特征条件的参考标识支线确定为目标参考标识支线。其中，所述特征信息包括线型信息、颜色信息和线宽信息中的至少一种。参考标识支线的特征信息满足预设的第二特征条件包括：参考标识支线的线型信息满足预设的第二线型条件、参考标识支线的颜色信息满足预设的第二颜色条件、以及参考标识支线的线宽信息满足预设的第二线宽条件中的至少一种。在另一实施例中，无人机按照预设巡线规则 从所述多条参考标识支线中确定出目标参考标识支线的方式可以为：向控制终端发送请求选择参考标识支线的提示信息；并接收所述控制终端发送的参考标识支线指示信息，将所述参考标识支线指示信息指示的参考标识支线确定为目标参考标识支线，其中，所述参考标识支线指示信息是所述控制终端通过检测用户的参考标识支线选择操作生成的。
为更好的理解本发明实施例所述的无人机的控制方法，下面结合图4进行举例说明。图4为本发明实施例提供的一种参考标识线移动的示意图。如图4所示，401表示空间中预置的参考标识线，包括4011所指示的第一参考标识线、4012所指示的第二参考标识线、4013所指示的第三参考标识线以及4014所指示的第四参考标识线。其中，4011所指示的第一参考标识线的线型为实线、颜色为灰色、线宽为第一宽度；4012所指示的第二参考标识线的线型为虚线、颜色为灰色、线宽为第一宽度；4013所指示的第三参考标识线的线型为实线、颜色为黑色、线宽为第一宽度；4014所指示的第四参考标识线的线型为实线、颜色为黑色、线宽为第二宽度。402为无人机在空中沿401所指示的部分参考标识线进行移动的移动轨迹，图中灰色填充的圆点4021、4022、4023、4024等表示无人机沿移动轨迹402移动过程中针对参考标识线401进行拍摄的拍摄位置点。
在无人机沿参考标识线401移动的过程中，若无人机在拍摄位置点4021控制其配置的拍摄装置针对参考标识线401进行拍照，则会得到第一参考标识线4011的图像；无人机根据拍摄装置输出的第一参考标识线4011的图像，可以识别出参考标识线的特征信息包括：线型为实线、颜色为灰色、线宽为第一宽度。假设线型为实线的参考标识线满足第一特征条件，且实线线型所指示的动作任务为拍照任务，无人机则控制其配置的拍摄装置针对其所处环境进行拍照。需要说明的是，无人机用于针对参考标识线进行拍照的拍摄装置，与用于针对无人机所处环境进行拍照的拍摄装置可以相同，也可以不同。当上述两个拍摄装置不同时，则表明无人机可以同时配置至少两个拍摄装置，该至少两个拍摄装置可以安装于无人机的不同位置。若无人机在拍摄位置点4024控制其配置的拍摄装置针对参考标识线401进行拍照，则会得到第四参考标识线4011的图像；无人机根据拍摄装置输出的第四参考标识线4011的图像，可以识别出参考标识线的特征信息包括：线型为实线、颜色为黑色、线宽为第二宽度。假设线宽为 第二宽度、颜色为黑色且线型为实线的参考标识线满足第一特征条件，且线宽为第二宽度、颜色为黑色且线型为实线的参考标识线所指示的动作任务为射击任务，无人机则控制其配置的BB弹发射装置发射BB弹，以针对无人机所处环境中的其他无人设备进行射击。
本发明实施例通过在无人机沿参考标识线移动的过程中，根据参考标识线的图像识别参考标识线的特征信息，并在特征信息满足预设的特征条件时，控制无人机执行特征信息所指示的动作任务，不仅可以通过识别标识线的特征信息准确获取动作任务，还可以通过将动作任务与标识线的特征信息融合，有效降低巡线系统布置的成本和复杂度。
请参阅图5，为本发明实施例提供的一种无人机的结构示意图。本发明实施例中所描述的无人机包括：处理器501、通信接口502和存储器503。其中，处理器501、通信接口502和存储器503可通过总线或其他方式连接，本发明实施例以通过总线连接为例。
所述处理器501可以是中央处理器(central processing unit，CPU)，也可以是多核CPU中用于实现通信标识绑定的核。所述处理器501可以是硬件芯片。所述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。所述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。
所述通信接口502可用于收发信息或信令的交互，以及信号的接收和传递，所述通信接口502可选的可以包括标准的无线接口(如Wi-Fi、移动通信接口等)。所述存储器503可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的存储程序(比如文字存储功能、位置存储功能等)；存储数据区可存储根据装置的使用所创建的数据(比如图像数据、文字数据)等，并可以包括应用存储程序等。此外，存储器403可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
所述存储器503还用于存储程序指令。所述处理器501，用于执行所述存储 器503存储的程序指令，当所述程序指令被执行时，所述处理器501用于：
在所述无人机沿空间中预置的参考标识线移动的过程中，根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息；
当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。
本发明实施例中处理器执行的方法均从处理器的角度来描述，可以理解的是，本发明实施例中处理器要执行上述方法需要其他硬件结构的配合。本发明实施例对具体的实现过程不作详细描述和限制。
在一实施例中，所述特征信息包括线型信息、颜色信息、线宽信息和分叉信息中的至少一种。
在一实施例中，所述特征信息满足预设的第一特征条件包括所述线型信息满足预设的第一线型条件、所述颜色信息满足预设的第一颜色条件、所述线宽信息满足预设的第一线宽条件和所述分叉信息指示所述参考标识线分叉出多条参考标识支线中的至少一种。
在一实施例中，所述动作任务包括速度或者加速度调节任务、掉头任务、沿参考标识线分叉出的多条参考标识支线中的目标参考标识支线移动的任务、停止移动任务、拍照或者录像任务、射击任务、拍摄装置的调整任务、向控制终端发送提示信息的任务中的至少一种。
在一实施例中，所述特征信息包括线型信息，所述处理器501根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息时，具体用于：
对所述拍摄装置输出的所述参考标识线的图像进行连通域检测处理以获取所述图像中所述参考标识线的连通域检测结果；
根据所述图像中所述参考标识线的连通域检测结果识别所述参考标识线的线型信息。
在一实施例中，所述特征信息包括线型信息，所述处理器401根据所述图像中所述参考标识线的连通域检测结果识别所述参考标识线的线型信息时，具体用于：
当所述图像中所述参考标识线的连通域检测结果指示所述参考标识线连 通时，确定所述参考标识线的线型信息为实线；
当所述图像中所述参考标识线的连通域检测结果指示所述参考标识线不连通时，确定所述参考标识线的线型信息为虚线。
在一实施例中，当确定所述参考标识线的线型信息为虚线时，所述处理器501还用于：
获取所述参考标识线在所述图像中多个不连续的参考标识线段；
获取所述多个不连续的参考标识线段中相邻的参考标识线段之间的距离，和/或确定所述多个不连续的参考标识线段中一个或多个参考标识线段的形状；
根据所述距离和/或形状，确定出所述参考标识线的虚线类型。
在一实施例中，所述特征信息包括分叉信息，所述当所述特征信息满足预设的第一特征条件时，所述处理器501控制所述无人机执行所述特征信息所指示的动作任务时，具体用于：
当所述分叉信息指示所述参考标识线分叉出多条参考标识支线时，按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线；
控制所述无人机沿所述目标参考标识支线移动。
在一实施例中，所述处理器501按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线时，具体用于：
根据所述参考标识线的图像确定所述多条参考标识支线的特征信息；
将特征信息满足预设的第二特征条件的参考标识支线确定为目标参考标识支线。
在一实施例中，所述处理器501按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线时，具体用于：
通过所述通信接口502向控制终端发送请求选择参考标识支线的提示信息；
通过所述通信接口502接收所述控制终端发送的参考标识支线指示信息，将所述参考标识支线指示信息指示的参考标识支线确定为目标参考标识支线，其中，所述参考标识支线指示信息是所述控制终端通过检测用户的参考标识支线选择操作生成的。
在一实施例中，所述处理器501还用于：
获取所述拍摄装置输出的所述参考标识线的图像；
根据所述图像确定所述无人机的目标路径；
根据所述目标路径控制所述无人机移动以使所述无人机沿所述参考标识线移动。
在一实施例中，所述无人机为无人地面机器人，所述参考标识线设置在地面上。
具体实现中，本发明实施例中所描述的处理器501、通信接口502和存储器503可执行本发明实施例提供的一种无人机的控制方法中所描述的实现方式，在此不再赘述。
本发明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中存储有计算机程序，所述计算机程序被处理器执行时实现上述方法实施例所述的无人机的控制方法。
本发明实施例还提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述方法实施例所述的无人机的控制方法。
需要说明的是，对于前述的各个方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某一些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本发明所必须的。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
以上对本发明实施例所提供的一种无人机的控制方法及无人机进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本发明的限制。

Claims (25)

  1. 一种无人机的控制方法，其中，所述无人机包括拍摄装置，其特征在于，所述方法包括：
    在所述无人机沿空间中预置的参考标识线移动的过程中，根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息；
    当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。
  2. 根据权利要求1所述的方法，其特征在于，所述特征信息包括线型信息、颜色信息、线宽信息和分叉信息中的至少一种。
  3. 根据权利要求2所述的方法，其特征在于，所述特征信息满足预设的第一特征条件包括所述线型信息满足预设的第一线型条件、所述颜色信息满足预设的第一颜色条件、所述线宽信息满足预设的第一线宽条件和所述分叉信息指示所述参考标识线分叉出多条参考标识支线中的至少一种。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述动作任务包括速度或者加速度调节任务、掉头任务、沿参考标识线分叉出的多条参考标识支线中的目标参考标识支线移动的任务、停止移动任务、拍照或者录像任务、射击任务、拍摄装置的调整任务、向控制终端发送提示信息的任务中的至少一种。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述特征信息包括线型信息，所述根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息，包括：
    对所述拍摄装置输出的所述参考标识线的图像进行连通域检测处理以获取所述图像中所述参考标识线的连通域检测结果；
    根据所述图像中所述参考标识线的连通域检测结果识别所述参考标识线的线型信息。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述图像中所述参考标识线的连通域检测结果识别所述参考标识线的线型信息，包括：
    当所述图像中所述参考标识线的连通域检测结果指示所述参考标识线连通时，确定所述参考标识线的线型信息为实线；
    当所述图像中所述参考标识线的连通域检测结果指示所述参考标识线不连通时，确定所述参考标识线的线型信息为虚线。
  7. 权利要求6所述的方法，其特征在于，当确定所述参考标识线的线型信息为虚线时，所述方法还包括：
    获取所述参考标识线在所述图像中多个不连续的参考标识线段；
    获取所述多个不连续的参考标识线段中相邻的参考标识线段之间的距离，和/或确定所述多个不连续的参考标识线段中一个或多个参考标识线段的形状；
    根据所述距离和/或形状，确定出所述参考标识线的虚线类型。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述特征信息包括分叉信息，所述当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务，包括：
    当所述分叉信息指示所述参考标识线分叉出多条参考标识支线时，按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线；
    控制所述无人机沿所述目标参考标识支线移动。
  9. 根据权利要求8所述的方法，其特征在于，所述按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线，包括：
    根据所述参考标识线的图像确定所述多条参考标识支线的特征信息；
    将特征信息满足预设的第二特征条件的参考标识支线确定为目标参考标识支线。
  10. 根据权利要求8所述的方法，其特征在于，所述按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线，包括：
    向控制终端发送请求选择参考标识支线的提示信息；
    接收所述控制终端发送的参考标识支线指示信息，将所述参考标识支线指示信息指示的参考标识支线确定为目标参考标识支线，其中，所述参考标识支线指示信息是所述控制终端通过检测用户的参考标识支线选择操作生成的。
  11. 根据权利要求1至10中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述拍摄装置输出的所述参考标识线的图像；
    根据所述图像确定所述无人机的目标路径；
    根据所述目标路径控制所述无人机移动以使所述无人机沿所述参考标识线移动。
  12. 根据权利要求1至11中任一项所述的方法，其特征在于，所述无人机为无人地面机器人，所述参考标识线设置在地面上。
  13. 一种无人机，其中，所述无人机包括拍摄装置，其特征在于，所述无人机还包括：存储器和处理器，
    所述存储器，用于存储程序指令；
    所述处理器，用于执行所述存储器存储的程序指令，当所述程序指令被执行时，所述处理器用于：
    在所述无人机沿空间中预置的参考标识线移动的过程中，根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息；
    当所述特征信息满足预设的第一特征条件时，控制所述无人机执行所述特征信息所指示的动作任务。
  14. 根据权利要求13所述的无人机，其特征在于，所述特征信息包括线型信息、颜色信息、线宽信息和分叉信息中的至少一种。
  15. 根据权利要求14所述的无人机，其特征在于，所述特征信息满足预设的第一特征条件包括所述线型信息满足预设的第一线型条件、所述颜色信息满足预设的第一颜色条件、所述线宽信息满足预设的第一线宽条件和所述分叉信息指示所述参考标识线分叉出多条参考标识支线中的至少一种。
  16. 根据权利要求13至15中任一项所述的无人机，其特征在于，所述动作任务包括速度或者加速度调节任务、掉头任务、沿参考标识线分叉出的多条参考标识支线中的目标参考标识支线移动的任务、停止移动任务、拍照或者录像任务、射击任务、拍摄装置的调整任务、向控制终端发送提示信息的任务中的至少一种。
  17. 根据权利要求13至16中任一项所述的无人机，其特征在于，所述特征信息包括线型信息，所述处理器根据所述拍摄装置输出的所述参考标识线的图像识别所述参考标识线的特征信息时，具体用于：
    对所述拍摄装置输出的所述参考标识线的图像进行连通域检测处理以获取所述图像中所述参考标识线的连通域检测结果；
    根据所述图像中所述参考标识线的连通域检测结果识别所述参考标识线的线型信息。
  18. 根据权利要求17所述的无人机，其特征在于，所述处理器根据所述图像中所述参考标识线的连通域检测结果识别所述参考标识线的线型信息时，具体用于：
    当所述图像中所述参考标识线的连通域检测结果指示所述参考标识线连通时，确定所述参考标识线的线型信息为实线；
    当所述图像中所述参考标识线的连通域检测结果指示所述参考标识线不连通时，确定所述参考标识线的线型信息为虚线。
  19. 权利要求18所述的无人机，其特征在于，当确定所述参考标识线的线 型信息为虚线时，所述处理器还用于：
    获取所述参考标识线在所述图像中多个不连续的参考标识线段；
    获取所述多个不连续的参考标识线段中相邻的参考标识线段之间的距离，和/或确定所述多个不连续的参考标识线段中一个或多个参考标识线段的形状；
    根据所述距离和/或形状，确定出所述参考标识线的虚线类型。
  20. 根据权利要求1至7中任一项所述的无人机，其特征在于，所述特征信息包括分叉信息，所述当所述特征信息满足预设的第一特征条件时，所述处理器控制所述无人机执行所述特征信息所指示的动作任务时，具体用于：
    当所述分叉信息指示所述参考标识线分叉出多条参考标识支线时，按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线；
    控制所述无人机沿所述目标参考标识支线移动。
  21. 根据权利要求20所述的无人机，其特征在于，所述处理器按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线时，具体用于：
    根据所述参考标识线的图像确定所述多条参考标识支线的特征信息；
    将特征信息满足预设的第二特征条件的参考标识支线确定为目标参考标识支线。
  22. 根据权利要求20所述的无人机，其特征在于，所述处理器按照预设巡线规则从所述多条参考标识支线中确定出目标参考标识支线时，具体用于：
    向控制终端发送请求选择参考标识支线的提示信息；
    接收所述控制终端发送的参考标识支线指示信息，将所述参考标识支线指示信息指示的参考标识支线确定为目标参考标识支线，其中，所述参考标识支线指示信息是所述控制终端通过检测用户的参考标识支线选择操作生成的。
  23. 根据权利要求13至22中任一项所述的无人机，其特征在于，所述处理器还用于：
    获取所述拍摄装置输出的所述参考标识线的图像；
    根据所述图像确定所述无人机的目标路径；
    根据所述目标路径控制所述无人机移动以使所述无人机沿所述参考标识线移动。
  24. 根据权利要求13至23中任一项所述的无人机，其特征在于，所述无人机为无人地面机器人，所述参考标识线设置在地面上。
  25. 一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，其特征在于：所述计算机程序被处理器执行时实现如权利要求1至12中任一项所述方法的步骤。
PCT/CN2019/084759 2019-04-28 2019-04-28 一种无人机的控制方法、无人机及计算机可读存储介质 WO2020220158A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/084759 WO2020220158A1 (zh) 2019-04-28 2019-04-28 一种无人机的控制方法、无人机及计算机可读存储介质
CN201980005063.7A CN111247792B (zh) 2019-04-28 2019-04-28 一种无人机的控制方法、无人机及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/084759 WO2020220158A1 (zh) 2019-04-28 2019-04-28 一种无人机的控制方法、无人机及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2020220158A1 true WO2020220158A1 (zh) 2020-11-05

Family

ID=70875652

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/084759 WO2020220158A1 (zh) 2019-04-28 2019-04-28 一种无人机的控制方法、无人机及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN111247792B (zh)
WO (1) WO2020220158A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112492197A (zh) * 2020-11-18 2021-03-12 京东数科海益信息科技有限公司 图像处理方法及相关设备
CN116989771A (zh) * 2023-09-18 2023-11-03 中冶建筑研究总院有限公司 一种用于检测结构缺陷的地空协同方法、系统及装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112162566B (zh) * 2020-09-04 2024-01-16 深圳市创客火科技有限公司 路线规划方法、电子设备及计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102880177A (zh) * 2011-07-15 2013-01-16 佳能精机株式会社 自动行驶车以及自动行驶系统
CN105045258A (zh) * 2014-04-25 2015-11-11 株式会社理光 自动移动装置
CN107330380A (zh) * 2017-06-14 2017-11-07 千寻位置网络有限公司 基于无人机航拍影像的车道线自动提取和识别方法
CN107632604A (zh) * 2017-09-25 2018-01-26 上海木爷机器人技术有限公司 自主移动装置导引线导航方法及装置
CN108762250A (zh) * 2018-04-27 2018-11-06 深圳市商汤科技有限公司 设备的控制方法和装置、设备、计算机程序和存储介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101669144B (zh) * 2007-03-13 2013-09-18 浦项产业科学研究院 用于移动式机器人的位置确定的路标和使用该路标的设备与方法
JP5083658B2 (ja) * 2008-03-26 2012-11-28 本田技研工業株式会社 車両用車線認識装置、車両、及び車両用車線認識プログラム
US8676431B1 (en) * 2013-03-12 2014-03-18 Google Inc. User interface for displaying object-based indications in an autonomous driving system
US9501056B2 (en) * 2013-11-20 2016-11-22 Qualcomm Incorporated Autonomous robot for a mobile device
US10386188B2 (en) * 2015-06-29 2019-08-20 Yuneec Technology Co., Limited Geo-location or navigation camera, and aircraft and navigation method therefor
CN105847684A (zh) * 2016-03-31 2016-08-10 深圳奥比中光科技有限公司 无人机
US20180181129A1 (en) * 2016-12-27 2018-06-28 Autel Robotics Co., Ltd. Method and apparatus for controlling flight of unmanned aerial vehicle and unmanned aerial vehicle
CN108965687B (zh) * 2017-05-22 2021-01-29 阿里巴巴集团控股有限公司 拍摄方向识别方法、服务器及监控方法、系统及摄像设备
KR102348120B1 (ko) * 2017-08-24 2022-01-07 현대자동차주식회사 주행 차로 변경 시 경로를 생성하는 시스템 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102880177A (zh) * 2011-07-15 2013-01-16 佳能精机株式会社 自动行驶车以及自动行驶系统
CN105045258A (zh) * 2014-04-25 2015-11-11 株式会社理光 自动移动装置
CN107330380A (zh) * 2017-06-14 2017-11-07 千寻位置网络有限公司 基于无人机航拍影像的车道线自动提取和识别方法
CN107632604A (zh) * 2017-09-25 2018-01-26 上海木爷机器人技术有限公司 自主移动装置导引线导航方法及装置
CN108762250A (zh) * 2018-04-27 2018-11-06 深圳市商汤科技有限公司 设备的控制方法和装置、设备、计算机程序和存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112492197A (zh) * 2020-11-18 2021-03-12 京东数科海益信息科技有限公司 图像处理方法及相关设备
CN112492197B (zh) * 2020-11-18 2022-01-07 京东科技信息技术有限公司 图像处理方法及相关设备
CN116989771A (zh) * 2023-09-18 2023-11-03 中冶建筑研究总院有限公司 一种用于检测结构缺陷的地空协同方法、系统及装置
CN116989771B (zh) * 2023-09-18 2024-01-23 中冶建筑研究总院有限公司 一种用于检测结构缺陷的地空协同方法、系统及装置

Also Published As

Publication number Publication date
CN111247792A (zh) 2020-06-05
CN111247792B (zh) 2021-11-02

Similar Documents

Publication Publication Date Title
US11126182B2 (en) Unmanned aerial image capture platform
US20210279444A1 (en) Systems and methods for depth map sampling
CN110278405B (zh) 一种自动驾驶车辆的侧向图像处理方法、装置和系统
US9632509B1 (en) Operating a UAV with a narrow obstacle-sensor field-of-view
US20180032042A1 (en) System And Method Of Dynamically Controlling Parameters For Processing Sensor Output Data
WO2020220158A1 (zh) 一种无人机的控制方法、无人机及计算机可读存储介质
WO2019113966A1 (zh) 一种避障方法、装置和无人机
US10733896B2 (en) Projection-based cooperative collision avoidance
US10304345B2 (en) Unmanned aerial vehicle
US20190265735A1 (en) Flight control device, unmanned aerial vehicle, flight control method, and computer-readable recording medium
US10133929B2 (en) Positioning method and positioning device for unmanned aerial vehicle
US20190243356A1 (en) Method for controlling flight of an aircraft, device, and aircraft
WO2019119201A1 (zh) 一种云台控制方法、无人机、云台及存储介质
US10157545B1 (en) Flight navigation using lenticular array
EP3367201A1 (en) Method and device for controlling flight of unmanned aerial vehicle, and unmanned aerial vehicle
JP6324649B1 (ja) 検出システム、検出方法、及びプログラム
US10254767B1 (en) Determining position or orientation relative to a marker
US9812020B2 (en) Electronic device and unmanned aerial vehicle control method
US20210208606A1 (en) Information processing system, information processing method, and program
US20180181129A1 (en) Method and apparatus for controlling flight of unmanned aerial vehicle and unmanned aerial vehicle
JP2020518500A (ja) 乗り物監視システムおよび外部の物体を検知するための方法
CN109885091B (zh) 一种无人机自主飞行控制方法及系统
WO2021056144A1 (zh) 可移动平台的返航控制方法、装置及可移动平台
CN110997488A (zh) 动态控制用于处理传感器输出数据的参数的系统和方法
KR101876829B1 (ko) 소형 드론의 실내 비행제어를 위한 유도 제어 시스템

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: 19927161

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: 19927161

Country of ref document: EP

Kind code of ref document: A1