CN110555885B - Calibration method and device of vehicle-mounted camera and terminal - Google Patents
Calibration method and device of vehicle-mounted camera and terminal Download PDFInfo
- Publication number
- CN110555885B CN110555885B CN201810550785.8A CN201810550785A CN110555885B CN 110555885 B CN110555885 B CN 110555885B CN 201810550785 A CN201810550785 A CN 201810550785A CN 110555885 B CN110555885 B CN 110555885B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- line
- mounted camera
- coordinate conversion
- sign
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- 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
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application provides a calibration method, device and terminal of a vehicle-mounted camera, wherein the method comprises the following steps: determining a marker line meeting a preset condition at the periphery of the vehicle; calculating to obtain the coordinate conversion relation between the vehicle and the mark line; identifying a sign line image corresponding to the sign line from an image shot by a vehicle-mounted camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line; according to the perspective view of the sign line, calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line; and calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line. By the method, the theodolite can be replaced to calibrate the vehicle-mounted camera, so that the operation is simpler, and the practicability of the vehicle-mounted camera is improved.
Description
Technical Field
The application relates to the technical field of auxiliary driving, in particular to a calibration method, device and terminal of a vehicle-mounted camera
Background
With the development trend of the intellectualization of automobiles, assisted driving, automatic driving, etc. are becoming research hotspots in academia and industry, in which the acquisition of vehicle-surrounding information based on vision prevents a collision of a vehicle as a main function of assisted driving.
The vehicle environment information acquired based on vision is based on a camera coordinate system, and how to determine a stable and accurate conversion relationship between the camera coordinate system and a vehicle self coordinate system is a very interesting problem for assisting driver developers. If the conversion relation between the camera coordinate system and the vehicle coordinate system cannot be accurately calculated, errors exist in the detection result of the vehicle anti-collision system based on the vehicle-mounted camera, so that the rated detection area is inconsistent with the actual detection area, errors exist in the transverse distance and the longitudinal distance between the obstacle and the vehicle, and accidents and dangers can even occur.
However, in practical applications, a method for calculating a conversion relationship between a camera coordinate system and a vehicle coordinate system is generally to measure parameters of a camera, a marker and a vehicle under the theodolite coordinate system by using a theodolite and the like, and then perform common point conversion to obtain a conversion relationship between the camera coordinate system and the theodolite coordinate system, and further obtain a conversion relationship between the camera coordinate system and the vehicle coordinate system. Because the method needs to use a professional measuring tool, the calibration between the camera and the vehicle coordinate system can be completed by a professional, and the calibration process is complex, time-consuming, labor-consuming and poor in practicability.
Disclosure of Invention
In view of the above, in order to solve the problem of complex calibration process caused by calculating the conversion relation between the camera coordinate system and the vehicle coordinate system by using the theodolite in the prior art, the application provides a calibration method, device and terminal of a vehicle-mounted camera, so as to realize self calibration of the vehicle-mounted camera through the vehicle, and simplify manual operation.
Specifically, the application is realized by the following technical scheme:
according to a first aspect of embodiments of the present application, there is provided a calibration method of an in-vehicle camera, the method including:
determining a marker line meeting a preset condition at the periphery of the vehicle;
calculating to obtain the coordinate conversion relation between the vehicle and the mark line;
identifying a sign line image corresponding to the sign line from an image shot by a vehicle-mounted camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line;
according to the perspective view of the sign line, calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line;
and calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line.
In one embodiment, the preset condition is specifically:
two straight lines or line segments intersecting perpendicularly, one of which is parallel to the body of the vehicle.
In one embodiment, the two perpendicular intersecting straight lines or line segments are specifically:
two straight lines or line segments perpendicularly intersecting in the same plane.
In one embodiment, the calculating the coordinate conversion relationship between the vehicle and the sign line includes:
and acquiring the transverse distance between the front point and the rear point on the parallel tangent line of the vehicle body and the marker line parallel to the vehicle body, and the longitudinal distance between the two points, and calculating to obtain the coordinate conversion relation between the vehicle and the marker line.
In one embodiment, the identifying the sign line image corresponding to the sign line from the image captured by the vehicle-mounted camera of the vehicle includes:
and extracting characteristic points of an image shot by the vehicle-mounted camera on the vehicle, and fitting the extracted characteristic points to obtain a mark line image corresponding to the mark line.
In one embodiment, the calculating, according to the perspective view of the sign line, the coordinate conversion relationship between the vehicle-mounted camera and the sign line includes:
and acquiring the center point coordinates of the perspective view of the sign line and the focal length of the vehicle-mounted camera, and calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line.
In one embodiment, when the vehicle is traveling straight, the calculating obtains a coordinate conversion relationship between the vehicle and the vehicle-mounted camera, and further includes:
and acquiring the coordinate conversion relations of the vehicles and the vehicle-mounted camera within a preset time, wherein the average value calculated by using a random sampling consistency algorithm or a least square method is the coordinate conversion relation of the coordinate conversion relations of the vehicles and the vehicle-mounted camera.
According to a second aspect of embodiments of the present application, there is provided a calibration device for an in-vehicle camera, the device including:
a sign line determining module for determining a sign line satisfying a preset condition in the periphery of the vehicle;
the first calculation module is used for calculating and obtaining the coordinate conversion relation between the vehicle and the sign line;
the image processing module is used for identifying a sign line image corresponding to the sign line from an image shot by an on-board camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line;
the second calculation module is used for calculating the coordinate conversion relation between the vehicle-mounted camera and the sign line according to the perspective view of the sign line;
and the relation conversion module is used for calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line.
According to a third aspect of embodiments of the present application, there is provided a calibration terminal for an in-vehicle camera, including a memory, a processor, a communication interface, a camera assembly, and a communication bus;
the memory, the processor, the communication interface and the camera component communicate with each other through the communication bus;
the camera component is used for collecting an image to be detected and sending the image to be detected to the processor through the communication bus;
the memory is used for storing a computer program;
the processor is configured to execute a computer program stored on the memory, where the processor executes the steps of the computer program to implement the calibration method of any vehicle-mounted camera provided in the embodiments of the present application.
According to a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of any of the calibration methods of the vehicle-mounted cameras provided by the embodiments of the present application.
As can be seen from the above embodiments, the present application can determine the marker line meeting the preset condition at the periphery of the vehicle, and compared with the calibration tools and complex calibration objects using theodolites, total stations, reference scales, etc. in the prior art, the present application uses only two perpendicular intersecting straight lines or line segments on the ground as the marker lines, such as lane lines, parking garage mark lines, etc., instead of the above-mentioned professional measurement tools, so that professional installers and complex operations are not required; calculating according to the determined mark line to obtain the coordinate conversion relation between the vehicle and the mark line; identifying a sign line image corresponding to the sign line from an image shot by a vehicle-mounted camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line; according to the perspective view of the sign line, calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line; and calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line. Therefore, the coordinate conversion relation between the vehicle and the marker line and the coordinate conversion relation between the vehicle-mounted camera and the marker line can be obtained through conversion, and the automatic high-precision calibration of the vehicle-mounted camera can be conveniently and rapidly completed by a common user under the condition that a professional calibration tool is not used.
In summary, the calibration method of the vehicle-mounted camera can replace a theodolite to calibrate the vehicle-mounted camera, so that the operation is simpler, and the practicability of the vehicle-mounted camera is improved.
Drawings
FIG. 1 is a coordinate system of an onboard camera;
FIG. 2 is a flow chart of one embodiment of a calibration method of the onboard camera of the present application;
FIG. 3 is a schematic diagram of coordinates of an onboard camera and a vehicle;
FIG. 4 is an image taken by an onboard camera;
FIG. 5 is a schematic diagram of marker line detection;
FIG. 6 is a graph of real-time attitude estimation of vehicle camera height and pitch angle;
FIG. 7 is a block diagram of one embodiment of a calibration device of the onboard camera of the present application;
fig. 8 is a hardware structure diagram of a calibration terminal of the vehicle-mounted camera where the calibration device of the vehicle-mounted camera is located.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
Fig. 1 shows a coordinate system of an onboard camera, wherein the onboard camera and the vehicle have 6 degrees of freedom of transformation, including displacement and rotation transformation in horizontal X-direction, vertical Y-direction and deep Z-direction, including pitch angle in X-direction, yaw angle in Y-direction and roll angle in Z-direction. The coordinate system conversion relation between the camera and the vehicle specifically refers to the displacement of the camera coordinate system in the X-axis, the Y-axis and the Z-axis relative to the vehicle coordinate system, and the pitch angle with the X-axis, the yaw angle with the Y-axis and the roll angle with the Z-axis respectively. If the conversion relation between the camera coordinate system and the vehicle coordinate system cannot be accurately calculated, errors exist in the detection result of the vehicle anti-collision system based on the vehicle-mounted camera, and accidents and dangers are easy to occur.
In the existing conversion relation method for calculating the vehicle-mounted camera coordinate system and the vehicle self coordinate system, parameters of the vehicle-mounted camera, the marker and the vehicle under the theodolite coordinate system are generally measured by using a theodolite and the like, and then common point conversion is carried out to obtain the conversion relation between the vehicle-mounted camera coordinate system and the theodolite coordinate system, and further the conversion relation between the vehicle-mounted camera coordinate system and the vehicle self coordinate system is obtained. The method is complex in calibration process, time-consuming and labor-consuming, and can be used for completing the calibration between the vehicle-mounted camera and the vehicle coordinate system only by a professional.
Based on the above, the application provides a calibration method of the vehicle-mounted camera, so as to realize the calibration of the vehicle-mounted camera instead of a theodolite, make the operation simpler and improve the practicability of the vehicle-mounted camera.
As follows, the following embodiments are shown to illustrate the calibration method of the vehicle-mounted camera provided in the present application.
Embodiment one:
referring to fig. 2, a flowchart of an embodiment of a calibration method of an in-vehicle camera of the present application includes the following steps:
in this embodiment, first, in order to reduce the influence of the road surface where the vehicle is located on the calibration result as much as possible, the calibration scene when calibrating the vehicle-mounted camera may be selected from a relatively flat ground or road surface. In this embodiment, the calibration scenario of the vehicle-mounted camera may include static calibration and dynamic calibration. When the vehicle is statically calibrated, scenes such as squares, underground parking lots, 4S shops and the like can be selected for calibration; when the vehicle is dynamically calibrated, scenes such as a flat road with clear lane lines can be selected for calibration. In addition, since the road surface is relatively flatter in a shorter distance, the marking lines can be selected on the ground or the road surface which is closer to the vehicle, so that the disturbance of the calibration caused by the uneven road surface can be reduced.
In this embodiment, the preset conditions of the selection marker line specifically include: the marking line is two straight lines or line segments which are perpendicularly intersected, wherein one straight line or line segment is parallel to the vehicle body of the vehicle, and accordingly the other straight line or line segment is perpendicular to the vehicle body. In a static calibration scenario, two straight lines or line segments that intersect vertically include two cases: in the first case, two sign lines are two perpendicular intersecting lines in the same plane, for example, parking sign lines perpendicular to each other on the ground of a parking lot; in the second case, the two sign lines are two perpendicular intersecting lines of different planes, for example, one ground sign line parallel to the car body on the ground of the parking lot, and the other object edge line standing above the ground and perpendicular to the ground. Since two straight lines or line segments intersecting perpendicularly in the same plane are more common in real life, the present application may select two straight lines or line segments intersecting perpendicularly in the same plane as the sign line. In the dynamic calibration scene, when the vehicle runs straight, a lane line of a lane where the vehicle runs and a straight line or a line segment perpendicular to the lane line can be selected as a mark line.
Because the prior art generally needs to use professional tools such as theodolites for calibration, operators are required to have certain professional knowledge, and the operation is difficult; the vehicle-mounted camera calibration method and device only use two perpendicular intersecting straight lines or line segments to calibrate the vehicle-mounted camera, so that a large number of measurement works can be reduced, the operation difficulty of an operator is reduced, and the two perpendicular intersecting straight lines or line segments used in the method and device are very common in life, so that the practicability of vehicle-mounted camera calibration can be further improved.
in this embodiment, after the marker line is determined, relevant parameters may be further measured, where the measured parameters include, but are not limited to: the vehicle width, the vehicle chassis height, the transverse distance between the front point and the rear point on the parallel tangent line of the vehicle body and the mark line parallel to the vehicle body, and the longitudinal distance between the two points; the vehicle-mounted camera can calculate and obtain the coordinate conversion relation between the vehicle and the sign line according to the obtained transverse distance between the front point and the rear point on the parallel tangent line of the vehicle body and the sign line parallel to the vehicle body and the longitudinal distance between the two points.
The following embodiments are used to respectively specifically describe a method for calculating the coordinate conversion relationship between the vehicle and the sign line in the static scene.
Embodiment two:
firstly, selecting a flatter field as a calibration field, such as a parking lot; then two sign lines which are vertically intersected are selected from the calibration field to serve as sign lines, then the vehicle is driven into the calibration field, the vehicle steering wheel is corrected, the vehicle is sideways to be parallel to the sign lines as much as possible or the included angle in a smaller threshold range is formed, as shown in fig. 3, a vehicle-mounted camera coordinate system X is established by taking the vehicle-mounted camera optical center as an origin point C O C Z C Establishing a vehicle coordinate system X by taking a chassis position right below the center of a vehicle head as an origin W O W Z W The method comprises the steps of carrying out a first treatment on the surface of the Measuring the lateral distance between the front and rear points on the parallel tangential line of the vehicle body side and the sign line parallel to the vehicle body (i.e. d in fig. 3) 1 And d 2 ) And the longitudinal distance between the two points (i.e. d in fig. 3 3 ). When the front and rear points on the parallel tangent line of the vehicle body are respectively measured to the transverse distance of the marker line parallel to the vehicle body, the transverse distance from the vehicle head and the vehicle tail to the marker line can be selected, the transverse distance from the front and rear wheels of the vehicle to the marker line can be measured, in addition, the average value can be measured for multiple times to reduce errors, or the transverse distances from the front and rear points on the parallel tangent line of the vehicle body on the left and right sides of the vehicle to the marker line parallel to the vehicle body can be respectively measured, so that the errors are further reduced. Finally, calculating an included angle sigma between the direction of the vehicle head and the marking line according to the formula (I), namely:
when the included angle sigma is larger than a certain threshold value, the vehicle orientation needs to be readjusted, and when the included angle sigma is smaller than the threshold value, the position of the vehicle in the calibration field is determined, and the coordinate conversion relation between the vehicle and the mark line is also determined.
Thus, the description of the second embodiment is completed.
in the present embodiment, the in-vehicle camera is first installed. Specifically, the vehicle-mounted camera is temporarily fixed at the installation position, and the horizontal X, vertical Y and longitudinal Z directions of the vehicle-mounted camera are roughly adjusted first, so that the vehicle-mounted camera is seen in front. The in-vehicle camera automatically or manually captures an image, adjusts the in-vehicle camera such that a line center line of the image captured by the in-vehicle camera coincides with the horizon, and a column center line is approximately located at the center of the lane such that an optical axis of the in-vehicle camera is parallel to the vehicle direction and parallel to the ground, as shown in fig. 4, (u) 0 ,v 0 ) Is the image center point. And then, carrying out fine adjustment on the posture of the vehicle-mounted camera in real time according to the included angle between the calibration line in the image shot by the vehicle-mounted camera and the vehicle, so that the angles of the vehicle-mounted camera in the horizontal X, vertical Y and longitudinal Z directions are smaller than a certain threshold value, and the installation of the vehicle-mounted camera is finished.
It should be noted that the manner of fine tuning the vehicle-mounted camera may be different according to the structures of different cameras, including adjusting the pitch angle of the vehicle-mounted camera module, or adjusting the slope of the inclined plane of the housing of the vehicle-mounted camera. Auxiliary tools such as horizontal bubbles can be arranged on the vehicle-mounted camera to adjust the angles of the vehicle-mounted camera in the horizontal X direction and the longitudinal Z direction. In addition, in the fine tuning process of the vehicle-mounted camera, the angles of the vehicle-mounted camera and the horizontal X, vertical Y and longitudinal Z directions can be displayed in real time through a display, and can also be displayed in a voice mode, a lamplight mode and the like until a user carries out fine tuning on the posture of the vehicle-mounted camera. In the static calibration, the angles of the camera around the horizontal X, vertical Y and longitudinal Z directions are finely adjusted, and in the dynamic calibration process, unless the posture of the vehicle-mounted camera is greatly changed due to special reasons, such as falling, movement, angle change and the like of the vehicle-mounted camera caused by human or external force, the posture of the vehicle-mounted camera is not finely adjusted, but only the vehicle-mounted camera is calibrated. If the automatic adjusting device for the posture of the vehicle-mounted camera is installed, fine adjustment in the dynamic calibration process can be performed. The fine adjustment method of the vehicle-mounted camera is not limited in this application.
After the installation of the vehicle-mounted camera is completed, a calibration field image can be manually or automatically shot in the running process of the vehicle; and then identifying a mark line image corresponding to the mark line from the image shot by the vehicle-mounted camera, wherein in an alternative embodiment, the vehicle-mounted camera can extract characteristic points of the shot image, and fitting the extracted characteristic points to obtain the mark line image corresponding to the mark line. The on-board camera can acquire the characteristic image of the marker line by using a line characteristic extraction method, and line characteristics which can be applied in the embodiment include but are not limited to gray scale, gradient, edge and other characteristics. The extracted feature points are subjected to linear fitting, and fitting methods which can be used include but are not limited to methods such as Hough transformation and least square method. The result of the marker line detection is shown in fig. 5, in which the detected marker lines (1) (2) (3) are indicated by black broken lines. And performing perspective transformation on the marker line image to obtain a perspective view of the marker line.
in this embodiment, a perspective view of the marker line is obtained, a center point coordinate in the perspective view and a focal length of the vehicle-mounted camera are obtained, and a coordinate conversion relationship between the vehicle-mounted camera and the marker line is calculated.
The following embodiments are used for respectively describing the calculation method of the coordinate conversion relation between the vehicle-mounted camera and the marker line in the static scene.
Embodiment III:
first, according to the perspective transformation theory of a pinhole camera, then:
in the formula (II), (u, v) is the image coordinates, (u) 0 ,v 0 ) Is the center coordinates of the image, (x) c ，y c ，z c ) Is the vehicle-mounted camera coordinates, and f is the unit focal length of the vehicle-mounted camera.
Because the vehicle-mounted camera needs to be parallel to the Z direction, the angle of the vehicle-mounted camera around the Z direction should be finely adjusted to 0, specifically, the adjustment is performed by using a mark line perpendicular to the optical axis direction of the vehicle-mounted camera, and the mark line can be a mark line perpendicular to the optical axis direction of the vehicle-mounted camera on the ground, or can be a mark line standing on the ground and perpendicular to the optical axis direction of the camera.
One method is a marker line on the ground perpendicular to the optical axis direction of the vehicle-mounted camera, as shown by a straight line (2) in fig. 5, which can be expressed as:
in the formula (III), d is the distance from the mark line to the vehicle-mounted camera, h is the height from the mark line to the vehicle-mounted camera, and the distance V in the direction of the image Y is specifically calculated by the formula (IV):
thus, a ground sign line perpendicular to the optical axis of the vehicle camera is described, on the image, as a horizontal straight line or line segment, the distance of which from the center of the image is related to the height and distance of the sign line from the vehicle camera. When the sign line is at infinity from the onboard camera, namely d → +) in the case of infinity, the air conditioner is controlled, then v=v 0 I.e. the projection of the sign line on the perspective is a horizontal straight line or line segment through the centre of the image.
Another method is a marker line standing on the ground and perpendicular to the optical axis direction of the vehicle-mounted camera, which can be expressed as:
in the formula (five), d is the distance between the edge of the object and the vehicle-mounted camera, and c is the lateral displacement between the edge of the object and the optical axis of the vehicle-mounted camera in the X direction, which is obtained by the formula (six):
therefore, the mark line standing on the ground and perpendicular to the optical axis direction of the vehicle-mounted camera is a vertical straight line or line segment on the image, and the distance of the straight line from the center of the image is related to the displacement and the distance of the edge of the object from the vehicle-mounted camera. When the sign line is at infinity from the onboard camera, namely d → +) in the case of infinity, the air conditioner is controlled, then u=u 0 I.e. the projection of the object edge onto the image is a vertical straight line or line segment through the center of the image.
Then, the angles and displacements of the cameras in the X-direction, Y-direction are estimated using the sign lines on the ground parallel to the optical axis of the in-vehicle camera, as indicated by black dotted lines (1) or (3) in fig. 5. When the ground sign line and the optical axis of the vehicle-mounted camera form a certain included angle theta around the X direction, the sign line coordinate can be expressed as a formula (seven):
in the formula (seventh), the slope k '=tan θ, the intercept b' =h, h is the height of the center of the vehicle-mounted camera from the ground, and c is the lateral displacement of the marker line from the optical axis of the vehicle-mounted camera in the X direction, which is calculated by the formula (eighth):
namely, the slope k and the intercept b of the projection straight line of the mark line on the image are respectively:
therefore, the slope of the projection straight line of the marker line on the image is related to the height of the vehicle-mounted camera, the displacement of the vehicle-mounted camera in the X direction, and the intercept is related to the angle of the optical axis of the vehicle-mounted camera around the X direction only, then the angle θ of the vehicle-mounted camera around the X direction is:
when the ground mark line and the optical axis of the vehicle-mounted camera form a certain included angle around the Y direction
When the sign line coordinates are expressed as:
in the formula (eleven), the slope
Intercept b″=c, h is the height of the vehicle camera center from the ground, c is the lateral displacement of the vehicle camera center in the X direction from the marker line, then:
namely, the slope and intercept of the projection straight line of the mark line on the image are respectively as follows:
thus, the slope of the projected straight line of the marker line on the image is related to the height of the vehicle-mounted camera, the displacement of the vehicle-mounted camera in the X-direction, and the intercept is related only to the angle of the vehicle-mounted camera optical axis around the Y-direction, then the angle of the vehicle-mounted camera around the Y-direction
The method comprises the following steps:
therefore, when the vehicle-mounted camera is in static calibration, the vehicle-mounted camera is firstly installed and coarse adjustment is carried out, so that the optical axis direction of the vehicle-mounted camera is approximately parallel to the ground; then manually or automatically adjusting the rotation angle of the vehicle-mounted camera around the Z direction according to the slope of a ground marking line or an object edge line in the image, wherein the ground marking line is a horizontal straight line or the object edge line is a vertical straight line in the image, and the rotation angle of the vehicle-mounted camera around the Z direction is approximately 0; according to the intercept of a ground marking line parallel to the optical axis in the image, adjusting the angles of the vehicle-mounted camera around the X direction and the Y direction; finally, one of the two displacements (namely the height of the vehicle-mounted camera or the transverse displacement of the vehicle-mounted camera from the ground marker line in the X direction) is obtained through direct measurement, and the other one of the two displacements (namely the transverse displacement of the vehicle-mounted camera from the ground marker line in the X direction or the camera height) is obtained according to the slope of the projection straight line in the image.
Thus, the description of the third embodiment is completed.
In this embodiment, the coordinate conversion relationship between the vehicle and the vehicle-mounted camera may be calculated according to the coordinate conversion relationship between the vehicle and the sign line and the coordinate conversion relationship between the vehicle-mounted camera and the sign line.
The method for obtaining the coordinate conversion relation between the vehicle and the vehicle-mounted camera is described in detail by taking static calibration as an example.
According to the coordinate conversion relationship between the vehicle and the sign line and the coordinate conversion relationship between the vehicle-mounted camera and the sign line obtained by calculation in the second and third embodiments, it is known that if the chassis position at the front edge of the center of the vehicle head is taken as the center O of the vehicle coordinate system w Then the vehicle-mounted camera coordinate system X C O C Z C With the coordinate system X of the vehicle w O w Z w The conversion relationship between them is as follows:
the displacement of the vehicle-mounted camera in the horizontal X direction is the horizontal displacement (c) of the vehicle-mounted camera relative to the sign line and the horizontal displacement (d) of the vehicle relative to the sign line 1 Etc.), vehicle width W car Is the difference between (a):
the angle of the vehicle-mounted camera in the horizontal X direction is the pitch angle theta of the vehicle-mounted camera, namely:
θ x =θ formula (sixteen)
The displacement of the vehicle-mounted camera in the vertical Y direction is the height h of the vehicle-mounted camera and the height h of the vehicle chassis c The difference is that:
y＝h c -h formula (seventeen)
The angle of the vehicle-mounted camera in the vertical Y direction is the yaw angle of the vehicle-mounted camera
The difference from the vehicle direction σ, namely:
the angle phi of the vehicle-mounted camera in the longitudinal Z direction is 0, namely:
φ z =0 formula (nineteen)
The displacement of the vehicle-mounted camera in the longitudinal Z direction is measured by measuring the distance d of the same object from the origin of the vehicle-mounted camera coordinate system and the distance d from the origin of the vehicle coordinate system c The method comprises the following steps:
z＝d c -d formula (twenty)
As an embodiment, in the dynamic calibration scenario, when the vehicle is traveling straight, the lane line may be used as a sign line, and the coordinate conversion relationships between the vehicle and the vehicle-mounted camera, which may be obtained in a preset time, may be statistically analyzed, and the average value calculated by using a random sampling consistency algorithm or a least square method may be the coordinate conversion relationship between the vehicle and the vehicle-mounted camera.
For example, before dynamic calibration, the rotation angle of the vehicle-mounted camera around the Z direction is negligible when the rotation angle is smaller than a preset threshold, otherwise, the rotation angle needs to be manually or automatically adjusted, the height of the vehicle-mounted camera is the same as that of the vehicle-mounted camera in a static state by default, and fine adjustment is not performed on the vehicle-mounted camera in the dynamic calibration process. And during dynamic calibration, estimating the angle of the vehicle-mounted camera in the horizontal X direction, the angle of the vertical Y direction and the displacement of the vehicle-mounted camera in the X direction. In the dynamic calibration process, the angle and displacement of the posture of the vehicle-mounted camera can have certain fluctuation under the influence of vehicle jolt and the like, as shown in fig. 6, so that a RANSAC (random sampling consistency algorithm), a least square method and the like can be adopted to obtain the average angle and displacement. In general cases, a RANSAC method is preferentially adopted, as in fig. 6, the real-time gesture of the vehicle-mounted camera is estimated, the estimation results with larger fluctuation are removed through multiple iterations, and only the rest estimation results are fitted, so that the average angles, displacements and the like of the vehicle-mounted camera in the horizontal X and vertical Y directions are obtained, and the specific RANSAC implementation method can refer to related literature materials and is not repeated in the scheme. In addition, due to the symmetry of the gesture fluctuation of the vehicle-mounted camera, namely the up-and-down fluctuation of the vehicle always happens in pairs, the dynamic calibration can be performed by adopting a least square method, namely in a calibration period T s And (3) performing least square fitting on all the real-time estimation results of the camera gestures, so as to obtain the average angles and displacements of the vehicle-mounted camera in the horizontal X and vertical Y directions. The least square method has relatively high speed, but has high requirement on the stability of the vehicle in the calibration process, and can be preferably adopted if the road surface has no large bump or fluctuation. The position relationship between the vehicle-mounted camera and the calibration line is obtained by estimating the pose of the camera, wherein the position relationship comprises displacement, angles and the like between the vehicle-mounted camera and the calibration line in the horizontal X, vertical Y and longitudinal Z directions, and the coordinate conversion relationship between the vehicle-mounted camera and the vehicle is obtained, and the position relationship comprises displacement, angles and the like between the vehicle-mounted camera and the vehicle in the horizontal X, vertical Y and longitudinal Z directions.
As can be seen from the above embodiments, the present application can determine the marker line meeting the preset condition around the vehicle, and compared with the prior art using the calibration tools such as theodolite, total station, reference ruler, and the like and the complex calibration object, the present application uses only two perpendicular intersecting straight lines or line segments on the ground, such as lane lines, parking garage marker lines, and the like, which are common in life, as marker lines, instead of the above-mentioned professional measurement tools, so that professional installers and complex operations are not needed; calculating according to the determined mark line to obtain the coordinate conversion relation between the vehicle and the mark line; identifying a sign line image corresponding to the sign line from an image shot by a vehicle-mounted camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line; according to the perspective view of the sign line, calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line; and calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line. Therefore, the coordinate conversion relation between the vehicle and the vehicle-mounted camera can be obtained through the coordinate conversion relation between the vehicle and the marker line and the coordinate conversion relation between the vehicle-mounted camera and the marker line, so that a common user can conveniently and rapidly complete automatic high-precision calibration of the vehicle-mounted camera under the condition of not using a professional calibration tool
In summary, the calibration method of the vehicle-mounted camera can replace a theodolite to calibrate the vehicle-mounted camera, so that the operation is simpler, and the practicability of the vehicle-mounted camera is improved.
Thus, the description of the first embodiment is completed.
Corresponding to the embodiment of the calibration method of the vehicle-mounted camera, the application also provides an embodiment of the calibration device of the vehicle-mounted camera.
Referring to fig. 7, a block diagram of an embodiment of a calibration device for an in-vehicle camera of the present application may include: the sign line determining module 71, the first calculating module 72, the image processing module 73, the second calculating module 74, the relationship converting module 75.
Wherein the sign line determining module 71 is configured to determine a sign line that satisfies a preset condition around the vehicle;
a first calculation module 72, configured to calculate a coordinate conversion relationship between the vehicle and the sign line;
an image processing module 73, configured to identify a sign line image corresponding to the sign line from an image captured by an on-board camera of the vehicle, and perform perspective transformation on the sign line image to obtain a perspective view of the sign line;
a second calculation module 74, configured to calculate, according to the perspective view of the marker line, a coordinate conversion relationship between the vehicle-mounted camera and the marker line;
the relationship conversion module 75 is configured to calculate a coordinate conversion relationship between the vehicle and the vehicle-mounted camera according to a coordinate conversion relationship between the vehicle and the sign line and a coordinate conversion relationship between the vehicle-mounted camera and the sign line.
In one embodiment, the preset condition is specifically:
two straight lines or line segments intersecting perpendicularly, one of which is parallel to the body of the vehicle.
In one embodiment, the two perpendicular intersecting straight lines or line segments are specifically:
two straight lines or line segments perpendicularly intersecting in the same plane.
In one embodiment, the first calculating module 72 is specifically configured to obtain a lateral distance between a front point and a rear point on a parallel tangent line of the vehicle body and a sign line parallel to the vehicle body, and a longitudinal distance between the two points, and calculate a coordinate transformation relationship between the vehicle and the sign line.
In one embodiment, the image processing module 73 is specifically configured to extract feature points of an image captured by an on-board camera of the vehicle, and fit the extracted feature points to obtain a sign line image corresponding to the sign line.
In one embodiment, the second calculating module 74 is specifically configured to obtain coordinates of a center point of the perspective view of the sign line and a focal length of the on-vehicle camera, so as to calculate a coordinate conversion relationship between the on-vehicle camera and the sign line.
In one embodiment, the relationship conversion module 75 is specifically configured to obtain coordinate conversion relationships between the vehicle and the vehicle-mounted camera within a preset time when the vehicle is traveling in a straight line, and the average value calculated by using the random sampling consistency algorithm or the least square method is the coordinate conversion relationship between the vehicle and the vehicle-mounted camera.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
The embodiment of the calibration device of the vehicle-mounted camera can be applied to the calibration terminal of the vehicle-mounted camera. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory through a processor of a calibration terminal of a vehicle-mounted camera where the device is located for operation. In terms of hardware, as shown in fig. 8, a hardware structure diagram of a calibration terminal of a vehicle-mounted camera where a calibration device of the vehicle-mounted camera is located in the present application is shown, where a processor 801 is a control center of the calibration terminal 800 of the vehicle-mounted camera, and uses various interfaces and lines to connect various parts of the entire lane line detection device, and executes various functions and processes data of the calibration terminal 800 of the vehicle-mounted camera by running or executing software programs and/or modules stored in a memory 802, and calling data stored in the memory 802, so as to perform overall monitoring on the calibration device of the vehicle-mounted camera.
Optionally, processor 801 may include (not shown in fig. 8) one or more processing cores; alternatively, the processor 801 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 801.
The memory 802 may be used to store software programs and modules, and the processor 801 executes various functional applications and data processing by executing the software programs and modules stored in the memory 802. The memory 802 mainly includes (not shown in fig. 8) a storage program area that can store an operating system, application programs required for at least one function, and the like, and a storage data area; the storage data area may store data created according to the use of the calibration terminal 800 of the in-vehicle camera (such as a captured image, a calculated parallax image, or calculation data), and the like.
In addition, memory 802 may include (not shown in FIG. 8) high-speed random access memory, and may also include (not shown in FIG. 8) non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 802 may also include a memory controller (not shown in fig. 8) to provide the processor 801 with access to the memory 802.
In some embodiments, the calibration terminal 800 may further optionally include: a peripheral interface 803, and at least one peripheral. The processor 801, memory 802, and peripheral interface 803 may be connected by a communication bus or signal line (not shown in fig. 8). Individual peripheral devices may be connected to peripheral device interface 803 by a communication bus or signal line. Specifically, the peripheral device may include: at least one of a radio frequency component 804, a touch display 805, a camera component 806, an audio component 807, a positioning component 808, and a power component 809.
In addition to the respective hardware illustrated in fig. 8, the calibration terminal of the vehicle-mounted camera where the device is located in the embodiment generally may further include other hardware according to the actual function of the calibration terminal of the vehicle-mounted camera, which will not be described herein.
It will be appreciated by those skilled in the art that the calibration terminal of the vehicle-mounted camera illustrated in fig. 8 may be applied to an automobile, or may be applied to other devices such as a computer, a smart phone, etc., which is not limited in this application.
The application also provides a computer readable storage medium, which is characterized in that a computer program is stored in the computer readable storage medium, and the computer program realizes the steps of the calibration method of any vehicle-mounted camera provided by the embodiment of the application when being executed by a processor.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A method for calibrating a vehicle-mounted camera, the method comprising:
determining a marking line meeting a preset condition around a vehicle, wherein the marking line is a marking line in a static calibration scene or a dynamic calibration scene, the preset condition is two straight lines or line segments which are vertically intersected, and one straight line or line segment is parallel to the vehicle body of the vehicle;
acquiring the transverse distance between a front point and a rear point on a parallel tangent line of the vehicle body and a marker line parallel to the vehicle body respectively, and the longitudinal distance between the two points, and calculating to obtain the coordinate conversion relation between the vehicle and the marker line;
identifying a sign line image corresponding to the sign line from an image shot by a vehicle-mounted camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line;
according to the perspective view of the sign line, calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line;
and calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line.
2. The method according to claim 1, wherein the two straight lines or line segments intersecting perpendicularly are specifically:
two straight lines or line segments perpendicularly intersecting in the same plane.
3. The method according to claim 1, wherein the identifying the marker line image corresponding to the marker line from the image captured by the onboard camera of the vehicle includes:
and extracting characteristic points from an image shot by the vehicle-mounted camera of the vehicle, and fitting the extracted characteristic points to obtain a mark line image corresponding to the mark line.
4. The method according to claim 1, wherein the calculating the coordinate conversion relationship between the vehicle-mounted camera and the sign line according to the perspective view of the sign line includes:
and acquiring the center point coordinates of the perspective view of the sign line and the focal length of the vehicle-mounted camera, and calculating to obtain the coordinate conversion relation between the vehicle-mounted camera and the sign line.
5. The method according to claim 1, wherein the calculating results in a coordinate conversion relationship between the vehicle and the in-vehicle camera when the vehicle is traveling straight, further comprising:
and acquiring the coordinate conversion relations of the vehicles and the vehicle-mounted camera within a preset time, wherein the average value calculated by using a random sampling consistency algorithm or a least square method is the coordinate conversion relation of the coordinate conversion relations of the vehicles and the vehicle-mounted camera.
6. A calibration device for an in-vehicle camera, the device comprising:
the marking line determining module is used for determining marking lines meeting preset conditions on the periphery of the vehicle, wherein the marking lines are marking lines in a static calibration scene or a dynamic calibration scene, the preset conditions are two straight lines or line segments which are perpendicularly intersected, and one straight line or line segment is parallel to the body of the vehicle;
the first calculation module is used for obtaining the transverse distance between the front point and the rear point on the parallel tangent line of the vehicle body and the marker line parallel to the vehicle body respectively and the longitudinal distance between the two points, and calculating to obtain the coordinate conversion relation between the vehicle and the marker line;
the image processing module is used for identifying a sign line image corresponding to the sign line from an image shot by an on-board camera of the vehicle, and performing perspective transformation on the sign line image to obtain a perspective view of the sign line;
the second calculation module is used for calculating the coordinate conversion relation between the vehicle-mounted camera and the sign line according to the perspective view of the sign line;
and the relation conversion module is used for calculating the coordinate conversion relation between the vehicle and the vehicle-mounted camera according to the coordinate conversion relation between the vehicle and the sign line and the coordinate conversion relation between the vehicle-mounted camera and the sign line.
7. The calibration terminal of the vehicle-mounted camera is characterized by comprising a memory, a processor, a communication interface, a camera component and a communication bus;
the memory, the processor, the communication interface and the camera component communicate with each other through the communication bus;
the camera component is used for collecting an image to be detected and sending the image to be detected to the processor through the communication bus;
the memory is used for storing a computer program;
the processor being adapted to execute a computer program stored on the memory, the processor executing the steps of the computer program for implementing the method according to any one of claims 1-5.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the steps of the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810550785.8A CN110555885B (en) | 2018-05-31 | 2018-05-31 | Calibration method and device of vehicle-mounted camera and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810550785.8A CN110555885B (en) | 2018-05-31 | 2018-05-31 | Calibration method and device of vehicle-mounted camera and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110555885A CN110555885A (en) | 2019-12-10 |
| CN110555885B true CN110555885B (en) | 2023-07-04 |
Family
ID=68733773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810550785.8A Active CN110555885B (en) | 2018-05-31 | 2018-05-31 | Calibration method and device of vehicle-mounted camera and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110555885B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111696160B (en) * | 2020-06-22 | 2023-08-18 | 江苏中天安驰科技有限公司 | Automatic calibration method and equipment for vehicle-mounted camera and readable storage medium |
| CN112419420B (en) * | 2020-09-17 | 2022-01-28 | 腾讯科技（深圳）有限公司 | Camera calibration method and device, electronic equipment and storage medium |
| CN112800986B (en) * | 2021-02-02 | 2021-12-07 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter calibration method and device, vehicle-mounted terminal and storage medium |
| CN112837381B (en) * | 2021-02-09 | 2024-06-25 | 上海振华重工(集团)股份有限公司 | Calibration method, system and equipment for camera suitable for driving equipment |
| CN114565681B (en) * | 2022-03-01 | 2022-11-22 | 禾多科技（北京）有限公司 | Camera calibration method, device, equipment, medium and product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608693A (en) * | 2015-12-18 | 2016-05-25 | 上海欧菲智能车联科技有限公司 | Vehicle-mounted panoramic around view calibration system and method |
| CN106875448A (en) * | 2017-02-16 | 2017-06-20 | 武汉极目智能技术有限公司 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
| CN106981082A (en) * | 2017-03-08 | 2017-07-25 | 驭势科技（北京）有限公司 | Vehicle-mounted camera scaling method, device and mobile unit |
| CN107133985A (en) * | 2017-04-20 | 2017-09-05 | 常州智行科技有限公司 | A kind of vehicle-mounted vidicon automatic calibration method for the point that disappeared based on lane line |
| CN107133988A (en) * | 2017-06-06 | 2017-09-05 | 科大讯飞股份有限公司 | The scaling method and calibration system of camera in vehicle-mounted panoramic viewing system |
-
2018
- 2018-05-31 CN CN201810550785.8A patent/CN110555885B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608693A (en) * | 2015-12-18 | 2016-05-25 | 上海欧菲智能车联科技有限公司 | Vehicle-mounted panoramic around view calibration system and method |
| CN106875448A (en) * | 2017-02-16 | 2017-06-20 | 武汉极目智能技术有限公司 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
| CN106981082A (en) * | 2017-03-08 | 2017-07-25 | 驭势科技（北京）有限公司 | Vehicle-mounted camera scaling method, device and mobile unit |
| CN107133985A (en) * | 2017-04-20 | 2017-09-05 | 常州智行科技有限公司 | A kind of vehicle-mounted vidicon automatic calibration method for the point that disappeared based on lane line |
| CN107133988A (en) * | 2017-06-06 | 2017-09-05 | 科大讯飞股份有限公司 | The scaling method and calibration system of camera in vehicle-mounted panoramic viewing system |
Non-Patent Citations (2)
| Title |
|---|
| 基于公路双平行线组的相机外参数在线标定;孙英慧;《电子科技》;20160715(第07期);第40-46页 * |
| 基于道路特征的车载相机标定动态补偿算法;陈军等;《机械工程学报》;20101020(第20期);正文第1节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110555885A (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110555885B (en) | Calibration method and device of vehicle-mounted camera and terminal | |
| CN110555884B (en) | Calibration method, device and terminal of vehicle-mounted binocular camera | |
| CN110148185B (en) | Method and device for determining coordinate system conversion parameters of imaging equipment and electronic equipment | |
| US10424081B2 (en) | Method and apparatus for calibrating a camera system of a motor vehicle | |
| WO2017124901A1 (en) | Information processing method, device, and terminal | |
| CN110969055B (en) | Method, apparatus, device and computer readable storage medium for vehicle positioning | |
| CN110411457B (en) | Positioning method, system, terminal and storage medium based on stroke perception and vision fusion | |
| CN112166059A (en) | Position estimation device for vehicle, position estimation method for vehicle, and computer-readable recording medium storing computer program programmed to execute the method | |
| CN113147738A (en) | Automatic parking positioning method and device | |
| US11703344B2 (en) | Landmark location estimation apparatus and method, and computer-readable recording medium storing computer program programmed to perform method | |
| JP6756101B2 (en) | Object recognition device | |
| CN113850867A (en) | Camera parameter calibration method, camera parameter calibration device control method, camera parameter calibration device control device, and storage medium | |
| CN108229406A (en) | A kind of method for detecting lane lines, device and terminal | |
| CN110728720B (en) | Method, apparatus, device and storage medium for camera calibration | |
| CN110962844A (en) | Vehicle course angle correction method and system, storage medium and terminal | |
| CN110766760A (en) | Method, device, equipment and storage medium for camera calibration | |
| CN110751693B (en) | Method, apparatus, device and storage medium for camera calibration | |
| CN110991232B (en) | Vehicle position correction method and system, storage medium and terminal | |
| CN109827516B (en) | Method for measuring distance through wheel | |
| CN111174722A (en) | Three-dimensional contour reconstruction method and device | |
| CN111627001A (en) | Image detection method and device | |
| KR20200094657A (en) | Method and device for estimating passenger statuses in 2 dimension image shot by using 2 dimension camera with fisheye lens | |
| CN114322856B (en) | Mining area pavement evenness detection method, device, storage medium and equipment | |
| US20220019812A1 (en) | Distance measuring method and device using image tracking for autonomous driving | |
| EP3872692A1 (en) | Compensation for vertical road curvature in road geometry estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |