WO2018196391A1 - Dispositif et procédé d'étalonnage de paramètres externes d'un appareil photo embarqué - Google Patents

Dispositif et procédé d'étalonnage de paramètres externes d'un appareil photo embarqué Download PDF

Info

Publication number
WO2018196391A1
WO2018196391A1 PCT/CN2017/115493 CN2017115493W WO2018196391A1 WO 2018196391 A1 WO2018196391 A1 WO 2018196391A1 CN 2017115493 W CN2017115493 W CN 2017115493W WO 2018196391 A1 WO2018196391 A1 WO 2018196391A1
Authority
WO
WIPO (PCT)
Prior art keywords
road traffic
vehicle
traffic markings
coordinates
time
Prior art date
Application number
PCT/CN2017/115493
Other languages
English (en)
Chinese (zh)
Inventor
杨臻
杨磊
沈骏强
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2018196391A1 publication Critical patent/WO2018196391A1/fr

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

Definitions

  • the present application relates to the field of computer vision technology, and in particular, to an external parameter calibration method and device for a vehicle camera.
  • car camera plays an increasingly important role in assisted driving and automatic driving.
  • the external parameters of the onboard camera play an important role in the process of associating the environment around the vehicle with the digital image captured by the onboard camera.
  • the external parameter of the vehicle camera refers to the translation distance and rotation angle of the vehicle camera relative to the vehicle.
  • the external parameters of the on-board camera are calibrated at the time of shipment or maintenance, that is, by detecting the calibration of the known size and position of the digital image placed around the vehicle while the vehicle is stationary.
  • External parameters of the car camera As shown in Figure 1, a black and white calibration plate is placed 1 meter in front of the front of the vehicle. The board surface is perpendicular to the vehicle body, and the physical dimensions of each small square on the board surface are known.
  • calibrating the external parameters of the onboard camera use the onboard camera to capture the black and white calibration plate, obtain the coordinates of the corner points in the digital image of the captured digital image, calculate the coordinates of the corner point in the vehicle coordinate system, and then establish the corner point.
  • the one-to-one correspondence between the coordinates in the digital image and the coordinates of the corner points in the vehicle body coordinate system after iterative calculation and optimization, can calculate the external parameters of the vehicle camera.
  • the above method of calibrating external parameters is cumbersome and can only be calibrated while the vehicle is stationary.
  • factors such as the bump of the vehicle and the deformation of the camera lens may cause the external parameters of the vehicle camera to change.
  • the external parameters of the onboard camera are inaccurate, there is an error in the process of associating the environment around the vehicle with the digital image captured by the onboard camera, which affects safe driving.
  • the solution provided in the prior art cannot calibrate the external parameters of the vehicle camera during the running of the vehicle, thereby causing the accuracy of the external parameters of the vehicle camera to be reduced, which affects safe driving.
  • the present application provides an external parameter calibration method and device for a vehicle camera to solve the problem that the external parameters of the vehicle camera cannot be calibrated during the running of the vehicle in the prior art.
  • the present application provides an external parameter calibration method for an in-vehicle camera, the method comprising the steps of: acquiring local coordinates of a plurality of road traffic markings in a digital image captured by an onboard camera, wherein the plurality of road traffic markings are in a plurality of road traffic markings Include at least two non-parallel line segments for indicating a position of the plurality of road traffic markings in the digital image; determining global coordinates of the plurality of road traffic markings in the digital map, the global coordinates are used to indicate the The position of a plurality of road traffic markings in the digital map; the local coordinates of the plurality of road traffic markings and the plurality of road traffic markings The global coordinate calculation yields an external parameter of the onboard camera that is used to indicate the translational distance and angle of rotation of the onboard camera relative to the vehicle.
  • the method provided by the first aspect can calibrate the external parameters of the vehicle camera in real time during the running of the vehicle, so that the external parameters can be corrected in time when the external parameters of the vehicle camera are changed, so that the information provided by the vehicle camera is further improved. To be accurate, the safety of driving can be improved.
  • acquiring local coordinates of multiple road traffic markings in the digital image captured by the onboard camera may be implemented by performing edge detection on the digital image and acquiring multiple Local coordinates of non-zero pixel points; straight line fitting of multiple non-zero pixel points, obtaining local coordinates of multiple candidate line segments; performing linear clustering on multiple candidate line segments to obtain local coordinates of multiple road traffic markings.
  • the external parameters of the vehicle camera are calculated, which may be implemented by: local coordinates of the plurality of road traffic markings and global coordinates of the plurality of road traffic markings Solving the homography matrix (Homography); decomposing the homography matrix to obtain a translation vector and a rotation matrix, wherein the translation vector is used to indicate the translation distance of the vehicle camera relative to the vehicle, and the rotation matrix is used to indicate the vehicle camera relative to the vehicle Rotation angle.
  • Homography homography matrix
  • the above homography matrix can be solved by calculating the external parameters as follows:
  • i takes a positive integer not greater than N
  • N is the number of multiple road traffic markings.
  • the above translation vector can be obtained by calculating the external parameters as follows:
  • T is the translation vector
  • the above rotation matrix can be obtained by calculating the external parameters as follows:
  • R [r1 r2 r3] is the rotation matrix
  • ⁇ represents the modulo operation
  • ⁇ represents the cross product operation
  • the digital image captured by the onboard camera may be pre-processed before acquiring the local coordinates of the plurality of road traffic markings in the digital image captured by the onboard camera.
  • the pre-processing operation mainly performs graying, brightness balancing and noise reduction processing on the digital image, so that a plurality of road traffic markings in the pre-processed digital image are more easily detected, thereby acquiring the plurality of pieces. Local coordinates of road traffic markings.
  • the location of the vehicle in the digital map may also be determined; The position determination in the digital map satisfies the preset condition.
  • the preset condition includes at least one of the following: the distance between the position of the vehicle in the digital map and the intersection in the digital map is less than the first preset distance; the distance between the position of the vehicle in the digital map and the sidewalk in the digital map is less than the first The second preset distance; the distance between the position of the vehicle in the digital map and the stop line in the digital map is less than the third preset distance.
  • first distance, the second distance, and the third distance may be according to factors such as a CCD (Charge-coupled Device) pixel of the vehicle camera, horizontal resolution, minimum illumination, weather conditions, and illumination intensity. Artificial setting.
  • CCD Charge-coupled Device
  • the method described in the foregoing first aspect or any possible implementation manner thereof may be repeatedly performed on the in-vehicle camera to obtain a plurality of external parameters; A plurality of external parameters are determined by the adjustment calculation method to determine the optimal external parameters.
  • the above implementation manner is used to optimize a plurality of external parameters obtained by multiple calibrations to obtain an optimal external parameter, which can reduce the error of the external parameter, so that the finally determined optimal external parameter is more accurate.
  • a specific implementation method for determining the optimal external parameters based on a plurality of external parameters using the adjustment calculation method is as follows:
  • the following operations are performed for the first external parameter and the second external parameter: calculating the T1 time according to the position and posture of the vehicle in the digital map at time T1, the global coordinates of the plurality of road traffic markings at the time T1, and the second external parameter
  • the local coordinates of the projection of the plurality of road traffic markings, and the calculated local coordinates of the plurality of road traffic markings at the time T1 and the local coordinates of the plurality of road traffic markings at the time T1 are obtained, and the first difference is obtained.
  • the first external parameter and the second external parameter are For any two external parameters, the time T1 is the time at which the first external parameter is obtained, and the time T2 is the time at which the second external parameter is obtained.
  • the first difference and the second difference obtained by the solution are optimized by a least squares method to obtain an optimal external parameter.
  • the external parameter implementation error can be minimized, so that the optimal external parameter is more accurate than the first external parameter and the second external parameter.
  • the present application provides an external parameter calibration device for a vehicle camera, which includes a driving computer and a car navigation system. among them,
  • the driving computer is configured to obtain local coordinates of a plurality of road traffic markings in the digital image captured by the vehicle camera, the plurality of road traffic markings including at least two non-parallel line segments, the local coordinates are used to indicate the plurality of road traffic The position of the line in the digital image.
  • the vehicle navigation system is configured to determine global coordinates of the plurality of road traffic markings in the digital map, and the global coordinates are used to indicate the position of the plurality of road traffic markings in the digital map.
  • the driving computer is also used for the local coordinates of the plurality of road traffic markings and the global of the plurality of road traffic markings
  • the coordinates acquire external parameters of the onboard camera, which are used to indicate the translational distance and angle of rotation of the onboard camera relative to the vehicle.
  • the driving computer acquires the local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera during the running of the vehicle, and then the vehicle The navigation system determines the global coordinates of the plurality of road traffic markings in the digital map, and the driving computer acquires the external parameters of the vehicle camera according to the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings.
  • the external parameter calibration device of the vehicle camera provided by the second aspect can calibrate the external parameters of the vehicle camera in real time during the running of the vehicle, so that the external parameters can be corrected in time when the external parameters of the vehicle camera are changed, so that The information provided by the car camera is more accurate and can improve the safety of driving.
  • the driving computer acquires external parameters of the vehicle camera according to local coordinates of the plurality of road traffic markings and global coordinates of the plurality of road traffic markings, specifically: driving The computer calculates the external parameters of the vehicle camera by calculating the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings; or, the driving computer sets the local coordinates of the plurality of road traffic markings and the plurality of roads The global coordinates of the traffic markings are sent to other terminals to obtain external parameters of the vehicle camera calculated by other terminals.
  • the operation of calculating the external parameters of the vehicle camera according to the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings may be performed by the driving computer in the device provided by the second aspect, or may be performed by other terminals.
  • the calculation result (external parameters of the vehicle camera) is sent to the driving computer.
  • the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings may be transmitted to other terminals, and the other terminals are based on the local coordinates of the plurality of road traffic markings.
  • the external parameters are sent to the driving computer.
  • the driving computer when the driving computer acquires the local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera, the driving computer is specifically configured to: perform edge detection on the digital image, and obtain more Local coordinates of non-zero pixel points; straight line fitting of multiple non-zero pixel points to obtain local coordinates of multiple candidate line segments; linear clustering of multiple candidate line segments to obtain local coordinates of multiple road traffic markings .
  • the driving computer calculates the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings, and obtains the external parameters of the vehicle camera
  • the method is: solving a homography matrix according to local coordinates of the plurality of road traffic markings and global coordinates of the plurality of road traffic markings; decomposing the homography matrix to obtain a translation vector and a rotation matrix, wherein the translation vector is used In order to indicate the translation distance of the onboard camera relative to the vehicle, the rotation matrix is used to indicate the angle of rotation of the onboard camera relative to the vehicle.
  • the driving computer is further configured to preprocess the digital image captured by the vehicle camera before acquiring local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera.
  • the pre-processing operation performed by the driving computer mainly performs graying, brightness balancing and noise reduction processing on the digital image, so that a plurality of road traffic markings in the pre-processed digital image are more easily detected, thereby Obtain local coordinates of the plurality of road traffic markings.
  • the in-vehicle navigation system is further configured to determine, before the driving computer acquires local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera, determine the vehicle in the digital map. Location; then the predetermined condition is determined based on the location of the vehicle in the digital map.
  • the preset condition includes at least one of the following: a position of the vehicle in the digital map and an intersection in the digital map The distance is less than the first preset distance; the distance between the position of the vehicle in the digital map and the sidewalk in the digital map is less than the second preset distance; the distance between the position of the vehicle in the digital map and the stop line in the digital map is less than the third pre- Set the distance.
  • first distance, the second distance, and the third distance may be manually set according to factors such as CCD pixels, horizontal resolution, minimum illumination, weather conditions, and illumination intensity of the on-vehicle camera.
  • the driving computer is further configured to: repeatedly perform the steps performed by the driving computer in the device described in the second aspect or any possible implementation manner thereof on the vehicle camera Obtaining a plurality of external parameters; determining an optimal external parameter by using an adjustment calculation method according to the obtained plurality of external parameters.
  • a plurality of external parameters obtained by multiple calibrations are optimized by the driving computer to obtain an optimal external parameter, which can reduce the error of the external parameter, so that the finally determined optimal external parameter is more accurate.
  • the apparatus further includes a vehicle driving state unit, where the vehicle driving state unit is configured to determine a position and a posture of the vehicle in the digital map;
  • the specific operation can be realized as follows:
  • the following operations are performed for the first external parameter and the second external parameter: calculating the T1 time according to the position and posture of the vehicle in the digital map at time T1, the global coordinates of the plurality of road traffic markings at the time T1, and the second external parameter
  • the local coordinates of the projection of the plurality of road traffic markings, and the calculated local coordinates of the plurality of road traffic markings at the time T1 and the local coordinates of the plurality of road traffic markings at the time T1 are obtained, and the first difference is obtained.
  • the first external parameter and the second external parameter are For any two external parameters, the time T1 is the time at which the first external parameter is obtained, and the time T2 is the time at which the second external parameter is obtained.
  • the first difference and the second difference obtained by the solution are optimized by a least squares method to obtain an optimal external parameter.
  • the external parameter implementation error can be minimized, so that the optimal external parameter is more accurate than the first external parameter and the second external parameter.
  • the present application provides a computer readable storage medium having stored therein instructions that, when executed on a computer, cause the computer to perform the first aspect described above or various possible implementations thereof The method provided in .
  • the present application provides a computer program product comprising instructions which, when executed on a computer, cause the computer to perform the method provided in the first aspect or various possible implementations thereof.
  • FIG. 1 is a schematic diagram of an external parameter calibration process of a vehicle camera provided by the prior art
  • FIG. 2 is a schematic structural view of a plurality of road traffic markings provided by the present application.
  • FIG. 3 is a schematic structural diagram of another plurality of road traffic markings provided by the present application.
  • FIG. 4 is a schematic flow chart of a method for external parameter calibration of a vehicle camera according to the present application.
  • FIG. 5 is a flowchart of Sobel edge detection provided by the present application.
  • FIG. 6 is a schematic diagram of a process for determining an optimal external parameter according to the present application.
  • FIG. 7 is a schematic flowchart diagram of another external parameter calibration method of a vehicle camera according to the present application.
  • FIG. 8 is a schematic structural diagram of an external parameter calibration device for a vehicle camera according to the present application.
  • a car camera is a sensor used to assist driving or autopilot.
  • the image captured by the on-board camera can determine the relationship between the vehicle and the surrounding environment, thus providing necessary information for lane correction, distance maintenance, and reverse operation to ensure safe driving.
  • the external parameters of the onboard camera play an important role in determining the relationship between the vehicle and the surrounding environment.
  • the external parameter of the vehicle camera refers to the translation distance and rotation angle of the vehicle camera relative to the vehicle. According to the image of the surrounding environment captured by the onboard camera and the external parameters of the onboard camera, the positional relationship between the vehicle and the surrounding objects (such as parking lines, street signs, lane lines, walls) can be determined, thereby correcting the lane correction and the distance between the vehicles. Operations such as reversing provide the necessary information.
  • the translation distance and rotation angle of the on-board camera relative to the vehicle may change due to factors such as road conditions, duration of use, and use environment, which may result in the inability to accurately determine the relationship between the vehicle and the surrounding environment by the on-board camera. Therefore, even if the external parameters of the onboard camera in the vehicle have been accurately determined when the vehicle is shipped from the factory, a solution for determining the external parameters of the onboard camera is required during the running of the vehicle to provide more accurate information for safe driving.
  • the present application provides an external parameter calibration method and device for the vehicle camera.
  • the method and the device are based on the same inventive concept. Since the principles of the method and the device for solving the problem are similar, the implementation of the device and the method can be referred to each other, and the repeated description is not repeated.
  • Global coordinates refer to the coordinates of an object in the global coordinate system
  • local coordinates refer to the coordinates of an object in a local coordinate system.
  • the global coordinate system is also called the world coordinate system, and its coordinate origin is a fixed point in the space.
  • the global coordinate system is an absolute coordinate system, and all objects in the space can be determined by the global coordinate system as the reference.
  • the local coordinate system is for an object.
  • the local coordinate system takes a certain point in the object (generally the center of the object) as the coordinate origin, and the rotation, translation and other operations of the object are all performed around the local coordinate system.
  • the global coordinate system may be a world coordinate system used in the digital map to represent the position of the object;
  • the local coordinate system may be a vehicle coordinate system, such as at a certain point in the vehicle (such as the axes of the two rear wheels)
  • the midpoint is the right-hand coordinate system of the coordinate origin, the X-axis of the vehicle traveling direction, and the upward direction of the vertical body plane.
  • the internal parameters include parameters such as the position of the optical center of the vehicle camera, focal length, pixel size, and lens distortion parameters;
  • the external parameters refer to the translation distance and rotation angle of the vehicle camera relative to the vehicle.
  • the translation distance of the vehicle camera relative to the vehicle means that the vehicle camera is regarded as a mass point, and the coordinates (x, y, z) of the mass point in the vehicle coordinate system O-x1y1z1 can indicate the translation of the vehicle camera relative to the vehicle.
  • the camera coordinate system O-x2y2z2 is established with the center of mass of the vehicle camera as the origin, and it is assumed that the vehicle coordinate system O-x1y1z1 is rotated by ⁇ 1, ⁇ 2, and ⁇ 3 around the x1 axis, the y1 axis, and the z1 axis, respectively.
  • the x1 axis and the x2 axis have the same direction in three-dimensional space
  • the y1 axis and the y2 axis have the same direction in three-dimensional space
  • the z1 axis and the z2 axis have the same direction in three-dimensional space
  • the internal parameters are determined when the vehicle camera is manufactured, and the accuracy is high and the change is small during the use of the vehicle camera.
  • the internal parameters of the same model of the vehicle camera are small, and the external parameters are small. Due to factors such as road conditions, length of use, use environment, and installation errors, the external parameters of the same type of on-board camera are highly different.
  • the installation error may cause the external parameters of the vehicle camera to change; for example, during the running of the vehicle, the bump of the vehicle may cause the translation distance and the rotation angle of the vehicle camera to change with respect to the vehicle, and thus This causes the external parameters of the on-board camera to change.
  • Digital maps are maps that are stored and consulted digitally using computer technology and are a collection of discrete data of ground features with defined coordinates and attributes.
  • the digital map supports zooming in or out of the display scale, direction rotation, and angle of view conversion without affecting the display effect.
  • Digital maps provide global coordinates of multiple road traffic markings in a digital map.
  • the position of the vehicle in the digital map can be determined by the in-vehicle navigation system.
  • a plurality of road traffic markings in a digital image may also be referred to as structured information in a digital image, and the plurality of road traffic markings include at least two non-parallel segments.
  • the global coordinates of multiple road traffic markings are recorded in the digital map. That is to say, the global coordinates of a plurality of road traffic markings can be obtained through a digital map. Therefore, in practical applications, multiple road traffic markings usually refer to lane lines, stop lines, sidewalk lines, etc. on the road surface where the vehicle is traveling. These road traffic markings are clear and easy to shoot, and there will be intersections of marking lines in specific road sections. The global coordinates of these reticle are also recorded in the digital map.
  • a plurality of road traffic markings are not limited to lane lines, stop lines, sidewalk lines, etc. on the road surface, as long as the plurality of road traffic marking lines include at least two non-parallel line segments, and the plurality of road traffic marking lines
  • the global coordinates can be recorded in the digital map.
  • the plurality of road traffic markings in the digital image captured by the onboard camera may be two lane lines and a stop line as shown in FIG. 2 when the vehicle camera travels to the intersection.
  • a stop line and a lane line can constitute a plurality of road traffic lines of the digital image.
  • a plurality of road traffic markings in the digital image captured by the onboard camera may be a parking lane and a lane line as shown in FIG. 3 when the vehicle camera travels to the intersection.
  • the parking lane includes two line segments that are parallel to each other and intersect the lane line.
  • a digital map is loaded in the car navigation system, and the car navigation system can provide the position and posture signals of the vehicle.
  • the position and posture of the vehicle are relative to the world coordinate system.
  • the vehicle is regarded as a mass point, and the coordinates (x, y, z) of the mass point in the world coordinate system O-x0y0z0 are the position information of the vehicle; it is assumed that the world coordinate system O-x0y0z0 is around the x0 axis, the y0 axis and After the z0 axis rotates the three angles ⁇ 4, ⁇ 5, and ⁇ 6, the x0 axis and x1
  • the axes are in the same direction in three-dimensional space, the y0 axis is the same as the y1 axis in three-dimensional space, and the z0 axis is the same as the z1 axis in three-dimensional space, then the three angles ⁇ 4, ⁇ 5, and ⁇ 6 can be regarded
  • the vehicle navigation system may include a Global Positioning System (GPS), and an Inertial Measurement Unit (IMU) such as a gyroscope.
  • GPS Global Positioning System
  • IMU Inertial Measurement Unit
  • the plurality referred to in the present application means two or more.
  • the terms "first”, “second” and the like are used for the purpose of distinguishing the description, and are not to be construed as indicating or implying a relative importance, nor as an indication or suggestion.
  • FIG. 4 is a flow chart of a method for external parameter calibration of a vehicle camera provided by the present application. The method comprises the following steps:
  • S401 Acquire local coordinates of a plurality of road traffic markings in the digital image captured by the onboard camera.
  • the plurality of road traffic markings comprise at least two non-parallel line segments, and the local coordinates of the plurality of road traffic markings in the digital image are used to indicate the positions of the plurality of road traffic markings in the digital image.
  • the plurality of road traffic markings include two parallel lane lines and a stopping line that is perpendicular to both lane lines.
  • a plurality of road traffic markings are limited to include at least two non-parallel line segments, and global coordinates of the plurality of road traffic markings are correspondingly recorded in the digital map.
  • the present application does not limit the number and position of the plurality of road traffic markings except for the two non-parallel segments.
  • the digital image captured by the vehicle camera Before acquiring the local coordinates of the plurality of road traffic markings in the digital image captured by the onboard camera, in order to more easily obtain the local coordinates of the plurality of road traffic markings in the digital image, the digital image captured by the vehicle camera may be obtained Pretreatment is performed.
  • the pre-processing operation mainly performs grayscale, brightness balance and noise reduction processing on the digital image, thereby making it easier to acquire a plurality of road traffic lines in the digital image.
  • the position of the vehicle in the digital map is updated in real time in the car navigation system, so the car navigation system can determine whether the preset condition is met according to the position of the vehicle in the digital map, and issue an instruction when the preset condition is met.
  • the process of calibrating the external parameters of the onboard camera shown in Figure 4 is initiated.
  • the scenario that satisfies the preset condition is not limited to the following three.
  • the distance of the location of the vehicle in the digital map from the intersection in the digital map is less than the first predetermined distance.
  • the position of the vehicle in the digital map is 100 meters from the intersection in the digital map, it can be considered as satisfying the preset condition. This is because: when the vehicle is 100 meters away from the intersection, the on-board camera can clearly capture the digital image containing the lane line and the stop line, while the lane line and the stop line satisfy the plurality of road traffic lines including at least two non- Parallel line segment requirements, therefore, the vehicle can be considered to meet the preset conditions when it is 100 meters away from the intersection.
  • the distance of the location of the vehicle in the digital map from the sidewalk in the digital map is less than the second predetermined distance. Similar to the first method, when the distance between the position of the vehicle in the digital map and the sidewalk in the digital map is less than the second preset distance (for example, 100 meters), the lane line and the sidewalk line satisfy at least the plurality of road traffic lines including at least The requirement of two non-parallel segments, therefore, the distance between the vehicle and the sidewalk is less than the second preset distance can be regarded as satisfying the preset condition.
  • the second preset distance for example, 100 meters
  • the distance of the location of the vehicle in the digital map from the stop line in the digital map is less than the third predetermined distance.
  • the third scenario is similar to the first scenario, and is also composed of a plurality of road traffic markings by lane lines and stop lines, and will not be described here.
  • the first distance, the second distance, and the third distance may be manually set according to factors such as CCD pixels, horizontal resolution, minimum illumination, weather conditions, and illumination intensity of the on-vehicle camera.
  • factors such as CCD pixels, horizontal resolution, minimum illumination, weather conditions, and illumination intensity of the on-vehicle camera.
  • the first preset distance can be set to 100 meters on a sunny day with strong illumination intensity; the first preset can be set on a cloudy day with weak illumination intensity
  • the distance is set to 80 meters, 70 meters, and so on.
  • Determining whether the preset condition is satisfied according to the position of the vehicle in the digital map may cause a plurality of road traffic markings in the digital image captured by the onboard camera, so that it is easier to acquire multiple pieces of the digital image captured by the onboard camera when performing S401. Local coordinates of road traffic markings.
  • S402 Determine global coordinates of the plurality of road traffic markings in the digital map.
  • the digital map records discrete data of ground elements with certain coordinates and attributes, that is, the global coordinates of multiple road traffic lines recorded in the digital map.
  • S403 Calculate external parameters of the vehicle camera according to local coordinates of the plurality of road traffic markings and global coordinates of the plurality of road traffic markings.
  • edge detection when acquiring local coordinates of a plurality of road traffic markings in the digital image captured by the onboard camera, edge detection may be adopted.
  • the basic idea of edge detection is to determine the boundary of a plurality of road traffic markings in a digital image by identifying pixels in the digital image with significant changes in brightness, thereby determining local coordinates of the plurality of road traffic markings in the digital image.
  • acquiring local coordinates of the plurality of road traffic markings in the digital image captured by the onboard camera may be implemented by performing edge detection on the digital image to obtain local coordinates of the plurality of non-zero pixel points;
  • the zero pixel is straight line fitted to obtain the local coordinates of the plurality of candidate segments;
  • the plurality of candidate segments are linearly clustered to obtain the local coordinates of at least two non-parallel segments.
  • Edge detection algorithms that can be used for edge detection of digital images captured by on-board cameras include, but are not limited to, Sobel edge detection, Canny edge detection, Roberts edge detection, Prewitt edge detection, and the like.
  • the first step Sobel edge detection
  • the Sobel template is convolved on the digital image to obtain the horizontal edge response I v (x, y) and the vertical edge response I h (x, y) in the digital image:
  • I(x, y) represents the pixel value at (x, y) in the digital image.
  • thrd sobel is a binarization threshold; a point with a value of 1 in I'(x, y) is a non-zero pixel.
  • all non-zero pixels constitute multiple road traffic lines.
  • ( ⁇ , ⁇ ) is a parameter in the Hough space, which represents the distance from the straight line of the point (x, y) to the coordinate origin of the local coordinate system and the angle between the line and the x-axis of the local coordinate system.
  • each non-zero pixel point (x, y) corresponds to a cluster parameter in the Hough space.
  • the Hough transform coefficients ( ⁇ , ⁇ ) of each non-zero pixel point (x, y) are counted, and when ( ⁇ , ⁇ ) satisfies the following formula (4), the set of transform coefficients ( ⁇ , ⁇ ) is represented by a Possible line:
  • n represents the number of the digital image may be a straight line, thrd hough the threshold value Hough clustering.
  • the third step straight line clustering
  • Straight line clustering of the possible straight lines output in the second step avoids repeated detection of the same line.
  • the specific operation of the linear clustering may be: when the plurality of possible straight lines outputted in the second step, the difference between the maximum slopes of the several straight lines is less than thrd slope , and the difference between the largest intercepts is less than thrd intercept , Think of these lines as the same line.
  • the average slope and the average intercept of these straight lines are obtained as the straight line after clustering, and finally the linear equation in the local coordinate system is output:
  • a i , b i , c i can be regarded as local coordinates of the plurality of road traffic markings in the digital image.
  • N is the number of multiple road traffic markings.
  • the three steps of the Sobel edge detection may be implemented by three software modules, namely, an edge detection module, a Hough fitting module and a linear clustering module, and the operation flow of each module may be as shown in FIG. 5 .
  • an edge detection module namely, a Hough fitting module and a linear clustering module
  • the operation flow of each module may be as shown in FIG. 5 .
  • the specific operation of each module refer to the related description in the above three steps.
  • the local coordinates of a plurality of road traffic markings in the digital image captured by the onboard camera can be accurately obtained, and a data basis is provided for calculating the external parameters of the vehicle camera.
  • the local coordinates of the plurality of road traffic markings in the digital image and the global coordinates of the plurality of road traffic markings in the digital map may be calculated.
  • External parameters of the car camera the external parameters of the vehicle camera are calculated, which can be realized by: solving the homography matrix according to the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings;
  • the maturity matrix obtains a translation vector and a rotation matrix, wherein the translation vector is used to indicate the translation distance of the onboard camera relative to the vehicle, and the rotation matrix is used to indicate the rotation angle of the onboard camera relative to the vehicle.
  • the translation vector and the rotation matrix can be used to characterize the external parameters of the vehicle camera.
  • the rotation matrix is converted into a rotation vector according to the Rodrigues formula, and the rotation vector can also be used to indicate the rotation angle of the onboard camera relative to the vehicle.
  • the translation vector and the rotation vector can represent the external parameters of the onboard camera.
  • R [r1 r2 r3] is the rotation matrix
  • ⁇ represents the modulo operation
  • ⁇ represents the cross product operation
  • a rotation vector r may be employed to indicate the angle of rotation of the onboard camera relative to the vehicle.
  • the rotation vector r can be solved by the rotation matrix R.
  • the specific method is as follows:
  • a 32 is the element of the third row and the second column in the matrix A
  • a 13 is the element of the first row and the third column of the matrix A
  • a 21 is the element of the second row and the first column of the matrix A
  • r 11 is the element of the first row and the first column in the matrix R
  • r 22 is the element of the second row and the second column of the matrix R
  • r 33 is the element of the third row and the third column of the matrix R.
  • the solution of the rotation vector r is divided into the following three cases.
  • the first case is a first case:
  • the second case is a first case
  • p1 is the first element in p
  • p2 is the second element in p
  • p3 is the third element in p.
  • the third case is a first case.
  • the external parameters of the vehicle camera can be calibrated by the external parameter calibration method of the above-mentioned vehicle camera.
  • the external parameters of the on-board camera calculated at different times are not the same.
  • the external parameters obtained by multiple calibrations can be optimized to obtain the optimal external parameters, thereby further improving the accuracy of the external parameters.
  • the method shown in FIG. 4 may be repeatedly executed in the present application, and multiple external parameters are calculated; and then the optimal external parameters are determined by using the adjustment calculation method according to the calculated multiple external parameters.
  • the above scheme is used to optimize a plurality of external parameters to obtain an optimal external parameter, which can reduce the error of the external parameter, so that the finally determined optimal external parameter is more accurate.
  • adjustment calculation methods used to determine the optimal external parameters.
  • the following is an example of the least squares method of adjustment calculation.
  • the example shows how to determine the optimal external parameters based on multiple external parameters obtained by multiple calibrations.
  • the following operations are performed: the position and posture of the vehicle in the digital map according to the time T1, the global coordinates of the plurality of road traffic markings at the time T1, and a second external parameter, calculating a projected local coordinate of the plurality of road traffic markings at time T1, and calculating a projected local coordinate of the plurality of road traffic markings at a T1 time and a part of the plurality of road traffic markings at a time T1
  • the coordinate difference is obtained, and the first difference is obtained; according to the position and posture of the vehicle in the digital map at time T2, the global coordinates of the plurality of road traffic markings at the time T2, and the first external parameter, the plurality of road traffic signs at the time T2 are calculated.
  • the local coordinates of the projection of the line, and the calculated local coordinates of the plurality of road traffic markings at the time T2 calculated and the local coordinates of the plurality of road traffic markings at the time T2 are obtained to obtain a second difference.
  • the time T1 is the time at which the first external parameter is obtained
  • the time T2 is the time at which the second external parameter is obtained.
  • the first difference and the second difference obtained by the solution are optimized by a least squares method to obtain an optimal external parameter.
  • the local coordinate of the projection of the plurality of road traffic markings at the time T1 refers to: according to the second external parameter and the position and posture of the vehicle in the digital map at the time T1, the plurality of road traffic markings at the time T1 can be The global coordinates are converted into the local coordinates of the plurality of road traffic markings at time T1.
  • the local coordinates are not determined according to the digital image taken at time T1, but are obtained by the reverse derivation process described above, and therefore will be referred to in the present application. Is "project local coordinates".
  • the local coordinates of the projection of the plurality of road traffic markings at the time T1 are calculated according to the second external parameter, it is not difficult to imagine that the local coordinates of the plurality of road traffic markings at the time T1 and the plurality of road traffic at the time T1
  • the smaller the difference (first difference) of the local coordinates of the reticle the more accurate the second external parameter.
  • the smaller the second difference the more accurate the first external parameter.
  • the first difference and the second difference obtained by the solution are optimized by the least squares method, and the first difference and the second difference can be minimized, thereby minimizing the error of the external parameter.
  • the position and posture of the vehicle in the digital map can be recorded by the in-vehicle navigation system in the vehicle.
  • the in-vehicle navigation system may record the position and posture of the vehicle in the digital map when S403 is executed, and may also record the position and posture of the vehicle in the digital map after executing S403.
  • the vehicle is recorded in the digital navigation system.
  • the timing of the position and posture in the map is not limited.
  • a first difference value and a second difference value are obtained.
  • a second difference is optimized by least squares method to obtain an optimal external parameter; if three calibrations are performed for determining the optimal external parameter, three first difference values and three second difference values are obtained, that is, a hypothesis
  • the time points for performing the three calibrations are t1, t2, and t3, and then a first difference and a first second difference are respectively obtained for the time t1 and the time t2, the time t1, the time t3, the time t2, and the time t2, that is, finally Obtaining three first difference values and three second difference values.
  • the least square method is used to optimize according to the three first difference values and the three second difference values, and the optimal is obtained.
  • External parameters That is to say, the more times the calibration is performed, the more the number of the first difference and the second difference obtained, and the more accurate the value of the finally determined optimal external parameter.
  • the above scheme only takes the least square method, which is an adjustment calculation method, as an example, and gives a root.
  • the adjustment calculation method in the present application is not limited to the least squares method, and other methods that can implement the adjustment calculation can also be applied in the present application, thereby obtaining an optimal external parameter according to a plurality of external parameters.
  • the stop line s0, the lane line s1, and the lane line s2 are detected to constitute a plurality of road traffic lines, and the external parameter calibration process of the vehicle camera is started.
  • the first external parameter is obtained; while the external parameter is calibrated, the position and posture of the vehicle at time T1 are recorded.
  • the vehicle continues to drive forward, and travels to the stop line s3 at time T2.
  • the stop line s3, the lane line s4, and the lane line s5 are detected to form a plurality of road traffic lines, and the external parameter calibration process of the vehicle camera is started.
  • a second external parameter is obtained; while the external parameter is calibrated, the position and attitude of the vehicle at time T2 are recorded.
  • E 1 is a first difference
  • l i_t1 is a local coordinate of the plurality of road traffic markings at time T1.
  • l i_t2 ' is the projected local coordinate of the plurality of road traffic markings at time T2;
  • L i_t2 is the global coordinate of the plurality of road traffic markings at time T2;
  • K 1 is the first external parameter;
  • E 2 is a second difference
  • l i_t2 is a local coordinate of the plurality of road traffic markings at time T2.
  • the objective function of the least squares method is as follows:
  • the optimal external parameters are determined as an example. Therefore, when defining the objective function of the least squares method, the objective function is The sum of the square of the first difference and the square of the second difference; if the external parameters of the onboard camera are calibrated N times to determine the optimal external parameter, N>2, then when defining the objective function of the least squares method, The objective function is the sum of the square of the plurality of first differences and the square of the plurality of second differences. For example, in order to determine the optimal external parameters, the external parameters of the vehicle camera are calibrated three times, and three external parameters are obtained.
  • the first difference E1 and the second can be obtained.
  • the difference E2 according to the first calibration process and the third calibration process, the first difference E3 and the second difference E4 are obtained, and the first difference E5 and the third calibration process are obtained according to the second calibration process and the third calibration process.
  • the second difference E6 then the objective function J of the least squares method can be as shown in the following equation (15):
  • the method shown in FIG. 4 can be used to calibrate the external parameters of the vehicle camera in real time during the running of the vehicle, so that the external parameters can be corrected in time when the external parameters of the vehicle camera are changed, so that the information provided by the vehicle camera is more Accurate, can improve the safety of driving.
  • the present application further provides an external parameter calibration method for a vehicle camera, which is shown in FIG. 7 .
  • the method shown in Fig. 7 can be regarded as a specific example of the method shown in Fig. 4.
  • n external parameters are calculated by n parameter calculation units, and each parameter calculation unit performs steps 1 to 3 to obtain n external parameters, and records the position and posture of the vehicle. After each parameter calculation unit determines an external parameter, the n external parameters are optimized to obtain an optimal external parameter.
  • the method shown in FIG. 7 may include the following steps:
  • Step 1 Vehicle location
  • the car navigation system issues an instruction to activate the external parameter calibration process of the onboard camera.
  • Step 2 Obtain local coordinates of multiple road traffic markings
  • the global coordinates of the plurality of road traffic markings in the digital map and the local coordinates of the plurality of road traffic markings obtained in the digital image in the digital image are determined by querying the digital map, and the external parameters in the calibration process are calculated.
  • Step 4 Record the position and posture of the vehicle
  • the n external parameters calculated n times can be projected onto each other in a coordinate system at other times, and the optimal external is optimized by an adjustment algorithm such as least squares method. parameter.
  • the external parameter calibration method shown in FIG. 7 can be regarded as a specific example of the external parameter calibration method shown in FIG. 4, and the implementation manner not described in detail in FIG. 7 can be referred to the related description in FIG.
  • the present application further provides an external parameter calibration device for an on-vehicle camera, which can be used to perform an external parameter calibration method of the on-vehicle camera provided in FIG. 4 or FIG. 7.
  • the external parameter calibration device 800 (hereinafter referred to as the device 800) of the in-vehicle camera includes a driving computer 801 and a car navigation system 802. among them,
  • the driving computer 801 is configured to acquire local coordinates of a plurality of road traffic markings in the digital image captured by the vehicle camera, where the plurality of road traffic markings include at least two non-parallel line segments, the local coordinates are used to indicate the multiple roads The location of the traffic markings in the digital image.
  • the in-vehicle navigation system 802 is configured to determine global coordinates of the plurality of road traffic markings in the digital map, the global coordinates being used to indicate the position of the plurality of road traffic markings in the digital map.
  • the driving computer 801 is further configured to acquire an external parameter of the vehicle camera according to local coordinates of the plurality of road traffic markings and global coordinates of the plurality of road traffic markings, the external parameter is used to indicate a translation distance of the vehicle camera relative to the vehicle Rotation angle.
  • the driving computer 801 acquires the external parameters of the vehicle camera according to the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings
  • the driving computer 801 is specifically used for: the local coordinates of the plurality of road traffic markings by the driving computer 801 And calculating global coordinates of the plurality of road traffic markings to obtain external parameters of the vehicle camera; or, the driving computer 801 transmits local coordinates of the plurality of road traffic markings and global coordinates of the plurality of road traffic markings to other terminals, Obtain external parameters of the onboard camera calculated by other terminals.
  • other terminals include, but are not limited to, personal computers, handheld computers, personal digital assistants, smart phones, smart watches, and tablets.
  • the operation of calculating the external parameters of the vehicle camera according to the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings may be performed by the driving computer 801 in the device provided by the second aspect, or may be performed by other terminals.
  • the calculation result (external parameters of the in-vehicle camera) is transmitted to the driving computer 801.
  • the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings may be transmitted to other terminals, and the other terminals are based on the parts of the plurality of road traffic markings.
  • the external parameters are sent to the driving computer 801.
  • the driving computer 801 can directly calculate the external parameters of the vehicle camera based on the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings.
  • the driving computer 801 calculates the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings, and the specific manner of obtaining the external parameters of the vehicle camera may be: according to the local coordinates of the plurality of road traffic markings Solving the homography matrix with the global coordinates of the plurality of road traffic markings; decomposing the homography matrix to obtain a translation vector and a rotation matrix, wherein the translation vector is used to indicate the translation distance of the vehicle camera relative to the vehicle, and the rotation matrix is used Instructing the angle of rotation of the onboard camera relative to the vehicle.
  • the driving computer 801 can also obtain the local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera. Preprocess the digital image captured by the onboard camera. The preprocessing operation is mainly to grayscale the digital image. Brightness balance and noise reduction processing.
  • the driving computer 801 can initiate the calibration process of the external parameters of the onboard camera when the preset conditions are met.
  • the manner of determining whether the preset condition is met may be: the car navigation system 802 determines the position of the vehicle in the digital map before the driving computer 801 acquires the local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera. Then, it is judged based on the position of the vehicle in the digital map whether the preset condition is satisfied.
  • the preset condition includes at least one of the following: the distance between the position of the vehicle in the digital map and the intersection in the digital map is less than the first preset distance; the distance between the position of the vehicle in the digital map and the sidewalk in the digital map is less than the first The second preset distance; the distance between the position of the vehicle in the digital map and the stop line in the digital map is less than the third preset distance.
  • the first distance, the second distance, and the third distance may be manually set according to factors such as CCD pixels, horizontal resolution, minimum illumination, weather conditions, and illumination intensity of the vehicle camera.
  • the driving computer 801 when acquiring the local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera, is specifically configured to: perform edge detection on the digital image to obtain local coordinates of the plurality of non-zero pixel points; Straight line fitting is performed on a plurality of non-zero pixel points to obtain local coordinates of a plurality of candidate line segments; linearly clustering the plurality of candidate line segments to obtain local coordinates of the plurality of road traffic markings.
  • the driving computer 801 can repeatedly perform the above operations on the vehicle camera to obtain a plurality of external parameters; and then determine the optimality by using the adjustment calculation method according to the obtained multiple external parameters. External parameters.
  • Optimizing the multiple external parameters obtained by multiple calibrations to determine the optimal external parameters can reduce the error of the external parameters, so that the final determined optimal external parameters are more accurate.
  • the device 800 optimizes multiple external parameters obtained by multiple calibrations to obtain the optimal external parameters. A specific implementation of the parameters.
  • the in-vehicle navigation system 802 in device 800 records the position and attitude of the vehicle in the digital map each time the external parameters are calibrated.
  • the driving computer 801 determines the optimal external parameter by using the adjustment calculation method according to a plurality of external parameters, the following is achieved by:
  • the following operations are performed for the first external parameter and the second external parameter: calculating the T1 time according to the position and posture of the vehicle in the digital map at time T1, the global coordinates of the plurality of road traffic markings at the time T1, and the second external parameter
  • the local coordinates of the projection of the plurality of road traffic markings, and the calculated local coordinates of the plurality of road traffic markings at the time T1 and the local coordinates of the plurality of road traffic markings at the time T1 are obtained, and the first difference is obtained.
  • the first external parameter and the second external parameter are For any two external parameters, the time T1 is the time at which the first external parameter is obtained, and the time T2 is the time at which the second external parameter is obtained.
  • the first difference and the second difference obtained by the solution are optimized by a least squares method to obtain an optimal external parameter.
  • the position and posture of the vehicle in the digital map are determined by the in-vehicle navigation system 802.
  • the in-vehicle navigation system 802 in the present application may be composed of a GPS and a gyroscope, and the in-vehicle navigation system 802 may determine the position of the vehicle in the digital map by GPS when determining the position and posture of the vehicle in the digital map.
  • the gyroscope determines the pose of the vehicle in the digital map.
  • the external parameter calibration device 800 of the vehicle camera provided by the embodiment of the present application can be used to perform the external parameter calibration method of the vehicle camera shown in FIG. 4, and the external parameter calibration device 800 of the vehicle camera does not explain and describe the implementation in detail. Reference may be made to the related description in the method of the external parameter calibration device 800 of the in-vehicle camera shown in FIG.
  • the driving computer 801 acquires the local coordinates of the plurality of road traffic markings in the digital image captured by the vehicle camera during the running of the vehicle, and then The vehicle navigation system 802 determines the global coordinates of the plurality of road traffic markings in the digital map, and the driving computer 801 acquires the vehicle camera according to the local coordinates of the plurality of road traffic markings and the global coordinates of the plurality of road traffic markings. External parameters.
  • the device 800 can be used to calibrate the external parameters of the vehicle camera in real time during the running of the vehicle, so that the external parameters can be corrected in time when the external parameters of the vehicle camera are changed, so that the information provided by the vehicle camera is more accurate, and Improve the safety of driving.
  • the present application provides an external parameter calibration method and device for a vehicle camera, which realizes real-time calibration of external parameters of the vehicle camera during driving of the vehicle, and timely corrects external parameters when the external parameters of the vehicle camera change.
  • the information provided by the on-board camera is more accurate and can improve the safety of driving.
  • embodiments of the present application can be provided as a method, system, or computer program product.
  • the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware.
  • the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un dispositif et un procédé d'étalonnage de paramètres externes d'un appareil photo monté sur un véhicule, destinés à être utilisés afin de résoudre le problème de l'état de la technique selon lequel des paramètres externes d'un appareil photo monté sur un véhicule ne peuvent pas être étalonnés pendant le déplacement d'un véhicule. Le procédé consiste : à acquérir des coordonnées locales de multiples lignes de marquage de trafic routier dans une image numérique photographiée par un appareil photo monté sur un véhicule, les multiples lignes de marquage de trafic routier comprenant au moins deux segments de ligne non parallèles, et les coordonnées locales étant utilisées pour indiquer des positions des multiples lignes de marquage de trafic routier dans l'image numérique ; à déterminer des coordonnées globales des multiples lignes de marquage de trafic routier dans une carte numérique, les coordonnées globales étant utilisées pour indiquer des positions des multiples lignes de marquage de trafic routier dans la carte numérique ; et à calculer des paramètres externes de l'appareil photo monté sur véhicule en fonction des coordonnées locales et des coordonnées globales des multiples lignes de marquage de trafic routier, les paramètres externes étant utilisés pour indiquer une distance de translation et un angle de rotation de l'appareil photo monté sur véhicule par rapport à un véhicule.
PCT/CN2017/115493 2017-04-28 2017-12-11 Dispositif et procédé d'étalonnage de paramètres externes d'un appareil photo embarqué WO2018196391A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710295112.8 2017-04-28
CN201710295112.8A CN108805934B (zh) 2017-04-28 2017-04-28 一种车载摄像机的外部参数标定方法及装置

Publications (1)

Publication Number Publication Date
WO2018196391A1 true WO2018196391A1 (fr) 2018-11-01

Family

ID=63919361

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/115493 WO2018196391A1 (fr) 2017-04-28 2017-12-11 Dispositif et procédé d'étalonnage de paramètres externes d'un appareil photo embarqué

Country Status (2)

Country Link
CN (1) CN108805934B (fr)
WO (1) WO2018196391A1 (fr)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109615659A (zh) * 2018-11-05 2019-04-12 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
CN109741402A (zh) * 2018-12-26 2019-05-10 上海交通大学 基于激光雷达的小重合视野多摄像机联合标定方法
CN109740422A (zh) * 2018-11-22 2019-05-10 深圳市元征科技股份有限公司 一种识别汽车的方法及装置
CN109754434A (zh) * 2018-12-27 2019-05-14 歌尔科技有限公司 相机标定方法、装置、用户设备及存储介质
CN110276807A (zh) * 2019-05-30 2019-09-24 文远知行有限公司 车载摄像头辅助标定方法、装置、设备和介质
CN111275766A (zh) * 2018-12-05 2020-06-12 杭州海康威视数字技术股份有限公司 图像坐标系与gps坐标系的标定方法、装置及摄像机
CN111598956A (zh) * 2020-04-30 2020-08-28 商汤集团有限公司 标定方法、装置和系统
CN111815719A (zh) * 2020-07-20 2020-10-23 北京百度网讯科技有限公司 图像采集设备的外参数标定方法、装置、设备及存储介质
CN112184821A (zh) * 2019-07-01 2021-01-05 上海安亭地平线智能交通技术有限公司 相机翻滚角的调整方法和装置、存储介质、电子设备
CN112419423A (zh) * 2020-10-30 2021-02-26 上海商汤临港智能科技有限公司 一种标定方法、装置、电子设备及存储介质
CN112819711A (zh) * 2021-01-20 2021-05-18 电子科技大学 一种基于单目视觉的利用道路车道线的车辆反向定位方法
CN113139031A (zh) * 2021-05-18 2021-07-20 智道网联科技(北京)有限公司 用于自动驾驶的交通标识的生成方法及相关装置
CN113450415A (zh) * 2020-03-26 2021-09-28 阿里巴巴集团控股有限公司 一种成像设备标定方法以及装置
CN115601435A (zh) * 2022-12-14 2023-01-13 天津所托瑞安汽车科技有限公司（Cn） 车辆姿态检测方法、装置、车辆及存储介质
CN117649454A (zh) * 2024-01-29 2024-03-05 北京友友天宇系统技术有限公司 双目相机外参自动校正方法、装置、电子设备及存储介质
CN117649454B (zh) * 2024-01-29 2024-05-31 北京友友天宇系统技术有限公司 双目相机外参自动校正方法、装置、电子设备及存储介质

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111652937B (zh) * 2019-03-04 2023-11-03 广州汽车集团股份有限公司 车载相机标定方法和装置
CN111145260B (zh) * 2019-08-30 2024-01-30 广东星舆科技有限公司 一种基于车载的双目标定方法
CN111145249B (zh) * 2019-08-30 2024-02-27 广东星舆科技有限公司 一种基于车载的自动标定控制方法、存储介质和系统
CN111145262B (zh) * 2019-09-04 2024-01-26 广东星舆科技有限公司 一种基于车载的单目标定方法
CN110793544B (zh) * 2019-10-29 2021-12-14 北京百度网讯科技有限公司 路侧感知传感器参数标定方法、装置、设备及存储介质
CN111275768A (zh) * 2019-12-11 2020-06-12 深圳市德赛微电子技术有限公司 一种基于卷积神经网络的镜头标定方法及其系统
CN111380502B (zh) * 2020-03-13 2022-05-24 商汤集团有限公司 标定方法、位置确定方法、装置、电子设备及存储介质
CN113052904B (zh) * 2021-03-19 2022-12-13 上海商汤临港智能科技有限公司 一种定位方法、装置、电子设备及存储介质
CN114663524B (zh) * 2022-03-09 2023-04-07 禾多科技（北京）有限公司 多相机在线标定方法、装置、电子设备和计算机可读介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1564581A (zh) * 2004-04-15 2005-01-12 上海交通大学 交通监视环境下的摄像机标定方法
CN101727671A (zh) * 2009-12-01 2010-06-09 湖南大学 基于路面共线三点及其平行线的单摄像机标定方法
CN102013099A (zh) * 2010-11-26 2011-04-13 中国人民解放军国防科学技术大学 车载摄像机外参数交互式标定方法
CN102622744A (zh) * 2012-01-17 2012-08-01 浙江大学 一种基于多项式投影模型的长焦相机标定方法
CN103729837A (zh) * 2013-06-25 2014-04-16 长沙理工大学 一种单个路况摄像机的快速标定方法
EP3086284A1 (fr) * 2015-04-23 2016-10-26 Application Solutions (Electronics and Vision) Limited Estimation de paramètres de caméra extrinsèques provenant de lignes d'image

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102103747B (zh) * 2009-12-16 2012-09-05 中国科学院电子学研究所 采用参照物高度的监控摄像机外部参数标定方法
WO2013111229A1 (fr) * 2012-01-23 2013-08-01 日本電気株式会社 Dispositif, procédé et programme d'étalonnage d'un appareil de prise de vues

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1564581A (zh) * 2004-04-15 2005-01-12 上海交通大学 交通监视环境下的摄像机标定方法
CN101727671A (zh) * 2009-12-01 2010-06-09 湖南大学 基于路面共线三点及其平行线的单摄像机标定方法
CN102013099A (zh) * 2010-11-26 2011-04-13 中国人民解放军国防科学技术大学 车载摄像机外参数交互式标定方法
CN102622744A (zh) * 2012-01-17 2012-08-01 浙江大学 一种基于多项式投影模型的长焦相机标定方法
CN103729837A (zh) * 2013-06-25 2014-04-16 长沙理工大学 一种单个路况摄像机的快速标定方法
EP3086284A1 (fr) * 2015-04-23 2016-10-26 Application Solutions (Electronics and Vision) Limited Estimation de paramètres de caméra extrinsèques provenant de lignes d'image

Cited By (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109615659A (zh) * 2018-11-05 2019-04-12 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
CN109740422A (zh) * 2018-11-22 2019-05-10 深圳市元征科技股份有限公司 一种识别汽车的方法及装置
CN111275766A (zh) * 2018-12-05 2020-06-12 杭州海康威视数字技术股份有限公司 图像坐标系与gps坐标系的标定方法、装置及摄像机
CN111275766B (zh) * 2018-12-05 2023-09-05 杭州海康威视数字技术股份有限公司 图像坐标系与gps坐标系的标定方法、装置及摄像机
CN109741402A (zh) * 2018-12-26 2019-05-10 上海交通大学 基于激光雷达的小重合视野多摄像机联合标定方法
CN109741402B (zh) * 2018-12-26 2023-04-07 上海交通大学 基于激光雷达的小重合视野多摄像机联合标定方法
CN109754434A (zh) * 2018-12-27 2019-05-14 歌尔科技有限公司 相机标定方法、装置、用户设备及存储介质
CN109754434B (zh) * 2018-12-27 2023-08-29 歌尔科技有限公司 相机标定方法、装置、用户设备及存储介质
CN110276807A (zh) * 2019-05-30 2019-09-24 文远知行有限公司 车载摄像头辅助标定方法、装置、设备和介质
CN110276807B (zh) * 2019-05-30 2023-09-29 文远知行有限公司 车载摄像头辅助标定方法、装置、设备和介质
CN112184821A (zh) * 2019-07-01 2021-01-05 上海安亭地平线智能交通技术有限公司 相机翻滚角的调整方法和装置、存储介质、电子设备
CN112184821B (zh) * 2019-07-01 2023-03-10 上海安亭地平线智能交通技术有限公司 相机翻滚角的调整方法和装置、存储介质、电子设备
CN113450415A (zh) * 2020-03-26 2021-09-28 阿里巴巴集团控股有限公司 一种成像设备标定方法以及装置
CN111598956A (zh) * 2020-04-30 2020-08-28 商汤集团有限公司 标定方法、装置和系统
CN111815719A (zh) * 2020-07-20 2020-10-23 北京百度网讯科技有限公司 图像采集设备的外参数标定方法、装置、设备及存储介质
CN111815719B (zh) * 2020-07-20 2023-12-22 阿波罗智能技术(北京)有限公司 图像采集设备的外参数标定方法、装置、设备及存储介质
CN112419423A (zh) * 2020-10-30 2021-02-26 上海商汤临港智能科技有限公司 一种标定方法、装置、电子设备及存储介质
CN112819711B (zh) * 2021-01-20 2022-11-22 电子科技大学 一种基于单目视觉的利用道路车道线的车辆反向定位方法
CN112819711A (zh) * 2021-01-20 2021-05-18 电子科技大学 一种基于单目视觉的利用道路车道线的车辆反向定位方法
CN113139031A (zh) * 2021-05-18 2021-07-20 智道网联科技(北京)有限公司 用于自动驾驶的交通标识的生成方法及相关装置
CN113139031B (zh) * 2021-05-18 2023-11-03 智道网联科技(北京)有限公司 用于自动驾驶的交通标识的生成方法及相关装置
CN115601435A (zh) * 2022-12-14 2023-01-13 天津所托瑞安汽车科技有限公司（Cn） 车辆姿态检测方法、装置、车辆及存储介质
CN115601435B (zh) * 2022-12-14 2023-03-14 天津所托瑞安汽车科技有限公司 车辆姿态检测方法、装置、车辆及存储介质
CN117649454A (zh) * 2024-01-29 2024-03-05 北京友友天宇系统技术有限公司 双目相机外参自动校正方法、装置、电子设备及存储介质
CN117649454B (zh) * 2024-01-29 2024-05-31 北京友友天宇系统技术有限公司 双目相机外参自动校正方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN108805934A (zh) 2018-11-13
CN108805934B (zh) 2021-12-28

Similar Documents

Publication Publication Date Title
WO2018196391A1 (fr) Dispositif et procédé d'étalonnage de paramètres externes d'un appareil photo embarqué
US11715232B2 (en) Method and device to determine the camera position and angle
KR101787304B1 (ko) 교정 방법, 교정 장치 및 컴퓨터 프로그램 제품
AU2018282302B2 (en) Integrated sensor calibration in natural scenes
US20230143687A1 (en) Method of estimating three-dimensional coordinate value for each pixel of two-dimensional image, and method of estimating autonomous driving information using the same
CN108692719B (zh) 物体检测装置
JP2018124787A (ja) 情報処理装置、データ管理装置、データ管理システム、方法、及びプログラム
JP2006252473A (ja) 障害物検出装置、キャリブレーション装置、キャリブレーション方法およびキャリブレーションプログラム
JP2012075060A (ja) 画像処理装置及びそれを用いた撮像装置
CN110766760B (zh) 用于相机标定的方法、装置、设备和存储介质
EP3505865A1 (fr) Caméra embarquée, procédé de réglage de caméra embarquée, et système de caméra embarquée
CN112284416B (zh) 一种自动驾驶定位信息校准装置、方法及存储介质
CN105551020A (zh) 一种检测目标物尺寸的方法及装置
CN112819711B (zh) 一种基于单目视觉的利用道路车道线的车辆反向定位方法
JP2017181476A (ja) 車両位置検出装置、車両位置検出方法及び車両位置検出用コンピュータプログラム
JP2015194397A (ja) 車両位置検出装置、車両位置検出方法及び車両位置検出用コンピュータプログラムならびに車両位置検出システム
US11315276B2 (en) System and method for dynamic stereoscopic calibration
JP2009276233A (ja) パラメータ計算装置、パラメータ計算システムおよびプログラム
KR20130034528A (ko) 도로시설물 자동 위치측정 방법
KR102490521B1 (ko) 라이다 좌표계와 카메라 좌표계의 벡터 정합을 통한 자동 캘리브레이션 방법
CN110751693A (zh) 用于相机标定的方法、装置、设备和存储介质
CN116184430B (zh) 一种激光雷达、可见光相机、惯性测量单元融合的位姿估计算法
KR102195040B1 (ko) 이동식 도면화 시스템 및 모노카메라를 이용한 도로 표지 정보 수집 방법
CN116958218A (zh) 一种基于标定板角点对齐的点云与图像配准方法及设备
CN111563936A (zh) 一种相机外部参数自动标定方法及行车记录仪

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: 17907750

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: 17907750

Country of ref document: EP

Kind code of ref document: A1