WO2020215296A1 - 可移动平台的巡线控制方法、设备、可移动平台及系统 - Google Patents

可移动平台的巡线控制方法、设备、可移动平台及系统 Download PDF

Info

Publication number
WO2020215296A1
WO2020215296A1 PCT/CN2019/084443 CN2019084443W WO2020215296A1 WO 2020215296 A1 WO2020215296 A1 WO 2020215296A1 CN 2019084443 W CN2019084443 W CN 2019084443W WO 2020215296 A1 WO2020215296 A1 WO 2020215296A1
Authority
WO
WIPO (PCT)
Prior art keywords
movable platform
line
linear
parameter matrix
pixel
Prior art date
Application number
PCT/CN2019/084443
Other languages
English (en)
French (fr)
Inventor
关雁铭
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2019/084443 priority Critical patent/WO2020215296A1/zh
Priority to CN201980004952.1A priority patent/CN111213101A/zh
Publication of WO2020215296A1 publication Critical patent/WO2020215296A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar

Definitions

  • the present invention relates to the field of control technology, and in particular to a line patrol control method, equipment, movable platform and system of a movable platform.
  • line patrol control has a wide range of applications in mobile platforms such as robots and unmanned vehicles.
  • the traditional line-following control is usually to detect the lines in the picture collected by the camera, and realize the line-following control by always placing the sampling point on the line in the center of the picture.
  • the embodiment of the present invention provides a line patrol control method, equipment, movable platform and system of a movable platform, which can improve the stability and accuracy of the line patrol control of the movable platform.
  • an embodiment of the present invention provides a line tracking control method for a movable platform, the movable platform is provided with a camera, and the method includes:
  • the movement of the movable platform is controlled according to the fitting line corresponding to the linear object.
  • an embodiment of the present invention provides a line tracking control device, including a memory and a processor;
  • the memory is used to store program instructions
  • the processor is configured to call the program instructions, and when the program instructions are executed, to perform the following operations:
  • the movement of the movable platform is controlled according to the fitting line corresponding to the linear object.
  • an embodiment of the present invention provides a movable platform, and the movable platform includes:
  • the power system configured on the fuselage is used to provide mobile power for the movable platform
  • an embodiment of the present invention provides a line inspection control system, including: line inspection control equipment and a movable platform;
  • the line-following control device is configured to determine the pixel points corresponding to the linear objects in the image according to the images collected by the photographing device, and map the pixels corresponding to the linear objects into the three-dimensional space to form a transformation point, Fitting the transformation points, determining a fitting line corresponding to the linear object, and sending the fitting line to the movable platform;
  • the movable platform is used for line-following movement according to the received fitting line.
  • an embodiment of the present invention provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.
  • the line-following control device maps the pixel points corresponding to the linear objects in the image collected by the photographing device to the three-dimensional space to form a transformation point, and determines the line by fitting the transformation point.
  • the fitting line corresponding to the object can more accurately approximate the trajectory of the linear object, avoiding tracking loss and oscillation when facing large curvatures and large corners, and improving the stability and accuracy of the line tracking control.
  • FIG. 1 is a schematic diagram of a pixel provided by an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of a conversion point provided by an embodiment of the present invention.
  • Figure 3 is a schematic structural diagram of a line tracking control system provided by an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of a line tracking control method for a movable platform according to an embodiment of the present invention
  • FIG. 5 is a schematic flowchart of another line tracking control method for a movable platform provided by an embodiment of the present invention.
  • Fig. 6 is a schematic structural diagram of a line tracking control device provided by an embodiment of the present invention.
  • the line patrol control method of the movable platform provided in the embodiment of the present invention may be executed by a line patrol control system, specifically, may be executed by a line patrol control device in the line patrol control system.
  • the line inspection control system includes line inspection control equipment and a movable platform.
  • the line patrol control device may be installed on a movable platform; in some embodiments, the line patrol control device may be spatially independent from the movable platform; in some embodiments
  • the line patrol control device may be a component of a movable platform, that is, the movable platform includes the line patrol control device.
  • the line patrol control method of the movable platform can also be applied to other movable devices, such as autonomous mobile robots, wheeled robots, unmanned vehicles, unmanned ships and other movable devices.
  • the line-following control device in the line-following control system can obtain the images collected by the shooting device of the movable platform, and extract the linear objects in the image collected by the shooting device to obtain corresponding pixels.
  • the line-following control device may map the pixel points corresponding to the linear object into a three-dimensional space to form a transformation point, and determine the fitted line corresponding to the linear object by fitting the transformation point, thereby The movement of the movable platform is controlled according to the fitting line corresponding to the linear object.
  • the linear object may include, but is not limited to, any shape such as a straight line, a line segment, a curve, etc., which is not specifically limited herein.
  • the line-following control device may extract the linear objects in the image collected by the photographing device by using a method such as skeletonization to obtain corresponding pixels, as shown in FIG. 1, which is A schematic diagram of a pixel point provided by an embodiment of the present invention.
  • filtering processing may be performed on the pixels to perform denoising processing on the pixels.
  • the line-following control device when the line-following control device maps the pixel points corresponding to the linear object into a three-dimensional space to form a transformation point, it can obtain the internal parameter matrix and the external parameter matrix of the shooting device, and according to The internal parameter matrix and the external parameter matrix map the pixel points corresponding to the linear objects into a three-dimensional space to form transformation points.
  • the internal parameter matrix may be pre-calibrated by the shooting device; in some embodiments, the internal parameter matrix is determined based on a plurality of internal parameters, and the internal parameters are obtained by camera calibration. Parameters, such as focal length, principal point coordinates, etc.
  • the external parameter matrix includes a rotation matrix and/or a translation vector; in some embodiments, when the origin of the world coordinate system is set on the movable platform, the external parameter The matrix only includes the rotation matrix.
  • the rotation matrix can be determined by the posture information of the camera, and the translation vector can be determined by the positioning information of the camera.
  • the line-following control device when the line-following control device maps the pixel points corresponding to the linear objects into a three-dimensional space to form a transformation point, the line-following control device may, according to the internal parameter matrix and the external parameter matrix, convert the The pixel points corresponding to the linear objects are transformed into the world coordinate system to obtain the transformed points.
  • FIG. 2 can be used as an example for description.
  • FIG. 2 is a schematic diagram of a conversion point provided by an embodiment of the present invention.
  • the transformation point shown in FIG. 2 is a transformation point in the world coordinate system obtained by converting the pixel points corresponding to the linear objects shown in FIG. 1.
  • the determined pixel point corresponding to the linear object is converted to the world coordinate system to obtain the conversion point.
  • the pixel points corresponding to the linear object can be processed such as distortion, so as to improve the accuracy of the transformed point.
  • the line-following control device when the line-following control device fits the transformation points and determines the fitting line corresponding to the linear object, it may use polynomial fitting to fit the transformation points , To determine the fitted line of the thread.
  • the polynomial fitting method can be expressed by an N-order polynomial shown in the following formula (1):
  • ⁇ is a vector of polynomial coefficients
  • the fitting process is to select a certain ⁇ so that the curve represented by the polynomial is closest to the sample.
  • the line-following control device may also use other non-polynomial fitting methods such as circles, ellipses, and splines, which are not specifically limited in the embodiment of the present invention.
  • the line-following control device when the line-following control device controls the movement of the movable platform according to the fitting line corresponding to the thread, it may determine the line according to the fitting line of the thread The error information between the movable platform and the fitting line is minimized to control the movement of the movable platform.
  • the error information includes a tangential error and a radial error.
  • the line-following control device may determine a processing method according to the type of the movable platform, and perform processing on the tangential error according to the processing method. The error and the radial error are minimized.
  • the tangential error includes the angle between the tangent direction of the point closest to the movable platform in the fitted line and the current movement direction of the movable platform; the radial error includes The distance between the point closest to the movable platform in the fitted line and the movable platform.
  • the point closest to the current position of the movable platform is calculated to obtain the curve parameter t at this point, and the tangent T(t) at this point can be calculated according to the following formula (2):
  • ⁇ T is the angle between the tangential direction and the current movement direction of the movable platform, called tangential error
  • d N is the distance from the closest point to the movable platform, called radial error.
  • the line tracking control is to minimize these two values.
  • a secondary closed-loop controller can be established to eliminate it.
  • the degree of curvature on the current curve can be obtained, and the control gain can be set a priori based on this.
  • the pixel points corresponding to the linear objects in the image captured by the photographing device are determined, the pixels corresponding to the linear objects are mapped into a three-dimensional space to form a transformation point, and the transformation point is simulated.
  • the fitting line corresponding to the linear object can be determined to more accurately approximate the trajectory of the linear object, and avoid tracking loss and oscillation when facing large curvatures and large corners.
  • the fitting line is controlled to control the movement of the movable platform, which can improve the stability of the line inspection process and the accuracy of the line inspection control.
  • FIG. 3 is a schematic structural diagram of a line tracking control system according to an embodiment of the present invention.
  • the line inspection control system includes: line inspection control equipment 31 and a movable platform 32.
  • a communication connection can be established between the movable platform 32 and the line inspection control device 31 through a wireless communication connection.
  • a communication connection between the movable platform 32 and the line inspection control device 31 may also be established through a wired communication connection.
  • the movable platform 32 may be a movable device such as an unmanned vehicle, an unmanned ship, and a movable robot.
  • the movable platform 32 includes a power system 321, and the power system 321 is used to provide the movable platform 32 with moving power.
  • the movable platform 32 and the line inspection control device 31 are independent of each other.
  • the line inspection control device 31 is set in a cloud server and establishes a communication connection with the movable platform 32 through a wireless communication connection.
  • the line-following control device 31 determines the pixel points corresponding to the linear objects in the image collected by the photographing device, and maps the pixels corresponding to the linear objects into the three-dimensional space to form a transformation point.
  • the trajectory of the linear object can be approximated more accurately, and the tracking loss, oscillation, etc. can be avoided when facing, for example, large curvature and large corners.
  • FIG. 4 is a schematic flow chart of a line patrol control method of a movable platform provided by an embodiment of the present invention.
  • the method may be executed by a line patrol control device.
  • the explanation is as before.
  • the method of the embodiment of the present invention includes the following steps.
  • S401 Determine pixels corresponding to linear objects in the image according to the image collected by the photographing device.
  • the line-following control device may determine the pixels corresponding to the linear objects in the image according to the image collected by the shooting device.
  • the photographing device includes any one or more of a camera and a TOF sensor.
  • the line-following control device determines the pixels corresponding to the linear objects in the image based on the image captured by the shooting device
  • the image may be captured by the camera, and the image captured by the camera may be determined.
  • the depth image may be collected by the TOF sensor, and according to the depth collected by the TOF sensor Image, determining the pixel points corresponding to the linear objects in the depth image.
  • the camera or the TOF sensor may be mounted on the movable platform. In some embodiments, the camera or the TOF sensor may be independent of the movable platform and installed in the environment where the movable platform is located. In some embodiments, the camera includes, but is not limited to, camera devices such as a binocular camera and a monocular camera.
  • the line-following control device may also perform filtering processing on the pixels corresponding to the linear objects in the image to remove redundant The remaining pixels reduce the computational complexity.
  • S402 Map the pixel points corresponding to the linear object into a three-dimensional space to form a transformation point.
  • the line-following control device may map the pixel points corresponding to the linear object into a three-dimensional space to form a transformation point.
  • the line-following control device when the line-following control device maps the pixel points corresponding to the linear objects into a three-dimensional space to form a transformation point, it may obtain the internal parameter matrix and the external parameter matrix of the photographing device, and according to The internal parameter matrix and the external parameter matrix map the pixel points corresponding to the linear objects into a three-dimensional space to form transformation points.
  • the line-following control device when the line-following control device obtains the internal parameter matrix and the external parameter matrix of the camera, it can obtain the internal parameter matrix obtained by the camera calibration in advance, and according to the posture information of the camera, Determine the external parameter matrix of the camera.
  • the internal parameter matrix is determined based on multiple internal parameters, and the internal parameters are parameters calibrated by the camera, such as focal length, image principal point coordinates, etc.
  • the external parameter matrix may include a rotation matrix and/or a translation vector, wherein the rotation matrix can be determined by the posture information of the camera, and the translation vector can be obtained by the positioning information of the camera. Okay.
  • the external parameter matrix when the origin of the world coordinate system is set on the movable platform, the external parameter matrix only includes a rotation matrix.
  • the photographing device is installed on a pan-tilt, and the posture information of the photographing device can be obtained through information such as a pan-tilt encoder; in some embodiments, the position information of the photographing device may be Obtained through the positioning module.
  • the positioning module may include, but is not limited to, a global positioning system (GPS) positioning device, a Beidou positioning device, or a real-time dynamic (RTK) carrier phase differential positioning device (RTK positioning device for short) .
  • GPS global positioning system
  • RTK real-time dynamic
  • the line-following control device when the line-following control device maps the pixel points corresponding to the linear object into a three-dimensional space according to the internal parameter matrix and the external parameter matrix to form a transformation point, it may The internal parameter matrix and the external parameter matrix transform the pixel points corresponding to the linear objects into the world coordinate system to obtain the transformation points.
  • the specific implementation is as described above and will not be repeated here.
  • the pixel points of the linear objects in the image collected by the photographing device are converted to the world coordinate system to obtain the conversion point.
  • the pixel points of the linear object may be processed such as distortion, thereby improving the accuracy of the transformed point.
  • the line-following control device may determine that the pixel points corresponding to the linear object satisfy a preset Conditional pixels are mapped to the three-dimensional space to form transformation points.
  • the meeting the preset condition includes: the size of the pixel corresponding to the linear object meets the preset size, and the line tracking control device may filter and delete the pixels that do not meet the preset size, The pixel points satisfying the preset size are mapped into the three-dimensional space to form a transformation point.
  • the preset size includes but is not limited to information such as a preset area.
  • the size of the pixel corresponding to the linear object includes the area of the pixel corresponding to the linear object, and the line-following control device may filter and delete pixels that do not meet the preset area.
  • the pixel points satisfying the preset area are mapped into the three-dimensional space to form a transformation point.
  • the meeting the preset condition includes: the pixel width of the pixel corresponding to the linear object meets the preset pixel width condition.
  • the linear object includes one or more pixels in the width direction of the image, and the pixel width of the pixel corresponding to the linear object may include one or more pixel widths.
  • the pixel width of the pixel corresponding to the linear object is a single pixel width; when the linear object is in the width direction of the image Including N pixel points, the pixel width of the pixel point corresponding to the linear object is N pixel width.
  • the line-following control device may filter and delete pixels whose pixel widths of pixels corresponding to the linear objects do not meet a preset pixel width condition, and remove pixels that meet the preset pixel width condition. Mapping into three-dimensional space to form transformation points.
  • the line tracking control device may output the image to the user interface for display when determining the pixels corresponding to the linear objects that meet the preset conditions, and according to the user The selection operation obtained on the interface determines the pixel points that meet the preset condition among the pixel points corresponding to the linear object.
  • the line-following control device can display the pixels corresponding to the linear objects in the image on the user interface through special color marks.
  • the line-following control device displays the two detected linear objects on the user interface with red lines, and the user can select the line that needs to be line-followed according to actual needs. Therefore, the line-following control device can operate according to the selection , Determining the pixel points that meet the preset condition among the pixel points corresponding to the linear objects.
  • determining the pixel points that meet the preset conditions in the pixel points in a variety of ways can improve the flexibility of determining the pixel points.
  • the pixel points that meet the preset conditions are mapped into the three-dimensional space to form a transformation point, which can improve the transformation. Point accuracy.
  • the line-following control device may fit the transformation points and determine the fitted line corresponding to the linear object.
  • the line-following control device when the line-following control device fits the transformation points and determines the fitting line corresponding to the linear object, it may use polynomial fitting to fit the transformation points , Determine the fitting line corresponding to the linear object.
  • polynomial fitting to fit the transformation points .
  • the line-following control device fits the transformation points and determines the fitted line corresponding to the linear object, if two or more linear objects are detected, then It is possible to further determine a line-following thread from the two or more thread-like objects.
  • the line-following control may determine that the line having the largest length is the line-following line according to the lengths of the two or more line objects. In other embodiments, other methods may be used to determine a line-following line-shaped object from a plurality of line-shaped objects, which is not specifically limited herein.
  • the embodiment of the present invention determines the fitting line corresponding to the linear object in the image collected by the shooting device by fitting the transformation point, so as to control the movement of the movable platform according to the fitting line, so as to avoid facing for example With large curvature and large turning angles, tracking loss and oscillation will occur, which improves the stability of the line tracking process.
  • the line tracking control device may control the movement of the movable platform according to the fitted line corresponding to the linear object.
  • the line-following control device when the line-following control device controls the movement of the movable platform according to the fitting line corresponding to the linear object, it may determine the corresponding fitting line according to the linear object.
  • the error information between the movable platform and the fitting line is described, and the error information is minimized to control the movement of the movable platform.
  • the error information includes a tangential error and a radial error.
  • the line-following control device may determine a processing method according to the type of the movable platform , And minimize the tangential error and the radial error according to the processing mode.
  • the tangential error includes the angle between the tangent direction of the point closest to the movable platform in the fitted line and the current movement direction of the movable platform; the radial error includes all The distance between the point closest to the movable platform in the fitted line and the movable platform.
  • the line tracking control device when the line tracking control device minimizes the tangential error and the radial error, it may be implemented through a control loop feedback mechanism (also referred to as a feedback loop control mechanism).
  • the line-following control device may implement a control loop feedback mechanism through a proportional-integral-derivative (PID) controller, wherein the control loop feedback mechanism may be used to update the control variable based on the current state Achieve the desired effect.
  • PID controller can be configured to calculate the error value (radial error, tangential error) as the difference between the current state (current position point, current movement direction) and target state (target position point, target movement direction) , And try to minimize the error value by adjusting the control variable.
  • the line-following control device can measure the position information of the movable platform through RTK technology, thereby achieving centimeter-level or sub-centimeter-level control of the movable platform.
  • the line-following control device maps the pixel points corresponding to the linear objects in the image collected by the photographing device to the three-dimensional space to form a transformation point, and determines the line by fitting the transformation point.
  • the fitting line corresponding to the object can be more accurately approximated to the trajectory of the linear object, avoiding tracking loss, oscillation, etc. when facing large curvatures and large corners; according to the fitting line corresponding to the linear object , The tangent error and radial error are minimized, the movement of the movable platform is controlled, and the stability and accuracy of the line tracking control are improved.
  • FIG. 5 is a schematic flowchart of another line-following control method of a movable platform provided by an embodiment of the present invention.
  • the method can be executed by a line-following control device.
  • the specific explanation is as before.
  • the difference between the embodiment of the present invention and the method described in FIG. 4 is that the embodiment of the present invention uses lidar to obtain point cloud data, and determines the pixel corresponding to the linear object according to the point cloud data, and according to the linear
  • the implementation process of controlling the movement of the movable platform by the pixel corresponding to the object is schematically illustrated.
  • the specific embodiment includes the following steps.
  • the line patrol control device can obtain point cloud data according to the lidar.
  • the lidar is a perceptual sensor that can obtain three-dimensional information of the scene.
  • the basic principle is to actively emit laser pulse signals to the detected object and obtain the reflected pulse signals.
  • the depth information of the distance detector of the object to be measured is calculated; Know the launch direction, obtain the angle information of the measured object relative to the lidar; combine the aforementioned depth information and angle information to obtain a large number of detection points (called point clouds), based on the point cloud, the spatial three-dimensional information of the measured object relative to the lidar can be reconstructed .
  • S502 Project each point cloud in the point cloud data into a two-dimensional plane to form a transformation point, and place each transformation point in a corresponding pixel to form an image.
  • the line tracking control device may project each point cloud in the point cloud data onto a two-dimensional plane to form a transformation point, and place each transformation point in a corresponding pixel to form image.
  • the two-dimensional plane may include a plane perpendicular to the detection signal of the lidar, and the line-following control device may project each point cloud in the point cloud data onto the plane to A transformation point is formed, and each of the transformation points is placed in a corresponding pixel to form an image.
  • the two-dimensional plane may include the ground, and the line-following control device may project each point cloud in the point cloud data onto the ground to form a transformation point, and set each transformation point Place in the corresponding pixel to form an image.
  • the ground is a ground parallel to the movable platform. Taking a wheeled mobile robot as an example, when the wheeled mobile robot is traveling on a level ground, the two-dimensional plane may be a horizontal plane. When the wheeled mobile robot is currently climbing a slope, the two-dimensional plane may be a plane parallel to the ramp.
  • the line-following control device can obtain the pixels corresponding to the linear objects in the image.
  • the specific implementation is as described above and will not be repeated here.
  • S504 Map the pixel points corresponding to the linear object into a three-dimensional space to form a transformation point.
  • the line-following control device may map the pixel points corresponding to the linear object into a three-dimensional space to form a transformation point.
  • the specific implementation is as described above and will not be repeated here.
  • the line-following control device may fit the transformation point to determine the fitted line of the linear object.
  • the specific implementation is as described above and will not be repeated here.
  • the line tracking control device may control the movement of the movable platform according to the fitted line corresponding to the linear object.
  • the specific implementation is as described above and will not be repeated here.
  • the line-following control device obtains point cloud data through lidar, projects each point cloud in the point cloud data onto a two-dimensional plane to form a transformation point, and places each transformation point In the corresponding pixels to form an image, it is convenient to intuitively calculate the point cloud on the plane; by mapping the pixel points corresponding to the linear objects in the image captured by the shooting device into the three-dimensional space to form a transformation point, Perform fitting on the transformation point to determine the fitting line corresponding to the linear object, which can more accurately approximate the trajectory of the linear object, and avoid situations such as tracking loss and oscillation when facing large curvatures and large corners; According to the fitting line corresponding to the linear object, the tangential error and the radial error are minimized, and the movement of the movable platform is controlled, which improves the stability and accuracy of the line tracking control.
  • FIG. 6 is a schematic structural diagram of a line tracking control device according to an embodiment of the present invention.
  • the line patrol control device includes: a memory 601 and a processor 602.
  • the line patrol control device of the movable platform further includes a data interface 603, and the data interface 603 is used to transfer data information between the line patrol control device of the movable platform and other devices.
  • the memory 601 may include a volatile memory (volatile memory); the memory 601 may also include a non-volatile memory (non-volatile memory); the memory 601 may also include a combination of the foregoing types of memories.
  • the processor 602 may be a central processing unit (CPU).
  • the processor 602 may further include a hardware chip.
  • the aforementioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
  • the foregoing PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), or any combination thereof.
  • the memory 601 is used to store program instructions, and the processor 602 can call the program instructions stored in the memory 601 to perform the following steps:
  • the movement of the movable platform is controlled according to the fitting line corresponding to the linear object.
  • the processor 602 maps the pixel points corresponding to the linear objects into a three-dimensional space to form a transformation point, it is specifically used for:
  • the pixel points corresponding to the linear objects are mapped into a three-dimensional space to form transformation points.
  • processor 602 obtains the internal parameter matrix and the external parameter matrix of the photographing device, it is specifically configured to:
  • the processor 602 maps the pixel points corresponding to the linear objects into a three-dimensional space according to the internal parameter matrix and the external parameter matrix to form transformation points, it is specifically used for:
  • the pixel points corresponding to the linear objects are transformed into the world coordinate system to obtain the transformation points.
  • the processor 602 fits the transformation points, and when determining the fitting line corresponding to the linear object, it is specifically used for:
  • a polynomial fitting method is used to fit the transformation points to determine a fitting line corresponding to the linear object.
  • the processor 602 maps the pixel points corresponding to the linear objects into a three-dimensional space to form a transformation point, it is also used to:
  • the processor 602 maps the pixel points corresponding to the linear objects into a three-dimensional space to form transformation points, it is specifically used for:
  • the pixel points satisfying the preset condition are mapped into a three-dimensional space to form a transformation point.
  • the meeting the preset condition includes: the size of the pixel point corresponding to the linear object meets the preset size.
  • the satisfying the preset condition includes: the pixel width of the pixel point corresponding to the linear object satisfies the preset pixel width condition.
  • the processor 602 determines a pixel that meets a preset condition among the pixels corresponding to the linear object, it is specifically configured to:
  • a pixel point that meets a preset condition among the pixel points corresponding to the linear object is determined.
  • the processor 602 controls the movement of the movable platform according to the fitting line corresponding to the linear object, it is specifically used for:
  • Minimizing the error information is performed to control the movement of the movable platform.
  • the error information includes tangential error and radial error.
  • processor 602 when the processor 602 performs minimization processing on the error information, it is specifically configured to:
  • the tangential error and the radial error are minimized according to the processing method.
  • the tangential error includes the angle between the tangent direction of the point closest to the movable platform in the fitted line and the current movement direction of the movable platform;
  • the radial error includes the distance between the closest point to the movable platform in the fitted line and the movable platform.
  • the processor 602 determines the pixels corresponding to the linear objects in the image, it is further configured to:
  • Filtering processing is performed on the pixels corresponding to the linear objects in the image.
  • the photographing device includes any one or more of a camera and a TOF sensor.
  • the line-following control device maps the pixel points corresponding to the linear objects in the image collected by the photographing device to the three-dimensional space to form a transformation point, and determines the line by fitting the transformation point.
  • the fitting line corresponding to the object can be more accurately approximated to the trajectory of the linear object, avoiding tracking loss, oscillation, etc. when facing large curvatures and large corners; according to the fitting line corresponding to the linear object , The tangent error and radial error are minimized, the movement of the movable platform is controlled, and the stability and accuracy of the line tracking control are improved.
  • the embodiment of the present invention also provides a movable platform, the movable platform includes: a fuselage; a power system configured on the fuselage for providing moving power for the movable platform; and the above-mentioned line tracking control device.
  • the movable platform maps the pixel points corresponding to the linear objects in the image collected by the shooting device to the three-dimensional space to form transformation points, and determines the linearity by fitting the transformation points.
  • the fitting line corresponding to the object can more accurately approximate the trajectory of the linear object, avoiding tracking loss, oscillation, etc. when facing large curvatures and large corners; according to the fitting line corresponding to the linear object,
  • the tangent error and the radial error are minimized, and the movement of the movable platform is controlled, which improves the stability and accuracy of the line tracking control.
  • the embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the embodiment of the present invention corresponding to FIG. 4 or FIG. 5
  • the described method can also implement the device corresponding to the embodiment of the present invention described in FIG. 6, and will not be repeated here.
  • the computer-readable storage medium may be an internal storage unit of the device described in any of the foregoing embodiments, such as a hard disk or memory of the device.
  • the computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk equipped on the device, a Smart Media Card (SMC), or a Secure Digital (SD) card , Flash Card, etc.
  • the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the terminal.
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Electromagnetism (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Processing (AREA)

Abstract

本发明实施例提供了一种可移动平台的巡线控制方法、设备、可移动平台及系统，所述可移动平台设置有拍摄装置，其中，该方法包括：根据所述拍摄装置采集的图像，确定所述图像中的线状物对应的像素点；将所述线状物对应的像素点映射到三维空间中以形成变换点；对所述变换点进行拟合，确定所述线状物对应的拟合线；根据所述线状物对应的拟合线，控制所述可移动平台的移动。通过这种方式可以提高可移动平台巡线控制的平稳性和准确性。

Description

可移动平台的巡线控制方法、设备、可移动平台及系统 技术领域
本发明涉及控制技术领域，尤其涉及一种可移动平台的巡线控制方法、设备、可移动平台及系统。
背景技术
目前，巡线控制在机器人、无人车等可移动平台中具有广泛的应用。传统的巡线控制通常是对摄像头采集画面中的线进行检测，通过将线上的采样点始终放在画面中央以实现巡线控制。
然而，传统巡线方法所使用的有限个采样点的表达能力有限，并不能完全描述当前所跟随的曲线的信息，因此在面对曲线形状非常规的情况下巡线表现较差。因此，如何更好地对可移动平台进行巡线控制具有十分重要的意义。
发明内容
本发明实施例提供了一种可移动平台的巡线控制方法、设备、可移动平台及系统，可以提高可移动平台巡线控制的平稳性和准确性。
第一方面，本发明实施例提供了一种可移动平台的巡线控制方法，所述可移动平台设置有拍摄装置，所述方法包括：
根据所述拍摄装置采集的图像，确定所述图像中的线状物对应的像素点；
将所述线状物对应的像素点映射到三维空间中以形成变换点；
对所述变换点进行拟合，确定所述线状物对应的拟合线；
根据所述线状物对应的拟合线，控制所述可移动平台的移动。
第二方面，本发明实施例提供了一种巡线控制设备，包括存储器和处理器；
所述存储器，用于存储程序指令；
所述处理器，用于调用所述程序指令，当所述程序指令被执行时，用于执行以下操作：
根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点；
将所述线状物对应的像素点映射到三维空间中以形成变换点；
对所述变换点进行拟合，确定所述线状物对应的拟合线；
根据所述线状物对应的拟合线，控制所述可移动平台的移动。
第三方面，本发明实施例提供了一种可移动平台，所述可移动平台包括：
机身；
配置在机身上的动力系统，用于为所述可移动平台提供移动的动力；
如上述第二方面所述的巡线控制设备。
第四方面，本发明实施例提供了一种巡线控制系统，包括：巡线控制设备和可移动平台；
所述巡线控制设备，用于根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点，将所述线状物对应的像素点映射到三维空间中以形成变换点，并对所述变换点进行拟合，确定所述线状物对应的拟合线，以及将所述拟合线发送给所述可移动平台；
所述可移动平台，用于根据接收到的所述拟合线进行巡线移动。
第五方面，本发明实施例提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，该计算机程序被处理器执行时实现如上述第一方面所述的方法。
本发明实施例中，巡线控制设备通过将拍摄装置采集的图像中的线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况，提高了巡线控制的平稳性和准确性。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，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的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例提供的一种像素点的示意图；
图2是本发明实施例提供的一种变换点的示意图；
图3是本发明实施例提供的一种巡线控制系统的结构示意图；
图4是本发明实施例提供的一种可移动平台的巡线控制方法的流程示意 图；
图5是本发明实施例提供的另一种可移动平台的巡线控制方法的流程示意图；
图6是本发明实施例提供的一种巡线控制设备的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
下面结合附图，对本发明的一些实施方式作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
本发明实施例中提供的可移动平台的巡线控制方法可以由一种巡线控制系统执行，具体地，可以由巡线控制系统中的巡线控制设备执行。其中，所述巡线控制系统包括巡线控制设备和可移动平台。在某些实施例中，所述巡线控制设备可以安装在可移动平台上；在某些实施例中，所述巡线控制设备可以在空间上独立于可移动平台；在某些实施例中，所述巡线控制设备可以是可移动平台的部件，即所述可移动平台包括巡线控制设备。
在其他实施例中，所述可移动平台的巡线控制方法还可以应用于其他可移动设备上，如能够自主移动的机器人、轮式机器人、无人车、无人船等可移动设备。
所述巡线控制系统中的巡线控制设备可以获取可移动平台的拍摄装置采集到的图像，并对所述拍摄装置采集的图像中的线状物进行提取，得到对应的像素点。所述巡线控制设备可以将所述线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，从而根据所述线状物对应的拟合线，控制所述可移动平台的移动。在某些实施例中，所述线状物可以包括但不限于直线、线段、曲线等任意一种形状，在此不做具体限定。
在一个实施例中，所述巡线控制设备可以通过使用骨骼化等方法对所述拍摄装置采集的图像中的线状物进行提取，得到对应的像素点，如图1所示，图 1是本发明实施例提供的一种像素点的示意图。在某些实施例中，在获取到所述线状物对应的像素点之后，可以对所述像素点进行滤波处理，以对所述像素点进行去噪处理。
在一个实施例中，所述巡线控制设备在将所述线状物对应的像素点映射到三维空间中以形成变换点时，可以获取所述拍摄装置的内参矩阵和外参矩阵，并根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点。
在一个实施例中，所述内参矩阵可以是所述拍摄装置预先标定得到的；在某些实施例中，所述内参矩阵是根据多个内参数确定得到，所述内参数是摄像头标定得到的参数，如焦距、像主点坐标等。
在一个实施例中，所述外参矩阵包括旋转矩阵和/或平移向量；在某些实施例中，当所述世界坐标系的原点设定在所述可移动平台上时，所述外参矩阵只包括旋转矩阵。在某些实施例中，所述旋转矩阵可以通过拍摄装置的姿态信息确定得到的，所述平移向量可以通过拍摄装置的定位信息确定得到。
在一个实施例中，所述巡线控制设备在将所述线状物对应的像素点映射到三维空间中以形成变换点时，可以根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点转换至世界坐标系中，得到所述变换点。
具体可以图2为例进行说明，图2是本发明实施例提供的一种变换点的示意图。如图2所示的变换点是根据图1所示的线状物对应的像素点转换得到的世界坐标系中的变换点。
本发明实施例通过将确定得到的所述线状物对应的像素点转换到世界坐标系，以得到所述变换点。在将所述线状物对应的像素点转换到世界坐标系的过程中，可以对所述线状物对应的像素点进行去畸变等处理，从而提升所述变换点的准确性。
在一个实施例中，所述巡线控制设备在对所述变换点进行拟合，确定所述线状物对应的拟合线时，可以采用多项式拟合的方式对所述变换点进行拟合，确定所述线状物的拟合线。在某些实施例中，所述多项式拟合的方式可以用如下的公式(1)所示的一个N阶多项式进行表达：
p(t)＝α Tτ,τ＝(1,t,t 2,...,t N) T  (1)
其中，公式(1)中，α为多项式系数向量，拟合的过程即是选取某个α， 使得该多项式所表示的曲线与样本最为贴近。
以轮式移动机器人为例，假设轮式移动机器人的运动平面和要跟随的曲线位于同一平面，则对于平面上的点，可以按照坐标轴分别单独求解p x(t)、p y(t)，最终形成以参数方程形式描述的轨迹曲线p(t)。
在其他实施例中，所述巡线控制设备还可以使用如圆、椭圆、样条曲线等其他非多项式的拟合方式，本发明实施例在此不做具体限定。
在一个实施例中，所述巡线控制设备在根据所述线状物对应的拟合线，控制所述可移动平台的移动时，可以根据所述线状物的拟合线，确定所述可移动平台与所述拟合线之间的误差信息，并对所述误差信息进行最小化处理，以控制所述可移动平台的移动。
在一些实施例中，所述误差信息包括切向误差和径向误差，所述巡线控制设备可以根据所述可移动平台的类型，确定处理方式，并根据所述处理方式对所述切向误差和所述径向误差进行最小化处理。在某些实施例中，所述切向误差包括所述拟合线中距离所述可移动平台最近的点的切线方向和所述可移动平台当前运动方向的夹角；所述径向误差包括所述拟合线中距离所述可移动平台最近的点与所述可移动平台的距离。
在一个实施例中，计算距离所述可移动平台当前位置最接近的点，得到该点处曲线参数t，可以根据如下公式(2)计算该点处的切线T(t)：
Figure PCTCN2019084443-appb-000001
切线对应的方向代表所述可移动平台的理想前进方向，与该方向垂直的法线方向即构成径向N(t)，且计算公式如下公式(3)所示：
N(t)＝(0 0 1) T×T(t)＝(-T y(t) T x(t) 0) T  (3)
由此可以定义误差为如下公式(4)所示：
e＝(θ T d N) T  (4)
其中，θ T为切线方向和可移动平台当前运动方向的夹角，称为切向误差，d N为最近点到可移动平台的距离，称为径向误差。在一种实施例中，巡线控制便是要最小化这两个值。对于平面运动解耦的可移动平台，这两个误差可以分别建立调节器予以消除，对于平面运动非解耦的可移动平台(例如三轮式机器人，径向误差和切向误差无法同时独立消除)，可建立二级闭环控制器予以 消除。
特别地，由于具有曲线的解析形式，可以得到在最近距离点位置的曲率X(t)如下公式(5)所示：
Figure PCTCN2019084443-appb-000002
根据曲率X(t)，可以获取目前曲线上的弯曲程度，并以此为先验设定控制增益。
本发明实施例，通过确定拍摄装置采集的图像中的线状物对应的像素点，将所述线状物对应的像素点映射到三维空间中以形成变换点，并对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况，根据所述线状物的拟合线，控制所述可移动平台的移动，可以提高巡线过程的平稳性以及巡线控制的准确性。
下面结合附图3对本发明实施例提供的巡线控制系统进行示意性说明。
请参见图3，图3是本发明实施例提供的一种巡线控制系统的结构示意图。所述巡线控制系统包括：巡线控制设备31、可移动平台32。其中，可移动平台32和巡线控制设备31之间可以通过无线通信连接方式建立通信连接。其中，在某些场景下，所述可移动平台32和巡线控制设备31之间也可以通过有线通信连接方式建立通信连接。所述可移动平台32可以为无人车、无人船、可移动机器人等可移动设备。所述可移动平台32包括动力系统321，所述动力系统321用于为可移动平台32提供移动的动力。在其他实施例中，可移动平台32和巡线控制设备31彼此独立，例如巡线控制设31设置在云端服务器中，通过无线通信连接方式与可移动平台32建立通信连接。
本发明实施例中，所述巡线控制设备31通过确定拍摄装置采集的图像中的线状物对应的像素点，将所述线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况；通过根据所述线状物对应的拟合线，对切线误差和径向误差进行最小化处理，控制所述可移动平台32的移动，提高了巡线控制的平稳性和准确 性。
下面结合附图4-附图6对本发明实施例提供的可移动平台的巡线控制方法进行示意性说明。
具体请参见图4，图4是本发明实施例提供的一种可移动平台的巡线控制方法的流程示意图，所述方法可以由巡线控制设备执行，其中，所述巡线控制设备的具体解释如前所述。具体地，本发明实施例的所述方法包括如下步骤。
S401：根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点。
本发明实施例中，巡线控制设备可以根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点。在某些实施例中，所述拍摄装置包括摄像头、TOF传感器中的任意一种或多种。
在一个实施例中，所述巡线控制设备在根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点时，可以通过摄像头采集图像，并根据摄像头采集的图像，确定所述图像中的线状物对应的像素点。
在一个实施例中，所述巡线控制设备在根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点时，可以通过TOF传感器采集深度图像，并根据TOF传感器采集的深度图像，确定所述深度图像中的线状物对应的像素点。
在某些实施例中，所述摄像头或所述TOF传感器可以挂载在所述可移动平台上。在某些实施例中，所述摄像头或所述TOF传感器可以独立于可移动平台，安装于所述可移动平台所处环境当中。在某些实施例中，所述摄像头包括但不限于双目摄像头、单目摄像头等摄像装置。
在一个实施例中，所述巡线控制设备在确定所述图像中的线状物对应的像素点之后，还可以对所述图像中的线状物对应的像素点进行滤波处理，以删除冗余的像素点，降低计算复杂度。
S402：将所述线状物对应的像素点映射到三维空间中以形成变换点。
本发明实施例中，巡线控制设备可以将所述线状物对应的像素点映射到三维空间中以形成变换点。
在一个实施例中，所述巡线控制设备在将所述线状物对应的像素点映射到三维空间中以形成变换点时，可以获取所述拍摄装置的内参矩阵和外参矩阵， 并根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点。
在一个实施例中，所述巡线控制设备在获取所述拍摄装置的内参矩阵和外参矩阵时，可以获取所述拍摄装置预先标定得到的内参矩阵，并根据所述拍摄装置的姿态信息，确定所述拍摄装置的外参矩阵。
在某些实施例中，所述内参矩阵是根据多个内参数确定得到，所述内参数是拍摄装置标定得到的参数，如焦距、像主点坐标等。在某些实施例中，所述外参矩阵可以包括旋转矩阵和/或平移向量，其中，所述旋转矩阵可以通过拍摄装置的姿态信息确定得到的，所述平移向量可以通过拍摄装置的定位信息确定得到。在某些实施例中，当所述世界坐标系的原点设定在所述可移动平台上时，所述外参矩阵只包括旋转矩阵。在某些实施例中，所述拍摄装置安装在云台上，所述拍摄装置的姿态信息可以通过云台编码器等信息获取得到；在某些实施例中，所述拍摄装置的位置信息可以通过定位模块获取得到，示例的，定位模块可以包括但不限于全球定位系统(GPS)定位装置、北斗定位装置或实时动态(Real-time kinematic，RTK)载波相位差分定位装置(简称RTK定位装置)。
在一个实施例中，所述巡线控制设备在根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点时，可以根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点转换至世界坐标系中，得到所述变换点。具体实施例如前所述，此处不再赘述。
本发明实施例通过将拍摄装置采集到的图像中线状物的像素点转换到世界坐标系，以得到所述变换点。在将线状物的像素点转换到世界坐标系的过程中，可以对所述线状物的像素点进行去畸变等处理，从而提升所述变换点的准确性。
在一个实施例中，所述巡线控制设备在将所述线状物对应的像素点映射到三维空间中以形成变换点之前，可以通过确定所述线状物对应的像素点中满足预设条件的像素点，将满足所述预设条件的像素点映射到三维空间中以形成变换点。
在一些实施例中，所述满足预设条件包括：所述线状物对应的像素点的尺寸满足预设尺寸，所述巡线控制设备可以将不满足预设尺寸的像素点进行过滤 删除，将满足预设尺寸的像素点映射到三维空间中以形成变换点。在某些实施例中，所述预设尺寸包括但不限于预设面积等信息。
在一个实施例中，所述线状物对应的像素点的尺寸包括所述线状物对应的像素点的面积，所述巡线控制设备可以将不满足预设面积的像素点进行过滤删除，将满足预设面积的像素点映射到三维空间中以形成变换点。
在一些实施例中，所述满足预设条件包括：所述线状物对应的像素点的像素宽度满足预设像素宽度条件。在一个实施例中，所述线状物在图像的宽度方向上包括一个或多个像素点，所述线状物对应的像素点的像素宽度可以包括一个或多个像素宽度。示例的，当所述线状物在图像的宽度方向上包括一个像素点，则所述线状物对应的像素点的像素宽度为单像素宽度；当所述线状物在图像的宽度方向上包括N个像素点，则所述线状物对应的像素点的像素宽度为N个像素宽度。
在一个实施例中，所述巡线控制设备可以将所述线状物对应的像素点的像素宽度不满足预设像素宽度条件的像素点进行过滤删除，将满足预设像素宽度条件的像素点映射到三维空间中以形成变换点。
在某些实施例中，巡线控制设备在确定所述线状物对应的像素点中满足预设条件的像素点时，可以将所述图像输出至用户界面进行显示，并根据在所述用户界面上获取到的选取操作，确定所述线状物对应的像素点中满足预设条件的像素点。示例的，巡线控制设备可将图像中线状物对应的像素点通过特殊颜色标记显示在用户界面上。例如，巡线控制设备将检测到的两条线状物用红色线条显示在用户界面上，用户可根据实际需求选取需要进行巡线的线条，由此，巡线控制设备则可以根据该选取操作，确定所述线状物对应的像素点中满足预设条件的像素点。
可见，通过多种方式确定所述像素点中满足预设条件的像素点，可以提高确定像素点的灵活性，将满足预设条件的像素点映射到三维空间中以形成变换点，可以提高变换点的准确性。
S403：对所述变换点进行拟合，确定所述线状物对应的拟合线。
本发明实施例中，巡线控制设备可以对所述变换点进行拟合，确定所述线状物对应的拟合线。
在一个实施例中，所述巡线控制设备在对所述变换点进行拟合，确定所述 线状物对应的拟合线时，可以采用多项式拟合的方式对所述变换点进行拟合，确定所述线状物对应的拟合线。具体实施例如前所述，此处不再赘述。
在一个实施例中，所述巡线控制设备在对所述变换点进行拟合，确定所述线状物对应的拟合线之后，如果检测到两条或两条以上的线状物，则可以进一步从所述两条或两条以上的线状物中确定出一条巡线的线状物。
在一个实施例中，所述巡线控制可以根据所述两条或两条以上的线状物的长度，确定长度最大的线状物为巡线的线状物。在其他实施例中，还可以采用其他方式从多条线状物中确定出一条巡线的线状物，在此不做具体限定。
可见，本发明实施例通过对所述变换点进行拟合，确定与拍摄装置采集的图像中的线状物对应的拟合线，以根据拟合线控制可移动平台移动，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况，提高巡线过程的平稳性。
S404：根据所述线状物对应的拟合线，控制所述可移动平台的移动。
本发明实施例中，巡线控制设备可以根据所述线状物对应的拟合线，控制所述可移动平台的移动。
在一个实施例中，所述巡线控制设备在根据所述线状物对应的拟合线，控制所述可移动平台的移动时，可以根据所述线状物对应的拟合线，确定所述可移动平台与所述拟合线之间的误差信息，并对所述误差信息进行最小化处理，以控制所述可移动平台的移动。
在一个实施例中，所述误差信息包括切向误差和径向误差，所述巡线控制设备在对所述误差信息进行最小化处理时，可以根据所述可移动平台的类型，确定处理方式，并根据所述处理方式对所述切向误差和所述径向误差进行最小化处理。
在一个实施例中，所述切向误差包括所述拟合线中距离所述可移动平台最近的点的切线方向和所述可移动平台当前运动方向的夹角；所述径向误差包括所述拟合线中距离所述可移动平台最近的点与所述可移动平台的距离。具体实施例如前所述，此处不再赘述。
在一些实施例中，所述巡线控制设备在对所述切向误差和所述径向误差进行最小化处理时，可以通过控制回路反馈机制(也称为反馈环控制机制)来实现。在某些实施例中，所述巡线控制设备可以通过比例-积分-微分(PID)控制器实现控制回路反馈机制，其中，所述控制回路反馈机制可以被用于基于当 前状态更新控制变量以实现期望效果。例如，PID控制器可以被配置为计算误差值(径向误差、切向误差)作为当前状态(当前位置点、当前运动方向)和目标状态(目标位置点，目标运动方向)之间的差值，并且试图通过调整控制变量使误差值最小化。一般情况下，越精确的测量状态，就可以越精确的测量误差，便可以越精确的调节控制变量。在一种实施例中，所述巡线控制设备可以通过RTK技术测量可移动平台的位置信息，从而实现可移动平台厘米级或亚厘米级的控制。
可见，通过最小化切向误差以及最小化径向误差的这种实施方式，可以实现对可移动平台的巡线控制，提高对可移动平台的巡线控制精度，从而提高了对可移动平台巡线控制的准确性。
本发明实施例中，巡线控制设备通过将拍摄装置采集的图像中的线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况；通过根据所述线状物对应的拟合线，对切线误差和径向误差进行最小化处理，控制所述可移动平台的移动，提高了巡线控制的稳定性和准确性。
具体请参见图5，图5是本发明实施例提供的另一种可移动平台的巡线控制方法的流程示意图，所述方法可以由巡线控制设备执行，其中，所述巡线控制设备的具体解释如前所述。具体地，本发明实施例与图4所述的方法的区别在于，本发明实施例是对利用激光雷达获取点云数据，并根据点云数据确定线状物对应的像素点，以及根据线状物对应的像素点控制所述可移动平台移动的实施过程进行示意性说明，具体实施例包括如下步骤。
S501：根据激光雷达获取点云数据。
本发明实施例中，巡线控制设备可以根据所述激光雷达获取点云数据。
在一些实施例中，所述激光雷达是一种感知传感器，可以获得场景的三维信息。其基本原理为主动对被探测对象发射激光脉冲信号，并获得其反射回来的脉冲信号，根据发射信号和接收信号之间的时间差计算被测对象的距离探测器的深度信息；基于激光雷达的已知发射方向，获得被测对象相对激光雷达的角度信息；结合前述深度信息和角度信息得到海量的探测点(称为点云)，基 于点云即可以重建被测对象相对激光雷达的空间三维信息。
S502：将所述点云数据中的每个点云投影至二维平面中以形成变换点，并将每个所述变换点放在对应的像素中以形成图像。
本发明实施例中，巡线控制设备可以将所述点云数据中的每个点云投影至二维平面中以形成变换点，并将每个所述变换点放在对应的像素中以形成图像。
在一个实施例中，所述二维平面可以包括与所述激光雷达的探测信号相垂直的平面，所述巡线控制设备可以将所述点云数据中的每个点云投影至该平面以形成变换点，并将每个所述变换点放在对应的像素中以形成图像。
在一个实施例中，所述二维平面可以包括地面，所述巡线控制设备可以将所述点云数据中的每个点云投影至地面以形成变换点，并将每个所述变换点放在对应的像素中以形成图像。在某些实施例中，所述地面为与所述可移动平台平行的地面。以轮式移动机器人为例，当轮式移动机器人在水平地面上行驶时，所述二维平面可以是水平面。当轮式移动机器人当前正在爬坡，则所述二维平面可以是与所述坡道平行的平面。
可见，本发明实施例通过将所述点云数据中的每个点云投影到二维平面，便于直观地在平面上对点云进行计算，针对所述二维平面进行线检测。
S503：获取所述图像中的线状物对应的像素点。
本发明实施例中，巡线控制设备可以获取所述图像中的线状物对应的像素点。具体实施例如前所述，此处不再赘述。
S504：将所述线状物对应的像素点映射到三维空间中以形成变换点。
本发明实施例中，巡线控制设备可以将所述线状物对应的像素点映射到三维空间中以形成变换点。具体实施例如前所述，此处不再赘述。
S505：对所述变换点进行拟合，确定所述线状物对应的拟合线。
本发明实施例中，巡线控制设备可以对所述变换点进行拟合，确定所述线状物的拟合线。具体实施例如前所述，此处不再赘述。
S506：根据所述线状物对应的拟合线，控制所述可移动平台的移动。
本发明实施例中，巡线控制设备可以根据所述线状物对应的拟合线，控制所述可移动平台的移动。具体实施例如前所述，此处不再赘述。
本发明实施例中，巡线控制设备通过激光雷达获取点云数据，将所述点云 数据中的每个点云投影至二维平面中以形成变换点，并将每个所述变换点放在对应的像素中以形成图像，便于直观地在平面上对点云进行计算；通过将拍摄装置采集的图像中的线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况；通过根据所述线状物对应的拟合线，对切线误差和径向误差进行最小化处理，控制所述可移动平台的移动，提高了巡线控制的平稳性和准确性。
请参见图6，图6是本发明实施例提供的一种巡线控制设备的结构示意图。具体的，所述巡线控制设备包括：存储器601、处理器602。
在一种实施例中，所述可移动平台的巡线控制设备还包括数据接口603，所述数据接口603，用于传递可移动平台的巡线控制设备和其他设备之间的数据信息。
所述存储器601可以包括易失性存储器(volatile memory)；存储器601也可以包括非易失性存储器(non-volatile memory)；存储器601还可以包括上述种类的存储器的组合。所述处理器602可以是中央处理器(central processing unit，CPU)。所述处理器602还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)或其任意组合。
所述存储器601用于存储程序指令，所述处理器602可以调用存储器601中存储的程序指令，用于执行如下步骤：
根据所述拍摄装置采集的图像，确定所述图像中的线状物对应的像素点；
将所述线状物对应的像素点映射到三维空间中以形成变换点；
对所述变换点进行拟合，确定所述线状物对应的拟合线；
根据所述线状物对应的拟合线，控制所述可移动平台的移动。
进一步地，所述处理器602将所述线状物对应的像素点映射到三维空间中以形成变换点时，具体用于：
获取所述拍摄装置的内参矩阵和外参矩阵；
根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点。
进一步地，所述处理器602获取所述拍摄装置的内参矩阵和外参矩阵时，具体用于：
获取所述拍摄装置预先标定得到的内参矩阵；
根据所述拍摄装置的姿态信息，确定所述拍摄装置的外参矩阵。
进一步地，所述处理器602根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点时，具体用于：
根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点转换至世界坐标系中，得到所述变换点。
进一步地，所述处理器602对所述变换点进行拟合，确定所述线状物对应的拟合线时，具体用于：
采用多项式拟合的方式对所述变换点进行拟合，确定所述线状物对应的拟合线。
进一步地，所述处理器602将所述线状物对应的像素点映射到三维空间中以形成变换点之前，还用于：
确定所述线状物对应的像素点中满足预设条件的像素点；
所述处理器602将所述线状物对应的像素点映射到三维空间中以形成变换点时，具体用于：
将满足所述预设条件的像素点映射到三维空间中以形成变换点。
进一步地，所述满足预设条件包括：所述线状物对应的像素点的尺寸满足预设尺寸。
进一步地，所述满足预设条件包括：所述线状物对应的像素点的像素宽度满足预设像素宽度条件。
进一步地，所述处理器602确定所述线状物对应的像素点中满足预设条件的像素点时，具体用于：
将所述图像输出至用户界面进行显示；
根据在所述用户界面上获取到的选取操作，确定所述线状物对应的像素点中满足预设条件的像素点。
进一步地，所述处理器602根据所述线状物对应的拟合线，控制所述可移 动平台的移动时，具体用于：
根据所述线状物对应的拟合线，确定所述可移动平台与所述拟合线之间的误差信息；
对所述误差信息进行最小化处理，以控制所述可移动平台的移动。
进一步地，所述误差信息包括切向误差和径向误差。
进一步地，所述处理器602对所述误差信息进行最小化处理时，具体用于：
根据所述可移动平台的类型，确定处理方式；
根据所述处理方式对所述切向误差和所述径向误差进行最小化处理。
进一步地，所述切向误差包括所述拟合线中距离所述可移动平台最近的点的切线方向和所述可移动平台当前运动方向的夹角；
所述径向误差包括所述拟合线中距离所述可移动平台最近的点与所述可移动平台的距离。
进一步地，所述处理器602确定所述图像中的线状物对应的像素点之后，还用于：
对所述图像中的线状物对应的像素点进行滤波处理。
进一步地，所述拍摄装置包括摄像头、TOF传感器中的任意一种或多种。
本发明实施例中，巡线控制设备通过将拍摄装置采集的图像中的线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况；通过根据所述线状物对应的拟合线，对切线误差和径向误差进行最小化处理，控制所述可移动平台的移动，提高了巡线控制的平稳性和准确性。
本发明实施例还提供了一种可移动平台，所述可移动平台包括：机身；配置在机身上的动力系统，用于为可移动平台提供移动的动力；以及上述巡线控制设备。本发明实施例中，可移动平台通过将拍摄装置采集的图像中的线状物对应的像素点映射到三维空间中以形成变换点，通过对所述变换点进行拟合，确定所述线状物对应的拟合线，可以更加准确的逼近线状物的轨迹，避免在面对例如大曲率、大转角时出现跟丢、振荡等情况；通过根据所述线状物对应的拟合线，对切线误差和径向误差进行最小化处理，控制所述可移动平台的移动，提高了巡线控制的平稳性和准确性。
本发明的实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现本发明图4或图5所对应实施例中描述的方法，也可实现图6所述本发明所对应实施例的设备，在此不再赘述。
所述计算机可读存储介质可以是前述任一实施例所述的设备的内部存储单元，例如设备的硬盘或内存。所述计算机可读存储介质也可以是所述设备的外部存储设备，例如所述设备上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，所述计算机可读存储介质还可以既包括所述设备的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序以及所述终端所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
以上所揭露的仅为本发明部分实施例而已，当然不能以此来限定本发明之权利范围，因此依本发明权利要求所作的等同变化，仍属本发明所涵盖的范围。

Claims (33)

  1. 一种可移动平台的巡线控制方法，其特征在于，所述可移动平台设置有拍摄装置，所述方法包括：
    根据所述拍摄装置采集的图像，确定所述图像中的线状物对应的像素点；
    将所述线状物对应的像素点映射到三维空间中以形成变换点；
    对所述变换点进行拟合，确定所述线状物对应的拟合线；
    根据所述线状物对应的拟合线，控制所述可移动平台的移动。
  2. 根据权利要求1所述的方法，其特征在于，所述将所述线状物对应的像素点映射到三维空间中以形成变换点，包括：
    获取所述拍摄装置的内参矩阵和外参矩阵；
    根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点。
  3. 根据权利要求2所述的方法，其特征在于，所述获取所述拍摄装置的内参矩阵和外参矩阵，包括：
    获取所述拍摄装置预先标定得到的内参矩阵；
    根据所述拍摄装置的姿态信息，确定所述拍摄装置的外参矩阵。
  4. 根据权利要求2所述的方法，其特征在于，所述根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点，包括：
    根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点转换至世界坐标系中，得到所述变换点。
  5. 根据权利要求1所述的方法，其特征在于，所述对所述变换点进行拟合，确定所述线状物对应的拟合线，包括：
    采用多项式拟合的方式对所述变换点进行拟合，确定所述线状物对应的拟合线。
  6. 根据权利要求1所述的方法，其特征在于，所述将所述线状物对应的像素点映射到三维空间中以形成变换点之前，还包括：
    确定所述线状物对应的像素点中满足预设条件的像素点；
    所述将所述线状物对应的像素点映射到三维空间中以形成变换点，包括：
    将满足所述预设条件的像素点映射到三维空间中以形成变换点。
  7. 根据权利要求6所述的方法，其特征在于，所述满足预设条件包括：所述线状物对应的像素点的尺寸满足预设尺寸。
  8. 根据权利要求7所述的方法，其特征在于，所述满足预设条件包括：所述线状物对应的像素点的像素宽度满足预设像素宽度条件。
  9. 根据权利要求6所述的方法，其特征在于，所述确定所述线状物对应的像素点中满足预设条件的像素点，包括：
    将所述图像输出至用户界面进行显示；
    根据在所述用户界面上获取到的选取操作，确定所述线状物对应的像素点中满足预设条件的像素点。
  10. 根据权利要求1所述的方法，其特征在于，所述根据所述线状物对应的拟合线，控制所述可移动平台的移动，包括：
    根据所述线状物对应的拟合线，确定所述可移动平台与所述拟合线之间的误差信息；
    对所述误差信息进行最小化处理，以控制所述可移动平台的移动。
  11. 根据权利要求10所述的方法，其特征在于，所述误差信息包括切向误差和径向误差。
  12. 根据权利要求11所述的方法，其特征在于，所述对所述误差信息进行最小化处理，包括：
    根据所述可移动平台的类型，确定处理方式；
    根据所述处理方式对所述切向误差和所述径向误差进行最小化处理。
  13. 根据权利要求11所述的方法，其特征在于，
    所述切向误差包括所述拟合线中距离所述可移动平台最近的点的切线方向和所述可移动平台当前运动方向的夹角；
    所述径向误差包括所述拟合线中距离所述可移动平台最近的点与所述可移动平台的距离。
  14. 根据权利要求1所述的方法，其特征在于，所述确定所述图像中的线状物对应的像素点之后，还包括：
    对所述图像中的线状物对应的像素点进行滤波处理。
  15. 根据权利要求1所述的方法，其特征在于，所述拍摄装置包括摄像头、TOF传感器中的任意一种或多种。
  16. 一种巡线控制设备，其特征在于，包括存储器和处理器；
    所述存储器，用于存储程序指令；
    所述处理器，用于调用所述程序指令，当所述程序指令被执行时，用于执行以下操作:
    根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点；
    将所述线状物对应的像素点映射到三维空间中以形成变换点；
    对所述变换点进行拟合，确定所述线状物对应的拟合线；
    根据所述线状物对应的拟合线，控制所述可移动平台的移动。
  17. 根据权利要求16所述的设备，其特征在于，所述处理器将所述线状物对应的像素点映射到三维空间中以形成变换点时，具体用于：
    获取所述拍摄装置的内参矩阵和外参矩阵；
    根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点。
  18. 根据权利要求17所述的设备，其特征在于，所述处理器获取所述拍摄装置的内参矩阵和外参矩阵时，具体用于：
    获取所述拍摄装置预先标定得到的内参矩阵；
    根据所述拍摄装置的姿态信息，确定所述拍摄装置的外参矩阵。
  19. 根据权利要求17所述的设备，其特征在于，所述处理器根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点映射到三维空间中以形成变换点时，具体用于：
    根据所述内参矩阵和所述外参矩阵，将所述线状物对应的像素点转换至世界坐标系中，得到所述变换点。
  20. 根据权利要求16所述的设备，其特征在于，所述处理器对所述变换点进行拟合，确定所述线状物对应的拟合线时，具体用于：
    采用多项式拟合的方式对所述变换点进行拟合，确定所述线状物对应的拟合线。
  21. 根据权利要求16所述的设备，其特征在于，所述处理器将所述线状物对应的像素点映射到三维空间中以形成变换点之前，还用于：
    确定所述线状物对应的像素点中满足预设条件的像素点；
    所述处理器将所述线状物对应的像素点映射到三维空间中以形成变换点时，具体用于：
    将满足所述预设条件的像素点映射到三维空间中以形成变换点。
  22. 根据权利要求21所述的设备，其特征在于，所述满足预设条件包括：所述线状物对应的像素点的尺寸满足预设尺寸。
  23. 根据权利要求22所述的设备，其特征在于，所述满足预设条件包括：所述线状物对应的像素点的像素宽度满足预设像素宽度条件。
  24. 根据权利要求21所述的设备，其特征在于，所述处理器确定所述线状物对应的像素点中满足预设条件的像素点时，具体用于：
    将所述图像输出至用户界面进行显示；
    根据在所述用户界面上获取到的选取操作，确定所述线状物对应的像素点中满足预设条件的像素点。
  25. 根据权利要求16所述的设备，其特征在于，所述处理器根据所述线状物对应的拟合线，控制所述可移动平台的移动时，具体用于：
    根据所述线状物对应的拟合线，确定所述可移动平台与所述拟合线之间的误差信息；
    对所述误差信息进行最小化处理，以控制所述可移动平台的移动。
  26. 根据权利要求25所述的设备，其特征在于，所述误差信息包括切向误差和径向误差。
  27. 根据权利要求26所述的设备，其特征在于，所述处理器对所述误差信息进行最小化处理时，具体用于：
    根据所述可移动平台的类型，确定处理方式；
    根据所述处理方式对所述切向误差和所述径向误差进行最小化处理。
  28. 根据权利要求26所述的设备，其特征在于，所述切向误差包括所述拟合线中距离所述可移动平台最近的点的切线方向和所述可移动平台当前运动方向的夹角；
    所述径向误差包括所述拟合线中距离所述可移动平台最近的点与所述可移动平台的距离。
  29. 根据权利要求16所述的设备，其特征在于，所述处理器确定所述图像中的线状物对应的像素点之后，还用于：
    对所述图像中的线状物对应的像素点进行滤波处理。
  30. 根据权利要求16所述的设备，其特征在于，所述拍摄装置包括摄像头、TOF传感器中的任意一种或多种。
  31. 一种可移动平台，其特征在于，包括：
    机身；
    配置在机身上的动力系统，用于为可移动平台提供移动的动力；
    以及如权利要求16-30任一所述的巡线控制设备。
  32. 一种巡线控制系统，其特征在于，包括：巡线控制设备和可移动平台；
    所述巡线控制设备，用于根据拍摄装置采集的图像，确定所述图像中的线状物对应的像素点，将所述线状物对应的像素点映射到三维空间中以形成变换点，并对所述变换点进行拟合，确定所述线状物对应的拟合线，以及将所述拟合线发送给所述可移动平台；
    所述可移动平台，用于根据接收到的所述拟合线进行巡线移动。
  33. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至15任一项所述方法。
PCT/CN2019/084443 2019-04-26 2019-04-26 可移动平台的巡线控制方法、设备、可移动平台及系统 WO2020215296A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/084443 WO2020215296A1 (zh) 2019-04-26 2019-04-26 可移动平台的巡线控制方法、设备、可移动平台及系统
CN201980004952.1A CN111213101A (zh) 2019-04-26 2019-04-26 可移动平台的巡线控制方法、设备、可移动平台及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/084443 WO2020215296A1 (zh) 2019-04-26 2019-04-26 可移动平台的巡线控制方法、设备、可移动平台及系统

Publications (1)

Publication Number Publication Date
WO2020215296A1 true WO2020215296A1 (zh) 2020-10-29

Family

ID=70790124

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/084443 WO2020215296A1 (zh) 2019-04-26 2019-04-26 可移动平台的巡线控制方法、设备、可移动平台及系统

Country Status (2)

Country Link
CN (1) CN111213101A (zh)
WO (1) WO2020215296A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI770965B (zh) * 2021-04-27 2022-07-11 陽程科技股份有限公司 無人自走車之導引控制方法
TWI770966B (zh) * 2021-04-27 2022-07-11 陽程科技股份有限公司 無人自走車之導引控制方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101067557A (zh) * 2007-07-03 2007-11-07 北京控制工程研究所 适用于自主移动车辆的环境感知的单目视觉导航方法
CN102788591A (zh) * 2012-08-07 2012-11-21 郭磊 基于视觉信息的机器人沿引导线巡线导航方法
CN105869150A (zh) * 2016-03-24 2016-08-17 杭州南江机器人股份有限公司 一种基于视觉识别的可移动平台标定装置及标定方法
CN108885459A (zh) * 2018-06-08 2018-11-23 珊口（深圳）智能科技有限公司 导航方法、导航系统、移动控制系统及移动机器人
CN108958250A (zh) * 2018-07-13 2018-12-07 华南理工大学 多传感器移动平台及基于已知地图的导航与避障方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101625723B (zh) * 2009-07-02 2012-03-28 浙江省电力公司 电力线轮廓的快速图像识别方法
CN107958486A (zh) * 2017-11-21 2018-04-24 北京煜邦电力技术股份有限公司 一种导线矢量模型的生成方法及装置
CN108132675B (zh) * 2017-11-23 2020-02-21 东南大学 一种工厂巡视无人机自主路径巡航以及智能避障方法
CN109144072A (zh) * 2018-09-30 2019-01-04 亿嘉和科技股份有限公司 一种基于三维激光的机器人智能避障方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101067557A (zh) * 2007-07-03 2007-11-07 北京控制工程研究所 适用于自主移动车辆的环境感知的单目视觉导航方法
CN102788591A (zh) * 2012-08-07 2012-11-21 郭磊 基于视觉信息的机器人沿引导线巡线导航方法
CN105869150A (zh) * 2016-03-24 2016-08-17 杭州南江机器人股份有限公司 一种基于视觉识别的可移动平台标定装置及标定方法
CN108885459A (zh) * 2018-06-08 2018-11-23 珊口（深圳）智能科技有限公司 导航方法、导航系统、移动控制系统及移动机器人
CN108958250A (zh) * 2018-07-13 2018-12-07 华南理工大学 多传感器移动平台及基于已知地图的导航与避障方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI770965B (zh) * 2021-04-27 2022-07-11 陽程科技股份有限公司 無人自走車之導引控制方法
TWI770966B (zh) * 2021-04-27 2022-07-11 陽程科技股份有限公司 無人自走車之導引控制方法

Also Published As

Publication number Publication date
CN111213101A (zh) 2020-05-29

Similar Documents

Publication Publication Date Title
US10970873B2 (en) Method and device to determine the camera position and angle
US10928838B2 (en) Method and device of determining position of target, tracking device and tracking system
WO2021026850A1 (zh) 一种基于二维码的导航定姿定位方法和系统
JP5992184B2 (ja) 画像データ処理装置、画像データ処理方法および画像データ処理用のプログラム
WO2018210078A1 (zh) 无人机的距离测量方法以及无人机
US11057604B2 (en) Image processing method and device
TWI693959B (zh) 控制裝置、飛行體以及記錄媒體
WO2021016854A1 (zh) 一种标定方法、设备、可移动平台及存储介质
CN103822644B (zh) 一种三维激光成像系统的相机标定方法
CN111612794A (zh) 基于多2d视觉的零部件高精度三维位姿估计方法及系统
WO2020258217A1 (zh) 可移动平台状态估计方法、系统、可移动平台及存储介质
CN111524194A (zh) 一种激光雷达和双目视觉相互融合的定位方法及终端
WO2021143664A1 (zh) 在载运工具中测量目标对象距离的方法、装置和载运工具
WO2022179094A1 (zh) 车载激光雷达外参数联合标定方法、系统、介质及设备
CN111247389B (zh) 关于拍摄设备的数据处理方法、装置及图像处理设备
WO2020215296A1 (zh) 可移动平台的巡线控制方法、设备、可移动平台及系统
WO2020181409A1 (zh) 拍摄装置参数标定方法、设备及存储介质
CN112396662B (zh) 一种转换矩阵修正的方法及装置
EP4086850A1 (en) Calibrating system for colorizing point-clouds
CN109146936B (zh) 一种图像匹配方法、装置、定位方法及系统
CN102620745A (zh) 一种机载imu视准轴误差检校方法
WO2021056503A1 (zh) 可移动平台的定位方法、装置、可移动平台及存储介质
CN111504320A (zh) 基于严格几何成像模型的带摆镜光学遥感卫星定位方法
WO2022037370A1 (zh) 一种运动估计方法及装置
WO2022160879A1 (zh) 一种转换参数的确定方法和装置

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: 19925756

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: 19925756

Country of ref document: EP

Kind code of ref document: A1