CN117808892A - Automatic driving vehicle-mounted sensor calibration system and method based on camera - Google Patents
Automatic driving vehicle-mounted sensor calibration system and method based on camera Download PDFInfo
- Publication number
- CN117808892A CN117808892A CN202311814907.7A CN202311814907A CN117808892A CN 117808892 A CN117808892 A CN 117808892A CN 202311814907 A CN202311814907 A CN 202311814907A CN 117808892 A CN117808892 A CN 117808892A
- Authority
- CN
- China
- Prior art keywords
- sensor
- vehicle
- identifier
- vehicle pose
- pose
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004891 communication Methods 0.000 claims abstract description 5
- 239000003550 marker Substances 0.000 abstract description 13
- 238000005259 measurement Methods 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application relates to an automatic driving vehicle-mounted sensor calibration system and method based on a camera, and relates to an automatic driving vehicle-mounted sensor calibration method. The system comprises camera equipment, a sensor to be calibrated, at least two vehicle pose identifiers, at least one sensor identifier and a controller; the controller is in communication connection with the camera equipment; the sensor to be calibrated, at least two vehicle pose markers and at least one sensor marker are used for being attached to a target vehicle arranged in a preset pose, and the camera equipment is at a preset distance from the target vehicle; the sensor identifier is attached to the sensor to be calibrated. The position and the posture of the vehicle body posture and the sensor relative to the vehicle are calibrated based on the high-resolution camera and the marker on the surface of the vehicle body, and the position and the posture of the sensor relative to the vehicle are determined, so that manual measurement is greatly reduced, measurement errors can be greatly reduced, and the preparation time of the calibration process is shortened.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to an automatic driving vehicle-mounted sensor calibration system and method based on a camera.
Background
To achieve autopilot, various sensors such as cameras, lidar, millimeter wave radar, inertial sensors (Inertial Measurement Unit, IMU) and satellite navigation systems (Global Positioning System, GPS) are relied upon. The sensors have advantages and disadvantages under various total complex scenes, and the automatic driving is difficult to finish in the complex scenes accurately by relying on a single sensor, so that the mutual information fusion among the sensors becomes a mainstream solution. The fusion of the sensor and the position and the posture of the sensor and the workshop is important.
In the related art, the vehicle-mounted sensor is usually calibrated through a camera calibration platform. The camera calibration platform comprises a camera calibration plate, laser or cameras are arranged on two sides of the camera calibration plate, and a scale calibration plate or a camera ranging calibration plate and the like are arranged on the wheels. The calibration method comprises the following steps: the method comprises the steps of (1) manually calibrating a central shaft of a vehicle, aligning the central shaft of a calibrating device with the central shaft extending in front of a vehicle head, and manually measuring the angle of the calibrating device on line (2) so as to ensure that the angle is vertical to the ground and horizontal to the plane of the vehicle head (3) calculating the position and the gesture of the sensor by a central position (4) algorithm of a laser ranging calibrating sensor and a radar.
However, in connection with the above description, the conventional calibration method mainly uses a plurality of manual measurements, the manual measurements include measurement errors, and the manual measurements have errors accumulated for a plurality of times to cause excessive errors, and the physical positions between the camera calibration plate on the calibration platform and the cameras/lasers on both sides also need to be calibrated, which also has the risk of measurement errors.
Disclosure of Invention
The application relates to an automatic driving vehicle-mounted sensor calibration system and method based on a camera, which can reduce errors generated in the calibration process, and the technical scheme is as follows:
in one aspect, a camera-based automatic driving vehicle sensor calibration system is provided, the system comprising a camera device, a sensor to be calibrated, at least two vehicle pose markers, at least one sensor marker, and a controller;
the controller is in communication connection with the camera equipment;
the sensor to be calibrated, at least two vehicle pose markers and at least one sensor marker are used for being attached to a target vehicle arranged in a preset pose, and the camera equipment is at a preset distance from the target vehicle;
the sensor identifier is attached to the sensor to be calibrated;
the camera equipment is used for acquiring a vehicle pose identifier image corresponding to the vehicle pose identifier and a sensor identifier image corresponding to the sensor identifier;
the controller is used for receiving and calibrating the sensor to be calibrated based on the vehicle pose identifier image and the sensor identifier image.
In an alternative embodiment, the vehicle pose identifier and the sensor identifier are both implemented as Apriltag two-dimensional codes.
In an alternative embodiment, the at least two vehicle pose identifiers include a first vehicle pose identifier, a second vehicle pose identifier, and a third vehicle pose identifier;
the first vehicle pose identifier and the second vehicle pose identifier are attached to two different rearview mirrors of the target vehicle;
the third vehicle pose identifier is attached to the rear wheels of the target vehicle.
In an alternative embodiment, the line connecting the first center of the first vehicle pose identifier and the second center of the second vehicle pose identifier is in the same plane and parallel with the line connecting the centers of the left and right rear view mirrors of the vehicle;
the third center of the third vehicle pose identifier is located on the rear axle axis of the target vehicle.
In an alternative embodiment, the center of the sensor identifier corresponds to the center position of the sensor to be calibrated.
In another aspect, a method for calibrating an autopilot vehicle-mounted sensor based on a camera is provided, and the method is applied to a controller in any one of the camera-based autopilot vehicle-mounted sensor calibration systems, and includes:
receiving a vehicle pose identifier image and a sensor identifier image sent by a camera device;
generating vehicle pose data based on the vehicle pose identification image;
generating sensor location data based on the sensor identification image;
and generating a sensor calibration result of the sensor to be calibrated based on the vehicle pose data and the sensor position data.
The beneficial effects that this application provided technical scheme brought include at least:
the position and the posture of the vehicle body posture and the sensor relative to the vehicle are calibrated based on the high-resolution camera and the marker on the surface of the vehicle body, and the position and the posture of the sensor relative to the vehicle are determined, so that manual measurement is greatly reduced, measurement errors can be greatly reduced, and the preparation time of the calibration process is shortened.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 illustrates a schematic frame diagram of a camera-based automatic vehicle sensor calibration system according to an exemplary embodiment of the present application.
Fig. 2 shows a schematic illustration of attaching pose of two vehicle pose markers and a sensor marker according to an exemplary embodiment of the present application.
Fig. 3 is a schematic flow chart of an automatic driving vehicle-mounted sensor calibration method based on a camera according to an exemplary embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Fig. 1 shows a schematic frame diagram of a camera-based automatic driving vehicle sensor calibration system according to an exemplary embodiment of the present application, please refer to fig. 1, which includes a camera device 110, a sensor 120 to be calibrated, at least two vehicle pose markers 130, at least one sensor marker 140, and a controller 150. The controller is in communication connection with the camera equipment; the sensor to be calibrated, at least two vehicle pose identifiers and at least one sensor are used for being attached to a target vehicle arranged in a preset pose, and the camera equipment is at a preset distance from the target vehicle; the sensor identifier is attached to the sensor to be calibrated; the camera equipment is used for acquiring a vehicle pose identifier image corresponding to the vehicle pose identifier and a sensor identifier image corresponding to the sensor identifier; the controller is used for receiving and calibrating the sensor to be calibrated based on the vehicle pose identifier image and the sensor identifier image.
In the embodiment of the application, the sensor to be calibrated, the at least two vehicle pose identifiers and the at least one sensor identifier are used for being attached to a target vehicle set in a preset pose. At least two vehicle pose markers and at least one sensor marker are attached to the vehicle while the vehicle remains stationary. The application does not limit the attaching position of the vehicle pose marker and the sensor marker. Optionally, the camera device needs to capture the complete sensor identifier as well as the vehicle pose identifier.
In the embodiment of the application, the controller is implemented as a computer device which is in communication connection with the camera device and has a data processing function, and the specific model of the controller is not limited in the application.
In an alternative embodiment, the vehicle pose identifier and the sensor identifier are both implemented as Apriltag two-dimensional codes. Apriltag is a visual reference system in the related art that can be used to perform camera calibration. In the embodiment of the application, namely, the vehicle pose identifier and the sensor identifier are both two-dimensional codes obtained through printing, and a corresponding program is carried in the controller to execute a calibration process.
In an alternative embodiment, referring to FIG. 2, the at least two vehicle pose identifiers include a first vehicle pose identifier 131, a second vehicle pose identifier 132, and a third vehicle pose identifier 133; the first vehicle pose identifier 131 and the second vehicle pose identifier 132 are attached to two different rear view mirrors of the target vehicle 200; the third vehicle pose identifier 131 is attached to the rear wheels of the target vehicle 200. In this case, the line connecting the first center of the first vehicle pose marker and the second center of the second vehicle pose marker is in the same plane and parallel with the center line of the left and right rear view mirrors of the vehicle, and the third center of the third vehicle pose marker is on the rear wheel axis of the target vehicle. In this case, referring to fig. 2, the camera apparatus 110 is located at the side front of the target vehicle 200, and can completely photograph the remaining markers. The sensor identifier 140 is located in front of the vehicle and is attached to the sensor 120 to be calibrated.
In an alternative embodiment, the center of the sensor identifier corresponds to the center position of the sensor to be calibrated.
Based on the foregoing, fig. 3 is a schematic flow chart of a calibration method of an autopilot vehicle-mounted sensor based on a camera according to an exemplary embodiment of the present application, and the method is described by taking the application of the method to the calibration system of the autopilot vehicle-mounted sensor based on a camera as an example, where the method includes:
step 301, a vehicle pose identifier image and a sensor identifier image transmitted by a camera device are received.
The process is a process of receiving the image by the controller, and the vehicle pose identifier image and the sensor identifier image are both realized as two-dimensional code images by combining the above expressions.
In step 302, vehicle pose data is generated based on the vehicle pose identification image.
Step 303, generating sensor position data based on the sensor identification image.
Steps 302 and 303 are a process of generating a vehicle pose and a sensor position based on a two-dimensional code.
And step 304, generating a sensor calibration result of the sensor to be calibrated based on the vehicle pose data and the sensor position data.
Step 304 is a determination of the sensor calibration results. After the calibration is completed, the program outputs the coordinate position and the posture of the sensor to be calibrated relative to the coordinate system corresponding to the target vehicle.
In summary, the system and the method provided by the embodiment of the application calibrate the posture of the vehicle and the position and posture of the sensor relative to the vehicle based on the high-resolution camera and the april tag two-dimensional code, and determine the position and posture of the sensor relative to the vehicle, so that manual measurement is greatly reduced, measurement errors can be greatly reduced, and the preparation time of the calibration process is shortened.
The foregoing description of the preferred embodiments is merely exemplary in nature and is not intended to limit the invention, but is intended to cover various modifications, substitutions, improvements, and alternatives falling within the spirit and principles of the invention.
Claims (6)
1. The automatic driving vehicle-mounted sensor calibration system based on the camera is characterized by comprising camera equipment, a sensor to be calibrated, at least two vehicle pose identifiers, at least one sensor identifier and a controller;
the controller is in communication connection with the camera device;
the sensor to be calibrated, the at least two vehicle pose identifiers and the at least one sensor identifier are used for being attached to a target vehicle arranged in a preset pose, and the camera equipment is separated from the target vehicle by a preset distance;
the sensor identifier is attached to the sensor to be calibrated;
the camera device is used for acquiring a vehicle pose identifier image corresponding to the vehicle pose identifier and a sensor identifier image corresponding to the sensor identifier;
the controller is used for receiving and calibrating the sensor to be calibrated based on the vehicle pose identifier image and the sensor identifier image.
2. The system of claim 1, wherein the vehicle pose identifier and the sensor identifier are each implemented as an Apriltag two-dimensional code.
3. The system of claim 1, wherein the at least two vehicle pose identifiers comprise a first vehicle pose identifier, a second vehicle pose identifier, and a third vehicle pose identifier;
the first vehicle pose identifier and the second vehicle pose identifier are attached to two different rearview mirrors of the target vehicle;
the third vehicle pose identifier is attached to a rear wheel of the target vehicle.
4. A system according to claim 3, wherein the line connecting the first center of the first vehicle pose identifier and the second center of the second vehicle pose identifier is in the same plane and parallel with the center line of the left and right vehicle rearview mirrors;
the third center of the third vehicle pose identifier is located on a rear axle axis of the target vehicle.
5. A system according to claim 3, wherein the centre of the sensor identifier corresponds to the centre position of the sensor to be calibrated.
6. A camera-based auto-driving vehicle-mounted sensor calibration method, wherein the method is applied to the controller in the camera-based auto-driving vehicle-mounted sensor calibration system according to any one of claims 1 to 5, and the method comprises:
receiving a vehicle pose identifier image and a sensor identifier image sent by a camera device;
generating vehicle pose data based on the vehicle pose identification image;
generating sensor location data based on the sensor identification image;
and generating a sensor calibration result of the sensor to be calibrated based on the vehicle pose data and the sensor position data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311814907.7A CN117808892A (en) | 2023-12-26 | 2023-12-26 | Automatic driving vehicle-mounted sensor calibration system and method based on camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311814907.7A CN117808892A (en) | 2023-12-26 | 2023-12-26 | Automatic driving vehicle-mounted sensor calibration system and method based on camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117808892A true CN117808892A (en) | 2024-04-02 |
Family
ID=90433309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311814907.7A Pending CN117808892A (en) | 2023-12-26 | 2023-12-26 | Automatic driving vehicle-mounted sensor calibration system and method based on camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808892A (en) |
-
2023
- 2023-12-26 CN CN202311814907.7A patent/CN117808892A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10659677B2 (en) | Camera parameter set calculation apparatus, camera parameter set calculation method, and recording medium | |
| US6915228B2 (en) | Method and device for calibrating an image sensor system in a motor vehicle | |
| CN108805934B (en) | External parameter calibration method and device for vehicle-mounted camera | |
| AU2018282302B2 (en) | Integrated sensor calibration in natural scenes | |
| US11017558B2 (en) | Camera registration in a multi-camera system | |
| US7424387B1 (en) | Method for use with an optical aligner system for positioning a fixture relative to a vehicle | |
| US10643342B2 (en) | Group optimization depth information method and system for constructing a 3D feature map | |
| 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 | |
| CN111243029B (en) | Calibration method and device of vision sensor | |
| US11908164B2 (en) | Automatic extrinsic calibration using sensed data as a target | |
| EP3324210B1 (en) | Self-calibrating sensor system for a wheeled vehicle | |
| CN110458885B (en) | Positioning system and mobile terminal based on stroke perception and vision fusion | |
| US20230351687A1 (en) | Method for detecting and modeling of object on surface of road | |
| CN113340272B (en) | Ground target real-time positioning method based on micro-group of unmanned aerial vehicle | |
| CN111538008A (en) | Transformation matrix determining method, system and device | |
| CN113358021A (en) | Method for aligning a vehicle service system relative to a vehicle | |
| CN117808892A (en) | Automatic driving vehicle-mounted sensor calibration system and method based on camera | |
| US11477371B2 (en) | Partial image generating device, storage medium storing computer program for partial image generation and partial image generating method | |
| US20220018950A1 (en) | Indoor device localization | |
| CN115235526A (en) | Method and system for automatic calibration of sensors | |
| CN112114316A (en) | Vehicle position confirmation method and device based on ultrasonic distance meter | |
| CN109029438B (en) | Vehicle positioning method in limited area | |
| EP4148674A1 (en) | Accuracy verification of a perception system of a vehicle | |
| US20230306638A1 (en) | Method for calibrating a camera and associated device | |
| WO2023004719A1 (en) | On-board sensor calibration method, apparatus, and system |
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 |