WO2022267481A1 - 多摄像设备的外参标定设备和方法、存储介质、电子设备 - Google Patents

多摄像设备的外参标定设备和方法、存储介质、电子设备 Download PDF

Info

Publication number
WO2022267481A1
WO2022267481A1 PCT/CN2022/075099 CN2022075099W WO2022267481A1 WO 2022267481 A1 WO2022267481 A1 WO 2022267481A1 CN 2022075099 W CN2022075099 W CN 2022075099W WO 2022267481 A1 WO2022267481 A1 WO 2022267481A1
Authority
WO
WIPO (PCT)
Prior art keywords
calibration
imaging devices
mobile
camera
imaging
Prior art date
Application number
PCT/CN2022/075099
Other languages
English (en)
French (fr)
Inventor
于雷
Original Assignee
地平线征程(杭州)人工智能科技有限公司
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 地平线征程(杭州)人工智能科技有限公司 filed Critical 地平线征程(杭州)人工智能科技有限公司
Priority to JP2022564660A priority Critical patent/JP2023534582A/ja
Priority to US18/003,798 priority patent/US20230252679A1/en
Publication of WO2022267481A1 publication Critical patent/WO2022267481A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30204—Marker
    • G06T2207/30208—Marker matrix
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose

Definitions

  • the present disclosure relates to the technical field of extrinsic parameter calibration, in particular to an extrinsic parameter calibration device and method, a storage medium, and an electronic device for multi-camera equipment.
  • the camera module acts as the eye corner of the driving assistance system, and is used to measure the surrounding environment and make driving judgments based on the external surrounding environment.
  • the camera image measurement process in order to determine the three-dimensional geometric position of a point on the surface of a space object and its corresponding image The relationship between points requires the establishment of geometric models of camera imaging, and the model parameters in these geometric models can be used as camera parameters.
  • camera calibration is a very critical link.
  • the accuracy of the calibration results and the stability of the algorithm directly affect the accuracy of the results produced by the camera. Therefore, doing a good job in camera calibration is the premise of doing a good job in the follow-up work, and improving the calibration accuracy is the focus of scientific research.
  • Embodiments of the present disclosure provide an extrinsic parameter calibration device and method for multi-camera devices, a storage medium, and an electronic device.
  • a multi-camera device external parameter calibration device including:
  • a plurality of mobile calibration boards are used to complete the external reference calibration of all the imaging equipment on the mobile carrier carrying multiple imaging equipment in the set space; each of the mobile calibration boards is respectively arranged on the slide rail , the slide rail is arranged on the wall in the set space; the control device is used to control each of the moving calibration plates in the plurality of moving calibration plates along the corresponding slide of the moving calibration plate Rail slides.
  • a method for calibrating external parameters of multi-camera devices including:
  • a method for calibrating external parameters of multi-camera devices including:
  • image acquisition is performed on the corresponding calibration plate to obtain multiple images; wherein, each of the imaging devices corresponds to an image; based on the plurality of images Each image of the image and the internal reference information of each of the multiple imaging devices, and determine the target external parameter information of each of the multiple imaging devices.
  • a computer-readable storage medium stores a computer program, and the computer program is used to perform the external parameter calibration of the multi-camera device described in any one of the above-mentioned embodiments. method.
  • an electronic device includes:
  • processors a processor; and memory for storing instructions executable by said processor;
  • the processor is configured to read the executable instructions from the memory, and execute the instructions to implement the external parameter calibration method for a multi-camera device described in any one of the above embodiments.
  • the simultaneous calibration of multiple calibration plates set on the mobile carrier is realized.
  • the external reference calibration of camera equipment improves the anti-noise and anti-interference ability of external reference calibration, has strong robustness, effectively improves the accuracy of calibration results and calibration efficiency, and also saves calibration cost and time.
  • Fig. 1a is a schematic diagram of a scene of a mass production calibration field to which the present disclosure is applicable.
  • Figure 1b is a top view of the mass production calibration field shown in Figure 1a.
  • Fig. 2 is a structural schematic diagram of a mechanically movable limit guide rail in the mass production calibration field to which the present disclosure is applicable.
  • Fig. 3 is a schematic structural diagram of a multi-camera device external parameter calibration device provided by an exemplary embodiment of the present disclosure.
  • Fig. 4 is a schematic flowchart of a method for calibrating extrinsic parameters of multi-camera devices provided by an exemplary embodiment of the present disclosure.
  • Fig. 5 is a schematic flowchart of a method for calibrating extrinsic parameters of multiple camera devices provided by another exemplary embodiment of the present disclosure.
  • FIG. 6 is a schematic flowchart of step 502 in the embodiment shown in FIG. 5 of the present disclosure.
  • Fig. 7 is a structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure.
  • plural may refer to two or more than two, and “at least one” may refer to one, two or more than two.
  • the term "and/or" in the present disclosure is only an association relationship describing associated objects, indicating that there may be three relationships, for example, A and/or B may indicate: A exists alone, and A and B exist simultaneously , there are three cases of B alone.
  • the character "/" in the present disclosure generally indicates that the contextual objects are an "or" relationship.
  • Embodiments of the present disclosure may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which may operate with numerous other general purpose or special purpose computing system environments or configurations.
  • Examples of well known terminal devices, computing systems, environments and/or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick client computers, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the foregoing, among others.
  • Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by the computer system.
  • program modules may include routines, programs, objects, components, logic, data structures, etc., that perform particular tasks or implement particular abstract data types.
  • the computer system/server can be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network.
  • program modules may be located in both local and remote computing system storage media including storage devices.
  • the common calibration method in the prior art has at least the following problems: complicated process, weak anti-noise and anti-interference ability, and low calibration efficiency.
  • the static calibration method needs to use a calibration object of known size. By establishing the correspondence between the coordinate points of the calibration object and its image points, a certain algorithm is used to obtain the internal and external parameters of the camera model. According to different calibration objects, it can be divided into three-dimensional calibration objects and planar calibration objects.
  • the three-dimensional calibration object can be calibrated by a single image, and the calibration accuracy is high. Most of them are suitable for mass production calibration of camera modules in car factories.
  • the static mass production calibration field can improve the reliability and accuracy of the calibration results, and greatly reduce the calibration time and cost.
  • Fig. 1a is a schematic diagram of a scene of a mass production calibration field to which the present disclosure is applicable.
  • the fixed calibration field specifications are calculated according to the mass-produced models, and the ground 2D checkerboard (fixed calibration board) 101 and the 3D wall checkerboard (movable calibration board) 102 are respectively arranged.
  • Figure 1b is the quantity shown in Figure 1a A top view of the production calibration field, in which the distribution of the 2D checkerboard 101 and the 3D wall checkerboard 102 in the mass production calibration field can be more intuitively understood;
  • the calibration field can be adapted to different car models, and different camera installation schemes are used for calibration of vehicle-mounted camera modules.
  • the 3D wall checkerboard 102 is set on the PLC control slide rail 103, and the 3D wall checkerboard 102 can be translated up, down, left, and right through the controller to the visible range of the camera module for calibration as required.
  • the 3D wall checkerboard 102 has relatively high movement precision, for example, the movement precision is 0.1 mm, which can realize control actions such as jogging or long pressing of the controller or parameter setting.
  • the 3D wall checkerboard 102 can realize the one-key automatic zero return function.
  • the checkerboard 102 can be moved to a designated position by reading parameters according to the set parameters.
  • the calibration field controller can implement functions such as parameter writing, reading, deleting, and saving functions.
  • Each 3D wall checkerboard 102 has a power-off self-locking function to prevent the 3D wall checkerboard 102 from slipping.
  • FIG. 2 is a structural schematic diagram of the mechanically movable limit guide rail in the mass production calibration field to which the present disclosure is applicable. As shown in Figure 2, the width of the mechanically movable limit guide rail is adjusted according to the tire specifications of different models, which is used to limit the position of the vehicle in the calibration field, thereby controlling the distance between the camera module and the calibration plate set on the vehicle. location distance.
  • the calibration board may include at least one or more of 2D checkerboard 101 and 3D wall checkerboard 102 .
  • the position of the vehicle in the calibration field is defined based on the mechanically movable limit guide rail, and the position of the vehicle in the calibration field can be accurately determined through the position of the mechanically movable limit guide rail, so as to obtain the target calibration plate and
  • the distance between the positions of the camera modules improves the accuracy of the calibration results and saves calibration costs and time.
  • Fig. 3 is a schematic structural diagram of a multi-camera device external parameter calibration device provided by an exemplary embodiment of the present disclosure. As shown in Figure 3, the equipment provided in this embodiment includes:
  • a plurality of mobile calibration boards 301 are used to complete the calibration of external parameters of all the imaging devices on the mobile carrier carrying multiple imaging devices in the set space.
  • each mobile calibration plate is respectively arranged on the slide rail, and the slide rail is arranged on the wall in the set space.
  • the mobile calibration board in this embodiment can be understood with reference to the 3D wall checkerboard 102 in the embodiment shown in Figure 1a, and the slide rails in this embodiment can be controlled with reference to the PLC in the embodiment shown in Figure 1a Rails 103 for understanding.
  • information such as the size, shape, and internal grid size of the mobile calibration plate can be freely set according to specific application scenarios, such as the direction and quantity of slide rails, and the setting process of these information is not provided by Figure 1a. limitations of the example.
  • the control device 302 is configured to control each of the multiple moving indexing plates 301 to slide along the slide rail corresponding to the moving indexing plate 301 .
  • the control device 302 in this embodiment can be any kind of controller, which is used to realize the control behavior of multiple mobile calibration boards 301 such as jog, long press, or parameter setting;
  • the precision position control improves the precision of the calibration result of extrinsic calibration of the camera equipment.
  • This embodiment provides a device for calibrating external parameters of multi-camera equipment.
  • the external parameter calibration of multiple camera equipment set on the mobile carrier is realized at the same time.
  • the external parameter calibration completed in the set space greatly reduces the interference such as noise generated by the outside world, thus improving the anti-noise and anti-interference ability of external parameter calibration, has strong robustness, and effectively improves the accuracy of calibration results and The calibration efficiency is improved, and the calibration cost and time are saved at the same time.
  • control device 302 is also used to control the sliding between a plurality of slide rails that have a connection relationship, so as to control the movement of the calibration plate 301 to move up, down, left, and right on the plane corresponding to the wall. Swipe right in all directions.
  • the 3D wall checkerboard 102 is set on the wall through a vertical slide rail, and the 3D wall checkerboard 102 is realized by sliding on the vertical slide rail The movement of the mobile calibration plate in the y-axis direction (moving up and down) under the coordinate system of the plane where the wall is located.
  • the vertical slide rail is flexibly connected to the horizontal slide rail arranged horizontally, and the vertical slide rail slides on the horizontal slide rail to realize the movement of the mobile calibration plate 301 on the x-axis under the plane coordinate system where the wall is located.
  • this embodiment realizes the arbitrary sliding of the mobile calibration plate 301 on the plane corresponding to the wall where it is located by combining the settings of the horizontal slide rail and the vertical slide rail, thereby improving the stability of the external reference calibration. Accuracy.
  • the moving calibration plate 301 can realize sliding in at least one of the following moving modes.
  • the at least one movement mode includes: set unit movement, set length movement and continuous movement.
  • a return button is also provided on the control device 302, and the plurality of moving calibration plates 301 can return to the initial position according to the control of the return button.
  • the size of the setting unit can be set according to the actual scene, and the smaller the setting unit is, the higher the movement accuracy can be achieved.
  • the setting unit is 1mm, and the movement by this setting unit can realize the movement of small distance and high precision.
  • this embodiment also proposes a method of setting the length movement and continuous movement.
  • the movement of the set length can be set by the moving distance in any direction of the moving calibration plate 301 directly set in the control device, based on setting the motor to directly move the moving calibration plate 301 to the corresponding position, if it is in the corresponding position
  • continuous movement realizes operations such as long pressing of the control device to control the designated mobile calibration plate to continuously move in the designated direction until it reaches the designated position and then stops.
  • it can also be fine-tuned by using the set unit movement.
  • the control device in this embodiment is also provided with a return button, and the return button is used to control all the mobile calibration boards 301 to return with one key, so that when the mobile calibration board needs to be moved next time, it can start to move from the initial position, which improves the mobility. accuracy and efficiency.
  • each mobile indexing plate 301 is provided with a locking device to lock the position of the checkerboard indexing plate when the power is off.
  • the locking device provided in this embodiment realizes the power-off self-locking function of the mobile calibration plate, effectively avoids the problem of the mobile calibration plate slipping due to a sudden power failure during the use of the slide rail, and improves the safety of the equipment.
  • the size of the setting space is set according to the size of the mobile carrier.
  • the setting space in this embodiment can be understood with reference to the calibration field shown in FIG. 1a, and the setting space can be used to accommodate a mobile carrier, such as a vehicle, and perform external parameter calibration on multiple imaging devices set on the mobile carrier.
  • the size of the setting space matches the size of the mobile carrier, for example, the matching relationship between the calibration field and the vehicles in the calibration field in the embodiment shown in FIG. 1a.
  • the equipment provided in this embodiment also includes a limit guide rail, which can be set on the ground of the set space, and the width of the limit guide rail is set according to the mobile carrier, used to limit The position of the mobile carrier in the set space.
  • the position of the mobile carrier in the set space is limited by the limit guide rail.
  • FIG. 1a shows the effect of the mechanically movable limit guide rail 104 arranged on the ground in the calibration field on the limit guide rail.
  • Figure 2 For the structure of the limit guide rail, reference can be made to the implementation shown in Figure 2
  • the fixation applicable to various mobile carriers is realized, which increases the range of use of the equipment.
  • the device provided in this embodiment further includes a plurality of fixed calibration plates.
  • the plurality of fixed calibration plates are arranged on the ground of the set space, and surround the limit guide rails set in the set space.
  • the plurality of fixed calibration plates in this embodiment can be understood with reference to the 2D checkerboard 101 on the ground in the embodiment shown in FIG. 1 a , and the distribution of the fixed calibration plates can be understood through the top view shown in FIG.
  • the surrounding mobile carrier is set around the limit guide rail, so as to facilitate the external parameter calibration of the camera equipment that can collect ground images in the mobile carrier, and realize the external parameter calibration of multi-directional camera equipment on the mobile carrier at the same time.
  • Fig. 4 is a schematic flowchart of a method for calibrating extrinsic parameters of multi-camera devices provided by an exemplary embodiment of the present disclosure.
  • the method provided in this embodiment can be applied to an electronic device, as shown in FIG. 4, the method includes the following steps:
  • Step 401 in response to a mobile carrier carrying multiple imaging devices entering a setting space.
  • the mobile carrier may be a movable carrier such as a vehicle on which multiple imaging devices can be installed; the setting space may be the calibration field provided in the embodiment shown in FIG. 1a.
  • Step 402 controlling multiple moving calibration plates in the set space to move to a position corresponding to each of the multiple imaging devices.
  • the position of the imaging device on the mobile carrier is fixed.
  • the corresponding position of each imaging device in the set space is determined, and the control device is used to control multiple mobile calibration
  • Each mobile calibration board in the board so that each mobile calibration board corresponds to a camera device.
  • Step 403 realizing external parameter calibration of multiple camera devices based on multiple moving calibration boards.
  • the external parameters of the camera device may include the coordinate position of the camera device in space and pose information of the camera device.
  • the coordinate position is the coordinates of the x-axis, y-axis, and z-axis in the calibration coordinate system
  • the pose information may include: pitch angle (pitch), yaw angle (yaw) and roll angle (roll), etc.
  • the calibration coordinate system may be a world coordinate system, or may also be a coordinate system with an origin at any point, for example, the arbitrary point is an origin with the imaging device.
  • the external parameter calibration device for multi-camera equipment realizes the external parameter calibration of multiple camera equipment set on the mobile carrier at the same time by setting a plurality of mobile calibration plates in the setting space, and these external parameters
  • the calibration is completed in the set space, which greatly reduces the interference such as noise generated by the outside world, improves the anti-noise and anti-interference ability of external reference calibration, has strong robustness, and effectively improves the accuracy of calibration results and calibration efficiency. It also saves calibration cost and time.
  • step 402 may include:
  • Each of the multiple mobile calibration plates is controlled to slide on at least one slide rail, and the mobile calibration plate is moved to a position corresponding to each of the multiple imaging devices.
  • the relationship between the mobile calibration board and the slide rail can refer to the relationship between the 3D wall checkerboard 102 and the PLC control slide rail 103 in the embodiment provided in Figure 1a; each mobile calibration board is respectively arranged on the slide rail , the slide rail is arranged on the wall in the set space.
  • the 3D wall checkerboard 102 realizes the movement (up and down) of the mobile calibration plate on the y-axis under the coordinate system of the plane where the wall is located by moving on the vertical slide rail.
  • the vertical slide rail is flexibly connected to the horizontal slide rail arranged horizontally, and the vertical slide rail slides on the horizontal slide rail to realize the movement of the mobile calibration plate on the x-axis under the plane coordinate system where the wall is located (left and right movement), the present embodiment realizes that the mobile calibration plate 301 slides arbitrarily in each direction of up, down, left and right on the plane corresponding to the wall surface by setting the horizontal slide rail and the vertical slide rail, which improves the appearance The accuracy of the reference calibration.
  • controlling each of the multiple mobile calibration plates to slide on multiple sliding rails includes: controlling each of the multiple mobile calibration plates to slide on multiple sliding rails according to at least one movement mode. slide on the rail.
  • the at least one movement mode includes: set unit movement, set length movement and continuous movement.
  • the size of the setting unit can be set according to the actual scene, and the smaller the setting unit is, the higher the movement accuracy can be achieved.
  • the setting unit is 1mm, and the movement with small distance and high precision can be realized by moving with this setting unit.
  • this embodiment also proposes a method of setting the length movement and continuous movement.
  • the movement of the set length can be set by the moving distance of the moving calibration plate 301 directly set in the control device in any direction, and the motor will directly move the moving calibration plate 301 to the corresponding position based on the setting motor.
  • the movement of the set unit can also be fine-tuned in combination with the movement of the set unit; continuous movement realizes operations such as long pressing of the control device, and controls the designated mobile calibration plate to continuously move in the designated direction until it reaches the designated position.
  • it can also be fine-tuned by using the set unit movement.
  • the method provided in this embodiment further includes: in response to the completion of external parameter calibration of multiple imaging devices; multiple moving calibration plates return to the initial position along the slide rail.
  • the process of returning each mobile calibration board to the initial position may include: determining the moving distance of the mobile calibration board in at least one direction based on the distance between the coordinates of the current location of the mobile calibration board and the coordinates of the initial position , returning the moving calibration plate to the initial position according to the moving distance in at least one direction.
  • the return button can control all the mobile calibration boards to return with one key, so that when the mobile calibration board needs to be moved next time, it can start to move from the initial position, which improves the accuracy and efficiency of the movement.
  • Fig. 5 is a schematic flowchart of a method for calibrating external parameters of multi-camera devices according to another exemplary embodiment of the present disclosure. The method can be applied to an electronic device, as shown in Figure 5, the method includes the following steps:
  • Step 501 based on each of the plurality of imaging devices set on the mobile carrier, image acquisition is performed on the corresponding calibration plate to obtain multiple images.
  • each camera device corresponds to a calibration board, and each calibration board collects one image, so multiple camera devices correspondingly collect multiple images.
  • each imaging device in this embodiment corresponds to at least one calibration board, and the calibration board may include a movable calibration board and/or a fixed calibration board.
  • the imaging device may include but not limited to a common camera, a fisheye camera, a 3D camera, etc., as long as the device capable of realizing the image acquisition function falls within the scope of the imaging device described in the present disclosure.
  • Step 502 based on each of the multiple images and the internal reference information of each of the multiple imaging devices, determine target extrinsic information of each of the multiple imaging devices.
  • the internal reference information of the camera equipment includes information such as the distortion value, center point, and focal length of the camera equipment. These internal reference information are inherent to each camera equipment, and the equipment is fixed at the factory, which is known information of each camera equipment.
  • the target extrinsic information of the imaging device can be determined through the corresponding relationship between the image coordinates in the collected images and the coordinates in the real space.
  • the embodiment of the present disclosure provides a method for calibrating external parameters of multiple camera devices.
  • the external parameter calibration of multiple camera devices on the mobile carrier is realized at the same time, and, for the same
  • the mobile carrier for example, vehicles, etc.
  • the mobile carrier has achieved mass production calibration and has strong applicability. It can be applied to mass production calibration of a variety of different mobile carriers, effectively improving the accuracy of calibration results and improving calibration efficiency.
  • the 4-channel vehicle-mounted fisheye camera module calibration board is located on the ground (2D checkerboard as shown in Figure 1a), and is determined according to the mass-produced model site size; in addition, a single 8-channel narrow-angle camera module external parameter calibration can also be achieved.
  • step 502 may include the following steps:
  • Step 5021 for each of the multiple imaging devices, based on the image corresponding to the imaging device and the internal parameter information of the imaging device, determine the first external parameter information of the imaging device in the first coordinate system.
  • the first coordinate system may be a coordinate system with the imaging device as an origin.
  • Step 5022 performing coordinate system transformation on the first extrinsic parameter information of the imaging device to obtain target extrinsic parameter information of the imaging device in the second coordinate system.
  • the first coordinate system is the device coordinate system corresponding to each camera device
  • the obtained sets of first external parameter information are different in coordinate system, so it is impossible to determine the relationship of the camera module as a whole
  • the first extrinsic information corresponding to each imaging device is transformed from its corresponding first coordinate system to the second coordinate system uniformly corresponding to all imaging devices
  • the second coordinate system is the The coordinate system of the equipment, at this time, the external parameter information of all camera equipment is in the same coordinate system, and then the overall labeling of the external parameter information of the camera module set on the mobile carrier is realized.
  • the plurality of imaging devices includes: a plurality of first imaging devices and a plurality of second imaging devices
  • the calibration plate includes a fixed calibration plate and a mobile calibration plate.
  • Each first image captured by the first camera corresponds to a plurality of fixed calibration plates
  • each second image captured by the second camera corresponds to a mobile calibration plate.
  • Step 5021 in the above embodiment may include: determining the first external parameter information of the first imaging device in the first coordinate system based on the first image and the internal parameter information of the first imaging device;
  • the internal reference information is used to determine the first external reference information of the second imaging device in the first coordinate system.
  • this embodiment includes two camera devices, such as a first camera device and a second camera device.
  • the first imaging device is a fisheye camera
  • the second imaging device is an ordinary camera.
  • Different camera equipment can correspond to different types of calibration boards, fisheye cameras can correspond to fixed calibration boards, and ordinary cameras can correspond to mobile calibration boards; the images collected by different types of cameras may be different, for example, fisheye cameras have a larger viewing angle range , the angle of view can generally reach 220° or 230°, which creates conditions for shooting a wide range of scenes at close range; fisheye lenses can cause a very strong perspective effect when shooting close to the subject, emphasizing the closeness of the subject The contrast makes the captured picture have a shocking appeal; the fisheye lens has a relatively long depth of field, which is conducive to expressing the long depth of field effect of the photo.
  • This embodiment provides different types of calibration plates for different types of cameras, which improves the accuracy of the obtained first extrinsic parameter information.
  • determining the first external parameter information of the first imaging device in the first coordinate system includes: according to each of the multiple first imaging devices For the overlapping area between the images corresponding to the first imaging device, and the internal reference information of each of the first imaging devices, determine the first set point in the fixed calibration plate under the world coordinate system and the first set point A mapping relationship in the image coordinate system corresponding to the first image.
  • each pair of the first imaging devices is two adjacent first imaging devices.
  • the mobile carrier is a vehicle and the first imaging device is a fisheye camera
  • four fisheye cameras can be installed on the vehicle, which are respectively arranged in front of the vehicle, behind the vehicle, and on both sides of the vehicle body.
  • Internal reference information, as well as the overlapping area of images between two 4-channel fisheye cameras, calculate the mapping relationship from any point on the vehicle surface to the 2D point on the ground.
  • the advantage of using a fisheye camera as the first imaging device is: due to the large viewing angle of the fisheye camera, when four fisheye cameras are respectively arranged in 4 directions of the vehicle body (each direction corresponds to 180 degrees), due to the fisheye
  • the viewing angle of the eye camera can reach 220° or 230°. Therefore, there must be an overlapping area between the two images obtained by every two adjacent fisheye cameras, and then based on the overlapping area, calculate a point on the surface of the spatial three-dimensional object and map it to the ground The mapping relationship of 2D points.
  • the fisheye camera includes camera internal reference information such as distortion value, center point, and focal length information
  • the corresponding relationship between a point in the world coordinate system space and the image pixel coordinates is found , that is, the corresponding relationship between a point in the actual space (a point on the fixed calibration plate in this embodiment) and the pixel coordinates in the image captured by the imaging device at this point; Calculate the space pose of the first camera device in the world coordinate system.
  • the first external parameter information of the imaging device, the first coordinate system at this time is the camera coordinate system with the first imaging device as the origin; this embodiment realizes the 4-way fisheye camera through the fixed calibration plate arranged on the ground Simultaneous calibration improves the calibration speed of the camera equipment.
  • determining the first external parameter information of the second imaging device in the first coordinate system includes: based on the second image and the second The internal reference information of the imaging device determines the mapping relationship between the second set point in the world coordinate system and the second set point in the image coordinate system corresponding to the second image in the moving calibration plate.
  • the second set point can be a corner point in the moving calibration board.
  • the second set point can be a corner point in the moving calibration board. For example, at the upper left corner of the mobile calibration board.
  • the first external parameter information of the imaging device in the first coordinate system is determined.
  • the calibration of at least 8-way narrow-angle camera equipment for example, when the mobile carrier is a vehicle, near the front, rear, left front door, right front door, left rear wheel, and Set up 8-channel narrow-angle cameras in the vicinity, the left corner of the front of the car, and the right corner of the front of the car respectively; according to the corresponding wall checkerboard within the visual range of the 8-channel narrow-angle camera, the inner corners of the checkerboard are identified to extract pixel coordinates; according to the corner points in the collected images The pixel coordinates and calculation relationship.
  • the calculation relationship includes the distance between the imaging device and the corner point on the mobile calibration board corresponding to the image (for example, the distance is determined by actual measurement) and the internal reference information of the imaging device, and the ideal coordinates of the corner point are calculated, and the ideal coordinates Indicates the pixel coordinates obtained when the pose of the camera device does not have any offset.
  • it may include: according to the pixel coordinates of the corner point in the collected image, determine the actual image height of the image point; calculate the ideal image height of the corner point according to the actual image height of the corner point and the calculation relationship; The ideal image height of the corner point determines the ideal coordinates of the corner point; based on the relationship between the pixel coordinates and the ideal coordinates of the angle in the image, the pose information of the imaging device can be determined;
  • the external parameter calibration of multi-channel camera equipment improves the efficiency of external parameter calibration for multi-channel ordinary cameras installed on mobile carriers such as vehicles, and realizes the technical effect of mass production calibration.
  • step 5022 may include:
  • the first extrinsic information is translated and rotated based on the conversion parameters to obtain target extrinsic information of the imaging device in the second coordinate system.
  • the first coordinate system may be a camera coordinate system with the camera device as an origin.
  • the direction the camera points to is the x-axis
  • the vertical x-axis to the left is the y-axis
  • the vertical x-axis is the z-axis, that is, when the coordinate system is determined, the coordinate system is known origin.
  • the transformation parameter only includes the distance information in the z-axis direction in the world coordinate system.
  • the origin of the second coordinate system For other positions, it may also include distance information on the x-axis and/or y-axis.
  • the target extrinsic information of the imaging device in the second coordinate system can be obtained by performing corresponding translation and rotation on the first extrinsic information by converting parameters;
  • the system conversion can unify the external parameter information of all camera equipment into the same coordinate system, which facilitates the processing of the entire mobile carrier, and increases the application range and scenarios of this embodiment.
  • Any method for calibrating external parameters of multi-camera devices provided in the embodiments of the present disclosure may be executed by any appropriate device with data processing capabilities, including but not limited to terminal devices and servers.
  • FIG. 7 illustrates a block diagram of an electronic device according to an embodiment of the present disclosure.
  • the electronic device 70 includes at least one processor 71 and at least one memory 72 .
  • each processor 71 may be a central processing unit (central processing unit, CPU), or other forms of processing units with data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 70 to perform the desired function.
  • CPU central processing unit
  • Memory 72 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include, for example, a random access memory (Random Access Memory, RAM) and/or a cache memory (cache).
  • the non-volatile memory may include, for example, a read-only memory (Read-Only Memory, ROM), a hard disk, a flash memory, and the like.
  • One or more computer program instructions can be stored on the computer-readable storage medium, and the processor 71 can execute the program instructions to implement the method for calibrating external parameters of multiple camera devices in various embodiments of the present disclosure described above and/or other desired functionality.
  • Other information may also be stored in the computer-readable storage medium, such as various contents such as input signal, signal component, and noise component.
  • the electronic device 70 may further include: an input device 73 and an output device 74, and these components are interconnected through a bus system and/or other forms of connection mechanisms (not shown).
  • the input device 73 may be the above-mentioned microphone or microphone array, which is used to capture the input signal of the sound source.
  • the input device 73 may be a communication network connector for receiving the collected input signal.
  • the input device 73 may also include, for example, a keyboard, a mouse, and the like.
  • the output device 74 can output various information to the outside, including determined distance information, direction information, and the like.
  • the output device 74 may include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, and the like.
  • the electronic device 70 may also include any other suitable components.
  • embodiments of the present disclosure may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the above-mentioned "exemplary method" of this specification. Steps in the method for calibrating extrinsic parameters of multi-camera devices according to various embodiments of the present disclosure described in the section.
  • the computer program product can be written in any combination of one or more programming languages to execute the program codes for performing the operations of the embodiments of the present disclosure, and the programming languages include object-oriented programming languages, such as Java, C++, etc. , also includes conventional procedural programming languages, such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute.
  • embodiments of the present disclosure may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when executed by a processor, cause the processor to perform the above-mentioned "Exemplary Method" section of this specification.
  • the computer readable storage medium may employ any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may include, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • the methods and apparatus of the present disclosure may be implemented in many ways.
  • the methods and apparatuses of the present disclosure may be implemented by software, hardware, firmware or any combination of software, hardware, and firmware.
  • the above sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise.
  • the present disclosure can also be implemented as programs recorded in recording media including machine-readable instructions for realizing the method according to the present disclosure.
  • the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
  • each component or each step can be decomposed and/or reassembled. These decompositions and/or recombinations should be considered equivalents of the present disclosure.

Landscapes

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

Abstract

本申请公开了一种多摄像设备的外参标定设备和方法、存储介质、电子设备，该设备包括：多个移动标定板，用于完成设置在设定空间内的载有多个摄像设备的移动载体上的所有所述摄像设备的外参标定；每个所述移动标定板分别设置于滑轨上，所述滑轨设置在所述设定空间内的墙面上；控制设备，用于控制所述多个移动标定板中每个所述移动标定板沿所述移动标定板对应的所述滑轨滑动。本公开实施例通过在设定空间内设置多个移动标定板，实现了同时对移动载体上设置的多个摄像设备的外参标定，提高了外参标定的抗噪声和抗干扰的能力，具有较强的鲁棒性，有效提高标定结果精度和标定效率，同时还节省了标定成本和时间。

Description

多摄像设备的外参标定设备和方法、存储介质、电子设备
本申请要求于2021年6月23日提交中国国家知识产权局、申请号为202110700660.0、发明名称为“多摄像设备外参标定设备和方法、存储介质、电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及外参标定技术领域，尤其是一种多摄像设备的外参标定设备和方法、存储介质、电子设备。
背景技术
交通安全一直是人们关心的重要问题之一，在高速公路上每年都会发生很多交通事故，造成了严重的人员伤亡和巨大的经济损失，因此，开发先进驾驶辅助系统具有重要的意义。摄像模组充当驾驶辅助系统的眼睛一角，被用做测量周围环境以及依据外部周围环境做出驾驶判断，在相机图像测量过程中，为确定空间物体表面某点的三维几何位置与其在图像中对应点之间的相互关系，需要建立相机成像的几何模型，这些几何模型中的模型参数可作为相机参数。
在大多数条件下，相机参数必须通过实验与计算才能得到，这个求解参数的过程就称之为相机标定。无论是在图像测量，还是在机器视觉应用中，相机标定都是非常关键的环节，其标定结果的精度及算法的稳定性直接影响相机工作产生结果的准确性。因此，做好相机标定是做好后续工作的前提，提高标定精度是科研工作的重点所在。
发明内容
为了解决上述技术问题，提出了本公开。本公开的实施例提供了一种多摄像设备的外参标定设备和方法、存储介质、电子设备。
根据本公开实施例的一个方面，提供了一种多摄像设备外参标定设备，包括：
多个移动标定板，用于完成设置在设定空间内的载有多个摄像设备的移动载体上的所有所述摄像设备的外参标定；每个所述移动标定板分别设置于滑轨上，所述滑轨设置在所述设定空间内的墙面上；控制设备，用于控制所述多个移动标定板中每个所述移动标定板沿所述移动标定板对应的所述滑轨滑动。
根据本公开实施例的另一方面，提供了一种多摄像设备外参标定方法，包括：
响应于载有多个摄像设备的移动载体进入设定空间；控制所述设定空间内的多个移动标定板移动到所述多个摄像设备中每个摄像设备对应的位置；基于所述多个移动标定板实现所述多个摄像设备的外参标定。
根据本公开实施例的另一方面，提供了一种多摄像设备外参标定方法，包括：
基于移动载体上设置的多个摄像设备中的每个摄像设备对对应的标定板进行图像采集，得到多幅图像；其中，每个所述摄像设备对应一幅图像；基于所述多幅图像中的每个图像以及所述多个摄像设备中每个所述摄像设备的内参信息，确定所述多个摄像设备中每 个所述摄像设备的目标外参信息。
根据本公开实施例的又一方面，提供了一种计算机可读存储介质，所述存储介质存储有计算机程序，所述计算机程序用于执行上述任一实施例所述的多摄像设备外参标定方法。
根据本公开实施例的还一方面，提供了一种电子设备，所述电子设备包括：
处理器；以及，用于存储所述处理器可执行指令的存储器；
所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现上述任一实施例所述的多摄像设备的外参标定方法。
基于本公开上述实施例提供的一种多摄像设备外参标定设备和方法、存储介质、电子设备，通过在设定空间内设置多个移动标定板，实现了同时对移动载体上设置的多个摄像设备的外参标定，提高了外参标定的抗噪声和抗干扰的能力，具有较强的鲁棒性，有效提高标定结果精度和标定效率，同时还节省了标定成本和时间。
附图说明
通过结合附图对本公开实施例进行更详细的描述，本公开的上述以及其他目的、特征和优势将变得更加明显。附图用来提供对本公开实施例的进一步理解，并且构成说明书的一部分，与本公开实施例一起用于解释本公开，并不构成对本公开的限制。在附图中，相同的参考标号通常代表相同部件或步骤。
图1a是本公开所适用的量产标定场的场景示意图。
图1b是图1a所示的量产标定场的俯视图。
图2是本公开所适用的量产标定场内的机械可移动式限位导轨的结构示意图。
图3是本公开一示例性实施例提供的多摄像设备外参标定设备的结构示意图。
图4是本公开一示例性实施例提供的多摄像设备外参标定方法的流程示意图。
图5是本公开另一示例性实施例提供的多摄像设备外参标定方法的流程示意图。
图6是本公开图5所示的实施例中步骤502的一个流程示意图。
图7是本公开一示例性实施例提供的电子设备的结构图。
具体实施方式
下面，将参考附图详细地描述根据本公开的示例实施例。显然，所描述的实施例仅仅是本公开的一部分实施例，而不是本公开的全部实施例，应理解，本公开不受这里描述的示例实施例的限制。
应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本公开的范围。
本领域技术人员可以理解，本公开实施例中的“第一”、“第二”等术语仅用于区别不同步骤、设备或模块等，既不代表任何特定技术含义，也不表示它们之间的必然逻辑顺序。
还应理解，在本公开实施例中，“多个”可以指两个或两个以上，“至少一个”可以指一个、两个或两个以上。
还应理解，对于本公开实施例中提及的任一部件、数据或结构，在没有明确限定或者在前后文给出相反启示的情况下，一般可以理解为一个或多个。
另外，本公开中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三 种情况。另外，本公开中字符“/”，一般表示前后关联对象是一种“或”的关系。
还应理解，本公开对各个实施例的描述着重强调各个实施例之间的不同之处，其相同或相似之处可以相互参考，为了简洁，不再一一赘述。
同时，应当明白，为了便于描述，附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本公开及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为说明书的一部分。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
本公开实施例可以应用于终端设备、计算机系统、服务器等电子设备，其可与众多其它通用或专用计算系统环境或配置一起操作。适于与终端设备、计算机系统、服务器等电子设备一起使用的众所周知的终端设备、计算系统、环境和/或配置的例子包括但不限于：个人计算机系统、服务器计算机系统、瘦客户机、厚客户机、手持或膝上设备、基于微处理器的系统、机顶盒、可编程消费电子产品、网络个人电脑、小型计算机系统、大型计算机系统和包括上述任何系统的分布式云计算技术环境，等等。
终端设备、计算机系统、服务器等电子设备可以在由计算机系统执行的计算机系统可执行指令(诸如程序模块)的一般语境下描述。通常，程序模块可以包括例程、程序、目标程序、组件、逻辑、数据结构等等，它们执行特定的任务或者实现特定的抽象数据类型。计算机系统/服务器可以在分布式云计算环境中实施，分布式云计算环境中，任务是由通过通信网络链接的远程处理设备执行的。在分布式云计算环境中，程序模块可以位于包括存储设备的本地或远程计算系统存储介质上。
申请概述
在实现本公开的过程中，申请人发现，现有技术中的普通标定方法至少存在以下问题：过程复杂、抗噪声和抗干扰的能力不强，标定效率低。
示例性系统
静态标定法需要使用已知尺寸的标定物，通过建立标定物坐标点与其图像点之间的对应，利用一定的算法获得相机模型的内外参数。根据标定物的不同可分为三维标定物和平面型标定物。三维标定物可由单幅图像进行标定，标定精度较高，多数适用于车厂摄像模组量产标定使用。
其中，静态量产标定场可以提高标定结果的可靠性和准确性，大大缩短标定时间成本。
图1a是本公开所适用的量产标定场的场景示意图。在本实施例中根据量产车型计算固定的标定场规格，分别布置地面2D棋盘格(固定标定板)101和3D墙面棋盘格(移动标定板)102，图1b是图1a所示的量产标定场的俯视图，在该俯视图中可更直观的理解2D棋盘格101和3D墙面棋盘格102在量产标定场中的分布；
标定场可适配不同车型，不同相机安装方案用于车载摄像模组进行标定。
3D墙面棋盘格102设置于PLC控制滑轨103上，可以根据需要通过控制器实现上、下、左、右平移3D墙面棋盘格102到摄像模组可视范围内进行标定。
3D墙面棋盘格102具有较高移动精度，例如，移动精度为0.1mm，可实现控制器点动或长按或参数设置等控制行为。
3D墙面棋盘格102可以实现一键自动回零功能，另外，还可以按照设置参数进行参数读取将棋盘格102移动至指定位置。标定场控制器可以实现参数编写、读入、删除、保存功能等功能。
每一块3D墙面棋盘格102都具有断电自锁功能，防止3D墙面棋盘格102滑落。
标定场内地面布置机械可移动式限位导轨104，在一个可选实施例中，图2是本公开所适用的量产标定场内的机械可移动式限位导轨的结构示意图。如图2所示，可机械可移动式限位导轨根据不同车型的轮胎规格调整宽度，用于限制车辆在标定场内的位置，从而控制设置在车辆上的摄像模组与标定板之间的位置距离。其中，所述标定板可以包括2D棋盘格101和3D墙面棋盘格102中的至少一种或多种。
本公开实施例，基于机械可移动式限位导轨限定了标定场内车辆的位置，通过机械可移动式限位导轨的位置可以准确的确定车辆在标定场内的位置，从而获取目标标定板与摄像模组的位置之间的距离，提高了标定结果的准确性，节省标定成本时间。
示例性设备
图3是本公开一示例性实施例提供的多摄像设备外参标定设备的结构示意图。如图3所示，本实施例提供的设备包括：
多个移动标定板301，用于完成设置在设定空间内的载有多个摄像设备的移动载体上的所有摄像设备的外参标定。
其中，每个移动标定板分别设置于滑轨上，滑轨设置在设定空间内的墙面上。
可选地，本实施例中的移动标定板可参照图1a所示实施例中的3D墙面棋盘格102进行理解，本实施例中的滑轨可以参照图1a所示实施例中的PLC控制滑轨103进行理解。当然，实际应用中，移动标定板的尺寸、形状和内部分格尺寸等信息可根据具体应用场景自由设置，例如包括滑轨的方向、数量等信息，且这些信息的设置过程不受图1a提供的实施例的限制。
控制设备302，用于控制多个移动标定板301中每个移动标定板沿移动标定板301对应的滑轨滑动。
本实施例中的控制设备302可以是任意的一种控制器，用于实现点动、长按、或参数设置等对多个移动标定板301的控制行为；本实施例通过控制设备302的高精度位置控制，提高了对摄像设备进行外参标定的标定结果的精度。
本实施例提供了一种多摄像设备外参标定设备，通过在设定空间内设置多个移动标定板，实现了同时对移动载体上设置的多个摄像设备的外参标定，由于本实施例在设定空间内完成的外参标定，大大减少了外界产生的噪声等干扰，因此提高了外参标定的抗噪声和抗干扰的能力，具有较强的鲁棒性，有效提高标定结果精度以及提高了标定的效率，且同时节省了标定成本和时间。
在一些可选的实施例中，控制设备302，还用于控制具有连接关系的多个滑轨之间的滑动，实现控制移动标定板301在所在墙面对应的平面上上、下、左、右沿各个方向滑动。
本实施例中，可参照图1a所示实施例中，3D墙面棋盘格102通过竖直滑轨设置在墙面上，且该3D墙面棋盘格102通过在该竖直滑轨上滑动实现移动标定板在墙面所在平面 的坐标系下的y轴方向上的移动(上下移动)。
可选地，将竖直滑轨与横向设置的横向滑轨活动连接，通过竖直导轨在横向滑轨上滑动，实现了移动标定板301在墙面所在的平面坐标系下的x轴上的移动(左右移动)，本实施例通过结合横向滑轨和竖直滑轨的设置，实现了移动标定板301在所在墙面对应的平面上各个方向上的任意滑动，进而提高了外参标定的精确度。
可选地，移动标定板301根据控制设备302的控制可实现以下至少一种移动模式的滑动。所述至少一种移动模式包括：设定单位移动、设定长度移动和连续移动。
另外，在控制设备302上还设置有回归按键，多个移动标定板301可根据回归按键的控制回归导初始位置。
本实施例中，设定单位的大小可根据实际场景进行设置，设置的设定单位越小，能达到的移动精度越高。例如，设定单位为1mm，通过该设定单位移动实现小距离高精度的移动。但当需要大幅度移动时，设定单位移动可能会导致速度变慢，因此，本实施例还提出了一种设定长度移动以及连续移动的方法。
其中，设定长度移动可以通过在控制设备中直接设置的移动标定板301上述的任意方向上的移动距离设定，基于设置电机直接将所述移动标定板301移动到对应位置，若是在对应位置不准确时，还可以结合设定单位移动进行微调；连续移动实现了通过控制设备长按等操作，控制指定移动标定板向指定方向进行持续性移动，直到到达指定位置后停止。在到达位置与目标位置有较小偏差时，同样可以利用设定单位移动进行微调。
本实施例控制设备还设有回归按键，所述回归按键用于控制所有移动标定板301一键回归，使下次再需要对移动标定板进行移动时，可以从初始位置开始移动，提高了移动准确率和效率。
可选地，每个移动标定板301上设置有锁扣装置，在断电时锁定棋盘标定板的位置。
本实施例中提供的锁扣装置实现了移动标定板的断电自锁功能，有效避免了在使用滑轨过程中突然断电导致的移动标定板滑落的问题，提高了设备的安全性。
在一些可选的实施例中，设定空间的大小根据移动载体的大小进行设置。
本实施例中的设定空间可以参照图1a所示的标定场进行理解，设定空间可用于容纳移动载体，比如车辆，以及对移动载体上设置的多个摄像设备进行外参标定。其中，设定空间的大小与移动载体的大小相匹配，例如，如图1a所示的实施例中标定场与标定场内的车辆的匹配关系。
在一些可选的实施例中，本实施例提供的设备还包括限位导轨，该限位导轨可被设置在设定空间的地面上，限位导轨的宽度根据移动载体进行设置，用于限制移动载体在设定空间内的位置。
本实施例中，通过限位导轨限定移动载体在设定空间中的位置。
可选地，可参照图1a所示实施例，示出了标定场内地面布置的机械可移动式限位导轨104对限位导轨的作用，对于限位导轨的结构可参照图2所示实施例，通过可调宽度的限位导轨实现了适用多种移动载体的固定，增大了设备的使用范围。
在一些可选的实施例中，本实施例提供的设备还包括多个固定标定板。所述多个固定标定板设置在设定空间的地面上，且环绕设置在设定空间内的限位导轨周围。
本实施例中的多个固定标定板可参照图1a所示实施例中的布置地面的2D棋盘格101 进行理解，并可通过图1b所示的俯视图理解固定标定板的分布，通过环绕分布在限位导轨周围实现了环绕移动载体设置，以便于对移动载体中设置在可采集地面图像的摄像设备进行外参标定，实现了同时对移动载体上多方位的摄像设备的外参标定。
示例性方法
图4是本公开一示例性实施例提供的多摄像设备外参标定方法的流程示意图。本实施例提供的方法可应用在一电子设备上，如图4所示，方法包括如下步骤：
步骤401，响应于载有多个摄像设备的移动载体进入设定空间。
本实施例中，移动载体可以是车辆等可以设置多个摄像设备的可移动的载体；设定空间可以是如图1a所示实施例中提供的标定场。
步骤402，控制设定空间内的多个移动标定板移动到多个摄像设备中每个摄像设备对应的位置。
在一实施例中，摄像设备在移动载体上的位置固定，当移动载体位置固定后，每个摄像设备在设定空间内对应的位置即已确定，而控制设备则用于控制多个移动标定板中的每个移动标定板，使每个移动标定板对应一个摄像设备。
步骤403，基于多个移动标定板实现多个摄像设备的外参标定。
具体地，摄像设备的外参可包括摄像设备在空间中的坐标位置及摄像设备的位姿信息。其中，所述坐标位置为标定坐标系下的x轴、y轴、z轴的坐标，所述位姿信息可以包括：俯仰角(pitch)、偏航角(yaw)和翻滚角(roll)等。所述标定坐标系可以是世界坐标系，或者也可以是以任意一点为原点的坐标系，例如，所述任意一点为以摄像设备为原点。
本实施例提供的一种多摄像设备外参标定设备，通过在设定空间内设置多个移动标定板，实现了同时对移动载体上设置的多个摄像设备的外参标定，且这些外参标定在设定空间内完成，大大减少了外界产生的噪声等干扰，提高了外参标定的抗噪声和抗干扰的能力，具有较强的鲁棒性，有效提高标定结果精确度和标定效率，同时还节省了标定成本和时间。
可选的，在上述实施例的基础上，步骤402可以包括：
控制多个移动标定板中的每个移动标定板在至少一个滑轨上滑动，将移动标定板移动到多个摄像设备中每个摄像设备对应的位置。
本实施例中，移动标定板与滑轨的关系可参照图1a提供的实施例中3D墙面棋盘格102与PLC控制滑轨103之间的关系；每个移动标定板分别设置于滑轨上，滑轨设置在设定空间内的墙面上。3D墙面棋盘格102通过在该竖直滑轨上移动实现移动标定板在墙面所在平面的坐标系下的y轴上的移动(上下移动)。
可选地，将竖直滑轨与横向设置的横向滑轨活动连接，通过竖直导轨在横向滑轨上滑动，实现了移动标定板在墙面所在的平面坐标系下的x轴上的移动(左右移动)，本实施例通过设置横向滑轨和竖直滑轨，实现了移动标定板301在所在墙面对应的平面上在上、下、左、右各个方向上任意滑动，提高了外参标定的精确度。
可选地，控制多个移动标定板中的每个移动标定板在多个滑轨上滑动，包括：控制多个移动标定板中的每个移动标定板按照至少一种移动模式在多个滑轨上滑动。其中，所述至少一种移动模式包括：设定单位移动、设定长度移动和连续移动。
本实施例中，设定单位的大小可根据实际场景进行设置，设置的设定单位越小，能达到的移动精度越高。例如，设定单位为1mm，通过该设定单位移动实现小距离高精度的移 动。但当需要大幅度移动时，设定单位移动可能会导致速度变慢，因此，本实施例还提出了一种设定长度移动以及连续移动的方法。
其中，设定长度移动可以通过在控制设备中直接设置的移动标定板301在任意方向上的移动距离设定，基于设置电机直接将所述移动标定板301移动到对应位置，若是在对应位置不准确时，还可以结合设定单位移动进行微调；连续移动实现了通过控制设备长按等操作，控制指定移动标定板向指定方向进行持续性移动，直到到达指定位置后停止，在到达位置与目标位置有较小偏差时，同样可以利用设定单位移动进行微调。
可选地，本实施例提供的方法还包括：响应于完成多个摄像设备的外参标定；多个移动标定板沿滑轨返回初始位置。
可选地，每个移动标定板返回初始位置的过程可以包括：基于该移动标定板当前所在位置的坐标和初始位置的坐标之间的距离，确定该移动标定板在至少一个方向上的移动距离，根据至少一个方向上的移动距离将该移动标定板返回初始位置。本实施例通过回归按键可以控制所有移动标定板一键回归，使下次需要对移动标定板进行移动时，可以从初始位置开始移动，提高了移动准确率和效率。
图5是本公开另一示例性实施例提供的一种多摄像设备的外参标定方法的流程示意图。该方法可应用在一电子设备上，如图5所示，所述方法包括如下步骤：
步骤501，基于移动载体上设置的多个摄像设备中的每个摄像设备，对对应的标定板进行图像采集，得到多幅图像。
其中，每个摄像设备对应一个标定板，每个标定板采集一幅图像，因此多个摄像设备对应采集多幅图像。
可选地，本实施例中的每个摄像设备对应至少一个标定板，标定板可包括移动标定板和/或固定标定板。摄像设备可以包括但不限于普通相机、鱼眼相机、3D相机等，只要能实现图像采集功能的设备都属于本公开所述的摄像设备范围内。
步骤502，基于多幅图像中的每个图像，以及多个摄像设备中每个摄像设备的内参信息，确定多个摄像设备中每个摄像设备的目标外参信息。
其中，摄像设备的内参信息包括摄像设备的畸变值、中心点、焦距等信息，这些内参信息是每个摄像设备固有的，该设备出厂时即已固定，为每个摄像设备的已知信息。本实施例中，可通过采集的图像中图像坐标与现实空间中坐标的对应关系，确定该摄像设备的目标外参信息。
本公开实施例提供的一种多摄像设备外参标定方法，通过同时利用多个摄像设备进行图像采集和标定，实现了同时对移动载体上的多个摄像设备的外参标定，并且，对于相同的移动载体(例如，车辆等)实现了量产标定，具有较强的适用性，可适用多种不同移动载体量产标定，有效提高标定结果精度，并提高了标定效率。例如，实现单次4路鱼眼环视摄像模组外参标定，形成环视拼接；4路车载鱼眼摄像模组标定板位于地面(如图1a所示的2D棋盘格)，根据量产车型确定场地尺寸；另外，还可以实现单次8路窄角摄像模组外参标定。
如图6所示，在上述图5所示实施例的基础上，步骤502可包括如下步骤：
步骤5021，针对多个摄像设备中每个摄像设备，基于摄像设备对应的图像和摄像设备的内参信息，确定摄像设备在第一坐标系下的第一外参信息。
本实施例中，在获取图像中某一点在世界坐标系下的坐标、图像中该点的像素坐标的对应关系，以及采集该图像的摄像设备的内参信息，即可确定该摄像设备在第一坐标系下的第一外参信息，该第一坐标系可以为以该摄像设备为原点的坐标系。
步骤5022，对摄像设备的第一外参信息进行坐标系转换，得到摄像设备在第二坐标系下的目标外参信息。
本实施例中，当第一坐标系分别为每个摄像设备对应的设备坐标系时，得到的多组第一外参信息之间由于坐标系不同，因此无法实现对摄像模组整体的关系确定，为了克服这一问题，将每个摄像设备对应的第一外参信息从其对应的第一坐标系下转换到所有摄像设备统一对应的第二坐标系下，所述第二坐标系为摄像设备的坐标系，此时所有摄像设备的外参信息在同一坐标系下，进而实现移动载体上设置的摄像模组的外参信息的整体标注。
在一些可选实施例中，所述多个摄像设备包括：多个第一摄像设备和多个第二摄像设备，所述标定板包括固定标定板和移动标定板。每个第一摄像设备采集的第一图像对应多个固定标定板，每个第二摄像设备采集的第二图像对应一个移动标定板。
上述实施例中步骤5021可以包括：基于第一图像以及第一摄像设备的内参信息，确定第一摄像设备在第一坐标系下的第一外参信息；基于第二图像以及第二摄像设备的内参信息，确定第二摄像设备在第一坐标系下的第一外参信息。
可选地，本实施例中包括了两种摄像设备，比如第一摄像设备和第二摄像设备。进一步地，所述第一摄像设备为鱼眼相机，所述第二摄像设备为普通相机。不同的摄像设备可以对应不同类别的标定板，鱼眼相机可对应固定标定板，而普通相机对应移动标定板；不同种类的相机采集的图像可能存在不同，例如，鱼眼相机的视角范围较大，视角一般可达到220°或230°，这为近距离拍摄大范围景物创造了条件；鱼眼镜头在接近被摄物拍摄时能造成非常强烈的透视效果，强调被摄物近大远小的对比，使所摄画面具有一种震撼人心的感染力；鱼眼镜头具有相当长的景深，有利于表现照片的长景深效果。
本实施例对不同种类相机提供不同类型的标定板，提高了获得的第一外参信息的准确性。
可选地，上述实施例中基于第一图像以及第一摄像设备的内参信息，确定第一摄像设备在第一坐标系下的第一外参信息，包括：根据多个第一摄像设备中每对第一摄像设备对应的图像之间的重叠区域，以及每个所述第一摄像设备的内参信息，确定固定标定板中的第一设定点位在世界坐标系下与第一设定点位在第一图像对应的图像坐标系下的映射关系。
其中，每对所述第一摄像设备为位置相邻的两个第一摄像设备。
例如，当移动载体为车辆，第一摄像设备为鱼眼相机时，可在该车辆上设置4路鱼眼相机，分别设置在车前、车后以及车身两侧，根据4路鱼眼相机的内参信息，以及4路鱼眼相机两两之间图像的重叠区域，计算车辆表面上任一点到地面2D点的映射关系。将鱼眼相机作为所述第一摄像设备的好处是：由于鱼眼相机的视角较大，在车身4个方向(每个方向对应180度)分别设置4个鱼眼相机的情况下，由于鱼眼相机的视角可达220°或230°，因此，每两个相邻的鱼眼相机获得的两个图像之间必然存在重叠区域，进而基于该重叠区域计算空间立体物体表面的一点映射到地面2D点的映射关系。
基于第一设定点位在世界坐标系下与第一设定点位在图像坐标系下的映射关系，确定 一对第一摄像设备中每个第一摄像设备在第一坐标系下的外参信息。
本实施例中，在已知鱼眼相机包括畸变值、中心点和焦距信息等相机内参信息的前提下，基于该摄像设备的内参信息，找到世界坐标系空间的一点与图像像素坐标的对应关系，即实际空间中的一点(本实施例中为固定标定板上的一点)于该点被摄像设备采集到图像中的像素坐标的对应关系；实现根据第一摄像设备通过识别固定标定板内角点计算第一摄像设备在世界坐标系下的空间位姿。
例如，根据分别对4路摄像模组所处车身的位置建立世界标定坐标系，获取标定坐标系下对应每组棋盘格左上角角点距离信息，例如，通过激光水平仪、卷尺量取多个摄像设备中每个摄像对应各个棋盘格左上内角点在对应标定坐标系下的空间位置距离；在获得每个第一摄像设备与对应的标定板中的第一设定点位在世界坐标系下的距离，以及该第一摄像设备的内参信息时，以及第一设定点位在世界坐标系下与第一设定点位在图像坐标系下的映射关系的情况下，即可获得该第一摄像设备的第一外参信息，此时的第一坐标系下为以该第一摄像设备为原点的相机坐标系；本实施例通过设置于地面的固定标定板实现了4路鱼眼相机的同时标定，提高了摄像设备的标定速度。
可选地，上述实施例中基于第二图像以及所述第二摄像设备的内参信息，确定第二摄像设备在第一坐标系下的第一外参信息，包括：基于第二图像和第二摄像设备的内参信息，确定移动标定板中第二设定点位在世界坐标系下与第二设定点位在第二图像对应的图像坐标系下的映射关系。
可选地，该第二设定点位可以为移动标定板中的一个角点。例如，位于移动标定板左上角角点。
基于第二设定点位在世界坐标系下与第二设定点位在图像坐标系下的映射关系，确定摄像设备在第一坐标系下的第一外参信息。
本实施例可知对至少8路窄角摄像设备的标定，例如，当移动载体为车辆时，在车头、车尾、车左前门附近、车右前门附近、车左后轮附近、车右后轮附近、车头左角以及车头右角分别设置8路窄角相机；根据8路窄角相机可视范围内对应的墙面棋盘格进行棋盘格内角点识别提取像素坐标；根据采集的图像中的角点的像素坐标和计算关系。
其中，计算关系包括摄像设备与该图像对应的移动标定板上角点的距离(例如，通过实际测量确定该距离)以及摄像设备的内参信息，计算出该角点的理想坐标，所述理想坐标表示该摄像设备位姿不存在任何偏移的情况下获得的像素坐标。
具体地，可包括：根据采集到的图像中角点的像素坐标，确定该像点的实际像高；根据该角点的实际像高和计算关系，计算出该角点的理想像高；根据该角点的理想像高，确定该角点的理想坐标；基于该角度在图像中的像素坐标和理想坐标之间的关系即可确定该摄像设备的位姿信息；本实施例实现了同时对多路摄像设备的外参标定，提高了对车辆等移动载体上设置的多路普通相机的外参标定效率，实现了量产标定的技术效果。
在上述图6所示实施例的基础上，步骤5022可以包括：
基于第一坐标系的原点和第二坐标系的原点之间的位置关系，确定转换参数；
基于转换参数对第一外参信息进行平移和旋转，得到摄像设备在第二坐标系下的目标外参信息。
可选地，针对一个摄像设备，第一坐标系可以为以该摄像设备为原点的摄像坐标系。 其中，在该坐标系下，摄像头指向的方向是x轴，垂直x轴向左的是y轴，垂直x轴向上的是z轴，即确定坐标系的情况下，就已知该坐标系的原点。当第二坐标系为以该摄像设备到地面的垂点为原点的坐标系时，该转换参数仅包括在世界坐标系下的z轴方向上的距离信息，当然，当第二坐标系的原点为其他位置时，还可能包括x轴和/或y轴上的距离信息。
通过转换参数对第一外参信息执行相应的平移和旋转，即可得到摄像设备在第二坐标系下的目标外参信息；因此，本实施例不仅实现了快速获取外参信息，还通过坐标系转换可将所有摄像设备的外参信息统一到同一坐标系下，方便对整个移动载体进行处理，增加了本实施例的应用范围和场景。
本公开实施例提供的任一种多摄像设备外参标定方法可以由任意适当的具有数据处理能力的设备执行，包括但不限于终端设备和服务器等。
示例性电子设备
图7图示了根据本公开实施例的电子设备的框图。如图7所示，该电子设备70包括至少一个处理器71和至少一个存储器72。
其中，每个处理器71可以是中央处理单元(central processing unit，CPU)，或者是具有数据处理能力和/或指令执行能力的其他形式的处理单元，并且可以控制电子设备70中的其他组件以执行期望的功能。
存储器72可以包括一个或多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。所述易失性存储器，例如可以包括随机存取存储器(Random Access Memory，RAM)和/或高速缓冲存储器(cache)等。所述非易失性存储器例如可以包括只读存储器(Read-Only Memory，ROM)、硬盘、闪存等。
在所述计算机可读存储介质上可以存储一个或多个计算机程序指令，处理器71可以运行所述程序指令，以实现上文所述的本公开的各个实施例的多摄像设备外参标定方法以及/或者其他期望的功能。在所述计算机可读存储介质中还可以存储其他信息，诸如输入信号、信号分量、噪声分量等各种内容。
在一个示例中，电子设备70还可以包括：输入装置73和输出装置74，这些组件通过总线系统和/或其他形式的连接机构(未示出)互连。
可选地，该输入装置73可以是上述的麦克风或麦克风阵列，用于捕捉声源的输入信号。当该电子设备是一种单机设备时，该输入装置73可以是通信网络连接器，用于接收所采集的输入信号。
可选地，该输入装置73还可以包括例如键盘、鼠标等等。该输出装置74可以向外部输出各种信息，包括确定出的距离信息、方向信息等。该输出装置74可以包括例如显示器、扬声器、打印机、以及通信网络及其所连接的远程输出设备等等。
当然，为了简化，图7中仅示出了该电子设备70中与本公开有关的组件中的一些，省略了诸如总线、输入/输出接口等等的组件。除此之外，根据具体应用情况，电子设备70还可以包括任何其他适当的组件。
示例性计算机程序产品和计算机可读存储介质
除了上述方法和设备以外，本公开的实施例还可以是计算机程序产品，其包括计算机 程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本公开各种实施例的多摄像设备外参标定方法中的步骤。
所述计算机程序产品可以以一种或多种程序设计语言的任意组合来编写用于执行本公开实施例操作的程序代码，所述程序设计语言包括面向对象的程序设计语言，诸如Java、C++等，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。
此外，本公开的实施例还可以是计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本公开各种实施例的多摄像设备外参标定方法中的步骤。
所述计算机可读存储介质可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以包括但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
以上结合具体实施例描述了本公开的基本原理，但是，需要指出的是，在本公开中提及的优点、优势、效果等仅是示例而非限制，不能认为这些优点、优势、效果等是本公开的各个实施例必须具备的。另外，上述公开的具体细节仅是为了示例的作用和便于理解的作用，而非限制，上述细节并不限制本公开为必须采用上述具体的细节来实现。
本说明书中各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似的部分相互参见即可。对于系统实施例而言，由于其与方法实施例基本对应，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
本公开中涉及的器件、装置、设备、系统的方框图仅作为例示性的例子并且不意图要求或暗示必须按照方框图示出的方式进行连接、布置、配置。如本领域技术人员将认识到的，可以按任意方式连接、布置、配置这些器件、装置、设备、系统。诸如“包括”、“包含”、“具有”等等的词语是开放性词汇，指“包括但不限于”，且可与其互换使用。这里所使用的词汇“或”和“和”指词汇“和/或”，且可与其互换使用，除非上下文明确指示不是如此。这里所使用的词汇“诸如”指词组“诸如但不限于”，且可与其互换使用。
可能以许多方式来实现本公开的方法和装置。例如，可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本公开的方法和装置。用于所述方法的步骤的上述顺序仅是为了进行说明，本公开的方法的步骤不限于以上具体描述的顺序，除非以其它方式特别说明。此外，在一些实施例中，还可将本公开实施为记录在记录介质中的程序，这些程序包括用于实现根据本公开的方法的机器可读指令。因而，本公开还覆盖存储用于执行根据本公开的方法的程序的记录介质。
还需要指出的是，在本公开的装置、设备和方法中，各部件或各步骤是可以分解和/或重新组合的。这些分解和/或重新组合应视为本公开的等效方案。
提供所公开的方面的以上描述以使本领域的任何技术人员能够做出或者使用本公开。对这些方面的各种修改对于本领域技术人员而言是非常显而易见的，并且在此定义的一般原理可以应用于其他方面而不脱离本公开的范围。因此，本公开不意图被限制到在此示出的方面，而是按照与在此公开的原理和新颖的特征一致的最宽范围。
为了例示和描述的目的已经给出了以上描述。此外，此描述不意图将本公开的实施例限制到在此公开的形式。尽管以上已经讨论了多个示例方面和实施例，但是本领域技术人员将认识到其某些变型、修改、改变、添加和子组合。

Claims (14)

  1. 一种多摄像设备的外参标定设备，所述设备包括：
    多个移动标定板，用于完成设置在设定空间内的载有多个摄像设备的移动载体上的所有所述摄像设备的外参标定；每个所述移动标定板分别设置于滑轨上，所述滑轨设置在所述设定空间内的墙面上；
    控制设备，用于控制所述多个移动标定板中每个所述移动标定板沿所述移动标定板对应的所述滑轨滑动。
  2. 根据权利要求1所述的设备，其中，所述控制设备，还用于控制具有连接关系的所述多个滑轨之间的滑动，实现控制所述移动标定板在所在墙面对应的平面上上下左右滑动。
  3. 根据权利要求2所述的设备，其中，所述控制设备控制所述移动标定板沿着对应的滑轨滑动可实现以下至少一种移动模式：设定单位移动、设定长度移动和连续移动；
    所述控制设备上设置有回归按键；
    所述控制设备，还用于利用所述回归按键控制所述多个移动标定板回归到初始位置。
  4. 根据权利要求1所述的设备，其中，每个所述移动标定板上还设置有锁扣装置，用于在断电时锁定所述棋盘标定板的位置。
  5. 根据权利要求1-4任一项所述的设备，其中，所述设定空间的大小根据所述移动载体的大小进行设置。
  6. 根据权利要求5所述的设备，其中，所述设备还包括：
    限位导轨，设置在所述设定空间的地面上，用于限制所述移动载体在所述设定空间内的位置。
  7. 一种多摄像设备的外参标定方法，所述方法包括：
    响应于载有多个摄像设备的移动载体进入设定空间，所述设定空间内包括多个移动标定版；
    控制所述多个移动标定板移动到所述多个摄像设备中每个摄像设备对应的位置；
    基于所述多个移动标定板实现所述多个摄像设备的外参标定。
  8. 根据权利要求7所述的方法，其中，控制所述多个移动标定板移动到所述多个摄像设备中每个摄像设备对应的位置，包括：
    控制所述多个移动标定板中的每个所述移动标定板在至少一个滑轨上滑动，将所述移动标定板移动到所述多个摄像设备中每个摄像设备对应的位置。
  9. 根据权利要求7所述的方法，其中，所述方法还包括：
    响应于完成所述多个摄像设备的外参标定；
    所述多个移动标定板自动返回初始位置。
  10. 一种多摄像设备的外参标定方法，所述方法包括：
    基于移动载体上设置的多个摄像设备中的每个摄像设备对对应的标定板进行图像采集，得到多幅图像；其中，每个所述摄像设备对应一幅图像；
    基于所述多幅图像中的每个图像，以及所述多个摄像设备中每个所述摄像设备的内参信息，确定所述多个摄像设备中每个所述摄像设备的目标外参信息。
  11. 根据权利要求10所述的方法，其中，
    所述基于所述多幅图像中的每个图像以及所述多个摄像设备中每个所述摄像设备的内参信息，确定所述多个摄像设备中每个所述摄像设备的目标外参信息，包括：
    针对所述多个摄像设备中每个所述摄像设备，基于每个所述摄像设备对应的图像和每个所述摄像设备的内参信息，确定所述多个摄像设备在第一坐标系下的第一外参信息；
    对所述多个摄像设备的第一外参信息进行坐标系转换，得到所述多个摄像设备在第二坐标系下的目标外参信息。
  12. 根据权利要求11所述的方法，其中，所述多个摄像设备包括多个第一摄像设备和多个第二摄像设备，所述标定板包括固定标定板和移动标定板；每个所述第一摄像设备采集的第一图像对应多个固定标定板，每个所述第二摄像设备采集的第二图像对应一个移动标定板；
    所述基于所述摄像设备对应的图像和所述摄像设备的内参信息，确定所述摄像设备在第一坐标系下的第一外参信息，包括：
    基于所述第一图像以及所述第一摄像设备的内参信息，确定所述第一摄像设备在第一坐标系下的第一外参信息；
    基于所述第二图像以及所述第二摄像设备的内参信息，确定所述第二摄像设备在第一坐标系下的第一外参信息。
  13. 一种计算机可读存储介质，所述存储介质存储有计算机程序，
    当所述计算机程序被执行时，实现如权利要求7至12中任一项所述的多摄像设备的外参标定方法。
  14. 一种电子设备，所述电子设备包括：
    处理器；以及，
    用于存储所述处理器可执行指令的存储器；
    所述处理器，用于从所述存储器中读取所述可执行指令，并执行所述指令以实现如权利要求7至12任一项所述的多摄像设备的外参标定方法。
PCT/CN2022/075099 2021-06-23 2022-01-29 多摄像设备的外参标定设备和方法、存储介质、电子设备 WO2022267481A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022564660A JP2023534582A (ja) 2021-06-23 2022-01-29 複数カメラの外部パラメータのキャリブレーション装置及び方法、記憶媒体、電子装置
US18/003,798 US20230252679A1 (en) 2021-06-23 2022-01-29 Extrinsic parameter calibration device and method for multiple camera devices, storage medium, and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110700660.0 2021-06-23
CN202110700660.0A CN113345031A (zh) 2021-06-23 2021-06-23 多摄像设备外参标定设备和方法、存储介质、电子设备

Publications (1)

Publication Number Publication Date
WO2022267481A1 true WO2022267481A1 (zh) 2022-12-29

Family

ID=77478031

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/075099 WO2022267481A1 (zh) 2021-06-23 2022-01-29 多摄像设备的外参标定设备和方法、存储介质、电子设备

Country Status (4)

Country Link
US (1) US20230252679A1 (zh)
JP (1) JP2023534582A (zh)
CN (1) CN113345031A (zh)
WO (1) WO2022267481A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115797467A (zh) * 2023-02-02 2023-03-14 深圳市德驰微视技术有限公司 车辆相机标定结果检测方法、装置、设备及存储介质

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111738923B (zh) * 2020-06-19 2024-05-10 京东方科技集团股份有限公司 图像处理方法、设备及存储介质
CN113345031A (zh) * 2021-06-23 2021-09-03 地平线征程(杭州)人工智能科技有限公司 多摄像设备外参标定设备和方法、存储介质、电子设备
CN113984342A (zh) * 2021-11-01 2022-01-28 南斗六星系统集成有限公司 适用于不同轴距长度的汽车环视系统标定装置以及方法
CN117141359A (zh) * 2022-05-23 2023-12-01 华为技术有限公司 一种标定方法和装置
CN114792343B (zh) * 2022-06-21 2022-09-30 阿里巴巴达摩院(杭州)科技有限公司 图像获取设备的标定方法、获取图像数据的方法、装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103985118A (zh) * 2014-04-28 2014-08-13 无锡观智视觉科技有限公司 一种车载环视系统摄像头参数标定方法
US20150208040A1 (en) * 2014-01-22 2015-07-23 Honeywell International Inc. Operating a surveillance system
CN210571298U (zh) * 2019-08-01 2020-05-19 北京汽车股份有限公司 全景影像标定装置
CN112215886A (zh) * 2020-10-10 2021-01-12 深圳道可视科技有限公司 全景泊车的标定方法及其系统
CN113345031A (zh) * 2021-06-23 2021-09-03 地平线征程(杭州)人工智能科技有限公司 多摄像设备外参标定设备和方法、存储介质、电子设备

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2523163B1 (en) * 2011-05-10 2019-10-16 Harman Becker Automotive Systems GmbH Method and program for calibrating a multicamera system
CN107205146A (zh) * 2016-03-16 2017-09-26 中航华东光电（上海）有限公司 多功能自动化标定系统及其标定方法
CN108564629A (zh) * 2018-03-23 2018-09-21 广州小鹏汽车科技有限公司 一种车载摄像头外部参数的标定方法及系统
CN108596982A (zh) * 2018-04-24 2018-09-28 深圳市航盛电子股份有限公司 一种简易的车载多目摄像机环视系统标定方法及装置
CN108805936B (zh) * 2018-05-24 2021-03-26 北京地平线机器人技术研发有限公司 摄像机外参标定方法、装置和电子设备
CN109360245B (zh) * 2018-10-26 2021-07-06 魔视智能科技(上海)有限公司 无人驾驶车辆多相机系统的外参数标定方法
DE102018008539B9 (de) * 2018-11-01 2023-03-16 Baumer Optronic Gmbh Kalibriervorrichtung und Verfahren zur Kamerakalibrierung für die Photogrammetrie
CN109615659B (zh) * 2018-11-05 2023-05-05 成都西纬科技有限公司 一种车载多摄像机环视系统的摄像机参数获得方法及装置
CN109859280A (zh) * 2019-03-31 2019-06-07 深圳市普渡科技有限公司 摄像头标定系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150208040A1 (en) * 2014-01-22 2015-07-23 Honeywell International Inc. Operating a surveillance system
CN103985118A (zh) * 2014-04-28 2014-08-13 无锡观智视觉科技有限公司 一种车载环视系统摄像头参数标定方法
CN210571298U (zh) * 2019-08-01 2020-05-19 北京汽车股份有限公司 全景影像标定装置
CN112215886A (zh) * 2020-10-10 2021-01-12 深圳道可视科技有限公司 全景泊车的标定方法及其系统
CN113345031A (zh) * 2021-06-23 2021-09-03 地平线征程(杭州)人工智能科技有限公司 多摄像设备外参标定设备和方法、存储介质、电子设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115797467A (zh) * 2023-02-02 2023-03-14 深圳市德驰微视技术有限公司 车辆相机标定结果检测方法、装置、设备及存储介质
CN115797467B (zh) * 2023-02-02 2023-07-28 深圳市德驰微视技术有限公司 车辆相机标定结果检测方法、装置、设备及存储介质

Also Published As

Publication number Publication date
US20230252679A1 (en) 2023-08-10
CN113345031A (zh) 2021-09-03
JP2023534582A (ja) 2023-08-10

Similar Documents

Publication Publication Date Title
WO2022267481A1 (zh) 多摄像设备的外参标定设备和方法、存储介质、电子设备
WO2022120567A1 (zh) 一种基于视觉引导的自动化标定系统
CN113657224B (zh) 车路协同中用于确定对象状态的方法、装置、设备
US10964040B2 (en) Depth data processing system capable of performing image registration on depth maps to optimize depth data
WO2022053015A1 (zh) 基于单目图像的目标检测方法和装置
EP3998580B1 (en) Camera calibration method and apparatus, electronic device, storage medium, program product, and road side device
CN103593658A (zh) 一种基于红外图像识别的三维空间定位系统
CN110796738B (zh) 巡检设备状态跟踪的三维可视化方法及装置
US20230025058A1 (en) Image rectification method and device, and electronic system
CN114399588B (zh) 三维车道线生成方法、装置、电子设备和计算机可读介质
WO2015098222A1 (ja) 情報処理装置及び情報処理方法及びプログラム
WO2023231435A1 (zh) 视觉感知方法、装置、存储介质和电子设备
US11893884B2 (en) Method for acquiring three-dimensional perception information based on external parameters of roadside camera, and roadside device
Wang et al. A novel binocular vision system for accurate 3-D reconstruction in large-scale scene based on improved calibration and stereo matching methods
CN109785444A (zh) 图像中现实平面的识别方法、装置及移动终端
CN111656404B (zh) 图像处理方法、系统及可移动平台
Kurka et al. Automatic estimation of camera parameters from a solid calibration box
Wang et al. The real-time depth map obtainment based on stereo matching
CN112348874B (zh) 一种车道线的结构化参数表示确定方法及装置
CN116136408A (zh) 室内导航方法、服务器、装置和终端
WO2021057582A1 (zh) 图像匹配、3d成像及姿态识别方法、装置及系统
CN111462251B (zh) 摄像机标定方法及终端
CN112308905B (zh) 一种平面标志物的坐标确定方法及装置
WO2023103884A1 (zh) 对象模型建立方法、装置、电子设备及存储介质
Fernández-Rodicio et al. Projection surfaces detection and image correction for mobile robots in HRI

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022564660

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 22826990

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE