CN114820816B - Automatic calibration method, device, equipment and medium for height of vehicle-mounted camera - Google Patents
Automatic calibration method, device, equipment and medium for height of vehicle-mounted cameraInfo
- Publication number
- CN114820816B CN114820816B CN202210490828.4A CN202210490828A CN114820816B CN 114820816 B CN114820816 B CN 114820816B CN 202210490828 A CN202210490828 A CN 202210490828A CN 114820816 B CN114820816 B CN 114820816B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- mounted camera
- point
- height
- ordinate
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an automatic calibration method, device, equipment and medium for height of a vehicle-mounted camera, which comprises the steps of S1, obtaining actual distance interval delta d between two end points A and B of a blank section in a lane line dotted line, calculating longitudinal coordinates a y、by of imaging points a and B of the two end points A and B in an image coordinate system of the vehicle-mounted camera, S2, substituting a y、by into a formula deduced from the actual distance interval delta d between the two end points A and B of the blank section in the lane line dotted line, and calculating to obtain the height h of the vehicle-mounted camera. According to the invention, the camera height is automatically calculated by positioning the part of the solid line and the dotted line of the standard lane line and combining with the distance estimation formula, so that the manual calibration error and cost are reduced, and the robustness of the calibration parameters is enhanced.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an automatic calibration method, device, equipment and medium for height of a vehicle-mounted camera.
Background
With the development of deep learning technology, convolutional neural networks are applied in the field of images. Advanced driving assistance systems (ADVANCED DRIVING ASSISTANCE SYSTEM) based on lens monitoring and pure images, as well as automated driving systems, have evolved rapidly. Whether it is a family car or various operation vehicles which are under national supervision, such as buses, freight transportation, dregs and the like, an intelligent auxiliary driving system is continuously installed, and the power-assisted driving safety is realized. For example, in an ADAS system, the main stream is according to monocular or binocular lenses (generally mounted on a windshield), some sensor devices such as a radar and a laser are also mounted, and the sensor devices such as the radar and the camera are used for monitoring the driving state of an automobile. Still further, for example, the automatic driving system can realize the function of assisting or replacing the driver to operate the vehicle through sensing, positioning, decision-making and control algorithms, so that driving accidents caused by human misoperation can be prevented and reduced, meanwhile, the intelligent system can reduce the driving threshold, and the accurate decision-making of each driver can be basically ensured through the assisting system. The most basic and core precondition in the automatic driving system is that peripheral objects can be perceived, the distance between the vehicle and each object is calculated through a formula, and the most basic and credible data basis is provided for subsequent decisions.
In the whole, whether the system is an ADAS system or an automatic driving system, if a monocular lens is adopted, the estimated distance is a ring which is the basis and the core of the system, and the subsequent decision and control of the system can be ensured to be effective only if the accuracy of distance calculation is ensured. In the distance estimation algorithm, the height of the camera mounting position from the ground is a very critical parameter in all parameters required to be calibrated, and the accurate camera height is obtained to be the basic guarantee of the distance estimation accuracy in consideration of the influence of the calibration parameter accuracy on the distance estimation error. In the actual use process, the height of the camera is a parameter which needs manual calibration, human errors are inevitably caused by manual calibration, manual calibration cost is difficult to calculate due to different calibration scenes, in addition, the situation that the camera is touched by people in a false manner or the pose of the camera is changed due to unexpected external factors such as jolt of a vehicle in the use process is not eliminated, so that the automatic driving distance estimation error is large, if only one-time manual calibration is performed after the camera is installed, the robustness of the system after long-term operation cannot be guaranteed necessarily, and if later-period manual correction is needed, the later-period maintenance cost is increased.
In addition to the intelligent driving system, most application scenes based on camera distance estimation need to be calibrated in terms of camera height, but due to the limitation of usage scenes, marker features of certain specific scenes often need to be captured under the condition that the camera is stationary, and the camera height is calculated by utilizing a specific triangular relationship. For a vehicle-mounted camera which follows a vehicle and runs on a highway for a long time, the static estimation is not reasonable, so that more common markers and formulas are required to be found, and the dynamic automatic calibration of the camera is realized.
Disclosure of Invention
The invention aims to solve the technical problem of providing an automatic calibration method, device, equipment and medium for the height of a vehicle-mounted camera, wherein the height of the camera is automatically calculated by positioning the part of a standard lane line with a solid line and a broken line and combining an estimated distance formula, so that the manual calibration error and cost are reduced, and the robustness of calibration parameters is enhanced.
In a first aspect, the present invention provides a method for automatically calibrating the height of a vehicle-mounted camera, including the following steps:
S1, obtaining an actual distance interval delta d between two end points A and B of a blank section in a lane line broken line, and calculating the ordinate a y、by of imaging points a and B of the two end points A and B in an image coordinate system of a vehicle-mounted camera;
S2, substituting a y、by into the following formula to calculate the height h of the vehicle-mounted camera:
Wherein d y is the actual size of a single pixel, f is the focal length of the vehicle-mounted camera, g y is the ordinate of the optical center point g in the image coordinate system, and v y is the ordinate of the imaging point v of the vanishing point of the horizon in the image coordinate system.
In a second aspect, the present invention provides an automatic calibration device for height of a vehicle-mounted camera, including:
the lane line parameter acquisition module is used for acquiring the actual distance interval delta d between the two end points A and B of the blank section in the lane line broken line;
The ordinate calculation module is used for calculating to obtain an average ordinate a y of the point a and an average ordinate B y of the point B through two imaging points a and B of the two end points A and B on an imaging plane in an image coordinate system of the vehicle-mounted camera;
The vehicle-mounted camera height calculation module is used for substituting a y、by into the following formula to calculate and obtain the height h of the vehicle-mounted camera:
Wherein d y is the actual size of a single pixel, f is the focal length of the vehicle-mounted camera, g y is the ordinate of the optical center point g in the image coordinate system, and v y is the ordinate of the imaging point v of the vanishing point of the horizon in the image coordinate system.
In a third aspect, the invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method of the first aspect.
The method and the device have the advantages that lane lines in the image are positioned by using a lane line detection algorithm (including but not limited to a traditional algorithm or a deep learning method and the like), stable and reliable pixel coordinate pairs of two ends of a dotted line in the image are obtained through constraint conditions, two-point coordinates and actual distances of the two ends of the dotted line are obtained through derivation according to a single-view distance estimation formula, the current camera height is obtained through the fact that the two-point coordinates and the actual distances of the two ends of the dotted line are brought into the single-view distance estimation formula, dynamic estimation is achieved for the camera height which is automatically calibrated in the running process of a vehicle due to the fact that the lane lines are commonly visible on a road, the method and the device are more suitable for practical use scenes compared with static estimation, and the feasibility of the scheme is greatly improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
The invention will be further described with reference to examples of embodiments with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method according to a first embodiment of the invention;
FIG. 2 is a schematic view of an imaging plane of a vehicle-mounted camera according to an embodiment of the present invention;
FIG. 3 is a side view of an image coordinate system of an onboard camera according to an embodiment of the present invention;
FIG. 4 is another side view of an image coordinate system of an onboard camera according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a device according to a second embodiment of the present invention;
Fig. 6 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention;
fig. 7 is a schematic structural diagram of a medium in a fourth embodiment of the present invention.
Detailed Description
According to the embodiment of the application, the automatic calibration method, the device, the equipment and the medium for the height of the vehicle-mounted camera are provided, the height of the camera is automatically calculated by positioning the part of the solid line and the dotted line of the standard lane line and combining with the distance estimation formula, so that the manual calibration error and the cost are reduced, and the robustness of calibration parameters is enhanced.
The technical scheme of the embodiment of the application has the general idea that a lane line detection algorithm (including but not limited to a traditional algorithm or a deep learning method and the like) is utilized to position a lane line in an image, a stable and reliable pixel coordinate pair of two ends of a dotted line in the image is obtained through constraint conditions, the two-point coordinates of the two ends of the dotted line and the actual distance are obtained through deduction according to a single-view distance estimation formula and are brought into the single-view distance estimation formula, so that the current camera height is obtained, and the automatically calibrated camera height realizes dynamic estimation in the running process of a vehicle because the lane line is generally visible on a highway, thereby being more in line with the actual use scene compared with static estimation and greatly improving the feasibility of the scheme.
Example 1
As shown in fig. 1, this embodiment provides an automatic calibration method for height of a vehicle-mounted camera, which includes the following steps:
S1, obtaining an actual distance interval delta d between two end points A and B of a blank section in a lane line broken line, and calculating the ordinate a y、by of imaging points a and B of the two end points A and B in an image coordinate system of a vehicle-mounted camera;
S2, substituting a y、by into the following formula to calculate the height h of the vehicle-mounted camera:
Wherein d y is the actual size of a single pixel, f is the focal length of the vehicle-mounted camera, g y is the ordinate of the optical center point g in the image coordinate system, v y is the ordinate of the imaging point v of the vanishing point of the horizon in the image coordinate system, and the parameter values can be obtained through camera calibration.
As shown in fig. 2, in the step S1, two points a and B of the blank section in the lane line dashed line are two points a and B in the imaging point of the image coordinate system, and the calculation process of the ordinate a y and B y of a and B specifically includes:
S11, positioning the ordinate of the two points a and b in an image coordinate system of the vehicle-mounted camera through a traditional algorithm or a depth learning algorithm to obtain candidate coordinates of the two points a and b;
S12, screening the candidate coordinates of the points a and b, and only selecting coordinates when the slopes of the left lane line and the right lane line are close to each other to obtain a screened coordinate set;
And S13, carrying out multi-frame averaging on the screened coordinate set to obtain average ordinate a y and average ordinate b y of the points a and b.
In the step S2, the deduction process of the height h of the vehicle-mounted camera is specifically as follows:
Establishing an image coordinate system of the vehicle-mounted camera, wherein in a side view of the image coordinate system, a point O c represents the vehicle-mounted camera, a point I is the orthographic projection of a point O c on the ground, O c G is the optical axis of the vehicle-mounted camera, G is the optical center point of the vertical intersection of O c G and an imaging plane, the focal length f=O Cg;Oc Q of the vehicle-mounted camera is the imaging lower boundary of the camera, Q is the near-viewpoint of the intersection of O c Q and the imaging plane, O c V is parallel to the ground, V is a horizontal vanishing point, V is the intersection of O c V and the imaging plane, P is the lower edge of a front frame, a point is the intersection of O c A and the imaging plane, B point is the intersection of O c B and the imaging plane, and d 2 is the distance from the point I to the point P;
The height formula of the camera is firstly deduced by using a single-view distance estimation formula based on d 2, namely:
In formula 1, α= = -O CPI＝∠VOCP＝∠VOCG-∠POC G;
Then
Then
Then
As can be seen from the above formula 6, the camera height h is only related to the horizontal distance d2 between the lower edge P of the front frame and the camera and the pixel coordinate system P y of the lower edge of the front frame in the imaging plane when the camera internal reference and the horizon vanishing point are known, so the camera height h can be directly calculated if d 2 and P y are known, and the calculation formula is as follows:
As shown in fig. 4, according to national road regulations, the size of the lane line boundary is generally a constant value, the distance between two ends a and B of the blank in the lane line dashed line of our country is Δd=9 meters, and according to this a priori knowledge and the ordinate a y and B y of a and B, three equations about h can be established according to equation 7, namely equation 8 to equation 10:
d b＝da +Δd equation 10
Then combining equation 8, equation 9 and equation 10 yields:
and then combining the formula 8 and the formula 11 to obtain a final calculation formula of the height h of the vehicle-mounted camera:
As shown in the formula 1, the camera height h can be obtained by directly taking the ordinate a y and the ordinate B y of the imaging points a and B of the two end points A and B obtained in the process, and similarly, as the method is obtained by inspiring the formula 6, the method can be popularized and used as long as an estimated distance formula for establishing the corresponding relation between the actual distance d and the camera height h is established, and the automatic calibration of the camera height can be realized by using the priori knowledge of the lane line dotted line interval.
Based on the same inventive concept, the application also provides a device corresponding to the method in the first embodiment, and the details of the second embodiment are shown.
Example two
As shown in fig. 5, in this embodiment, an automatic calibration device for height of a vehicle-mounted camera is provided, including:
the lane line parameter acquisition module is used for acquiring the actual distance interval delta d between the two end points A and B of the blank section in the lane line broken line;
The ordinate calculation module is used for calculating to obtain an average ordinate a y of the point a and an average ordinate B y of the point B through two imaging points a and B of the two end points A and B on an imaging plane in an image coordinate system of the vehicle-mounted camera;
The vehicle-mounted camera height calculation module is used for substituting a y、by into the following formula to calculate and obtain the height h of the vehicle-mounted camera:
Wherein d y is the actual size of a single pixel, f is the focal length of the vehicle-mounted camera, g y is the ordinate of the optical center point g in the image coordinate system, and v y is the ordinate of the imaging point v of the vanishing point of the horizon in the image coordinate system. These parameter values can be obtained by camera calibration.
As shown in fig. 2, the process of calculating average ordinate a y and b y by the ordinate calculation module is specifically:
S11, positioning the ordinate of the two points a and b in an image coordinate system of the vehicle-mounted camera through a traditional algorithm or a depth learning algorithm to obtain candidate coordinates of the two points a and b;
S12, screening the candidate coordinates of the points a and b, and only selecting coordinates when the slopes of the left lane line and the right lane line are close to each other to obtain a screened coordinate set;
And S13, carrying out multi-frame averaging on the screened coordinate set to obtain average ordinate a y and average ordinate b y of the points a and b.
The deduction process of the height h formula of the vehicle-mounted camera is specifically as follows:
Establishing an image coordinate system of the vehicle-mounted camera, wherein in a side view of the image coordinate system, a point O c represents the vehicle-mounted camera, a point I is the orthographic projection of a point O c on the ground, O c G is the optical axis of the vehicle-mounted camera, G is the optical center point of the vertical intersection of O c G and an imaging plane, the focal length f=O Cg;Oc Q of the vehicle-mounted camera is the imaging lower boundary of the camera, Q is the near-viewpoint of the intersection of O c Q and the imaging plane, O c V is parallel to the ground, V is a horizontal vanishing point, V is the intersection of O c V and the imaging plane, P is the lower edge of a front frame, a point is the intersection of O c A and the imaging plane, B point is the intersection of O c B and the imaging plane, and d 2 is the distance from the point I to the point P;
The height formula of the camera is firstly deduced by using a single-view distance estimation formula based on d 2, namely:
In formula 1, α= = -O CPI＝∠VOCP＝∠VOCG-∠POC G;
Then
Then
As can be seen from the above formula 6, the camera height h is only related to the horizontal distance d2 between the lower edge P of the front frame and the camera and the pixel coordinate system P y of the lower edge of the front frame in the imaging plane when the camera internal reference and the horizon vanishing point are known, so the camera height h can be directly calculated if d 2 and P y are known, and the calculation formula is as follows:
As shown in fig. 4, according to national road regulations, the size of the lane line boundary is generally a constant value, the distance between two ends a and B of the blank in the lane line dashed line of our country is Δd=9 meters, and according to this a priori knowledge and the ordinate a y and B y of a and B, three equations about h can be established according to equation 7, namely equation 8 to equation 10:
d b＝da +Δd equation 10
Then combining equation 8, equation 9 and equation 10 yields:
and then combining the formula 8 and the formula 11 to obtain a final calculation formula of the height h of the vehicle-mounted camera:
As shown in the formula 1, the camera height h can be obtained by directly taking the ordinate a y and the ordinate B y of the imaging points a and B of the two end points A and B obtained in the process, and similarly, as the method is obtained by inspiring the formula 6, the method can be popularized and used as long as an estimated distance formula for establishing the corresponding relation between the actual distance d and the camera height h is established, and the automatic calibration of the camera height can be realized by using the priori knowledge of the lane line dotted line interval.
Since the device described in the second embodiment of the present invention is a device for implementing the method described in the first embodiment of the present invention, based on the method described in the first embodiment of the present invention, a person skilled in the art can understand the specific structure and the deformation of the device, and thus the detailed description thereof is omitted herein. All devices used in the method according to the first embodiment of the present invention are within the scope of the present invention.
Based on the same inventive concept, the application provides an electronic device embodiment corresponding to the first embodiment, and the details of the third embodiment are shown in the specification.
Example III
The present embodiment provides an electronic device, as shown in fig. 6, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where any implementation of the first embodiment may be implemented when the processor executes the computer program.
Since the electronic device described in this embodiment is a device for implementing the method in the first embodiment of the present application, those skilled in the art will be able to understand the specific implementation of the electronic device and various modifications thereof based on the method described in the first embodiment of the present application, so how the electronic device implements the method in the embodiment of the present application will not be described in detail herein. The apparatus used to implement the methods of embodiments of the present application will be within the scope of the intended protection of the present application.
Based on the same inventive concept, the application provides a storage medium corresponding to the first embodiment, and the detail of the fourth embodiment is shown in the specification.
Example IV
The present embodiment provides a computer readable storage medium, as shown in fig. 7, on which a computer program is stored, which when executed by a processor, can implement any implementation of the first embodiment.
The technical scheme provided by the embodiment of the application has at least the following technical effects or advantages that a lane line detection algorithm (including but not limited to a traditional algorithm or a deep learning method and the like) is utilized to position a lane line in an image, a stable and reliable pixel coordinate pair of two ends of a dotted line in the image is obtained through constraint conditions, the two-point coordinates and the actual distance of the two ends of the dotted line are obtained through deduction according to a single-view distance estimation formula, and the current camera height is obtained through carrying the two-point coordinates and the actual distance of the two ends of the dotted line into the single-view distance estimation formula, and the camera height which is automatically calibrated realizes dynamic estimation in the running process of a vehicle because the lane line is generally visible on a road, and is more in line with the actual use scene compared with static estimation, so that the feasibility of the scheme is greatly improved.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus or system, or a computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may 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, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that the specific embodiments described are illustrative only and not intended to limit the scope of the invention, and that equivalent modifications and variations of the invention in light of the spirit of the invention will be covered by the claims of the present invention.
Claims (10)
1. The automatic calibration method for the height of the vehicle-mounted camera is characterized by comprising the following steps of:
S1, obtaining an actual distance interval delta d between two end points A and B of a blank section in a lane line broken line, and calculating the ordinate a y、by of imaging points a and B of the two end points A and B in an image coordinate system of a vehicle-mounted camera;
S2, substituting a y、by into the following formula to calculate the height h of the vehicle-mounted camera:
Wherein d y is the actual size of a single pixel, f is the focal length of the vehicle-mounted camera, g y is the ordinate of the optical center point g in the image coordinate system, and v y is the ordinate of the imaging point v of the vanishing point of the horizon in the image coordinate system.
2. The method according to claim 1, wherein the calculating of the ordinate a y and b y of the step S1 is specifically:
S11, positioning the ordinate of the two points a and b in an image coordinate system of the vehicle-mounted camera through a depth learning algorithm to obtain candidate coordinates of the two points a and b;
S12, screening the candidate coordinates of the points a and b, and only selecting coordinates when the slopes of the left lane line and the right lane line are close to each other to obtain a screened coordinate set;
And S13, carrying out multi-frame averaging on the screened coordinate set to obtain average ordinate a y and average ordinate b y of the points a and b.
3. The method according to claim 1, wherein in the step S2, the deriving process of the height h of the vehicle-mounted camera is specifically:
Establishing an image coordinate system of the vehicle-mounted camera, wherein in a side view of the image coordinate system, a point O c represents the vehicle-mounted camera, a point I is the orthographic projection of a point O c on the ground, O c G is the optical axis of the vehicle-mounted camera, G is the optical center point of the vertical intersection of O c G and an imaging plane, the focal length f=O Cg;Oc Q of the vehicle-mounted camera is the imaging lower boundary of the camera, Q is the near-viewpoint of the intersection of O c Q and the imaging plane, O c V is parallel to the ground, V is a horizontal vanishing point, V is the intersection of O c V and the imaging plane, P is the lower edge of a front frame, a point is the intersection of O c A and the imaging plane, B point is the intersection of O c B and the imaging plane, and d 2 is the distance from the point I to the point P;
The camera height formula is derived based on d 2 using the following formula:
And deducing a height formula of the camera based on the actual distance interval delta d between the two end points A and B of the blank section in the lane line dotted line, and obtaining the following steps:
d b＝da +Δd equation 10
Then combining equation 8, equation 9 and equation 10 yields:
and then combining the formula 8 and the formula 11 to obtain a final calculation formula of the height h of the vehicle-mounted camera:
4. the method of claim 1, wherein the actual distance interval Δd between the two end points A and B of the blank section in the lane line broken line is obtained from the size of the lane line dividing line in national road regulation.
5. The automatic calibration device for the height of the vehicle-mounted camera is characterized by comprising the following components:
the lane line parameter acquisition module is used for acquiring the actual distance interval delta d between the two end points A and B of the blank section in the lane line broken line;
The ordinate calculation module is used for calculating to obtain an average ordinate a y of the point a and an average ordinate B y of the point B through two imaging points a and B of the two end points A and B on an imaging plane in an image coordinate system of the vehicle-mounted camera;
The vehicle-mounted camera height calculation module is used for substituting a y、by into the following formula to calculate and obtain the height h of the vehicle-mounted camera:
Wherein d y is the actual size of a single pixel, f is the focal length of the vehicle-mounted camera, g y is the ordinate of the optical center point g in the image coordinate system, and v y is the ordinate of the imaging point v of the vanishing point of the horizon in the image coordinate system.
6. The apparatus of claim 5, wherein the means for calculating the average ordinate a y and b y comprises:
S11, positioning the ordinate of the two points a and b in an image coordinate system of the vehicle-mounted camera through a depth learning algorithm to obtain candidate coordinates of the two points a and b;
S12, screening the candidate coordinates of the points a and b, and only selecting coordinates when the slopes of the left lane line and the right lane line are close to each other to obtain a screened coordinate set;
And S13, carrying out multi-frame averaging on the screened coordinate set to obtain average ordinate a y and average ordinate b y of the points a and b.
7. The device of claim 5, wherein the derivation process of the formula of the height h of the vehicle-mounted camera is specifically as follows:
Establishing an image coordinate system of the vehicle-mounted camera, wherein in a side view of the image coordinate system, a point O c represents the vehicle-mounted camera, a point I is the orthographic projection of a point O c on the ground, O c G is the optical axis of the vehicle-mounted camera, G is the optical center point of the vertical intersection of O c G and an imaging plane, the focal length f=O Cg;Oc Q of the vehicle-mounted camera is the imaging lower boundary of the camera, Q is the near-viewpoint of the intersection of O c Q and the imaging plane, O c V is parallel to the ground, V is a horizontal vanishing point, V is the intersection of O c V and the imaging plane, P is the lower edge of a front frame, a point is the intersection of O c A and the imaging plane, B point is the intersection of O c B and the imaging plane, and d 2 is the distance from the point I to the point P;
The camera height formula is derived based on d 2 using the following formula:
And deducing a height formula of the camera based on the actual distance interval delta d between the two end points A and B of the blank section in the lane line dotted line, and obtaining the following steps:
d b＝da +Δd equation 10
Then combining equation 8, equation 9 and equation 10 yields:
and then combining the formula 8 and the formula 11 to obtain a final calculation formula of the height h of the vehicle-mounted camera:
8. the apparatus of claim 5, wherein the lane line parameter obtaining module obtains the actual distance Δd between the two ends A and B of the blank section in the lane line dashed line by inquiring the size of the lane line boundary in the national road regulation.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when the program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210490828.4A CN114820816B (en) | 2022-05-07 | 2022-05-07 | Automatic calibration method, device, equipment and medium for height of vehicle-mounted camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210490828.4A CN114820816B (en) | 2022-05-07 | 2022-05-07 | Automatic calibration method, device, equipment and medium for height of vehicle-mounted camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114820816A CN114820816A (en) | 2022-07-29 |
| CN114820816B true CN114820816B (en) | 2025-07-25 |
Family
ID=82511468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210490828.4A Active CN114820816B (en) | 2022-05-07 | 2022-05-07 | Automatic calibration method, device, equipment and medium for height of vehicle-mounted camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114820816B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115619875A (en) * | 2022-10-21 | 2023-01-17 | 广州汽车集团股份有限公司 | Vehicle-mounted camera calibration method, device, electronic equipment and storage medium |
| CN117036503A (en) * | 2023-08-18 | 2023-11-10 | 上海安亭地平线智能交通技术有限公司 | Camera height estimation method and device, readable storage medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007274564A (en) * | 2006-03-31 | 2007-10-18 | Aisin Aw Co Ltd | Calibration apparatus and calibration method |
| CN112102413A (en) * | 2020-07-22 | 2020-12-18 | 西安交通大学 | Virtual lane line-based automatic calibration method for vehicle-mounted camera |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570475A (en) * | 2018-06-05 | 2019-12-13 | 上海商汤智能科技有限公司 | vehicle-mounted camera self-calibration method and device and vehicle driving method and device |
| CN109859278B (en) * | 2019-01-24 | 2023-09-01 | 惠州市德赛西威汽车电子股份有限公司 | Calibration method and calibration system for camera extrinsic parameters of vehicle-mounted camera system |
-
2022
- 2022-05-07 CN CN202210490828.4A patent/CN114820816B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007274564A (en) * | 2006-03-31 | 2007-10-18 | Aisin Aw Co Ltd | Calibration apparatus and calibration method |
| CN112102413A (en) * | 2020-07-22 | 2020-12-18 | 西安交通大学 | Virtual lane line-based automatic calibration method for vehicle-mounted camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114820816A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111696160B (en) | Automatic calibration method and equipment for vehicle-mounted camera and readable storage medium | |
| LU502288B1 (en) | Method and system for detecting position relation between vehicle and lane line, and storage medium | |
| EP2933790B1 (en) | Moving object location/attitude angle estimation device and moving object location/attitude angle estimation method | |
| CN110942038B (en) | Traffic scene recognition method and device based on vision, medium and electronic equipment | |
| EP1806595B1 (en) | Estimating distance to an object using a sequence of images recorded by a monocular camera | |
| US8259174B2 (en) | Camera auto-calibration by horizon estimation | |
| CN112109633B (en) | Lane departure early warning method, device, equipment, vehicle and storage medium | |
| US9697421B2 (en) | Stereoscopic camera apparatus | |
| CN114820816B (en) | Automatic calibration method, device, equipment and medium for height of vehicle-mounted camera | |
| CN110341621B (en) | An obstacle detection method and device | |
| CN108197590B (en) | Pavement detection method, device, terminal and storage medium | |
| CN106651963A (en) | Mounting parameter calibration method for vehicular camera of driving assistant system | |
| US6628210B2 (en) | Control system to prevent lane deviation of vehicle and control method thereof | |
| CN113345087B (en) | Surface model fitting method and device based on monocular vision | |
| US20200090347A1 (en) | Apparatus for estimating movement information | |
| US20190297314A1 (en) | Method and Apparatus for the Autocalibration of a Vehicle Camera System | |
| CN109753841B (en) | Lane line identification method and device | |
| US20200193184A1 (en) | Image processing device and image processing method | |
| US9519833B2 (en) | Lane detection method and system using photographing unit | |
| US11403770B2 (en) | Road surface area detection device | |
| US11477371B2 (en) | Partial image generating device, storage medium storing computer program for partial image generation and partial image generating method | |
| JP7122394B2 (en) | Imaging unit controller | |
| JP2019107944A (en) | Vehicle control device | |
| CN108416305B (en) | Pose estimation method and device for continuous road segmentation object and terminal | |
| CN107452230B (en) | Obstacle detection method and device, terminal equipment and storage medium |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 361000 b1f-112, Zone C, Huaxun building, software park, Xiamen Torch High tech Zone, Xiamen, Fujian Patentee after: Reconova Technologies Co.,Ltd. Country or region after: China Address before: 361000 b1f-112, Zone C, Huaxun building, software park, Xiamen Torch High tech Zone, Xiamen, Fujian Patentee before: XIAMEN RUIWEI INFORMATION TECHNOLOGY CO.,LTD. Country or region before: China |