CN112363130B - Vehicle-mounted sensor calibration method, storage medium and system - Google Patents
Vehicle-mounted sensor calibration method, storage medium and system Download PDFInfo
- Publication number
- CN112363130B CN112363130B CN202011382366.1A CN202011382366A CN112363130B CN 112363130 B CN112363130 B CN 112363130B CN 202011382366 A CN202011382366 A CN 202011382366A CN 112363130 B CN112363130 B CN 112363130B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- point cloud
- cloud model
- mounted sensor
- position relation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000015654 memory Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- CLOMYZFHNHFSIQ-UHFFFAOYSA-N clonixin Chemical compound CC1=C(Cl)C=CC=C1NC1=NC=CC=C1C(O)=O CLOMYZFHNHFSIQ-UHFFFAOYSA-N 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function 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
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/40—Means for monitoring or calibrating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/497—Means for monitoring or calibrating
Abstract
The invention provides a vehicle-mounted sensor calibration method, a storage medium and a system, wherein the method comprises the following steps: acquiring a vehicle contour point cloud model and a calibration plate contour point cloud model; matching the vehicle contour point cloud model with the vehicle standard point cloud model to obtain a vehicle real-time point cloud model and a set point position in the vehicle real-time point cloud model; acquiring a relative position relation between a calibration plate point cloud model and a set point position in a vehicle real-time point cloud model as a first position relation; acquiring the relative position relation between the calibration plate position detected by the vehicle-mounted sensor and the vehicle-mounted sensor as a second position relation; determining the relative position relation between the vehicle-mounted sensor and the set point position as an actual position relation according to the second position relation and the first position relation; and calibrating the vehicle-mounted sensor according to the actual position relationship and the standard position relationship between the vehicle-mounted sensor and the set point position. The scheme can improve the convenience of the calibration process of the vehicle-mounted sensor and the accuracy of the calibration result.
Description
Technical Field
The invention relates to the technical field of automobile accessories, in particular to a vehicle-mounted sensor calibration method, a storage medium and a system.
Background
The vehicle-mounted sensors play an important role in the ADAS (advanced driving assistance system) function of the vehicle, and different vehicle-mounted sensors are used for detecting different parameters in the running process of the vehicle and sending detection results to a driving computer, and the driving computer analyzes according to detection data sent by each vehicle-mounted sensor so as to control the vehicle.
In order to ensure accurate and reliable detection results of the vehicle-mounted sensor, the vehicle-mounted sensor can be calibrated according to requirements, and an existing vehicle-mounted sensor calibration mode is described by taking a vehicle-mounted millimeter wave radar sensor as an example. The calibration technology of the existing vehicle-mounted millimeter wave radar sensor can be divided into two scenes of production line calibration and after-sale point calibration, wherein:
(1) Production line calibration scene: and determining the relative relation between the calibrating machine and the calibrating plate by using a theodolite and a level meter, determining the relative relation between the vehicle and the calibrating machine by using a four-wheel positioning method, and starting a calibrating program of the millimeter wave radar. The calibration mode has the following defects: the positioning is needed by means of theodolites, level gauges and other equipment, and the arrangement requirement on the production line is high; special four-wheel centering platforms are needed, and the cost is high; importantly, errors in the relative positions of the vehicle and the calibration plate can lead to inaccurate calibration results.
(2) After-sales point calibration scenario: acquiring a plumb point at the center of the wheel; extending the connecting lines of plumb points at two sides to a specific length; determining the position of a central point of a specific distance in front of a vehicle; placing a radar reflecting plate at a central point; adjusting the height of the radar reflecting plate to the height of the millimeter wave radar; and adjusting the pitching angle of the radar reflecting plate to calibrate the millimeter wave radar. The calibration mode has the following defects: the operation steps are complicated, measurement errors are easy to generate during calibration, and the calibration precision is low; and the requirements on the calibration area are high, which needs to be kept as horizontal as possible.
The calibration modes of other vehicle-mounted sensors on the vehicle are similar to those of millimeter wave radar sensors, a calibration plate needs to be introduced, and the relative position relation between the vehicle and the calibration plate needs to be strictly and accurately measured, so that the calibration process of the vehicle-mounted sensor is inconvenient, larger sites and more vehicle positioning equipment are needed, and the accuracy of the calibration result of the vehicle-mounted sensor is affected due to the inaccuracy of the measurement of the relative positions of the calibration plate and the vehicle.
Disclosure of Invention
In view of the above, the invention provides a vehicle-mounted sensor calibration method, a storage medium and a system to solve the technical problems of poor convenience and low accuracy of the vehicle-mounted sensor calibration method in the prior art.
To this end, some embodiments of the present invention provide a calibration method for a vehicle-mounted sensor, including the following steps:
acquiring space point cloud data, wherein the space point cloud data comprises a vehicle contour point cloud model and a calibration plate contour point cloud model;
acquiring a vehicle standard point cloud model, and matching the vehicle contour point cloud model with the vehicle standard point cloud model to obtain a vehicle real-time point cloud model and a set point position in the vehicle real-time point cloud model;
acquiring a relative position relation between the calibration plate point cloud model and the set point position in the vehicle real-time point cloud model as a first position relation; acquiring the relative position relation between the calibration plate position detected by the vehicle-mounted sensor and the vehicle-mounted sensor as a second position relation;
determining the relative position relation between the vehicle-mounted sensor and the set point position as an actual position relation according to the second position relation and the first position relation;
and calibrating the vehicle-mounted sensor according to the actual position relation and the standard position relation between the vehicle-mounted sensor and the set point position.
Optionally, in the above-mentioned calibration method for a vehicle-mounted sensor:
the set point position is the center point position of the rear axle of the vehicle;
the first positional relationship is obtained by: and establishing a first coordinate system by taking the set point position in the real-time point cloud model of the vehicle as a center, taking the length direction of the vehicle body as an X axis, taking the width direction of the vehicle body as a Y axis and taking the height direction of the vehicle body as a Z axis, and obtaining the relative position relation between the calibration plate point cloud model and the set point position under the first coordinate system as a first position relation.
Optionally, in the above-mentioned calibration method for a vehicle-mounted sensor:
the second positional relationship is obtained by: and taking the center point of the vehicle-mounted sensor as a center, taking the coordinate system of the vehicle-mounted sensor as a second coordinate system, and obtaining the relative position relationship between the calibration plate position and the vehicle-mounted sensor under the second coordinate system as a second position relationship.
Optionally, in the vehicle-mounted sensor calibration method, a vehicle standard point cloud model is obtained, and the vehicle contour point cloud model is matched with the vehicle standard point cloud model to obtain a vehicle real-time point cloud model and a set point position in the vehicle real-time point cloud model, wherein the vehicle real-time point cloud model comprises:
and matching the vehicle contour point cloud model with the vehicle standard point cloud model by adopting an iterative nearest point algorithm to obtain a vehicle real-time point cloud model.
Optionally, in the above-mentioned calibration method for a vehicle-mounted sensor: the step of obtaining the standard point cloud model of the vehicle further comprises the following steps: and acquiring a standard position relation between the vehicle-mounted sensor and the set point position.
Optionally, in the above-mentioned calibration method for a vehicle-mounted sensor:
the first position relation comprises a course angle of the calibration plate point cloud model relative to the Z-axis direction of the first coordinate system and a roll angle relative to the X-axis direction of the first coordinate system under the first coordinate system;
the second position relation comprises a course angle of the calibration plate point cloud model relative to the Z-axis direction of the second coordinate system and a roll angle of the X-axis direction of the second coordinate system under the second coordinate system;
the standard position relationship comprises a standard course angle of the vehicle-mounted sensor relative to the Z-axis direction of the first coordinate system and a standard roll angle relative to the X-axis direction of the first coordinate system under the first coordinate system.
Optionally, in the above method for calibrating a vehicle-mounted sensor, the step of calibrating the vehicle-mounted sensor according to the actual positional relationship and the standard positional relationship between the vehicle-mounted sensor and the set point position includes:
determining an actual course angle of the vehicle-mounted sensor and the Z-axis direction of the first coordinate system and an actual roll angle of the X-axis direction of the first coordinate system according to the first position relation and the second position relation;
acquiring a course angle difference value between the actual course angle and the standard course angle and a roll angle difference value between the actual roll angle and the standard roll angle;
and if the course angle difference exceeds the set error range or the roll angle difference exceeds the set error range, judging that the angle of the vehicle-mounted sensor needs to be adjusted.
Some embodiments of the present invention further provide a storage medium, where program instructions are stored in the storage medium, and after a computer reads the program instructions, the method for calibrating the vehicle-mounted sensor according to any one of the above embodiments is executed.
In some embodiments of the present invention, a system for calibrating a vehicle-mounted sensor is further provided, including at least one processor and at least one memory, at least one of the memories storing program instructions, at least one of the processors executing the method for calibrating a vehicle-mounted sensor according to any of claims 1 to 7 after reading the program instructions.
Optionally, the vehicle-mounted sensor calibration system further comprises a three-dimensional sensor and a calibration plate; wherein:
the positional relationship among the vehicle, the three-dimensional sensor and the calibration plate satisfies: the vehicle and the calibration plate are both in the scanning range of the three-dimensional sensor, and the calibration plate is in the scanning range of the vehicle-mounted sensor;
the three-dimensional sensor is used for detecting the obtained space point cloud data and sending the space point cloud data to the processor, and the space point cloud data comprises a vehicle contour point cloud model and a calibration plate contour point cloud model;
and the vehicle-mounted sensor of the vehicle detects the position of the calibration plate and sends the position of the calibration plate to the processor.
Compared with the prior art, the technical scheme provided by the invention has at least the following beneficial effects: the relative position relation between the vehicle and the calibration plate can be accurately obtained through the space point cloud data scanned by the three-dimensional sensor and the vehicle standard point cloud model, which is equivalent to obtaining the relative position relation between the calibration plate and the vehicle set point position under the vehicle standard point cloud model, and the actual position relation between the calibration plate and the vehicle set point position can be obtained through detecting the actual position relation between the vehicle-mounted sensor actually mounted on the vehicle, so that whether the position of the vehicle-mounted sensor actually mounted on the vehicle needs to be adjusted can be detected. The scheme of the invention has no strict requirements on the position of the vehicle and the position of the calibration plate, does not need additional vehicle positioning equipment, brings convenience to the calibration of the vehicle-mounted sensor, and greatly reduces the risk of generating calibration errors, thereby improving the accuracy of the calibration result.
Drawings
FIG. 1 is a flow chart of a method for calibrating an in-vehicle sensor according to an embodiment of the invention;
FIG. 2 is a flow chart of calibrating a vehicle millimeter wave radar according to one embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a process of matching a vehicle contour point cloud model with a vehicle standard point cloud model to obtain a vehicle real-time point cloud model according to an embodiment of the present invention;
FIG. 4 is a schematic hardware architecture of a calibration system for an on-board sensor according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a calibration system for an on-board sensor according to another embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be further described below with reference to the accompanying drawings. In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of description of the present invention, and are not to indicate or imply that the apparatus or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Wherein the terms "first position" and "second position" are two different positions.
Some embodiments of the present invention provide a calibration method for a vehicle-mounted sensor, as shown in fig. 1, including the following steps:
s101: acquiring space point cloud data, wherein the space point cloud data comprises a vehicle contour point cloud model and a calibration plate contour point cloud model; the space point cloud data can be obtained through detection of the three-dimensional sensor, or can be obtained through direct extraction of pre-stored data by the method, if the space point cloud data are obtained through detection of the three-dimensional sensor, the three-dimensional sensor can be achieved through the existing sensor capable of scanning and detecting the space environment in the prior art, and after the vehicle and the calibration plate are placed in the detection area of the three-dimensional sensor, the three-dimensional sensor can scan the vehicle outline and the calibration plate outline.
S102: acquiring a vehicle standard point cloud model, and matching the vehicle contour point cloud model (namely a vehicle standard three-dimensional model) with the vehicle standard point cloud model to obtain a vehicle real-time point cloud model and a set point position in the vehicle real-time point cloud model; the standard point cloud model of the vehicle can be stored in a database, and the model can be directly called according to the model of the vehicle when the model is needed. In the step, on the premise of knowing the vehicle outline and the three-dimensional model of the whole vehicle, the vehicle outline and the three-dimensional model can be matched, and the accurate positioning of the position, the posture and the like of the vehicle on a software level is realized. The installation position and the installation angle of the vehicle-mounted sensor in the vehicle can be determined in the vehicle standard point cloud model, and the set point can be any point on the vehicle body, so that the set point can be selected as the center of the rear axle of the vehicle for analysis and calculation.
S103: acquiring a relative position relation between the calibration plate point cloud model and the set point position in the vehicle real-time point cloud model as a first position relation; and acquiring the relative position relation between the calibration plate position detected by the vehicle-mounted sensor and the vehicle-mounted sensor as a second position relation. The above positional relationship may include various parameters such as a horizontal position, a vertical position, an angle, and the like in space.
S104: and determining the relative position relation between the vehicle-mounted sensor and the set point position as an actual position relation according to the second position relation and the first position relation. Namely, the position of the calibration plate and the actual position of the vehicle are determined, and the relative position relation between the vehicle-mounted sensor and the set point position in the actual vehicle can be determined after the detection result of the three-dimensional sensor and the detection result of the vehicle-mounted sensor are corresponding.
S105: and calibrating the vehicle-mounted sensor according to the actual position relation and the standard position relation between the vehicle-mounted sensor and the set point position, wherein the step can be realized by calling a calibration program of the vehicle-mounted sensor.
According to the scheme, the relative position relation between the vehicle and the calibration plate can be accurately obtained through the space point cloud data scanned by the three-dimensional sensor and the vehicle standard point cloud model, which is equivalent to the relative position relation between the calibration plate and the vehicle set point position under the vehicle standard point cloud model, and the actual position relation between the calibration plate and the vehicle set point position can be obtained through detecting the actual position relation between the vehicle-mounted sensor and the vehicle-mounted sensor by the vehicle-mounted sensor actually mounted on the vehicle, so that whether the position of the vehicle-mounted sensor actually mounted on the vehicle needs to be adjusted or not can be detected. The scheme of the invention has no strict requirements on the position of the vehicle and the position of the calibration plate, does not need additional vehicle positioning equipment, brings convenience to the calibration of the vehicle-mounted sensor, and greatly reduces the risk of generating calibration errors, thereby improving the accuracy of the calibration result.
As mentioned above, the first positional relationship and the second positional relationship in the above solution may include various positional parameters, and preferably, the first positional relationship in the present solution is obtained by: the set point position is the center point position of the rear axle of the vehicle; and establishing a first coordinate system by taking the set point position in the real-time point cloud model of the vehicle as a center, taking the length direction of the vehicle body as an X axis, taking the width direction of the vehicle body as a Y axis and taking the height direction of the vehicle body as a Z axis, and obtaining the relative position relation between the calibration plate point cloud model and the set point position under the first coordinate system as a first position relation. The first position relation comprises a course angle of the calibration plate point cloud model relative to a Z-axis direction (namely, a vehicle height direction) of a first coordinate system and a roll angle relative to an X-axis direction (namely, a vehicle length direction) of the first coordinate system under the first coordinate system. The second positional relationship is obtained by: the relative positional relationship between the calibration plate position and the vehicle-mounted sensor in the second coordinate system is obtained as a second positional relationship by taking the center point of the vehicle-mounted sensor as the center and taking the coordinate system of the vehicle-mounted sensor as the second coordinate system (after the vehicle-mounted sensor is mounted, the directions of the respective axes in the own coordinate system are determined, for example, the direction right in front of the vehicle-mounted sensor is taken as the positive direction of the X axis, the direction right above the vehicle-mounted sensor is taken as the positive direction of the Z axis, and the like, specifically, the relative positional relationship between the calibration plate position and the vehicle-mounted sensor in the second coordinate system can be determined according to the mounting result of the vehicle-mounted sensor). The second position relation comprises a course angle of the calibration plate point cloud model relative to the Z-axis direction of the second coordinate system and a roll angle of the X-axis direction of the second coordinate system under the second coordinate system. On the basis, the standard position relation comprises a standard course angle of the vehicle-mounted sensor relative to the Z-axis direction of the first coordinate system and a standard roll angle relative to the X-axis direction of the first coordinate system under the first coordinate system. When the vehicle-mounted sensor is installed, the influence of the deviation of the vehicle-mounted sensor in the horizontal or vertical direction on the vehicle control is small, in order to simplify the operation logic, the accuracy of the calibration result of the vehicle-mounted sensor can be ensured by calibrating the course angle and the roll angle of the vehicle-mounted sensor, and the deviation of the vehicle-mounted sensor in the horizontal or vertical direction can be calibrated by adopting the calibration mode in the scheme based on a similar calibration mode. On this basis, the calibration process may include:
determining an actual course angle of the vehicle-mounted sensor and the Z-axis direction of the first coordinate system and an actual roll angle of the X-axis direction of the first coordinate system according to the first position relation and the second position relation; acquiring a course angle difference value between the actual course angle and the standard course angle and a roll angle difference value between the actual roll angle and the standard roll angle; and if the course angle difference exceeds the set error range or the roll angle difference exceeds the set error range, judging that the angle of the vehicle-mounted sensor needs to be adjusted. According to the method, the device and the system, the relative position relation between the vehicle-mounted sensor and the calibration plate and the relative position relation between the vehicle point cloud model and the calibration plate point cloud model are only needed to be determined in the calibration process, so that the vehicle-mounted sensor is calibrated by adopting the method, the actual position relation between the vehicle point cloud model and the calibration plate is calculated under the scanning coordinate system of the three-dimensional sensor, the actual position relation between the vehicle-mounted sensor and the calibration plate is calculated under the scanning coordinate system of the vehicle-mounted sensor, and the calculation result is simplified.
The calibration process is described in detail below by taking the vehicle millimeter wave radar shown in fig. 2 as an example, wherein the three-dimensional sensor is implemented by selecting a laser radar, and the method specifically comprises the following steps:
s201: scanning a vehicle and a calibration plate by a laser radar;
s202: obtaining real-time point cloud data P of a vehicle;
s203: acquiring vehicle standard point cloud data Q;
s204: registering Q and P by adopting an ICP algorithm to obtain a rotation matrix QPR and a translation matrix QPT of the Q relative to the vehicle in P; converting the point cloud coordinate of Q into P by utilizing QPR and QPT to obtain Q';
s205: the attitude angles Y and R from the calibration plate to the center of the rear axle in the Q 'are obtained, and because the Q' is the whole vehicle digital-analog, the center of the rear axle can be easily found, and the course angle Y and the roll angle R of the calibration plate relative to the center coordinate system of the rear axle are calculated;
s206: scanning the calibration plate according to self detection of the millimeter wave radar;
s207: determining a course angle Y1 and a roll angle R1 of the calibration plate relative to a millimeter wave radar coordinate system;
s208: according to the results of the step S205 and the step S206, a course angle Y2 and a roll angle R2 of the millimeter wave radar relative to the center of the rear axle are obtained;
s209: acquiring ideal attitude angles Y0 and R0 of the millimeter wave radar relative to the center of the rear axle, namely reference position data;
s210: according to the results of the step S208 and the step S209, a course angle calibration value delta Y and a roll angle delta R of the millimeter wave radar are obtained;
s211: determining if the calibration value deltay and roll angle deltar are within the threshold value?
S212: the calibration value deltay and the roll angle deltar are both within the threshold range, and if they are within the threshold range, the calibration value is written into the ECU of the millimeter wave radar.
And S213, if the calibration value delta Y or the roll angle delta R is not in the threshold value range, judging that the calibration program is not passed, and reinstalling the millimeter wave radar.
Preferably, in the above scheme, an iterative nearest algorithm is adopted to match the vehicle contour point cloud model with the vehicle standard point cloud model, so as to obtain a vehicle real-time point cloud model. Referring to fig. 3, a vehicle standard point cloud model 301 includes a positional relationship between a vehicle-mounted sensor 302 and a vehicle rear axle center, which is a coordinate system origin in the vehicle standard point cloud model 301 shown in the drawing. While the three-dimensional sensor 303 scans the vehicle to obtain the vehicle profile 304 and the calibration plate profile 305, it can be seen from the figure that the vehicle profile 304 has only one L-shaped frame, and thus it is difficult to determine the actual position of the rear axle center of the vehicle. Then, the vehicle standard point cloud model 301 is matched with the vehicle outline 304, so that the actual rear axle center position of the vehicle scanned by the three-dimensional sensor 304 can be accurately determined, and the position relationship between the rear axle center of the vehicle outline 304 and the calibration plate can be obtained. Based on the above, the actual position relationship between the vehicle-mounted sensor 302 and the calibration plate is obtained by combining the result of the calibration plate actually scanned by the vehicle-mounted sensor 302, the actual position relationship between the vehicle contour 304 and the vehicle-mounted sensor 302 is further obtained, and the calibration value of the vehicle-mounted sensor can be determined by comparing the actual position relationship with the theoretical relative position relationship.
The standard position relation in the scheme can be pre-stored standard data, and the standard position relation can be directly extracted in the calibration process of the method, and the standard position data is related to the actual calibrated vehicle type. Preferably, in this solution, the standard positional relationship between the vehicle-mounted sensor and the set point position may be used as standard data, where the data is obtained in advance and stored in a corresponding position, and when the calibration operation of the vehicle-mounted sensor needs to be performed, the standard data is directly called, thereby simplifying the data obtaining process.
Some embodiments of the present invention further provide a storage medium, where program instructions are stored in the storage medium, and after a computer reads the program instructions, the method for calibrating the vehicle-mounted sensor according to any one of the above schemes is executed.
In some embodiments of the present invention, as shown in fig. 4, the system further includes at least one processor 401 and at least one memory 402, at least one memory 402 stores program instructions, and at least one processor 401 executes the method for calibrating the vehicle-mounted sensor according to any one of the above schemes after reading the program instructions. The system may further include: an input device 403 and an output device 404. Memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 401 executes various functional applications and data processing of the server by running nonvolatile software programs, instructions and modules stored in the memory 402, that is, implements the on-vehicle sensor calibration method of the above-described method embodiment.
Further, as shown in fig. 5, the above system may further include a three-dimensional sensor 405 and a calibration plate; wherein: the positional relationship of the vehicle, the three-dimensional sensor 405, and the calibration plate satisfies: the vehicle and the calibration plate are both in the scanning range of the three-dimensional sensor 405, and the calibration plate is in the scanning range of the vehicle-mounted sensor 406; the three-dimensional sensor 405 is configured to detect obtained spatial point cloud data and send the spatial point cloud data to the processor 401, where the spatial point cloud data includes a vehicle contour point cloud model and a calibration board contour point cloud model; the onboard sensors 406 of the vehicle detect the calibration plate position and send the calibration plate position to the processor.
The scheme has low requirements on the layout of the production line in the earlier stage when being implemented on the production line, has no special requirements on the field when being implemented at the after-sale point, and has no strict limitations on the placement of vehicles and calibration plates; because the three-dimensional sensor is used for auxiliary calibration, the accurate relative relation between the calibration plate and the vehicle can be directly obtained, errors caused by inaccurate four-wheel positioning and manual measurement of after-sales points on a production line are avoided, and the calibration result is more accurate; furthermore, the calibration equipment in the system is simple and low in cost, and can be used for calibrating in production lines or after-sale places and the like; and because the calibration process is highly automated, the calibration time is short, the manual measurement steps of after-sales points are reduced, and time and labor are saved. The scheme is applicable to various vehicle-mounted sensors, including forward radar, angle radar, cameras and the like, and can calibrate a plurality of vehicle-mounted sensors at the same time.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The vehicle-mounted sensor calibration method is characterized by comprising the following steps of:
acquiring space point cloud data, wherein the space point cloud data comprises a vehicle contour point cloud model and a calibration plate contour point cloud model;
acquiring a vehicle standard point cloud model, and matching the vehicle contour point cloud model with the vehicle standard point cloud model to obtain a vehicle real-time point cloud model and a set point position in the vehicle real-time point cloud model;
acquiring a relative position relation between the calibration plate point cloud model and the set point position in the vehicle real-time point cloud model as a first position relation; acquiring the relative position relation between the calibration plate position detected by the vehicle-mounted sensor and the vehicle-mounted sensor as a second position relation;
determining the relative position relation between the vehicle-mounted sensor and the set point position as an actual position relation according to the second position relation and the first position relation;
and calibrating the vehicle-mounted sensor according to the actual position relation and the standard position relation between the vehicle-mounted sensor and the set point position.
2. The method for calibrating the vehicle-mounted sensor according to claim 1, wherein the method comprises the following steps:
the set point position is the center point position of the rear axle of the vehicle;
the first positional relationship is obtained by: and establishing a first coordinate system by taking the set point position in the real-time point cloud model of the vehicle as a center, taking the length direction of the vehicle body as an X axis, taking the width direction of the vehicle body as a Y axis and taking the height direction of the vehicle body as a Z axis, and obtaining the relative position relation between the calibration plate point cloud model and the set point position under the first coordinate system as a first position relation.
3. The vehicle-mounted sensor calibration method according to claim 2, characterized in that:
the second positional relationship is obtained by: and taking the center point of the vehicle-mounted sensor as a center, taking the coordinate system of the vehicle-mounted sensor as a second coordinate system, and obtaining the relative position relationship between the calibration plate position and the vehicle-mounted sensor under the second coordinate system as a second position relationship.
4. The method for calibrating a vehicle-mounted sensor according to any one of claims 1 to 3, wherein in the step of obtaining a vehicle standard point cloud model, and obtaining a vehicle real-time point cloud model and a set point position in the vehicle real-time point cloud model after matching the vehicle contour point cloud model with the vehicle standard point cloud model, the method is characterized in that:
and matching the vehicle contour point cloud model with the vehicle standard point cloud model by adopting an iterative nearest point algorithm to obtain a vehicle real-time point cloud model.
5. The method for calibrating an on-vehicle sensor according to claim 4, wherein:
the step of obtaining the standard point cloud model of the vehicle further comprises the following steps: and acquiring a standard position relation between the vehicle-mounted sensor and the set point position.
6. The method for calibrating an on-vehicle sensor according to claim 5, wherein:
the first position relation comprises a course angle of the calibration plate point cloud model relative to the Z-axis direction of the first coordinate system and a roll angle relative to the X-axis direction of the first coordinate system under the first coordinate system;
the second position relation comprises a course angle of the calibration plate point cloud model relative to the Z-axis direction of the second coordinate system and a roll angle of the X-axis direction of the second coordinate system under the second coordinate system;
the standard position relationship comprises a standard course angle of the vehicle-mounted sensor relative to the Z-axis direction of the first coordinate system and a standard roll angle relative to the X-axis direction of the first coordinate system under the first coordinate system.
7. The method according to claim 6, wherein the step of calibrating the in-vehicle sensor according to the actual positional relationship and the standard positional relationship between the in-vehicle sensor and the set point position includes:
determining an actual course angle of the vehicle-mounted sensor and the Z-axis direction of the first coordinate system and an actual roll angle of the X-axis direction of the first coordinate system according to the first position relation and the second position relation;
acquiring a course angle difference value between the actual course angle and the standard course angle and a roll angle difference value between the actual roll angle and the standard roll angle;
and if the course angle difference exceeds the set error range or the roll angle difference exceeds the set error range, judging that the angle of the vehicle-mounted sensor needs to be adjusted.
8. A storage medium, wherein program instructions are stored in the storage medium, and a computer executes the method for calibrating an in-vehicle sensor according to any one of claims 1 to 7 after reading the program instructions.
9. A vehicle-mounted sensor calibration system, comprising at least one processor and at least one memory, at least one of the memories having program instructions stored therein, at least one of the processors executing the vehicle-mounted sensor calibration method of any of claims 1-7 after reading the program instructions.
10. The vehicle-mounted sensor calibration system of claim 9, further comprising a three-dimensional sensor and a calibration plate; wherein:
the positional relationship among the vehicle, the three-dimensional sensor and the calibration plate satisfies: the vehicle and the calibration plate are both in the scanning range of the three-dimensional sensor, and the calibration plate is in the scanning range of the vehicle-mounted sensor;
the three-dimensional sensor is used for detecting the obtained space point cloud data and sending the space point cloud data to the processor, and the space point cloud data comprises a vehicle contour point cloud model and a calibration plate contour point cloud model;
and the vehicle-mounted sensor of the vehicle detects the position of the calibration plate and sends the position of the calibration plate to the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011382366.1A CN112363130B (en) | 2020-11-30 | 2020-11-30 | Vehicle-mounted sensor calibration method, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011382366.1A CN112363130B (en) | 2020-11-30 | 2020-11-30 | Vehicle-mounted sensor calibration method, storage medium and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112363130A CN112363130A (en) | 2021-02-12 |
| CN112363130B true CN112363130B (en) | 2023-11-14 |
Family
ID=74535800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011382366.1A Active CN112363130B (en) | 2020-11-30 | 2020-11-30 | Vehicle-mounted sensor calibration method, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112363130B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114655131B (en) * | 2022-03-29 | 2023-10-13 | 东风汽车集团股份有限公司 | Vehicle-mounted sensing sensor adjustment method, device, equipment and readable storage medium |
| CN114935747B (en) * | 2022-05-02 | 2023-05-12 | 苏州一径科技有限公司 | Laser radar calibration method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4375130A (en) * | 1981-05-08 | 1983-03-01 | Fmc Corporation | Method for adjusting the toe of the steerable wheels on a vehicle relative to the average rolling direction of the vehicle nonsteerable wheels |
| CN107167090A (en) * | 2017-03-13 | 2017-09-15 | 深圳市速腾聚创科技有限公司 | Vehicle overall dimension measuring method and system |
| CN109345596A (en) * | 2018-09-19 | 2019-02-15 | 百度在线网络技术（北京）有限公司 | Multisensor scaling method, device, computer equipment, medium and vehicle |
| CN110111603A (en) * | 2019-05-10 | 2019-08-09 | 广州达泊智能科技有限公司 | Parking assistance method, apparatus and system based on three dimensional detection technology |
| CN110221275A (en) * | 2019-05-21 | 2019-09-10 | 菜鸟智能物流控股有限公司 | Calibration method and device between laser radar and camera |
| CN110375786A (en) * | 2019-06-27 | 2019-10-25 | 驭势科技（北京）有限公司 | A kind of scaling method, mobile unit and storage medium that sensor is joined outside |
| CN110930462A (en) * | 2019-11-27 | 2020-03-27 | 驭势科技（浙江）有限公司 | Vehicle camera external parameter calibration method, device, system and computer equipment |
| CN111301259A (en) * | 2020-04-10 | 2020-06-19 | 贵刚 | Automatic butt-joint filling system and method for transport vehicle and truck and computer storage medium |
-
2020
- 2020-11-30 CN CN202011382366.1A patent/CN112363130B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4375130A (en) * | 1981-05-08 | 1983-03-01 | Fmc Corporation | Method for adjusting the toe of the steerable wheels on a vehicle relative to the average rolling direction of the vehicle nonsteerable wheels |
| CN107167090A (en) * | 2017-03-13 | 2017-09-15 | 深圳市速腾聚创科技有限公司 | Vehicle overall dimension measuring method and system |
| CN109345596A (en) * | 2018-09-19 | 2019-02-15 | 百度在线网络技术（北京）有限公司 | Multisensor scaling method, device, computer equipment, medium and vehicle |
| CN110111603A (en) * | 2019-05-10 | 2019-08-09 | 广州达泊智能科技有限公司 | Parking assistance method, apparatus and system based on three dimensional detection technology |
| CN110221275A (en) * | 2019-05-21 | 2019-09-10 | 菜鸟智能物流控股有限公司 | Calibration method and device between laser radar and camera |
| CN110375786A (en) * | 2019-06-27 | 2019-10-25 | 驭势科技（北京）有限公司 | A kind of scaling method, mobile unit and storage medium that sensor is joined outside |
| CN110930462A (en) * | 2019-11-27 | 2020-03-27 | 驭势科技（浙江）有限公司 | Vehicle camera external parameter calibration method, device, system and computer equipment |
| CN111301259A (en) * | 2020-04-10 | 2020-06-19 | 贵刚 | Automatic butt-joint filling system and method for transport vehicle and truck and computer storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 一种激光扫描自动测量轮对几何参数的方法;高岩;邵双运;冯其波;;中国激光(07);正文 * |
| 基于手眼模型的三维激光雷达外参数标定;韩栋斌;徐友春;李华;谢德胜;陈文;;光电工程(08);正文 * |
| 点云频域配准的双目双线结构光列车轮对检测;王华;邢春齐;高金刚;张爽;朱可可;;光学精密工程(03);正文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112363130A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110146869B (en) | Method and device for determining coordinate system conversion parameters, electronic equipment and storage medium | |
| CN112363130B (en) | Vehicle-mounted sensor calibration method, storage medium and system | |
| WO2021254468A1 (en) | Vehicle detection system and vehicle detection method | |
| CN108051839B (en) | Vehicle-mounted three-dimensional positioning device and three-dimensional positioning method | |
| CN113147738A (en) | Automatic parking positioning method and device | |
| CN108225185A (en) | A kind of vehicle-mounted scanning system calibration method | |
| CN112284416B (en) | Automatic driving positioning information calibration device, method and storage medium | |
| CN111208493A (en) | Rapid calibration method of vehicle-mounted laser radar in whole vehicle coordinate system | |
| EP4119977A1 (en) | Method and apparatus for calibrating a vehicle-mounted lidar, vehicle and storage medium | |
| CN111796258A (en) | Method and device for constructing radar parameter calibration field and readable storage medium | |
| CN112556625B (en) | Method, device and equipment for measuring angle of hub mounting surface and storage medium | |
| CN112233184B (en) | Laser radar and camera calibration parameter correction method and device based on image registration | |
| CN111605547B (en) | Automatic parking performance evaluation method | |
| WO2020121838A1 (en) | External environment recognition device | |
| KR20230129936A (en) | Method for calibrating a portable reference sensor system, portable reference sensor system and use of the portable reference sensor system | |
| WO2019188886A1 (en) | Terminal device, information processing method, and storage medium | |
| CN215867088U (en) | System for calibrating millimeter wave radar and vehicle | |
| CN114755663A (en) | External reference calibration method and device for vehicle sensor and computer readable storage medium | |
| CN114004949A (en) | Airborne point cloud assisted mobile measurement system arrangement parameter calibration method and system | |
| CN113256734B (en) | Vehicle-mounted sensing sensor calibration method and system and electronic equipment | |
| US20230417914A1 (en) | Method for determining a relative position of a first part of a mobile platform with respect to a second part of the mobile platform | |
| CN116026349B (en) | Method, apparatus, electronic device and medium for vehicle distance measurement | |
| CN116109696A (en) | ACC calibration plate position accuracy verification method, device and storage medium | |
| CN117516592A (en) | Vehicle-mounted IMU installation angle estimation method and device, electronic equipment and storage medium | |
| KR102626079B1 (en) | Apparatus for calibrating multi lidar and method thereof |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 430056 No. 10 Dongfeng Avenue, Wuhan economic and Technological Development Zone, Wuhan, Hubei Applicant after: DONGFENG MOTER Co.,Ltd. Address before: 510800, Fengshen Road, Huadu District, Guangdong, Guangzhou 12 Applicant before: DONGFENG MOTER Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |