WO2019061466A1 - Flight control method, remote control device, and remote control system - Google Patents

Flight control method, remote control device, and remote control system Download PDF

Info

Publication number
WO2019061466A1
WO2019061466A1 PCT/CN2017/104911 CN2017104911W WO2019061466A1 WO 2019061466 A1 WO2019061466 A1 WO 2019061466A1 CN 2017104911 W CN2017104911 W CN 2017104911W WO 2019061466 A1 WO2019061466 A1 WO 2019061466A1
Authority
WO
WIPO (PCT)
Prior art keywords
target object
information
remote control
feature
area
Prior art date
Application number
PCT/CN2017/104911
Other languages
French (fr)
Chinese (zh)
Inventor
封旭阳
赵丛
李思晋
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/CN2017/104911 priority Critical patent/WO2019061466A1/en
Priority to CN201780007166.8A priority patent/CN108700885B/en
Publication of WO2019061466A1 publication Critical patent/WO2019061466A1/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
    • G05D1/08Control of attitude, i.e. control of roll, pitch, or yaw
    • G05D1/0808Control of attitude, i.e. control of roll, pitch, or yaw 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
    • G05D1/10Simultaneous control of position or course in three dimensions
    • G05D1/101Simultaneous control of position or course in three dimensions specially adapted for aircraft

Definitions

  • the present invention relates to the field of electronic technologies, and in particular, to a flight control method, a remote control device, and a remote control system.
  • aircraft such as drones, remote-controlled aircraft, aerial vehicles, etc.
  • People can carry cameras, spray devices, etc. through drones to achieve aerial photography, spraying and other tasks.
  • the operator can control the rocker on the remote control device by both hands, and shake the rocker up and down as needed to control the drone, and generate control according to the rocking direction and the rocking amplitude of the rocker. Command to control the flight of the aircraft.
  • the embodiment of the invention discloses a flight control method, a remote control device and a remote control system, which can enrich the control of the aircraft.
  • an embodiment of the present invention discloses a flight control method, which is applied to a remote control device, where the remote control device is used to remotely control aircraft flight, and the method includes:
  • the control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
  • an embodiment of the present invention discloses a remote control device for remotely controlling aircraft flight, including: a memory and a processor;
  • the memory is configured to store program instructions
  • the processor is configured to execute program instructions stored in the memory, when program instructions are executed,
  • the processor is used to:
  • the control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
  • an embodiment of the present invention discloses a remote control system, including:
  • At least one camera device and/or at least one sensor comprising a red, green and blue camera device;
  • a remote control device as in the second aspect is a remote control device as in the second aspect.
  • the remote control device can detect the movement trajectory of the feature position area on the target object in the space, determine the levitation control action, generate a control instruction according to the levitation control action, and finally use the wireless link to control the command.
  • Sending to the aircraft and controlling the flight of the aircraft can accurately control the flight of the aircraft without the operator touching the remote control device, enriching the control mode of the aircraft and improving the intelligence of the remote control device.
  • FIG. 1 is a schematic diagram of a scenario for flight control according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of another scenario for flight control according to an embodiment of the present invention.
  • FIG. 3 is a schematic flow chart of a flight control method according to an embodiment of the present invention.
  • FIG. 4 is a schematic flow chart of another flight control method according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a remote control device according to an embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a remote control system according to an embodiment of the present invention.
  • UAVs have a very wide range of uses. They are currently well used in aerial photography, agriculture, express transportation, disaster relief, surveying and mapping, news reporting, power inspection, disaster relief, etc., making drone technology a Popular emerging technologies. In the UAV technology, achieving precise control of the drone is an important research direction.
  • the first way is to require the operator to manipulate the remote control device such as the joystick with both hands to achieve more precise control of the drone.
  • the above method requires an artificial contact with the remote control device, and the remote control device can recognize the operation of the operator, and the control method of the aircraft is limited.
  • the second way is that the operator performs a wave motion against the aircraft, and then the aircraft uses the camera device (such as a camera, a close-up binocular stereo module, etc.) provided on the aircraft to collect the depth information of the palm, and the depth information is used to identify the operation.
  • the player's wave action then controls the aircraft to fly in accordance with the flight instructions represented by the wave action.
  • the second method described above can control the flight of the aircraft without a remote control device.
  • the control can only be controlled by the action of the operator waving, the control method is relatively simple, and the operator's hand needs to be very close to the aircraft and in the same horizontal plane.
  • the aircraft can take in the waved action and cannot control the flight of the aircraft remotely.
  • the present invention provides a flight control method, a remote control device, and a remote control system.
  • FIG. 1 and FIG. 2 are schematic diagrams of scenarios for flight control according to an embodiment of the present invention.
  • the hand is the target object
  • the knuckle point is the feature position area of the target object, but it should be understood that in the embodiment of the present invention, the hand and the knuckle joint point are only for the target object and the target.
  • An example of the feature location area of the object, in other embodiments, the target object and the feature location area of the target object may also be other objects, which is not limited in this embodiment of the present invention.
  • the execution body of 101-106 is a remote control device, and the remote control device can be used for Remotely control the flight of the aircraft.
  • the remote control device may be a wearable device, an augmented reality device, or the like.
  • the wearable device may be, for example, a smart watch, a smart bracelet, smart glasses, etc.
  • the augmented reality device may be, for example, a head mounted display or the like.
  • the remote control device is exemplified by a smart watch, but it should be understood that in other embodiments, the remote control device may be any of the above-mentioned remote control devices.
  • the remote control device can acquire the depth of the detection area through a depth information collection device (for example, a binocular stereo vision module, a 3D time of flight (ToF) module, a depth sensor, etc.) disposed on the remote control device. information.
  • a depth information collection device for example, a binocular stereo vision module, a 3D time of flight (ToF) module, a depth sensor, etc.
  • an area between two broken lines may be the detection area, and the remote control device may acquire depth information in the detection area.
  • the depth information may be determined from a depth map of the current frame.
  • the remote control device can detect whether there is a hand (ie, a target object) in the detection area by using the depth information, and if present, the opponent can perform rough positioning, and specifically, the palm can perform rough positioning.
  • the remote control device may use the surface of the current dial as a reference coordinate system, project the depth information of the current frame onto the reference coordinate system to generate a point cloud image, and then the point cloud image.
  • the presence or absence of the palm is detected, and if present, the palm is roughly positioned and steps 103-106 are performed.
  • the remote control can enter a sleep mode.
  • the remote control device can adjust the frequency of detecting the palm from the first frequency to the second frequency (the second frequency is less than the first frequency). If the remote control device receives a wake-up command (for example, shaking the remote control device, etc.), the sleep mode can be released and the second frequency can be adjusted back to the first frequency.
  • a wake-up command for example, shaking the remote control device, etc.
  • the knuckle point can be accurately positioned after the palm is roughly positioned.
  • a black dot on the tip of the finger can be used to indicate a feature position area (ie, a knuckle point) of the target object, and the remote control device can accurately position the knuckle point.
  • the remote control device may extract a region of interest (ROI) in the point cloud image, and perform palm fitting according to the point cloud data provided by the point cloud image within the ROI range. Thereby precise positioning of each knuckle point.
  • ROI region of interest
  • the remote control device can perform a movement trajectory fit based on the positional movement of the knuckle joint point.
  • the remote control device may further remove the positional deviation of the movement trajectory caused by the shaking of the remote control device according to the preset filter function and the posture information of the remote control device, to implement smoothing filtering processing, and obtain the knuckle point.
  • the movement track may further remove the positional deviation of the movement trajectory caused by the shaking of the remote control device according to the preset filter function and the posture information of the remote control device, to implement smoothing filtering processing, and obtain the knuckle point.
  • the movement track may further remove the positional deviation of the movement trajectory caused by the shaking of the remote control device according to the preset filter function and the posture information of the remote control device, to implement smoothing filtering processing, and obtain the knuckle point.
  • the remote control device can determine a hovering control action according to the movement trajectory and generate a corresponding control command. For example, if the remote control device fits a horizontal to right movement trajectory, then the levitation control action is to control the aircraft to fly horizontally to the right.
  • the control command is an instruction to control the aircraft to fly horizontally to the right.
  • the remote control device can transmit the control command to the drone via a wireless link (e.g., cellular mobile data network, Bluetooth, infrared, etc.) to cause the drone to fly in accordance with the indication of the control command.
  • a wireless link e.g., cellular mobile data network, Bluetooth, infrared, etc.
  • the operator can control the flight of the aircraft without touching the remote control device, which breaks the limitation of the artificial contact remote control device and realizes the precise control of the aircraft, and the form of the remote control device is not limited to the traditional rocker. It can also be a wearable device, an augmented reality device, etc., which enriches the control mode of the aircraft and improves the intelligence of the remote control device.
  • FIG. 3 is a schematic flowchart of a flight control method according to an embodiment of the present invention.
  • the method shown in FIG. 3 may include:
  • execution body of the embodiment of the present invention may be a remote control device for remotely controlling aircraft flight.
  • the remote control device is a wearable device or an augmented reality device.
  • the wearable device is any one or more of a smart watch, smart glasses, and a smart bracelet; the augmented reality device is a head mounted display.
  • the remote control device detects a movement trajectory of the feature location area on the target object in the space, and specifically includes: acquiring image feature information of the detection area; and determining the target object from the image feature information of the detection area. The movement track of the feature position area on the space.
  • the detection area may be an area that can be detected by the depth information collection device on the remote control device.
  • image feature information can be used to represent feature information in the scene image within the range of the detection region.
  • the remote control device may be a smart watch, and the detection area may be an area above the dial of the smart watch and between two broken lines, and the remote control device may collect the detection area.
  • Image feature information may be a smart watch, and the detection area may be an area above the dial of the smart watch and between two broken lines, and the remote control device may collect the detection area.
  • the remote control device may acquire an image in real time, acquire image feature information in the image, or acquire image feature information in the image according to a preset time, where each frame image is provided.
  • the image feature information may correspond to image feature information provided by an image captured at a time of, for example, 12:30:10, and the corresponding time may be 12:30:10, and the current time may correspond to the current frame image.
  • Image feature information may correspond to image feature information provided by an image captured at a time of, for example, 12:30:10, and the corresponding time may be 12:30:10, and the current time may correspond to the current frame image.
  • the image feature information may be the image feature information in the current frame image, or may be the image feature information in the continuous multi-frame image, and the like, which is not limited in this embodiment of the present invention.
  • the remote control device may acquire a current frame image of the detection area, extract image feature information in the current frame image, and detect a movement trajectory of the feature position area on the target object in the space according to the image feature information.
  • the remote control device before determining the movement trajectory of the feature location area on the target object in the image from the image feature information of the detection area, further includes: detecting whether the detection area exists a target object; if there is a target object, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the first frequency.
  • the target object is a hand
  • the feature location area on the target object is an knuckle point on the hand.
  • the target object may also be other biometric parts, such as eyes, mouth, head, etc.
  • the feature area on the target object may also be the pupil of the eye, the lip of the mouth, the hair of the head. Etc., the present invention does not impose any limitation on this.
  • the remote control device may determine, according to the image feature information, whether the target object exists after extracting the image feature information in the current frame image, and if present, acquire the image feature of the detection region.
  • the acquisition frequency at the time of information is adjusted to the first frequency.
  • the first frequency may be, for example, a high acquisition frequency such as 50 Hz, 100 Hz, or the like. That is to say, if the remote control device detects the target object, the acquisition frequency of the remote control device at this time may be the first frequency, which may facilitate fitting the movement trajectory of the target object.
  • the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the second frequency.
  • the second frequency may be, for example, a lower acquisition frequency such as 5 Hz, 10 Hz, or the like. That is to say, if the remote control device detects that the target object does not exist, the acquisition frequency of the remote control device may be the second frequency, which may reduce the power consumption of the remote control device and increase the usage time of the remote control device.
  • the remote control device is in a sleep mode at the second frequency, the method further comprising: if receiving the wake-up command, acquiring frequency of the image feature information of the detection region from The second frequency is adjusted to the first frequency; wherein the first frequency is higher than the second frequency.
  • the wake-up command may be, for example, an operation command for recognizing a wrist by an inertial measurement unit.
  • the remote control device is a smart wristband or a smart watch, it is determined that the wake-up command is received by recognizing the action of raising the hand and the face of the dial facing up.
  • the remote control device may determine that the working mode (ie, the mode of detecting the target object) needs to be entered, and the acquiring frequency corresponding to the working mode may be the first frequency, and the remote control device may The acquisition frequency can be adjusted from the second frequency to the first frequency.
  • the working mode ie, the mode of detecting the target object
  • determining the movement trajectory of the feature location area on the target object in the image from the image feature information of the detection area comprises: determining features on the target object according to image feature information of the detection area a location area; determining a movement trajectory of the feature location area in the space according to at least two frames of image feature information of the detection area.
  • the image feature information provided by the at least two frames of the detection area may be image feature information provided by two consecutive frames of images.
  • the remote control device determines the feature location area on the target object by using the image feature information provided by the current frame image, and then the root device can And according to the image feature information provided by the current frame image and the image feature information provided by the next frame image of the current frame image feature information, the movement trajectory of the feature location region in the space is determined.
  • the moving track may refer to a position change track of the feature position area in space.
  • the image feature information of the detection area is depth information of the detection area.
  • the remote control device may first acquire a depth image in the detection area, and then determine depth information from the depth image, and according to the depth change indicated by the depth information, the contour movement of the target object The direction, size and other parameters determine the movement trajectory of the feature location area on the target object in space.
  • the remote control device may acquire image feature information in the detection area by using a binocular stereo vision module, a 3D TOF module, a depth sensor, or the like, and further detect whether the target object exists in the detection area.
  • the determining the feature location area on the target object according to the depth information of the detection area comprises: performing projection processing on the reference coordinate system according to the depth information of the detection area, and generating on the reference coordinate system a point cloud image, the reference coordinate system is determined according to the remote control device; determining contour information of the target object according to the point cloud image; determining position information of the feature position region according to the contour information of the target object, A feature location area on the target object is determined.
  • the reference coordinate system may be a coordinate system centered on the remote control device.
  • the center point or other points of the surface of the remote control device may be taken as the origin of the reference coordinate system, and then the horizontal axis and the vertical axis of the reference coordinate system are established with the surface of the remote control device (for example, the dial of the smart watch). .
  • the depth information may be determined from an image in which the distance (depth) value from each point in the detection area to the detection area is taken as a pixel value.
  • the reflected light carries information such as the orientation and distance of the target object. If the light beam is scanned according to the preset trajectory, the reflection is recorded while scanning. Information, when the scan is very fine, you can get a lot of light spots, so A point cloud image can be formed. That is to say, the point cloud image can indicate information such as the orientation and distance of the target object.
  • the remote control device may first determine depth information represented by the depth map of the detection area, then project the depth information into a reference coordinate system, and generate a point cloud image in the reference coordinate system,
  • the point cloud image can represent information such as the orientation and distance of the target object, and the contour information of the target object can be determined according to the information such as the azimuth and the distance.
  • the position of the point cloud data in the contour is dense, and can be regarded as the feature position on the target object. region.
  • the determining the location information of the feature location area according to the profile information of the target object comprises: determining initial location information of the feature location area according to the profile information of the target object; filtering according to a preset The function and the posture information of the remote control device perform smoothing processing on the initial position information to obtain position information of the feature position area.
  • location information of the feature location area may be used to indicate the location change of the feature location area itself.
  • the initial location information of the feature location area may include information of the location movement of the feature location area due to the movement of the remote control device itself.
  • the remote control device can remove the position of the feature location area caused by the movement of the remote control device by using a preset filter function and the attitude information of the remote control device measured by the inertial measurement unit. Move to obtain the location information of the feature location area.
  • the detecting a movement trajectory of the feature location area on the target object in the space comprises: acquiring motion sensing data of the feature location area on the target object by using a sensor disposed on the feature location area; Obtaining a movement trajectory of the feature location area on the target object in the space according to the motion sensing data.
  • the senor may be pre-set in the area of the feature, and the sensor may be, for example, a temperature sensor, an infrared sensor, or the like, which is not limited in the embodiment of the present invention.
  • the senor can be wirelessly connected to the remote control device, and the sensor transmits the mobile sensing data to the remote control device by wireless transmission.
  • the operator can wear gloves
  • the sensor is provided at the knuckle point of the glove, and the operator can issue some control actions, and the sensor converts these control actions
  • the motion sensing data is sent to the remote control device, and the remote control device can perform data fitting according to the motion sensing data to obtain a movement track of the operator's knuckle point in the space.
  • the image feature information of the detection area is color information or infrared information of the detection area.
  • the color information may be, for example, color information in an image captured in the detection area, for example, the image is an RGB (Red Green Blue) image captured by the imaging device.
  • the infrared information may be, for example, information represented by an image taken by the infrared camera.
  • the feature location area on the target object may be determined from image feature information of the detection area based on depth learning. After the feature position area on the target object is located, the movement track of the feature position area on the target object in the space may be obtained according to the position change of the feature position area on the target object.
  • the levitation control action can be determined according to the movement trajectory.
  • the suspension control action may refer to a control action triggered by the operator when the remote control device is not touched.
  • the palm (target object) shown in FIG. 2 performs a control action in a space area above the smart watch (remote control device).
  • control command can be used to control the flight of the aircraft.
  • the suspension control action and the control command may have a corresponding relationship.
  • the correspondence may be a correspondence between a direction and an angle.
  • the hovering control action is a horizontal left motion
  • the control command may be an instruction to control the aircraft horizontally to the left.
  • the generating the control instruction according to the suspension control action comprises: obtaining a type of the suspension control action and a motion vector of the feature location area according to the determined contour information; according to the type of the suspension control action The motion vector of the feature location area generates a control instruction.
  • the motion vector of the feature location area includes a motion direction and a motion amplitude of the feature location area determined according to at least two frame depth information.
  • the moving direction of the feature location area may be any direction, such as upper, lower, left, right, upper left, lower right, lower left, upper right, and the like, which is not limited in this embodiment of the present invention.
  • the type of the suspension control action can be used to indicate the suspension control action.
  • the direction may be, for example, a type that controls the upward direction, a type that controls the downward direction, a type that controls the leftward, a type that controls the rightward, and the like.
  • the target object may be a palm
  • the feature location area of the target object is a joint point
  • the remote control device determines the suspension control action after positioning the joint finger point, and then the remote control device
  • the type of the levitation control action may be determined by the classifier, for example, to control the downward type
  • the motion vector of each knuckle point may be calculated according to the depth information provided by the at least two frames of depth information, and the motion vector may include a motion direction. , the magnitude of the movement and other parameters.
  • the remote control device can determine a control command that can be used to control the aircraft to fly downward in accordance with parameters in the motion vector.
  • the wireless link may be, for example, a cellular mobile data network, a wireless fidelity (WiFi), an infrared, a Bluetooth, etc., and the present invention does not impose any limitation.
  • WiFi wireless fidelity
  • WiFi infrared
  • Bluetooth Bluetooth
  • the remote control device can transmit a control command to the aircraft via a wireless link, and after receiving the control command, the aircraft can fly according to the instruction of the control command.
  • the control command indicates that the flight is horizontal to the right, and the aircraft can fly to the right according to the level of the control command.
  • the remote control device can detect the movement trajectory of the feature location area on the target object in the space, and determine the corresponding levitation control action, generate a control instruction according to the levitation control action, and finally pass the wireless link.
  • Sending the control command to the aircraft can control the flight of the aircraft without the operator touching the remote control device, which breaks the limitation of the artificial contact with the remote control device, realizes the precise control of the aircraft, and enriches the control mode of the aircraft. Improves the intelligence of the remote control device.
  • FIG. 4 is a schematic flowchart diagram of another flight control method according to an embodiment of the present invention.
  • the method as shown in FIG. 4 may include:
  • the remote control device may acquire depth information of the detection area before detecting a movement trajectory of the feature position area on the target object in the space; according to the depth information of the detection area It is detected whether there is a target object; if there is a target object, a movement trajectory of the feature position area on the detection target object in space is performed.
  • a virtual image is superimposed on the detection area.
  • the virtual image may be a non-realistic image generated by a virtual reality device, an augmented reality device, or the like.
  • S402. Generate and display the virtual image in the detection area according to location information of the target object.
  • the virtual image may be superimposed and displayed in the detection area by the remote control device.
  • the remote control device can display the virtual image in any orientation directly below, directly above the target object, and the present invention does not impose any limitation.
  • the remote control device may be an augmented reality device a
  • the detection area may be an area directly in front of the line of sight of the augmented reality device a
  • the augmented reality device a may detect the target object (eg, a palm) within the detection area.
  • the virtual image is displayed directly below the palm, and the virtual image can be, for example, a virtual airplane.
  • the virtual image may also be superimposed and displayed in the detection area by other devices.
  • the remote control device is a smart watch
  • the operator can wear an augmented reality device b
  • the augmented reality device b can establish a connection with the smart watch, and then the remote device detects the target object, the enhancement
  • the reality device b can project a virtual image on the detection area of the smart watch, such as a virtual aircraft.
  • the movement trajectory of the feature position area of the target object can be used as the movement trajectory of the virtual image.
  • the target object may be a palm
  • the feature location area of the target object may be a joint point
  • the movement track fitted by the remote control device may mean that the joint point moves horizontally to the right, then the virtual image is also It can be moved to the right horizontally according to the movement trajectory.
  • the virtual image may be a virtual aircraft, and the operator may “pinch” the virtual aircraft in the detection area, and the operator's knuckles point moves horizontally to the right, and the virtual aircraft can also follow the operation.
  • the author's knuckle points move horizontally to the right.
  • the remote control device can also obtain a suspension control action according to the movement trajectory of the knuckle joint point, and determine a corresponding control command, send the control command to the aircraft, and control the aircraft to fly according to the control instruction.
  • the remote control device can display the virtual image in the detection area, and control the movement of the virtual image according to the movement trajectory of the feature position area on the target object in the space, thereby enhancing the interest in remote control of the aircraft. Sex, but also improve the intelligence of the remote control device.
  • FIG. 5 is a schematic structural diagram of a remote control device according to an embodiment of the present invention.
  • the remote control device described in this embodiment includes:
  • the memory 501 is configured to store program instructions
  • the processor 502 is configured to execute the program instructions stored in the memory, when the program instructions are executed, to:
  • the control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
  • the processor 502 is configured to: acquire depth information of the detection area before detecting a movement trajectory of the feature location area on the target object in the space; and detect whether the target exists according to the depth information of the detection area. An object; if there is a target object, performing a movement trajectory of the feature position area on the detection target object in the space.
  • the processor 502 when the processor 502 detects a movement trajectory of a feature location area on the target object in the space, the processor 502 is specifically configured to:
  • a movement trajectory of the feature position area on the target object in the space is determined from the image feature information of the detection area.
  • the image feature information of the detection area is depth information of the detection area.
  • the processor 502 is further configured to: detect whether the target object exists in the detection area; if the target object exists, acquire frequency when acquiring image feature information of the detection area Adjust to the first frequency.
  • the processor 502 is further configured to: if the target object does not exist, adjust an acquisition frequency when acquiring image feature information of the detection area to a second frequency.
  • the remote control device is in a sleep mode at the second frequency
  • the processor 502 is further configured to: when the wake-up instruction is received, the image feature information of the detection area is acquired The acquisition frequency is adjusted from the second frequency to the first frequency; wherein the first frequency is higher than the second frequency.
  • the processor 502 determines the movement trajectory of the feature location area on the target object in the space from the image feature information of the detection area
  • the processor 502 is specifically configured to: according to the image feature information of the detection area Determining a feature location area on the target object; determining a movement trajectory of the feature location area in the space according to the image feature information provided by the at least two frames of the detection area.
  • the image feature information of the detection area is depth information of the detection area.
  • the processor 502 when the processor 502 determines the feature location area on the target object according to the image feature information of the detection area, the processor 502 is specifically configured to: perform projection processing on the reference coordinate system according to the depth information of the detection area, and generate a point cloud image on the reference coordinate system, the reference coordinate system is determined according to the remote control device; determining contour information of the target object according to the point cloud image; determining a feature according to the contour information of the target object Position information of the location area to determine a feature location area on the target object.
  • the method when the processor 502 determines the location information of the feature location area according to the profile information of the target object, the method is specifically configured to: determine initial location information of the feature location area according to the profile information of the target object. And performing smoothing processing on the initial position information according to the preset filter function and the posture information of the remote control device to obtain position information of the feature position area.
  • the method when the processor 502 generates a control instruction according to the levitation control action, the method is specifically configured to: obtain a type of the levitation control action and the feature position according to the determined contour information. a motion vector of the region; generating a control instruction according to the type of the suspension control action and the motion vector of the feature location region.
  • the motion vector of the feature location area includes a motion direction and a motion amplitude of the feature location area determined according to at least two frame depth information.
  • the processor 502 when the processor 502 detects a movement trajectory of the feature location area on the target object in the space, the processor 502 is configured to: acquire a feature location area on the target object by using a sensor disposed on the feature location area Moving sensing data; obtaining a moving trajectory of the feature location area on the target object in the space according to the motion sensing data.
  • the image feature information of the detection area is color information or infrared information of the detection area; the processor 502 determines a feature position on the target object from image feature information of the detection area.
  • the method is specifically: determining, according to the depth learning, the feature location region on the target object from the image feature information of the detection region; acquiring the feature location region of the target object in the space Move the track.
  • a virtual image is superimposed and displayed in the detection area.
  • the processor 502 is further configured to: generate and display the virtual image in the detection area according to location information of the target object.
  • the processor 502 is further configured to: control the virtual image movement according to the movement trajectory.
  • the remote control device is a wearable device or an augmented reality device.
  • the wearable device is any one or more of a smart watch, smart glasses, and a smart bracelet; the augmented reality device is a head mounted display.
  • the target object is a hand
  • the feature location area on the target object is an knuckle point on the hand.
  • FIG. 6 is a schematic structural diagram of a remote control system according to an embodiment of the present invention.
  • the remote control system includes: at least one camera device and/or at least one sensor, wherein the camera device includes a red, green and blue camera device; an aircraft; a remote control device.
  • the remote control device 601 is the remote control device disclosed in the foregoing embodiment of the present invention, and the principles and implementations are similar to the foregoing embodiments, and details are not described herein again.
  • the camera 603 can be disposed on the remote control device for capturing depth information of the detection area.
  • the camera device 603 may include a red, green and blue camera device, and the red, green and blue camera device may acquire a color map of a feature location area of the target object, and the remote control device 601 may use the color map to target the target object.
  • the location area is positioned and tracked to obtain a moving track.
  • the senor 604 can be disposed at a feature location area of the target object, such as a temperature sensor, a distance sensor, an infrared sensor, and the like.
  • the senor 604 can also be disposed on the remote control device 601 for acquiring depth information of the detection area.
  • the sensor 604 can be, for example, a depth sensor or the like.
  • the remote control system can be applied to remotely controlled aircraft devices.
  • the remote control device 601 can be configured to detect a movement trajectory of the feature position area on the target object in the space, and determine a levitation control action based on the movement trajectory, generate a control instruction according to the levitation control action, and use the remote link to control the command. Send to the aircraft to control the flight of the aircraft.
  • remote control device 601 can be used to perform the flight control method shown in the foregoing method embodiment, and the specific implementation process can refer to the method embodiment, and details are not described herein.
  • the program can be stored in a computer readable storage medium, and the storage medium can include: Flash disk, Read-Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Selective Calling Equipment (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

Provided in an embodiment of the present invention are a flight control method, a remote control device, and a remote control system. The method comprises: detecting a movement track of a feature position region of a target object in a space, and determining a non-touch control movement on the basis of the movement track; generating a control command according to the non-touch control movement; and transmitting the control command to an aerial vehicle by means of a wireless link so as to control flight of the aerial vehicle. The invention provides a new manner of controlling an aerial vehicle, and enables a remote control device to have a higher level of intelligence.

Description

一种飞行控制方法、遥控装置、遥控系统Flight control method, remote control device and remote control system 技术领域Technical field
本发明涉及电子技术领域,尤其涉及一种飞行控制方法、遥控装置、遥控系统。The present invention relates to the field of electronic technologies, and in particular, to a flight control method, a remote control device, and a remote control system.
背景技术Background technique
随着电子技术的不断发展,飞行器(例如无人机、遥控飞行器、航拍飞行器等)也逐渐普及。人们可以通过无人机携带摄像机、喷洒装置等,来实现航拍、喷洒等任务。With the continuous development of electronic technology, aircraft (such as drones, remote-controlled aircraft, aerial vehicles, etc.) have also become popular. People can carry cameras, spray devices, etc. through drones to achieve aerial photography, spraying and other tasks.
在操纵飞行器时,常常需要操作者双手操纵遥控装置,实现对飞行器的控制。以无人机为例,操作者可以通过双手控制遥控装置上的摇杆,根据需要通过上下左右的摇动摇杆,来实现对无人机的控制,根据摇杆的摇动方向和摇动幅度生成控制指令来控制飞行器飞行。When maneuvering an aircraft, it is often necessary for the operator to manipulate the remote control device with both hands to achieve control of the aircraft. Taking the drone as an example, the operator can control the rocker on the remote control device by both hands, and shake the rocker up and down as needed to control the drone, and generate control according to the rocking direction and the rocking amplitude of the rocker. Command to control the flight of the aircraft.
如何便捷地控制飞行器成为研究的热点。How to conveniently control the aircraft has become a research hotspot.
发明内容Summary of the invention
本发明实施例公开了一种飞行控制方法、遥控装置、遥控系统,可丰富对飞行器的控制。The embodiment of the invention discloses a flight control method, a remote control device and a remote control system, which can enrich the control of the aircraft.
第一方面,本发明实施例公开了一种飞行控制方法,应用于遥控装置,所述遥控装置用于远程控制飞行器飞行,所述方法包括:In a first aspect, an embodiment of the present invention discloses a flight control method, which is applied to a remote control device, where the remote control device is used to remotely control aircraft flight, and the method includes:
检测目标对象上的特征位置区域在空间中的移动轨迹,并基于所述移动轨迹确定悬浮控制动作;Detecting a movement trajectory of the feature position area on the target object in the space, and determining a levitation control action based on the movement trajectory;
根据所述悬浮控制动作生成控制指令;Generating a control instruction according to the suspension control action;
通过无线链路将所述控制指令发送至飞行器,以控制所述飞行器飞行。The control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
第二方面,本发明实施例公开了一种遥控装置,所述遥控装置用于远程控制飞行器飞行,包括:存储器和处理器;In a second aspect, an embodiment of the present invention discloses a remote control device for remotely controlling aircraft flight, including: a memory and a processor;
所述存储器,用于存储程序指令;The memory is configured to store program instructions;
所述处理器,用于执行所述存储器存储的程序指令,当程序指令被执行时, 所述处理器用于:The processor is configured to execute program instructions stored in the memory, when program instructions are executed, The processor is used to:
检测目标对象上的特征位置区域在空间中的移动轨迹,并基于所述移动轨迹确定悬浮控制动作;Detecting a movement trajectory of the feature position area on the target object in the space, and determining a levitation control action based on the movement trajectory;
根据所述悬浮控制动作生成控制指令;Generating a control instruction according to the suspension control action;
通过无线链路将所述控制指令发送至飞行器,以控制所述飞行器飞行。The control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
第三方面,本发明实施例公开了一种遥控系统,包括:In a third aspect, an embodiment of the present invention discloses a remote control system, including:
至少一个摄像装置和/或至少一个传感器,所述摄像装置包括红绿蓝摄像装置;At least one camera device and/or at least one sensor, the camera device comprising a red, green and blue camera device;
飞行器;Aircraft
如第二方面所述的遥控装置。A remote control device as in the second aspect.
本发明实施例中,遥控装置可以通过检测目标对象上的特征位置区域在空间中的移动轨迹,并确定出悬浮控制动作,根据该悬浮控制动作生成控制指令,最后通过无线链路将该控制指令发送至飞行器,控制飞行器飞行,可以在操作者不接触遥控装置的情况下,也能精准控制飞行器飞行,丰富了对飞行器的控制方式,提高了遥控装置的智能性。In the embodiment of the present invention, the remote control device can detect the movement trajectory of the feature position area on the target object in the space, determine the levitation control action, generate a control instruction according to the levitation control action, and finally use the wireless link to control the command. Sending to the aircraft and controlling the flight of the aircraft can accurately control the flight of the aircraft without the operator touching the remote control device, enriching the control mode of the aircraft and improving the intelligence of the remote control device.
附图说明DRAWINGS
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。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings to be used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without paying for creative labor.
图1是本发明实施例提供的一种用于飞行控制的情景示意图;FIG. 1 is a schematic diagram of a scenario for flight control according to an embodiment of the present invention; FIG.
图2是本发明实施例提供的另一种用于飞行控制的情景示意图;2 is a schematic diagram of another scenario for flight control according to an embodiment of the present invention;
图3是本发明实施例提供的一种飞行控制方法的流程示意图;3 is a schematic flow chart of a flight control method according to an embodiment of the present invention;
图4是本发明实施例提供的另一种飞行控制方法的流程示意图;4 is a schematic flow chart of another flight control method according to an embodiment of the present invention;
图5是本发明实施例提供的一种遥控装置的结构示意图;FIG. 5 is a schematic structural diagram of a remote control device according to an embodiment of the present invention; FIG.
图6是本发明实施例提供的一种遥控系统的结构示意图。FIG. 6 is a schematic structural diagram of a remote control system according to an embodiment of the present invention.
具体实施方式 Detailed ways
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。The technical solutions in the embodiments of the present invention will be clearly and completely described in the following with reference to the accompanying drawings.
无人机具有十分广泛的用途,目前在航拍、农业、快递运输、灾难救援、测绘、新闻报道、电力巡检、救灾等众多领域都得到了很好的应用,使得无人机技术成为了一项热门的新兴技术。而在无人机技术中,实现对无人机的精准控制是一个重要的研究方向。UAVs have a very wide range of uses. They are currently well used in aerial photography, agriculture, express transportation, disaster relief, surveying and mapping, news reporting, power inspection, disaster relief, etc., making drone technology a Popular emerging technologies. In the UAV technology, achieving precise control of the drone is an important research direction.
对无人机进行控制通常采用以下两种方式。第一种方式是需要操作者双手操纵摇杆等遥控装置,来实现对无人机较为精准的控制。There are two ways to control a drone. The first way is to require the operator to manipulate the remote control device such as the joystick with both hands to achieve more precise control of the drone.
然而,上述方式需要人为接触遥控装置,遥控装置才能识别出操作者的操作,对飞行器的控制方式较为局限。However, the above method requires an artificial contact with the remote control device, and the remote control device can recognize the operation of the operator, and the control method of the aircraft is limited.
第二种方式是操作者对着飞行器进行挥手的动作,然后飞行器利用在该飞行器上设置的摄像装置(例如摄像头、近距离双目立体模块等)采集手掌的深度信息,通过深度信息来识别操作者的挥手动作,然后控制该飞行器按照该挥手动作代表的飞行指令进行飞行。The second way is that the operator performs a wave motion against the aircraft, and then the aircraft uses the camera device (such as a camera, a close-up binocular stereo module, etc.) provided on the aircraft to collect the depth information of the palm, and the depth information is used to identify the operation. The player's wave action then controls the aircraft to fly in accordance with the flight instructions represented by the wave action.
上述第二种方式无需遥控装置便可控制飞行器飞行,然而,仅仅只能通过操作者挥手的动作才能进行控制,控制方式比较单一,并且,需要操作者的手距离飞行器非常近且在同一水平面内,飞行器才能摄取到该挥手的动作,不能远程控制飞行器飞行。The second method described above can control the flight of the aircraft without a remote control device. However, the control can only be controlled by the action of the operator waving, the control method is relatively simple, and the operator's hand needs to be very close to the aircraft and in the same horizontal plane. The aircraft can take in the waved action and cannot control the flight of the aircraft remotely.
因此,如何既能远程控制遥控装置飞行,又能打破人为接触遥控装置的局限,提高遥控装置的智能性成为了一个亟待解决的问题。Therefore, how to remotely control the remote control device to fly, and to break the limitations of artificial contact with the remote control device, and improve the intelligence of the remote control device has become an urgent problem to be solved.
为了解决上述技术问题,本发明提供了一种飞行控制方法、遥控装置、遥控系统。In order to solve the above technical problems, the present invention provides a flight control method, a remote control device, and a remote control system.
为了更清楚的描述,下面请参阅图1和图2,为本发明实施例提供的用于飞行控制的情景示意图。在图1和图2中,手为目标对象,指关节点为该目标对象的特征位置区域,但应知,在本发明实施例中,手和该指关节点仅为对目标对象和该目标对象的特征位置区域的一个示例,在其他实施例中,该目标对象和该目标对象的特征位置区域还可以是其它物体,本发明实施例对此不作任何限制。For a clearer description, please refer to FIG. 1 and FIG. 2 below, which are schematic diagrams of scenarios for flight control according to an embodiment of the present invention. In FIG. 1 and FIG. 2, the hand is the target object, and the knuckle point is the feature position area of the target object, but it should be understood that in the embodiment of the present invention, the hand and the knuckle joint point are only for the target object and the target. An example of the feature location area of the object, in other embodiments, the target object and the feature location area of the target object may also be other objects, which is not limited in this embodiment of the present invention.
还需要说明的是,101-106的执行主体为遥控装置,该遥控装置可以用于 远程控制飞行器飞行。具体的,该遥控装置可以是可穿戴设备、增强现实设备等等。其中,该可穿戴设备,例如可以是智能手表、智能手环、智能眼镜等,该增强现实设备,例如可以是头戴式显示器等等。在图2中,该遥控装置以智能手表为例,但应知,在其他实施例中,该遥控装置可以为上述任意一种遥控装置。It should also be noted that the execution body of 101-106 is a remote control device, and the remote control device can be used for Remotely control the flight of the aircraft. Specifically, the remote control device may be a wearable device, an augmented reality device, or the like. The wearable device may be, for example, a smart watch, a smart bracelet, smart glasses, etc., and the augmented reality device may be, for example, a head mounted display or the like. In FIG. 2, the remote control device is exemplified by a smart watch, but it should be understood that in other embodiments, the remote control device may be any of the above-mentioned remote control devices.
下面结合图1和图2对本发明实施例进行具体说明。The embodiments of the present invention are specifically described below with reference to FIGS. 1 and 2.
在101中,该遥控装置可以通过设置在该遥控装置上的深度信息采集装置(例如双目立体视觉模块、3D飞行时间(Time of Flight,ToF)模块、深度传感器等),获取探测区域的深度信息。In 101, the remote control device can acquire the depth of the detection area through a depth information collection device (for example, a binocular stereo vision module, a 3D time of flight (ToF) module, a depth sensor, etc.) disposed on the remote control device. information.
在一个实施例中,如图2所示,遥控装置的表盘上方,两条虚线之间的区域可以为该探测区域,遥控装置可以获取该探测区域内的深度信息。In one embodiment, as shown in FIG. 2, above the dial of the remote control device, an area between two broken lines may be the detection area, and the remote control device may acquire depth information in the detection area.
在一个实施例中,该深度信息可以根据当前帧的深度图确定。In one embodiment, the depth information may be determined from a depth map of the current frame.
在102中,该遥控装置可以通过该深度信息检测在该探测区域内是否存在手(即目标对象),如果存在,就可以对手进行粗略定位,具体的,可以是对手掌进行粗略定位。In 102, the remote control device can detect whether there is a hand (ie, a target object) in the detection area by using the depth information, and if present, the opponent can perform rough positioning, and specifically, the palm can perform rough positioning.
在一个实施例中,如图2所示,遥控装置可以以当前表盘的表面为参考坐标系,将该当前帧的深度信息投影到该参考坐标系上生成点云图像,然后在该点云图像上检测是否存在该手掌,如果存在,就对该手掌进行粗略定位,并执行103-106步骤。In an embodiment, as shown in FIG. 2, the remote control device may use the surface of the current dial as a reference coordinate system, project the depth information of the current frame onto the reference coordinate system to generate a point cloud image, and then the point cloud image. The presence or absence of the palm is detected, and if present, the palm is roughly positioned and steps 103-106 are performed.
在一个实施例中,如果没有检测到该手掌,那么该遥控装置可以进入休眠模式。该遥控装置可以将检测手掌的频率从第一频率调为第二频率(第二频率小于第一频率)。如果该遥控装置接收到唤醒指令(例如摇晃该遥控装置等),便可以解除休眠模式,并将该第二频率调回第一频率。In one embodiment, if the palm is not detected, the remote control can enter a sleep mode. The remote control device can adjust the frequency of detecting the palm from the first frequency to the second frequency (the second frequency is less than the first frequency). If the remote control device receives a wake-up command (for example, shaking the remote control device, etc.), the sleep mode can be released and the second frequency can be adjusted back to the first frequency.
在103中,该遥控装置如果检测到手掌,可以在对该手掌进行粗略定位之后,再对指关节点进行精确定位。如图2所示,手指尖上的黑色圆点可以用于表示该目标对象的特征位置区域(即指关节点),该遥控装置可以对该指关节点进行精确定位。In 103, if the remote control device detects the palm, the knuckle point can be accurately positioned after the palm is roughly positioned. As shown in FIG. 2, a black dot on the tip of the finger can be used to indicate a feature position area (ie, a knuckle point) of the target object, and the remote control device can accurately position the knuckle point.
在一个实施例中,该遥控装置可以提取点云图像中的感兴趣区域(region of interest,ROI),在ROI范围内根据点云图像提供的点云数据进行手掌拟合, 从而对各个指关节点进行精确定位。In one embodiment, the remote control device may extract a region of interest (ROI) in the point cloud image, and perform palm fitting according to the point cloud data provided by the point cloud image within the ROI range. Thereby precise positioning of each knuckle point.
在104中,该遥控装置可根据该指关节点的位置移动进行移动轨迹拟合。At 104, the remote control device can perform a movement trajectory fit based on the positional movement of the knuckle joint point.
在一个实施例中,该遥控装置还可以根据预设的滤波函数和遥控装置的姿态信息,去除遥控装置自身的抖动造成的移动轨迹的位置偏差,以实现平滑滤波处理,并得到指关节点的该移动轨迹。In an embodiment, the remote control device may further remove the positional deviation of the movement trajectory caused by the shaking of the remote control device according to the preset filter function and the posture information of the remote control device, to implement smoothing filtering processing, and obtain the knuckle point. The movement track.
在105中,该遥控装置可以根据该移动轨迹确定出悬浮控制动作,并生成对应的控制指令。例如,遥控装置拟合出水平向右的移动轨迹,那么该悬浮控制动作就是控制该飞行器水平向右飞行的动作,该控制指令就是控制该飞行器水平向右飞行的指令。In 105, the remote control device can determine a hovering control action according to the movement trajectory and generate a corresponding control command. For example, if the remote control device fits a horizontal to right movement trajectory, then the levitation control action is to control the aircraft to fly horizontally to the right. The control command is an instruction to control the aircraft to fly horizontally to the right.
在106中,该遥控装置可以将该控制指令通过无线链路(例如蜂窝移动数据网、蓝牙、红外等)发送至无人机,以使该无人机按照该控制指令的指示飞行。At 106, the remote control device can transmit the control command to the drone via a wireless link (e.g., cellular mobile data network, Bluetooth, infrared, etc.) to cause the drone to fly in accordance with the indication of the control command.
可知,操作者可以在不接触遥控装置的情况下,实现控制飞行器飞行,既打破了人为接触遥控装置的局限,又实现了对飞行器的精准控制,且遥控装置的形式不局限于传统的摇杆,还可以是可穿戴设备、增强现实设备等,丰富了对飞行器的控制方式,提高了遥控装置的智能性。It can be seen that the operator can control the flight of the aircraft without touching the remote control device, which breaks the limitation of the artificial contact remote control device and realizes the precise control of the aircraft, and the form of the remote control device is not limited to the traditional rocker. It can also be a wearable device, an augmented reality device, etc., which enriches the control mode of the aircraft and improves the intelligence of the remote control device.
为了更清楚的描述,下面描述本发明实施例中所描述的飞行控制方法。请参阅图3,为本发明实施例提供的一种飞行控制方法的流程示意图,图3所示的方法可包括:For a clearer description, the flight control method described in the embodiment of the present invention will be described below. FIG. 3 is a schematic flowchart of a flight control method according to an embodiment of the present invention. The method shown in FIG. 3 may include:
S301、检测目标对象上的特征位置区域在空间中的移动轨迹,并基于所述移动轨迹确定悬浮控制动作。S301. Detect a movement trajectory of a feature position area on the target object in the space, and determine a levitation control action based on the movement trajectory.
需要说明的是,本发明实施例的执行主体可以是遥控装置,该遥控装置用于远程控制飞行器飞行。It should be noted that the execution body of the embodiment of the present invention may be a remote control device for remotely controlling aircraft flight.
在一个实施例中,所述遥控装置为可穿戴设备或增强现实设备。In one embodiment, the remote control device is a wearable device or an augmented reality device.
在一个实施例中,所述可穿戴设备为智能手表、智能眼镜、智能手环中的任意一种或多种;所述增强现实设备为头戴式显示器。 In one embodiment, the wearable device is any one or more of a smart watch, smart glasses, and a smart bracelet; the augmented reality device is a head mounted display.
在一个实施例中,该遥控装置检测目标对象上的特征位置区域在空间中的移动轨迹,具体包括:获取探测区域的图像特征信息;从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹。In an embodiment, the remote control device detects a movement trajectory of the feature location area on the target object in the space, and specifically includes: acquiring image feature information of the detection area; and determining the target object from the image feature information of the detection area. The movement track of the feature position area on the space.
需要说明的是,该探测区域可以是遥控装置上的深度信息采集装置可以探测到的区域。It should be noted that the detection area may be an area that can be detected by the depth information collection device on the remote control device.
还需要说明的是,该图像特征信息可以用于表示该探测区域范围内的场景图像中的特征信息。It should also be noted that the image feature information can be used to represent feature information in the scene image within the range of the detection region.
在一个实施例中,如图2所示,该遥控装置可以是智能手表,该探测区域可以是该智能手表的表盘上方,两条虚线之间的区域,该遥控装置可以采集到该探测区域内的图像特征信息。In an embodiment, as shown in FIG. 2, the remote control device may be a smart watch, and the detection area may be an area above the dial of the smart watch and between two broken lines, and the remote control device may collect the detection area. Image feature information.
在一些可行的实施方式中,该遥控装置可以实时的采集图像,并获取该图像中的图像特征信息,或者按照预设时间来获取该图像中的图像特征信息,其中,每一帧图像提供的图像特征信息可以对应着一个时间,例如12点30分10秒拍摄到的图像提供的图像特征信息,对应的时间就可以为12点30分10秒,当前时间就可以对应着当前帧图像提供的图像特征信息。In some feasible implementation manners, the remote control device may acquire an image in real time, acquire image feature information in the image, or acquire image feature information in the image according to a preset time, where each frame image is provided. The image feature information may correspond to image feature information provided by an image captured at a time of, for example, 12:30:10, and the corresponding time may be 12:30:10, and the current time may correspond to the current frame image. Image feature information.
其中,该图像特征信息可以是当前帧图像中的图像特征信息,也可以是连续多帧图像中的图像特征信息等等,本发明实施例对此不作任何限制。The image feature information may be the image feature information in the current frame image, or may be the image feature information in the continuous multi-frame image, and the like, which is not limited in this embodiment of the present invention.
在一个实施例中,该遥控装置可以获取探测区域的当前帧图像,并提取该当前帧图像中的图像特征信息,并根据该图像特征信息检测目标对象上的特征位置区域在空间中的移动轨迹。In an embodiment, the remote control device may acquire a current frame image of the detection area, extract image feature information in the current frame image, and detect a movement trajectory of the feature position area on the target object in the space according to the image feature information. .
在一个实施例中,该遥控装置从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹之前,还包括:检测所述探测区域中是否存在所述目标对象;如果存在目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第一频率。In an embodiment, the remote control device, before determining the movement trajectory of the feature location area on the target object in the image from the image feature information of the detection area, further includes: detecting whether the detection area exists a target object; if there is a target object, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the first frequency.
在一个实施例中,所述目标对象为手,所述目标对象上的特征位置区域为手上的指关节点。In one embodiment, the target object is a hand, and the feature location area on the target object is an knuckle point on the hand.
在一个实施例中,该目标对象还可以是其他生物特征部位,例如眼睛、嘴巴、头部等等,该目标对象上的特征区域还可以是眼睛的瞳孔,嘴巴的唇峰、头部的头发等等,本发明对此不作任何限制。 In one embodiment, the target object may also be other biometric parts, such as eyes, mouth, head, etc., and the feature area on the target object may also be the pupil of the eye, the lip of the mouth, the hair of the head. Etc., the present invention does not impose any limitation on this.
在一些可行的实施方式中,该遥控装置可以在提取该当前帧图像中的图像特征信息之后,根据该图像特征信息确定是否存在该目标对象,如果存在,则将获取所述探测区域的图像特征信息时的获取频率调整至第一频率。In some possible implementations, the remote control device may determine, according to the image feature information, whether the target object exists after extracting the image feature information in the current frame image, and if present, acquire the image feature of the detection region. The acquisition frequency at the time of information is adjusted to the first frequency.
需要说明的是,该第一频率例如可以是50Hz,100Hz等较高的获取频率。也就是说,如果该遥控装置检测到该目标对象时,那么该遥控装置此时的获取频率可以为第一频率,可以便于对该目标对象的移动轨迹进行拟合。It should be noted that the first frequency may be, for example, a high acquisition frequency such as 50 Hz, 100 Hz, or the like. That is to say, if the remote control device detects the target object, the acquisition frequency of the remote control device at this time may be the first frequency, which may facilitate fitting the movement trajectory of the target object.
在一个实施例中,如果不存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第二频率。In one embodiment, if the target object is not present, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the second frequency.
需要说明的是,该第二频率例如可以是5Hz,10Hz等较低的获取频率。也就是说,如果该遥控装置检测到不存在该目标对象时,该遥控装置此时的获取频率可以为第二频率,可以降低该遥控装置的功耗,提高遥控装置的使用时间。It should be noted that the second frequency may be, for example, a lower acquisition frequency such as 5 Hz, 10 Hz, or the like. That is to say, if the remote control device detects that the target object does not exist, the acquisition frequency of the remote control device may be the second frequency, which may reduce the power consumption of the remote control device and increase the usage time of the remote control device.
在一个实施例中,在所述第二频率下,所述遥控装置处于休眠模式,所述方法还包括:若接收到唤醒指令,则将获取所述探测区域的图像特征信息时的获取频率从所述第二频率调整至所述第一频率;其中,所述第一频率高于所述第二频率。In one embodiment, the remote control device is in a sleep mode at the second frequency, the method further comprising: if receiving the wake-up command, acquiring frequency of the image feature information of the detection region from The second frequency is adjusted to the first frequency; wherein the first frequency is higher than the second frequency.
还需要说明的是,该唤醒指令例如可以是通过惯性测量单元识别晃动手腕的操作指令。或者在该遥控装置为智能手环、智能手表时,通过识别到抬手的动作且表盘正面朝上,便可以确定接收到唤醒指令。It should also be noted that the wake-up command may be, for example, an operation command for recognizing a wrist by an inertial measurement unit. Alternatively, when the remote control device is a smart wristband or a smart watch, it is determined that the wake-up command is received by recognizing the action of raising the hand and the face of the dial facing up.
在一些可行的实施方式中,该遥控装置若接收到唤醒指令,则可以确定需要进入工作模式(即检测目标对象的模式),该工作模式对应的获取频率可以为第一频率,该遥控装置便可以将获取频率从第二频率调整至第一频率。In some feasible implementation manners, if the remote control device receives the wake-up command, it may determine that the working mode (ie, the mode of detecting the target object) needs to be entered, and the acquiring frequency corresponding to the working mode may be the first frequency, and the remote control device may The acquisition frequency can be adjusted from the second frequency to the first frequency.
在一个实施例中,所述从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹,包括:根据探测区域的图像特征信息确定目标对象上的特征位置区域;根据所述探测区域的至少两帧图像特征信息确定出所述特征位置区域在空间中的移动轨迹。In an embodiment, determining the movement trajectory of the feature location area on the target object in the image from the image feature information of the detection area comprises: determining features on the target object according to image feature information of the detection area a location area; determining a movement trajectory of the feature location area in the space according to at least two frames of image feature information of the detection area.
需要说明的是,该探测区域的至少两帧图像提供的图像特征信息,可以是前后连续两帧图像提供的图像特征信息。在一个实施例中,该遥控装置通过当前帧图像提供的图像特征信息确定了该目标对象上的特征位置区域,便可以根 据该当前帧图像提供的图像特征信息和该当前帧图像特征信息的下一帧图像提供的图像特征信息确定出该特征位置区域在空间中的移动轨迹。It should be noted that the image feature information provided by the at least two frames of the detection area may be image feature information provided by two consecutive frames of images. In an embodiment, the remote control device determines the feature location area on the target object by using the image feature information provided by the current frame image, and then the root device can And according to the image feature information provided by the current frame image and the image feature information provided by the next frame image of the current frame image feature information, the movement trajectory of the feature location region in the space is determined.
还需要说明的是,该移动轨迹可以是指该特征位置区域在空间中的位置变化轨迹。It should also be noted that the moving track may refer to a position change track of the feature position area in space.
在一个实施例中,所述探测区域的图像特征信息为所述探测区域的深度信息。In an embodiment, the image feature information of the detection area is depth information of the detection area.
在一些可行的实施方式中,该遥控装置可以首先获取该探测区域内的深度图像,然后从该深度图像中确定出深度信息,并根据该深度信息所指示的深度变化情况、目标对象的轮廓移动的方向、大小等参数,确定出该目标对象上的特征位置区域在空间中的移动轨迹。In some feasible implementation manners, the remote control device may first acquire a depth image in the detection area, and then determine depth information from the depth image, and according to the depth change indicated by the depth information, the contour movement of the target object The direction, size and other parameters determine the movement trajectory of the feature location area on the target object in space.
其中,该遥控装置例如可以通过双目立体视觉模块,3D TOF模块、深度传感器等来获取该探测区域中的图像特征信息,并进一步检测该探测区域中是否存在该目标对象。The remote control device may acquire image feature information in the detection area by using a binocular stereo vision module, a 3D TOF module, a depth sensor, or the like, and further detect whether the target object exists in the detection area.
在一个实施例中,所述根据探测区域的深度信息确定目标对象上的特征位置区域,包括:根据所述探测区域的深度信息在参考坐标系进行投影处理,并生成在所述参考坐标系上的点云图像,所述参考坐标系是根据所述遥控装置确定的;根据所述点云图像确定目标对象的轮廓信息;根据所述目标对象的轮廓信息确定出特征位置区域的位置信息,以确定出所述目标对象上的特征位置区域。In an embodiment, the determining the feature location area on the target object according to the depth information of the detection area comprises: performing projection processing on the reference coordinate system according to the depth information of the detection area, and generating on the reference coordinate system a point cloud image, the reference coordinate system is determined according to the remote control device; determining contour information of the target object according to the point cloud image; determining position information of the feature position region according to the contour information of the target object, A feature location area on the target object is determined.
需要说明的是,该参考坐标系可以是以该遥控装置为中心建立的坐标系。举例来说,可以取该遥控装置的表面的中心点或者其他点作为该参考坐标系的原点,然后以该遥控装置的表面(例如智能手表的表盘)建立该参考坐标系的横轴和纵轴。It should be noted that the reference coordinate system may be a coordinate system centered on the remote control device. For example, the center point or other points of the surface of the remote control device may be taken as the origin of the reference coordinate system, and then the horizontal axis and the vertical axis of the reference coordinate system are established with the surface of the remote control device (for example, the dial of the smart watch). .
还需要说明的是,深度信息可以是根据从深度信息采集装置到探测区域中各点的距离(深度)值作为像素值的图像中确定。It should also be noted that the depth information may be determined from an image in which the distance (depth) value from each point in the detection area to the detection area is taken as a pixel value.
还需要说明的是,当光束照射到目标对象的表面时,所反射的光会携带目标对象的方位、距离等信息,如果将光束按照预设的轨迹进行扫描,便会边扫描边记录到反射的信息,当扫描十分精细时,便能够得到大量的光点,因而就 可形成点云图像。也就是说,点云图像可以表示出目标对象的方位、距离等信息。It should also be noted that when the light beam is irradiated onto the surface of the target object, the reflected light carries information such as the orientation and distance of the target object. If the light beam is scanned according to the preset trajectory, the reflection is recorded while scanning. Information, when the scan is very fine, you can get a lot of light spots, so A point cloud image can be formed. That is to say, the point cloud image can indicate information such as the orientation and distance of the target object.
在一些可行的实施方式中,该遥控装置可以首先确定出该探测区域的深度图表示的深度信息,然后将该深度信息投影到参考坐标系中,并在该参考坐标系中生成点云图像,该点云图像可以表示出目标对象的方位、距离等信息,根据方位、距离等信息可以确定出目标对象的轮廓信息,轮廓中点云数据密集的位置,可以认为是该目标对象上的特征位置区域。In some feasible implementation manners, the remote control device may first determine depth information represented by the depth map of the detection area, then project the depth information into a reference coordinate system, and generate a point cloud image in the reference coordinate system, The point cloud image can represent information such as the orientation and distance of the target object, and the contour information of the target object can be determined according to the information such as the azimuth and the distance. The position of the point cloud data in the contour is dense, and can be regarded as the feature position on the target object. region.
在一个实施例中,所述根据所述目标对象的轮廓信息确定出特征位置区域的位置信息,包括:根据所述目标对象的轮廓信息确定出特征位置区域的初始位置信息;根据预设的滤波函数和遥控装置的姿态信息,对所述初始位置信息进行平滑滤波处理,得到所述特征位置区域的位置信息。In an embodiment, the determining the location information of the feature location area according to the profile information of the target object comprises: determining initial location information of the feature location area according to the profile information of the target object; filtering according to a preset The function and the posture information of the remote control device perform smoothing processing on the initial position information to obtain position information of the feature position area.
需要说明的是,该特征位置区域的位置信息可以用于表示特征位置区域自身的位置变化。It should be noted that the location information of the feature location area may be used to indicate the location change of the feature location area itself.
还需要说明的是,该特征位置区域的初始位置信息,可以包括由于遥控装置本身的移动而造成的特征位置区域的位置移动的信息。It should also be noted that the initial location information of the feature location area may include information of the location movement of the feature location area due to the movement of the remote control device itself.
在一些可行的实施方式中,该遥控装置可以通过预设的滤波函数,并结合惯性测量单元测得的该遥控装置的姿态信息,去除由于该遥控装置本身的移动而造成的特征位置区域的位置移动,得到该特征位置区域的位置信息。In some feasible implementation manners, the remote control device can remove the position of the feature location area caused by the movement of the remote control device by using a preset filter function and the attitude information of the remote control device measured by the inertial measurement unit. Move to obtain the location information of the feature location area.
在一个实施例中,所述检测目标对象上的特征位置区域在空间中的移动轨迹,包括:通过设置在特征位置区域上的传感器获取所述目标对象上的特征位置区域的移动感测数据;根据所述移动感测数据得到所述目标对象上的特征位置区域在空间中的移动轨迹。In one embodiment, the detecting a movement trajectory of the feature location area on the target object in the space comprises: acquiring motion sensing data of the feature location area on the target object by using a sensor disposed on the feature location area; Obtaining a movement trajectory of the feature location area on the target object in the space according to the motion sensing data.
还需要说明的是,该特征位置区域上可以预先设置传感器,该传感器例如可以是温度传感器、红外传感器等等,本发明实施例对此不作限制。It should be noted that the sensor may be pre-set in the area of the feature, and the sensor may be, for example, a temperature sensor, an infrared sensor, or the like, which is not limited in the embodiment of the present invention.
还需要说明的是,该传感器可以与该遥控装置进行无线连接,该传感器将移动感测数据通过无线传输的方式发送给该遥控装置。It should also be noted that the sensor can be wirelessly connected to the remote control device, and the sensor transmits the mobile sensing data to the remote control device by wireless transmission.
在一些可行的实施方式中,操作者可以戴上手套,该手套的指关节点处设置有该传感器,操作者可以发出一些控制动作,该传感器将这些控制动作转换 成移动感测数据发送给该遥控装置,该遥控装置便可以根据该移动感测数据进行数据拟合,得到操作者的指关节点在空间中的移动轨迹。In some possible embodiments, the operator can wear gloves, the sensor is provided at the knuckle point of the glove, and the operator can issue some control actions, and the sensor converts these control actions The motion sensing data is sent to the remote control device, and the remote control device can perform data fitting according to the motion sensing data to obtain a movement track of the operator's knuckle point in the space.
在一个实施例中,所述探测区域的图像特征信息为所述探测区域的颜色信息或者红外信息。In an embodiment, the image feature information of the detection area is color information or infrared information of the detection area.
需要说明的是,该颜色信息例如可以是在探测区域内所摄取到的图像中的颜色信息,例如,该图像为摄像装置摄取到的RGB(Red Green Blue,红绿蓝)图像。该红外信息例如可以是红外摄像装置摄取到的图像所表示的信息。It should be noted that the color information may be, for example, color information in an image captured in the detection area, for example, the image is an RGB (Red Green Blue) image captured by the imaging device. The infrared information may be, for example, information represented by an image taken by the infrared camera.
在一些可行的实施方式中,可以基于深度学习从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域。在对目标对象上的特征位置区域进行定位之后,可以根据目标对象上的特征位置区域的位置变化情况,得到目标对象上的特征位置区域在空间中的移动轨迹。In some possible implementations, the feature location area on the target object may be determined from image feature information of the detection area based on depth learning. After the feature position area on the target object is located, the movement track of the feature position area on the target object in the space may be obtained according to the position change of the feature position area on the target object.
还需要说明的是,在该遥控装置确定了该目标对象上的特征位置区域在空间中的移动轨迹之后,可以根据该移动轨迹确定出悬浮控制动作。It should also be noted that after the remote control device determines the movement trajectory of the feature position area on the target object in space, the levitation control action can be determined according to the movement trajectory.
其中,该悬浮控制动作可以是指操作者在未接触该遥控装置时,所触发的控制动作。例如,如图2所示的手掌(目标对象)在智能手表(遥控装置)上方的空间区域内发出的控制动作。The suspension control action may refer to a control action triggered by the operator when the remote control device is not touched. For example, the palm (target object) shown in FIG. 2 performs a control action in a space area above the smart watch (remote control device).
S302、根据所述悬浮控制动作生成控制指令。S302. Generate a control instruction according to the suspension control action.
需要说明的是,该控制指令可以用于控制该飞行器飞行。It should be noted that the control command can be used to control the flight of the aircraft.
在一些可行的实施方式中,悬浮控制动作与控制指令可以具有对应关系。具体的,该对应关系可以是方向、角度的对应。例如,悬浮控制动作是一个水平向左的动作,那么,该控制指令便可以是控制该飞行器水平向左的指令。In some possible implementations, the suspension control action and the control command may have a corresponding relationship. Specifically, the correspondence may be a correspondence between a direction and an angle. For example, the hovering control action is a horizontal left motion, then the control command may be an instruction to control the aircraft horizontally to the left.
在一个实施例中,所述根据所述悬浮控制动作生成控制指令,包括:根据确定的轮廓信息得到悬浮控制动作的类型和所述特征位置区域的运动矢量;根据所述悬浮控制动作的类型和所述特征位置区域的运动矢量生成控制指令。In one embodiment, the generating the control instruction according to the suspension control action comprises: obtaining a type of the suspension control action and a motion vector of the feature location area according to the determined contour information; according to the type of the suspension control action The motion vector of the feature location area generates a control instruction.
在一个实施例中,所述特征位置区域的运动矢量包括:根据至少两帧深度信息确定的所述特征位置区域的运动方向和运动幅度。In one embodiment, the motion vector of the feature location area includes a motion direction and a motion amplitude of the feature location area determined according to at least two frame depth information.
需要说明的是,该特征位置区域的运动方向可以是任意的方向,例如上、下、左、右、左上、右下、左下、右上等等,本发明实施例对此不作任何限制。It should be noted that the moving direction of the feature location area may be any direction, such as upper, lower, left, right, upper left, lower right, lower left, upper right, and the like, which is not limited in this embodiment of the present invention.
还需要说明的是,该悬浮控制动作的类型可以用于指示该悬浮控制动作的 方向,例如可以是控制向上的类型、控制向下的类型、控制向左的类型、控制向右的类型等等。It should also be noted that the type of the suspension control action can be used to indicate the suspension control action. The direction may be, for example, a type that controls the upward direction, a type that controls the downward direction, a type that controls the leftward, a type that controls the rightward, and the like.
在一个实施例中,该目标对象可为手掌,该目标对象的特征位置区域为指关节点,该遥控装置在对该指关节点进行定位之后,并确定出悬浮控制动作,然后,该遥控装置可以通过分类器判断该悬浮控制动作的类型,例如为控制向下的类型,并根据至少两帧深度信息提供的深度信息,计算出每个指关节点的运动矢量,该运动矢量可包括运动方向、运动幅度等参数。该遥控装置可以确定出控制指令,该控制指令可以用于控制该飞行器按照该运动矢量中的参数向下飞行。In one embodiment, the target object may be a palm, the feature location area of the target object is a joint point, and the remote control device determines the suspension control action after positioning the joint finger point, and then the remote control device The type of the levitation control action may be determined by the classifier, for example, to control the downward type, and the motion vector of each knuckle point may be calculated according to the depth information provided by the at least two frames of depth information, and the motion vector may include a motion direction. , the magnitude of the movement and other parameters. The remote control device can determine a control command that can be used to control the aircraft to fly downward in accordance with parameters in the motion vector.
S303、通过无线链路将所述控制指令发送至飞行器,以控制所述飞行器飞行。S303. Send the control command to the aircraft through a wireless link to control the aircraft to fly.
需要说明的是,该无线链路例如可以是蜂窝移动数据网、无线保真(Wireless Fidelity,WiFi),红外、蓝牙等等,本发明对此不作任何限制。It should be noted that the wireless link may be, for example, a cellular mobile data network, a wireless fidelity (WiFi), an infrared, a Bluetooth, etc., and the present invention does not impose any limitation.
在一些可行的实施方式中,该遥控装置可以通过无线链路将控制指令发送给飞行器,飞行器在接收到该控制指令之后,可以根据该控制指令的指示进行飞行。例如,控制指令指示水平向右飞行,该飞行器便可以根据该控制指令水平向右飞行。In some possible implementations, the remote control device can transmit a control command to the aircraft via a wireless link, and after receiving the control command, the aircraft can fly according to the instruction of the control command. For example, the control command indicates that the flight is horizontal to the right, and the aircraft can fly to the right according to the level of the control command.
可见,在本发明实施例中,遥控装置可以检测目标对象上的特征位置区在空间中的移动轨迹,并确定出对应的悬浮控制动作,根据该悬浮控制动作生成控制指令,最后通过无线链路将控制指令发送至飞行器,可以在操作者不接触遥控装置的情况下,实现控制飞行器飞行,既打破了人为接触遥控装置的局限,又实现了对飞行器的精准控制,丰富了对飞行器的控制方式,提高了遥控装置的智能性。It can be seen that, in the embodiment of the present invention, the remote control device can detect the movement trajectory of the feature location area on the target object in the space, and determine the corresponding levitation control action, generate a control instruction according to the levitation control action, and finally pass the wireless link. Sending the control command to the aircraft can control the flight of the aircraft without the operator touching the remote control device, which breaks the limitation of the artificial contact with the remote control device, realizes the precise control of the aircraft, and enriches the control mode of the aircraft. Improves the intelligence of the remote control device.
请参阅图4,是本发明实施例提供的另一种飞行控制方法的流程示意图。如图4所示的方法可包括:Please refer to FIG. 4 , which is a schematic flowchart diagram of another flight control method according to an embodiment of the present invention. The method as shown in FIG. 4 may include:
S401、检测目标对象上的特征位置区域在空间中的移动轨迹。S401. Detect a movement track of a feature position area on the target object in the space.
在一个实施例中,在检测目标对象上的特征位置区域在空间中的移动轨迹之前,遥控装置可以获取探测区域的深度信息;根据所述探测区域的深度信息 检测是否存在目标对象;如果存在目标对象,则执行所述检测目标对象上的特征位置区域在空间中的移动轨迹。In an embodiment, the remote control device may acquire depth information of the detection area before detecting a movement trajectory of the feature position area on the target object in the space; according to the depth information of the detection area It is detected whether there is a target object; if there is a target object, a movement trajectory of the feature position area on the detection target object in space is performed.
在一个实施例中,所述探测区域中叠加显示有虚拟影像。In one embodiment, a virtual image is superimposed on the detection area.
需要说明的是,该虚拟影像可以是由虚拟现实设备、增强现实设备等投影产生的非现实影像。It should be noted that the virtual image may be a non-realistic image generated by a virtual reality device, an augmented reality device, or the like.
S402、根据目标对象的位置信息,在所述探测区域中生成并显示所述虚拟影像。S402. Generate and display the virtual image in the detection area according to location information of the target object.
在一个实施例中,该虚拟影像可以由该遥控装置叠加显示在该探测区域中。In one embodiment, the virtual image may be superimposed and displayed in the detection area by the remote control device.
还需要说明的是,该遥控装置可以将该虚拟影像显示在该目标对象的正下方、正上方等任意方位,本发明对此不作任何限制。It should be noted that the remote control device can display the virtual image in any orientation directly below, directly above the target object, and the present invention does not impose any limitation.
在一个实施例中,该遥控装置可以为增强现实设备a,探测区域可以为该增强现实设备a视线正前方的区域,增强现实设备a可以在该探测区域内检测到目标对象(例如为手掌)时,将该虚拟影像显示在手掌的正下方,该虚拟影像例如可以为虚拟飞机。In one embodiment, the remote control device may be an augmented reality device a, and the detection area may be an area directly in front of the line of sight of the augmented reality device a, and the augmented reality device a may detect the target object (eg, a palm) within the detection area. The virtual image is displayed directly below the palm, and the virtual image can be, for example, a virtual airplane.
在一个实施例中,该虚拟影像也可以由其他设备叠加显示在该探测区域中。In one embodiment, the virtual image may also be superimposed and displayed in the detection area by other devices.
在一个实施例中,该遥控装置为智能手表,操作者可以头戴增强现实设备b,该增强现实设备b可以与该智能手表建立连接,然后,该遥控装置在检测到目标对象时,该增强现实设备b可以在智能手表的探测区域投影显示出虚拟影像,例如为虚拟飞机。In one embodiment, the remote control device is a smart watch, the operator can wear an augmented reality device b, the augmented reality device b can establish a connection with the smart watch, and then the remote device detects the target object, the enhancement The reality device b can project a virtual image on the detection area of the smart watch, such as a virtual aircraft.
S403、根据所述移动轨迹控制所述虚拟影像移动。S403. Control the virtual image movement according to the movement trajectory.
需要说明的是,该目标对象的特征位置区域的移动轨迹可以作为该虚拟影像的移动轨迹。It should be noted that the movement trajectory of the feature position area of the target object can be used as the movement trajectory of the virtual image.
在一个实施例中,该目标对象可以是手掌,该目标对象的特征位置区域可以是指关节点,遥控装置拟合出来的移动轨迹可以是指关节点水平向右移动,那么,该虚拟影像也可以按照该移动轨迹水平向右移动。In one embodiment, the target object may be a palm, the feature location area of the target object may be a joint point, and the movement track fitted by the remote control device may mean that the joint point moves horizontally to the right, then the virtual image is also It can be moved to the right horizontally according to the movement trajectory.
在一个实施例中,该虚拟影像可以是一虚拟飞机,操作者可以在探测区域“捏”住该虚拟飞机,操作者的指关节点水平向右移动,虚拟飞机也可以随着操 作者的指关节点水平向右移动。此时,该遥控装置还可以根据该指关节点的移动轨迹得到悬浮控制动作,并确定出对应的控制指令,将该控制指令发送至飞行器,控制飞行器按照控制指令飞行。In one embodiment, the virtual image may be a virtual aircraft, and the operator may “pinch” the virtual aircraft in the detection area, and the operator's knuckles point moves horizontally to the right, and the virtual aircraft can also follow the operation. The author's knuckle points move horizontally to the right. At this time, the remote control device can also obtain a suspension control action according to the movement trajectory of the knuckle joint point, and determine a corresponding control command, send the control command to the aircraft, and control the aircraft to fly according to the control instruction.
可见,在本发明实施例中,遥控装置可以在探测区域显示虚拟影像,并根据目标对象上的特征位置区域在空间中的移动轨迹,控制虚拟影像移动,增强了对飞行器进行远程控制时的趣味性,同时也提高了遥控装置的智能性。It can be seen that, in the embodiment of the present invention, the remote control device can display the virtual image in the detection area, and control the movement of the virtual image according to the movement trajectory of the feature position area on the target object in the space, thereby enhancing the interest in remote control of the aircraft. Sex, but also improve the intelligence of the remote control device.
本发明实施例提供一种遥控装置。请参阅图5,为本发明实施例提供的一种遥控装置的结构示意图,本实施例中所描述的遥控装置,包括:Embodiments of the present invention provide a remote control device. FIG. 5 is a schematic structural diagram of a remote control device according to an embodiment of the present invention. The remote control device described in this embodiment includes:
存储器501和处理器502;Memory 501 and processor 502;
所述存储器501,用于存储程序指令;The memory 501 is configured to store program instructions;
所述处理器502,用于执行所述存储器存储的程序指令,当程序指令被执行时,用于:The processor 502 is configured to execute the program instructions stored in the memory, when the program instructions are executed, to:
检测目标对象上的特征位置区域在空间中的移动轨迹,并基于所述移动轨迹确定悬浮控制动作;Detecting a movement trajectory of the feature position area on the target object in the space, and determining a levitation control action based on the movement trajectory;
根据所述悬浮控制动作生成控制指令;Generating a control instruction according to the suspension control action;
通过无线链路将所述控制指令发送至飞行器,以控制所述飞行器飞行。The control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
在一个实施例中,所述处理器502检测目标对象上的特征位置区域在空间中的移动轨迹之前,还用于:获取探测区域的深度信息;根据所述探测区域的深度信息检测是否存在目标对象;如果存在目标对象,则执行所述检测目标对象上的特征位置区域在空间中的移动轨迹。In an embodiment, the processor 502 is configured to: acquire depth information of the detection area before detecting a movement trajectory of the feature location area on the target object in the space; and detect whether the target exists according to the depth information of the detection area. An object; if there is a target object, performing a movement trajectory of the feature position area on the detection target object in the space.
在一个实施例中,所述处理器502检测目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:In an embodiment, when the processor 502 detects a movement trajectory of a feature location area on the target object in the space, the processor 502 is specifically configured to:
获取探测区域的图像特征信息;Obtaining image feature information of the detection area;
从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹。A movement trajectory of the feature position area on the target object in the space is determined from the image feature information of the detection area.
在一个实施例中,所述探测区域的图像特征信息为所述探测区域的深度信息。 In an embodiment, the image feature information of the detection area is depth information of the detection area.
在一个实施例中,所述处理器502还用于:检测所述探测区域中是否存在所述目标对象;如果存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第一频率。In an embodiment, the processor 502 is further configured to: detect whether the target object exists in the detection area; if the target object exists, acquire frequency when acquiring image feature information of the detection area Adjust to the first frequency.
在一个实施例中,所述处理器502还用于:如果不存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第二频率。In an embodiment, the processor 502 is further configured to: if the target object does not exist, adjust an acquisition frequency when acquiring image feature information of the detection area to a second frequency.
在一个实施例中,在所述第二频率下,所述遥控装置处于休眠模式,所述处理器502还用于:若接收到唤醒指令,则将获取所述探测区域的图像特征信息时的获取频率从所述第二频率调整至所述第一频率;其中,所述第一频率高于所述第二频率。In an embodiment, the remote control device is in a sleep mode at the second frequency, and the processor 502 is further configured to: when the wake-up instruction is received, the image feature information of the detection area is acquired The acquisition frequency is adjusted from the second frequency to the first frequency; wherein the first frequency is higher than the second frequency.
在一个实施例中,所述处理器502从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:根据探测区域的图像特征信息确定目标对象上的特征位置区域;根据所述探测区域的至少两帧图像提供的图像特征信息确定出所述特征位置区域在空间中的移动轨迹。In an embodiment, when the processor 502 determines the movement trajectory of the feature location area on the target object in the space from the image feature information of the detection area, the processor 502 is specifically configured to: according to the image feature information of the detection area Determining a feature location area on the target object; determining a movement trajectory of the feature location area in the space according to the image feature information provided by the at least two frames of the detection area.
在一个实施例中,所述探测区域的图像特征信息为所述探测区域的深度信息。In an embodiment, the image feature information of the detection area is depth information of the detection area.
在一个实施例中,所述处理器502根据探测区域的图像特征信息确定目标对象上的特征位置区域时,具体用于:根据所述探测区域的深度信息在参考坐标系进行投影处理,并生成在所述参考坐标系上的点云图像,所述参考坐标系是根据所述遥控装置确定的;根据所述点云图像确定目标对象的轮廓信息;根据所述目标对象的轮廓信息确定出特征位置区域的位置信息,以确定出所述目标对象上的特征位置区域。In an embodiment, when the processor 502 determines the feature location area on the target object according to the image feature information of the detection area, the processor 502 is specifically configured to: perform projection processing on the reference coordinate system according to the depth information of the detection area, and generate a point cloud image on the reference coordinate system, the reference coordinate system is determined according to the remote control device; determining contour information of the target object according to the point cloud image; determining a feature according to the contour information of the target object Position information of the location area to determine a feature location area on the target object.
在一个实施例中,所述处理器502根据所述目标对象的轮廓信息确定出特征位置区域的位置信息时,具体用于:根据所述目标对象的轮廓信息确定出特征位置区域的初始位置信息;根据预设的滤波函数和遥控装置的姿态信息,对所述初始位置信息进行平滑滤波处理,得到所述特征位置区域的位置信息。In an embodiment, when the processor 502 determines the location information of the feature location area according to the profile information of the target object, the method is specifically configured to: determine initial location information of the feature location area according to the profile information of the target object. And performing smoothing processing on the initial position information according to the preset filter function and the posture information of the remote control device to obtain position information of the feature position area.
在一个实施例中,所述处理器502根据所述悬浮控制动作生成控制指令时,具体用于:根据确定的轮廓信息得到悬浮控制动作的类型和所述特征位置 区域的运动矢量;根据所述悬浮控制动作的类型和所述特征位置区域的运动矢量生成控制指令。In an embodiment, when the processor 502 generates a control instruction according to the levitation control action, the method is specifically configured to: obtain a type of the levitation control action and the feature position according to the determined contour information. a motion vector of the region; generating a control instruction according to the type of the suspension control action and the motion vector of the feature location region.
在一个实施例中,所述特征位置区域的运动矢量包括:根据至少两帧深度信息确定的所述特征位置区域的运动方向和运动幅度。In one embodiment, the motion vector of the feature location area includes a motion direction and a motion amplitude of the feature location area determined according to at least two frame depth information.
在一个实施例中,所述处理器502检测目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:通过设置在特征位置区域上的传感器获取所述目标对象上的特征位置区域的移动感测数据;根据所述移动感测数据得到所述目标对象上的特征位置区域在空间中的移动轨迹。In an embodiment, when the processor 502 detects a movement trajectory of the feature location area on the target object in the space, the processor 502 is configured to: acquire a feature location area on the target object by using a sensor disposed on the feature location area Moving sensing data; obtaining a moving trajectory of the feature location area on the target object in the space according to the motion sensing data.
在一个实施例中,所述探测区域的图像特征信息为所述探测区域的颜色信息或者红外信息;所述处理器502从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:基于深度学习从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域;获取所述目标对象的特征位置区域在空间中的移动轨迹。In one embodiment, the image feature information of the detection area is color information or infrared information of the detection area; the processor 502 determines a feature position on the target object from image feature information of the detection area. When the trajectory of the region is in the space, the method is specifically: determining, according to the depth learning, the feature location region on the target object from the image feature information of the detection region; acquiring the feature location region of the target object in the space Move the track.
在一个实施例中,在所述探测区域中叠加显示有虚拟影像。In one embodiment, a virtual image is superimposed and displayed in the detection area.
在一个实施例中,所述处理器502还用于:根据目标对象的位置信息,在所述探测区域中生成并显示所述虚拟影像。In an embodiment, the processor 502 is further configured to: generate and display the virtual image in the detection area according to location information of the target object.
在一个实施例中,所述处理器502还用于:根据所述移动轨迹控制所述虚拟影像移动。In an embodiment, the processor 502 is further configured to: control the virtual image movement according to the movement trajectory.
在一个实施例中,所述遥控装置为可穿戴设备或增强现实设备。In one embodiment, the remote control device is a wearable device or an augmented reality device.
在一个实施例中,所述可穿戴设备为智能手表、智能眼镜、智能手环中的任意一种或多种;所述增强现实设备为头戴式显示器。In one embodiment, the wearable device is any one or more of a smart watch, smart glasses, and a smart bracelet; the augmented reality device is a head mounted display.
在一个实施例中,所述目标对象为手,所述目标对象上的特征位置区域为手上的指关节点。In one embodiment, the target object is a hand, and the feature location area on the target object is an knuckle point on the hand.
本发明实施例提供一种遥控系统。图6是本发明实施例提供的遥控系统的架构示意图。如图6所示,该遥控系统包括:至少一个摄像装置和/或至少一个传感器,其中,所述摄像装置包括红绿蓝摄像装置;飞行器;遥控装置。Embodiments of the present invention provide a remote control system. FIG. 6 is a schematic structural diagram of a remote control system according to an embodiment of the present invention. As shown in FIG. 6, the remote control system includes: at least one camera device and/or at least one sensor, wherein the camera device includes a red, green and blue camera device; an aircraft; a remote control device.
其中,该遥控装置601为上述本发明实施例中公开的遥控装置,原理和实现方式均与上述实施例类似,此处不再赘述。 The remote control device 601 is the remote control device disclosed in the foregoing embodiment of the present invention, and the principles and implementations are similar to the foregoing embodiments, and details are not described herein again.
其中,该摄像装置603可以设置在该遥控装置上,用于拍摄探测区域的深度信息。The camera 603 can be disposed on the remote control device for capturing depth information of the detection area.
在一个实施例中,该摄像装置603可以包括红绿蓝摄像装置,该红绿蓝摄像装置可以获取目标对象的特征位置区域的色彩图,该遥控装置601可以通过该色彩图对目标对象的特征位置区域进行定位和追踪,得到移动轨迹。In an embodiment, the camera device 603 may include a red, green and blue camera device, and the red, green and blue camera device may acquire a color map of a feature location area of the target object, and the remote control device 601 may use the color map to target the target object. The location area is positioned and tracked to obtain a moving track.
在一个实施例中,该传感器604可以设置在目标对象的特征位置区域处,该传感器604例如可以是温度传感器、距离传感器、红外传感器等等。In one embodiment, the sensor 604 can be disposed at a feature location area of the target object, such as a temperature sensor, a distance sensor, an infrared sensor, and the like.
在一个实施例中,该传感器604还可以设置在该遥控装置601上,用于获取探测区域的深度信息,该传感器604例如可以是深度传感器等。In one embodiment, the sensor 604 can also be disposed on the remote control device 601 for acquiring depth information of the detection area. The sensor 604 can be, for example, a depth sensor or the like.
具体地,遥控系统可应用于远程遥控飞机装置。其中,该遥控装置601可用于检测目标对象上的特征位置区域在空间中的移动轨迹,并基于该移动轨迹确定悬浮控制动作,根据该悬浮控制动作生成控制指令,通过无线链路将该控制指令发送至飞行器,以控制该飞行器飞行。In particular, the remote control system can be applied to remotely controlled aircraft devices. The remote control device 601 can be configured to detect a movement trajectory of the feature position area on the target object in the space, and determine a levitation control action based on the movement trajectory, generate a control instruction according to the levitation control action, and use the remote link to control the command. Send to the aircraft to control the flight of the aircraft.
需要说明的是,该遥控装置601可用于执行前述方法实施例所示的飞行控制方法,其具体实现过程可参照该方法实施例,在此不作赘述。It should be noted that the remote control device 601 can be used to perform the flight control method shown in the foregoing method embodiment, and the specific implementation process can refer to the method embodiment, and details are not described herein.
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。It should be noted that, for the foregoing various method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should understand that the present invention is not limited by the described action sequence. Because certain steps may be performed in other sequences or concurrently in accordance with the present invention. In the following, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.
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。A person skilled in the art can understand that all or part of the steps of the foregoing embodiments can be completed by a program to instruct related hardware. The program can be stored in a computer readable storage medium, and the storage medium can include: Flash disk, Read-Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.
以上对本发明实施例所提供的一种飞行控制方法、遥控器及遥控系统进行了详细介绍,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。 A flight control method, a remote controller and a remote control system provided by the embodiments of the present invention are described in detail. The principles and embodiments of the present invention are described in the following. The description of the above embodiments is only used for To help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in specific embodiments and application scopes. It should not be construed as limiting the invention.

Claims (39)

  1. 一种飞行控制方法,其特征在于,应用于遥控装置,所述遥控装置用于远程控制飞行器飞行,所述方法包括:A flight control method is characterized in that it is applied to a remote control device for remotely controlling aircraft flight, and the method includes:
    检测目标对象上的特征位置区域在空间中的移动轨迹,并基于所述移动轨迹确定悬浮控制动作;Detecting a movement trajectory of the feature position area on the target object in the space, and determining a levitation control action based on the movement trajectory;
    根据所述悬浮控制动作生成控制指令;Generating a control instruction according to the suspension control action;
    通过无线链路将所述控制指令发送至飞行器,以控制所述飞行器飞行。The control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
  2. 如权利要求1所述的方法,其特征在于,所述检测目标对象上的特征位置区域在空间中的移动轨迹,包括:The method according to claim 1, wherein the detecting a movement trajectory of the feature position area on the target object in the space comprises:
    获取探测区域的图像特征信息;Obtaining image feature information of the detection area;
    从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹。A movement trajectory of the feature position area on the target object in the space is determined from the image feature information of the detection area.
  3. 如权利要求2所述的方法,其特征在于,所述从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹之前,还包括:The method of claim 2, wherein the determining, before determining the movement trajectory of the feature location area on the target object in the image from the image feature information of the detection area, further comprises:
    检测所述探测区域中是否存在所述目标对象;Detecting whether the target object exists in the detection area;
    如果存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第一频率。If the target object exists, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the first frequency.
  4. 如权利要求3所述的方法,其特征在于,所述方法还包括:The method of claim 3, wherein the method further comprises:
    如果不存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第二频率。If the target object does not exist, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the second frequency.
  5. 如权利要求4所述的方法,其特征在于,在所述第二频率下,所述遥控装置处于休眠模式,所述方法还包括: The method of claim 4, wherein the remote control device is in a sleep mode at the second frequency, the method further comprising:
    若接收到唤醒指令,则将获取所述探测区域的图像特征信息时的获取频率从所述第二频率调整至所述第一频率;If the wake-up instruction is received, the acquisition frequency when acquiring the image feature information of the detection area is adjusted from the second frequency to the first frequency;
    其中,所述第一频率高于所述第二频率。Wherein the first frequency is higher than the second frequency.
  6. 如权利要求2所述的方法,其特征在于,所述从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹,包括:The method according to claim 2, wherein the determining a movement trajectory of the feature location area on the target object in the space from the image feature information of the detection area comprises:
    根据探测区域的图像特征信息确定目标对象上的特征位置区域;Determining a feature location area on the target object according to image feature information of the detection area;
    根据所述探测区域的至少两帧图像提供的图像特征信息确定出所述特征位置区域在空间中的移动轨迹。And determining, according to the image feature information provided by the at least two frames of the detection area, a movement trajectory of the feature location area in the space.
  7. 如权利要求2所述的方法,其特征在于,所述探测区域的图像特征信息为所述探测区域的深度信息。The method according to claim 2, wherein the image feature information of the detection area is depth information of the detection area.
  8. 如权利要求7所述的方法,其特征在于,所述根据探测区域的图像特征信息确定目标对象上的特征位置区域,包括:The method according to claim 7, wherein the determining the feature location area on the target object according to the image feature information of the detection area comprises:
    根据所述探测区域的深度信息在参考坐标系进行投影处理,并生成在所述参考坐标系上的点云图像,所述参考坐标系是根据所述遥控装置确定的;Performing a projection process on the reference coordinate system according to the depth information of the detection area, and generating a point cloud image on the reference coordinate system, the reference coordinate system being determined according to the remote control device;
    根据所述点云图像确定目标对象的轮廓信息;Determining contour information of the target object according to the point cloud image;
    根据所述目标对象的轮廓信息确定出特征位置区域的位置信息,以确定出所述目标对象上的特征位置区域。Determining location information of the feature location area according to the contour information of the target object to determine a feature location area on the target object.
  9. 如权利要求8所述的方法,其特征在于,所述根据所述目标对象的轮廓信息确定出特征位置区域的位置信息,包括:The method according to claim 8, wherein the determining the location information of the feature location area according to the profile information of the target object comprises:
    根据所述目标对象的轮廓信息确定出特征位置区域的初始位置信息;Determining initial position information of the feature location area according to the contour information of the target object;
    根据预设的滤波函数和遥控装置的姿态信息,对所述初始位置信息进行平滑滤波处理,得到所述特征位置区域的位置信息。The initial position information is smoothed and filtered according to the preset filter function and the posture information of the remote control device, and the position information of the feature position area is obtained.
  10. 如权利要求8或9所述的方法,其特征在于,所述根据所述悬浮控制动作生成控制指令,包括: The method according to claim 8 or 9, wherein the generating the control instruction according to the suspension control action comprises:
    根据确定的轮廓信息得到悬浮控制动作的类型和所述特征位置区域的运动矢量;Obtaining a type of the suspension control action and a motion vector of the feature location area according to the determined contour information;
    根据所述悬浮控制动作的类型和所述特征位置区域的运动矢量生成控制指令。A control instruction is generated according to the type of the suspension control action and the motion vector of the feature position area.
  11. 如权利要求10所述的方法,其特征在于,所述特征位置区域的运动矢量包括:根据至少两帧深度信息确定的所述特征位置区域的运动方向和运动幅度。The method according to claim 10, wherein the motion vector of the feature location area comprises: a motion direction and a motion amplitude of the feature location area determined according to at least two frame depth information.
  12. 如权利要求1所述的方法,其特征在于,所述检测目标对象上的特征位置区域在空间中的移动轨迹,包括:The method according to claim 1, wherein the detecting a movement trajectory of the feature position area on the target object in the space comprises:
    通过设置在特征位置区域上的传感器获取所述目标对象上的特征位置区域的移动感测数据;Acquiring movement sensing data of the feature location area on the target object by a sensor disposed on the feature location area;
    根据所述移动感测数据得到所述目标对象上的特征位置区域在空间中的移动轨迹。Obtaining a movement trajectory of the feature location area on the target object in the space according to the motion sensing data.
  13. 如权利要求2所述的方法,其特征在于,所述探测区域的图像特征信息为所述探测区域的颜色信息或者红外信息;The method according to claim 2, wherein the image feature information of the detection area is color information or infrared information of the detection area;
    所述从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹,包括:Determining a movement trajectory of the feature location area on the target object in the space from the image feature information of the detection area, including:
    基于深度学习从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域;Determining a feature location area on the target object from image feature information of the detection area based on depth learning;
    获取所述目标对象的特征位置区域在空间中的移动轨迹。Obtaining a movement trajectory of the feature position area of the target object in the space.
  14. 如权利要求1所述的方法,其特征在于,在所述探测区域中叠加显示有虚拟影像。The method of claim 1 wherein a virtual image is superimposed on said detection area.
  15. 如权利要求14所述的方法,其特征在于,还包括:The method of claim 14 further comprising:
    根据目标对象的位置信息,在所述探测区域中生成并显示所述虚拟影像。 The virtual image is generated and displayed in the detection area according to the location information of the target object.
  16. 如权利要求14或15所述的方法,其特征在于,还包括:The method of claim 14 or 15, further comprising:
    根据所述移动轨迹控制所述虚拟影像移动。The virtual image movement is controlled according to the movement trajectory.
  17. 如权利要求1所述的方法,其特征在于,所述遥控装置为可穿戴设备或增强现实设备。The method of claim 1 wherein said remote control device is a wearable device or an augmented reality device.
  18. 如权利要求17所述的方法,其特征在于,所述可穿戴设备为智能手表、智能眼镜、智能手环中的任意一种或多种;The method according to claim 17, wherein the wearable device is any one or more of a smart watch, smart glasses, and a smart bracelet;
    所述增强现实设备为头戴式显示器。The augmented reality device is a head mounted display.
  19. 如权利要求1所述的方法,其特征在于,所述目标对象为手,所述目标对象上的特征位置区域为手上的指关节点。The method of claim 1 wherein said target object is a hand and said feature location area on said target object is an knuckle point on the hand.
  20. 一种遥控装置,所述遥控装置用于远程控制飞行器飞行,包括:存储器和处理器;A remote control device for remotely controlling aircraft flight, comprising: a memory and a processor;
    所述存储器,用于存储程序指令;The memory is configured to store program instructions;
    所述处理器,用于执行所述存储器存储的程序指令,当程序指令被执行时,用于:The processor is configured to execute the program instructions stored by the memory, when the program instructions are executed, for:
    检测目标对象上的特征位置区域在空间中的移动轨迹,并基于所述移动轨迹确定悬浮控制动作;Detecting a movement trajectory of the feature position area on the target object in the space, and determining a levitation control action based on the movement trajectory;
    根据所述悬浮控制动作生成控制指令;Generating a control instruction according to the suspension control action;
    通过无线链路将所述控制指令发送至飞行器,以控制所述飞行器飞行。The control command is transmitted to the aircraft over a wireless link to control the aircraft to fly.
  21. 如权利要求20所述的遥控装置,其特征在于,所述处理器检测目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:The remote control device according to claim 20, wherein when the processor detects a movement trajectory of the feature location area on the target object in the space, the method is specifically configured to:
    获取探测区域的图像特征信息;Obtaining image feature information of the detection area;
    从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹。 A movement trajectory of the feature position area on the target object in the space is determined from the image feature information of the detection area.
  22. 如权利要求21所述的遥控装置,其特征在于,所述处理器还用于:The remote control device according to claim 21, wherein the processor is further configured to:
    检测所述探测区域中是否存在所述目标对象;Detecting whether the target object exists in the detection area;
    如果存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第一频率。If the target object exists, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the first frequency.
  23. 如权利要求22所述的遥控装置,其特征在于,所述处理器还用于:The remote control device of claim 22, wherein the processor is further configured to:
    如果不存在所述目标对象,则将获取所述探测区域的图像特征信息时的获取频率调整至第二频率。If the target object does not exist, the acquisition frequency when acquiring the image feature information of the detection area is adjusted to the second frequency.
  24. 如权利要求23所述的遥控装置,其特征在于,在所述第二频率下,所述遥控装置处于休眠模式,所述处理器还用于:The remote control device of claim 23, wherein the remote control device is in a sleep mode at the second frequency, the processor is further configured to:
    若接收到唤醒指令,则将获取所述探测区域的图像特征信息时的获取频率从所述第二频率调整至所述第一频率;If the wake-up instruction is received, the acquisition frequency when acquiring the image feature information of the detection area is adjusted from the second frequency to the first frequency;
    其中,所述第一频率高于所述第二频率。Wherein the first frequency is higher than the second frequency.
  25. 如权利要求21所述的遥控装置,其特征在于,所述处理器从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:The remote control device according to claim 21, wherein the processor is configured to: when determining a movement trajectory of the feature location area on the target object in the space from the image feature information of the detection area, specifically:
    根据探测区域的图像特征信息确定目标对象上的特征位置区域;Determining a feature location area on the target object according to image feature information of the detection area;
    根据所述探测区域的至少两帧图像提供的图像特征信息确定出所述特征位置区域在空间中的移动轨迹。And determining, according to the image feature information provided by the at least two frames of the detection area, a movement trajectory of the feature location area in the space.
  26. 如权利要求21所述的遥控装置,其特征在于,所述探测区域的图像特征信息为所述探测区域的深度信息。The remote control device according to claim 21, wherein the image feature information of the detection area is depth information of the detection area.
  27. 如权利要求26所述的遥控装置,其特征在于,所述处理器根据探测区域的图像特征信息确定目标对象上的特征位置区域时,具体用于: The remote control device according to claim 26, wherein when the processor determines the feature location area on the target object according to the image feature information of the detection area, the processor is specifically configured to:
    根据所述探测区域的深度信息在参考坐标系进行投影处理,并生成在所述参考坐标系上的点云图像,所述参考坐标系是根据所述遥控装置确定的;Performing a projection process on the reference coordinate system according to the depth information of the detection area, and generating a point cloud image on the reference coordinate system, the reference coordinate system being determined according to the remote control device;
    根据所述点云图像确定目标对象的轮廓信息;Determining contour information of the target object according to the point cloud image;
    根据所述目标对象的轮廓信息确定出特征位置区域的位置信息,以确定出所述目标对象上的特征位置区域。Determining location information of the feature location area according to the contour information of the target object to determine a feature location area on the target object.
  28. 如权利要求27所述的遥控装置,其特征在于,所述处理器根据所述目标对象的轮廓信息确定出特征位置区域的位置信息时,具体用于:The remote control device according to claim 27, wherein when the processor determines the location information of the feature location area according to the profile information of the target object, the method is specifically configured to:
    根据所述目标对象的轮廓信息确定出特征位置区域的初始位置信息;Determining initial position information of the feature location area according to the contour information of the target object;
    根据预设的滤波函数和遥控装置的姿态信息,对所述初始位置信息进行平滑滤波处理,得到所述特征位置区域的位置信息。The initial position information is smoothed and filtered according to the preset filter function and the posture information of the remote control device, and the position information of the feature position area is obtained.
  29. 如权利要求27或28所述的遥控装置,其特征在于,所述处理器根据所述悬浮控制动作生成控制指令时,具体用于:The remote control device according to claim 27 or 28, wherein when the processor generates a control command according to the levitation control action, the processor is specifically configured to:
    根据确定的轮廓信息得到悬浮控制动作的类型和所述特征位置区域的运动矢量;Obtaining a type of the suspension control action and a motion vector of the feature location area according to the determined contour information;
    根据所述悬浮控制动作的类型和所述特征位置区域的运动矢量生成控制指令。A control instruction is generated according to the type of the suspension control action and the motion vector of the feature position area.
  30. 如权利要求29所述的遥控装置,其特征在于,所述特征位置区域的运动矢量包括:根据至少两帧深度信息确定的所述特征位置区域的运动方向和运动幅度。The remote control device according to claim 29, wherein the motion vector of the feature position region comprises: a motion direction and a motion amplitude of the feature position region determined according to at least two frame depth information.
  31. 如权利要求20所述的遥控装置,其特征在于,所述处理器检测目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:The remote control device according to claim 20, wherein when the processor detects a movement trajectory of the feature location area on the target object in the space, the method is specifically configured to:
    通过设置在特征位置区域上的传感器获取所述目标对象上的特征位置区域的移动感测数据;Acquiring movement sensing data of the feature location area on the target object by a sensor disposed on the feature location area;
    根据所述移动感测数据得到所述目标对象上的特征位置区域在空间中的移动轨迹。 Obtaining a movement trajectory of the feature location area on the target object in the space according to the motion sensing data.
  32. 如权利要求19所述的遥控装置,其特征在于,所述探测区域的图像特征信息为所述探测区域的颜色信息或者红外信息;The remote control device according to claim 19, wherein the image feature information of the detection area is color information or infrared information of the detection area;
    所述处理器从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域在空间中的移动轨迹时,具体用于:When the processor determines the movement trajectory of the feature location area on the target object in the space from the image feature information of the detection area, the processor is specifically configured to:
    基于深度学习从所述探测区域的图像特征信息中确定所述目标对象上的特征位置区域;Determining a feature location area on the target object from image feature information of the detection area based on depth learning;
    获取所述目标对象的特征位置区域在空间中的移动轨迹。Obtaining a movement trajectory of the feature position area of the target object in the space.
  33. 如权利要求20所述的遥控装置,其特征在于,在所述探测区域中叠加显示有虚拟影像。A remote control device according to claim 20, wherein a virtual image is superimposed and displayed in said detection area.
  34. 如权利要求33所述的遥控装置,其特征在于,所述处理器还用于:The remote control device of claim 33, wherein the processor is further configured to:
    根据目标对象的位置信息,在所述探测区域中生成并显示所述虚拟影像。The virtual image is generated and displayed in the detection area according to the location information of the target object.
  35. 如权利要求33或34所述的遥控装置,其特征在于,所述处理器还用于:The remote control device according to claim 33 or 34, wherein the processor is further configured to:
    根据所述移动轨迹控制所述虚拟影像移动。The virtual image movement is controlled according to the movement trajectory.
  36. 如权利要求20所述的遥控装置,其特征在于,所述遥控装置为可穿戴设备或增强现实设备。A remote control device according to claim 20, wherein said remote control device is a wearable device or an augmented reality device.
  37. 如权利要求36所述的遥控装置,其特征在于,所述可穿戴设备为智能手表、智能眼镜、智能手环中的任意一种或多种;The remote control device according to claim 36, wherein the wearable device is any one or more of a smart watch, smart glasses, and a smart bracelet;
    所述增强现实设备为头戴式显示器。The augmented reality device is a head mounted display.
  38. 如权利要求20所述的遥控装置,其特征在于,所述目标对象为手,所述目标对象上的特征位置区域为手上的指关节点。 The remote control device according to claim 20, wherein the target object is a hand, and the feature position area on the target object is an knuckle point of the hand.
  39. 一种遥控系统,其特征在于,包括:A remote control system, comprising:
    至少一个摄像装置和/或至少一个传感器,所述摄像装置包括红绿蓝摄像装置;At least one camera device and/or at least one sensor, the camera device comprising a red, green and blue camera device;
    飞行器;Aircraft
    如权利要求1-19任一项所述的遥控装置。 A remote control device according to any of claims 1-19.
PCT/CN2017/104911 2017-09-30 2017-09-30 Flight control method, remote control device, and remote control system WO2019061466A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2017/104911 WO2019061466A1 (en) 2017-09-30 2017-09-30 Flight control method, remote control device, and remote control system
CN201780007166.8A CN108700885B (en) 2017-09-30 2017-09-30 Flight control method, remote control device and remote control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/104911 WO2019061466A1 (en) 2017-09-30 2017-09-30 Flight control method, remote control device, and remote control system

Publications (1)

Publication Number Publication Date
WO2019061466A1 true WO2019061466A1 (en) 2019-04-04

Family

ID=63844086

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/104911 WO2019061466A1 (en) 2017-09-30 2017-09-30 Flight control method, remote control device, and remote control system

Country Status (2)

Country Link
CN (1) CN108700885B (en)
WO (1) WO2019061466A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190095247A1 (en) * 2017-09-26 2019-03-28 Omron Corporation Control device
CN115620182A (en) * 2022-12-20 2023-01-17 成都鹰谷米特科技有限公司 Signal processing method, device, terminal and storage medium

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109521784B (en) * 2018-12-13 2021-05-11 华南农业大学 Touch sensing type wearable upper limb exoskeleton unmanned aerial vehicle control system and method
CN110096066A (en) * 2019-04-18 2019-08-06 华南农业大学 A kind of power tactile regeneration ectoskeleton structure and unmanned plane during flying attitude control method

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105607740A (en) * 2015-12-29 2016-05-25 清华大学深圳研究生院 Unmanned aerial vehicle control method and device based on computer vision
CN105807926A (en) * 2016-03-08 2016-07-27 中山大学 Unmanned aerial vehicle man-machine interaction method based on three-dimensional continuous gesture recognition
CN106200657A (en) * 2016-07-09 2016-12-07 东莞市华睿电子科技有限公司 A kind of unmanned aerial vehicle (UAV) control method
CN106227341A (en) * 2016-07-20 2016-12-14 南京邮电大学 Unmanned plane gesture interaction method based on degree of depth study and system
CN106327854A (en) * 2016-09-22 2017-01-11 北京奇虎科技有限公司 Unmanned plane system and infrared remote control equipment for unmanned plane
CN106339079A (en) * 2016-08-08 2017-01-18 清华大学深圳研究生院 Method and device for realizing virtual reality by using unmanned aerial vehicle based on computer vision
CN106569508A (en) * 2016-10-28 2017-04-19 深圳市元征软件开发有限公司 Unmanned aerial vehicle control method and device
CN107066935A (en) * 2017-01-25 2017-08-18 网易(杭州)网络有限公司 Hand gestures method of estimation and device based on deep learning
US20170269588A1 (en) * 2015-12-22 2017-09-21 Gopro, Inc. Systems and methods for controlling an unmanned aerial vehicle

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101615472B1 (en) * 2007-09-24 2016-04-25 애플 인크. Embedded authentication systems in an electronic device
CN101446812A (en) * 2008-12-22 2009-06-03 深圳华为通信技术有限公司 Control method and control device of state of equipment and equipment
CN101458560B (en) * 2008-12-25 2011-06-29 南京壹进制信息技术有限公司 Computer intelligent energy-conserving method
CN102982557B (en) * 2012-11-06 2015-03-25 桂林电子科技大学 Method for processing space hand signal gesture command based on depth camera
US20160101856A1 (en) * 2014-06-23 2016-04-14 Nixie Labs, Inc. Wearable unmanned aerial vehicles, and associated systems and methods
CN105223959B (en) * 2015-09-28 2018-07-13 佛山市南海区广工大数控装备协同创新研究院 A kind of unmanned plane glove control system and control method
WO2017060782A1 (en) * 2015-10-07 2017-04-13 Lee Hoi Hung Herbert Flying apparatus with multiple sensors and gesture-based operation
CN105739525B (en) * 2016-02-14 2019-09-03 普宙飞行器科技(深圳)有限公司 A kind of system that cooperation somatosensory operation realizes virtual flight
CN106094868A (en) * 2016-08-01 2016-11-09 杨珊珊 The Hovering control device of unmanned vehicle and Hovering control method thereof

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170269588A1 (en) * 2015-12-22 2017-09-21 Gopro, Inc. Systems and methods for controlling an unmanned aerial vehicle
CN105607740A (en) * 2015-12-29 2016-05-25 清华大学深圳研究生院 Unmanned aerial vehicle control method and device based on computer vision
CN105807926A (en) * 2016-03-08 2016-07-27 中山大学 Unmanned aerial vehicle man-machine interaction method based on three-dimensional continuous gesture recognition
CN106200657A (en) * 2016-07-09 2016-12-07 东莞市华睿电子科技有限公司 A kind of unmanned aerial vehicle (UAV) control method
CN106227341A (en) * 2016-07-20 2016-12-14 南京邮电大学 Unmanned plane gesture interaction method based on degree of depth study and system
CN106339079A (en) * 2016-08-08 2017-01-18 清华大学深圳研究生院 Method and device for realizing virtual reality by using unmanned aerial vehicle based on computer vision
CN106327854A (en) * 2016-09-22 2017-01-11 北京奇虎科技有限公司 Unmanned plane system and infrared remote control equipment for unmanned plane
CN106569508A (en) * 2016-10-28 2017-04-19 深圳市元征软件开发有限公司 Unmanned aerial vehicle control method and device
CN107066935A (en) * 2017-01-25 2017-08-18 网易(杭州)网络有限公司 Hand gestures method of estimation and device based on deep learning

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190095247A1 (en) * 2017-09-26 2019-03-28 Omron Corporation Control device
US10761884B2 (en) * 2017-09-26 2020-09-01 Omron Corporation Control device for operating multiple types of programs in different execution formats
CN115620182A (en) * 2022-12-20 2023-01-17 成都鹰谷米特科技有限公司 Signal processing method, device, terminal and storage medium

Also Published As

Publication number Publication date
CN108700885A (en) 2018-10-23
CN108700885B (en) 2022-03-01

Similar Documents

Publication Publication Date Title
US11914370B2 (en) System and method for providing easy-to-use release and auto-positioning for drone applications
US11546505B2 (en) Touchless photo capture in response to detected hand gestures
US11796309B2 (en) Information processing apparatus, information processing method, and recording medium
WO2018214078A1 (en) Photographing control method and device
US20200346750A1 (en) Method for generating flight path, control device, and unmanned aerial vehicle
US10551834B2 (en) Method and electronic device for controlling unmanned aerial vehicle
CN107223223B (en) Control method and system for first-view-angle flight of unmanned aerial vehicle and intelligent glasses
US10169880B2 (en) Information processing apparatus, information processing method, and program
WO2019061466A1 (en) Flight control method, remote control device, and remote control system
US11132763B2 (en) Creating shockwaves in three-dimensional depth videos and images
JP2018160228A (en) Route generation device, route control system, and route generation method
US11443540B2 (en) Information processing apparatus and information processing method
WO2021127888A1 (en) Control method, smart glasses, mobile platform, gimbal, control system, and computer-readable storage medium
WO2022068193A1 (en) Wearable device, intelligent guidance method and apparatus, guidance system and storage medium
WO2020073245A1 (en) Gesture recognition method, vr angle of view control method and vr system
JP7103354B2 (en) Information processing equipment, information processing methods, and programs
WO2018146922A1 (en) Information processing device, information processing method, and program
WO2020164003A1 (en) Visualization method and system for intelligent wheelchair
WO2020209167A1 (en) Information processing device, information processing method, and program
US11589001B2 (en) Information processing apparatus, information processing method, and program
JP6467039B2 (en) Information processing device

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: 17927557

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: 17927557

Country of ref document: EP

Kind code of ref document: A1