CN112558044A - Automatic correction method for vehicle-mounted laser radar pitch angle - Google Patents
Automatic correction method for vehicle-mounted laser radar pitch angle Download PDFInfo
- Publication number
- CN112558044A CN112558044A CN202011353527.4A CN202011353527A CN112558044A CN 112558044 A CN112558044 A CN 112558044A CN 202011353527 A CN202011353527 A CN 202011353527A CN 112558044 A CN112558044 A CN 112558044A
- Authority
- CN
- China
- Prior art keywords
- pitch angle
- laser radar
- ground
- strategy
- vehicle
- 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
Images
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
- G01S7/48—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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention provides an automatic correction method for a vehicle-mounted laser radar pitch angle, which comprises the steps of screening and obtaining a point where a laser radar strikes the ground according to a denoising strategy; calculating the current pitch angle of the laser radar for the points on the ground according to a ground fitting strategy; and correcting the current pitch angle by adopting an updating strategy. According to the method, linear fitting is carried out on the point cloud point ground data subjected to data denoising according to a ground fitting strategy, and the current pitch angle is estimated and obtained, so that the calculation amount is small, and the occupied calculation resources are less.
Description
Technical Field
The invention relates to the technical field of vehicle environment sensing, in particular to an automatic correction method for a vehicle-mounted laser radar pitch angle.
Background
With the development of deep learning technology, the lidar3D detection algorithm based on deep learning becomes the first choice for lidar3D target detection. Common gridding-based radar detection algorithms usually use the ground plane as an x _ y plane and the vertical direction as a z-axis to establish a 3D coordinate system, so that the lidar3D detection algorithm based on deep learning is sensitive to the pitch angle of the radar. An excessively large pitch angle can cause the target to be distributed on the z-axis more dispersedly, so that the detection rate of the model is greatly reduced.
At present, external reference calibration of a common vehicle-mounted laser radar is usually completed in a calibration workshop before a vehicle leaves a factory. The calibrated parameters are fixed, and the parameters are not automatically updated after being sent out by the vehicle. On one hand, a fixed calibration site is needed in the prior art; on the other hand, the method cannot overcome the angle change of the laser radar in the use process and the ground scene with uneven road surface. However, there are several reasons for the angle between the lidar and the ground plane in real vehicle application scenarios, such as: 1. angle of introduction of radar installation. 2. The radar installation angle changes during the actual use process. 3. Slow ground heave.
Therefore, a method for automatically correcting the pitch angle of the vehicle-mounted laser radar is needed, and the change of the pitch angle of the vehicle-mounted laser radar caused by the reason is corrected.
Disclosure of Invention
In view of this, the invention provides an automatic vehicle-mounted laser radar pitch angle correction method.
In order to solve the technical problems, the invention adopts the technical scheme that: a vehicle-mounted laser radar pitch angle automatic correction method comprises the following steps:
screening and obtaining points of the laser radar on the ground according to a denoising strategy;
calculating the current pitch angle of the laser radar for the points on the ground according to a ground fitting strategy;
and correcting the current pitch angle by adopting an updating strategy.
In the present invention, preferably, the denoising strategy specifically includes the following steps:
acquiring original data of point cloud points through laser radar;
selecting an ROI (region of interest);
and selecting n point cloud point ground data in the ROI area to respectively obtain the horizontal and vertical coordinates of the n point cloud point ground data.
In the present invention, preferably, the ROI area is set to x ∈ (0,15), y ∈ (-0.5, 0.5).
In the present invention, preferably, the ground fitting strategy specifically includes the following steps:
establishing a pitch angle linear equation y which is kx + b according to the point cloud point ground data, wherein k represents the slope of a point cloud point ground data fitting straight line, and b represents the distance between the laser radar and the ground;
using fitting slope formula according to pitch angle linear equation
And solving to obtain the current pitch angle k.
In the present invention, preferably, the update policy specifically includes the following steps:
calculating the current pitch angle according to an error measurement strategy to obtain a deviation pitch angle gt；
According to kt＝β1kt-1+(1-β1)gtGet the updated pitch angle ktWherein, β1Indicating the learning rate.
In the present invention, preferably, the error measurement policy is a difference g between a current pitch angle and a previous pitch anglet＝k-kt-1Where k denotes the current pitch angle, kt-1The pitch angle at the previous moment is indicated.
In the present invention, preferably, β in the update policy1Set to 0.99.
In the present invention, preferably, the correction step is performed on the point cloud data after the current pitch angle is updated.
In the present invention, preferably, the correcting step is to project the point cloud point raw data onto a plane with a slope of zero.
The invention has the advantages and positive effects that: firstly, point cloud point original data acquired by a laser radar is three-dimensional point cloud point original data, the three-dimensional point cloud point original data is projected to the ground to obtain two-dimensional point cloud point data, a current pitch angle of the laser radar is calculated for points on the ground according to a ground fitting strategy, a deviation pitch angle is calculated and obtained for the current pitch angle according to an error metering strategy, an updating strategy is utilized to obtain an updated pitch angle, the current pitch angle is corrected, finally, correction operation on all the point cloud point original data acquired by the laser radar is realized by projecting the point cloud point original data onto a plane with zero slope, and the lower limit of the vehicle speed is set by selecting an ROI (region of interest) area and setting based on the ROI area, so that data interference caused by a non-road surface area can be; in addition, straight line fitting is carried out on the point cloud point ground data subjected to data denoising according to a ground fitting strategy, and the current pitch angle is estimated and obtained, so that the calculation amount is small, and the occupied calculation resources are less; the pitch angle change caused by the position movement of the laser radar after the vehicle leaves a factory can be solved through the updating strategy, so that the distribution of the measured and calculated target of the processed pitch angle on the z axis becomes concentrated through the lidar3D detection algorithm based on deep learning, and the problem that the detection rate of the model is greatly reduced is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is an overall structure diagram of a vehicle-mounted laser radar pitch angle automatic correction method of the invention;
FIG. 2 is a schematic flow diagram of a denoising strategy of the automatic vehicle-mounted laser radar pitch angle correction method of the invention;
FIG. 3 is a schematic diagram of a laser radar ground fitting strategy of the vehicle-mounted laser radar pitch angle automatic correction method of the invention;
FIG. 4 is a schematic diagram of point cloud point data distribution obtained by a laser radar before correction in the automatic vehicle-mounted laser radar pitch angle correction method of the present invention;
fig. 5 is a schematic diagram of point cloud point data distribution after correction of the vehicle-mounted laser radar pitch angle automatic correction method of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When a component is referred to as being "connected" to another component, it can be directly connected to the other component or intervening components may also be present. When a component is referred to as being "disposed on" another component, it can be directly on the other component or intervening components may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
As shown in fig. 1 to 5, the invention provides a vehicle-mounted laser radar pitch angle automatic correction method, which comprises the following steps:
screening and obtaining points of the laser radar on the ground according to a denoising strategy;
calculating the current pitch angle of the laser radar for the points on the ground according to a ground fitting strategy;
and correcting the current pitch angle by adopting an updating strategy.
The original data of point cloud points captured by a laser radar site contains a large amount of noise data, which causes incomplete target point cloud, irregular point cloud and uneven discreteness, and interference point cloud information entanglement with other objects or self-shielding problem caused by self angle change of a target possibly occurs in a three-dimensional imaging site. Due to the angle introduced by radar installation, the influence caused by the change of the installation angle of the radar in the actual use process and the slow ground fluctuation, the original data of point cloud points acquired by the laser radar are difficult to be all hit on the ground, that is, the positions of vehicle characteristic points in a real space are not located on a road coordinate system, but have a certain height from the ground, the positions of different vehicle characteristic points are different, the height difference of vehicles of different types is large, the real coordinate system needs to be on a plane corresponding to the vehicle characteristic points and is not directly established on the ground, and if the road coordinate system is directly used as the coordinate system of the vehicle characteristic points in the space, the pitch angle has huge deviation, and the precision is difficult to guarantee. Therefore, the original data of the point cloud points collected by the laser radar needs to be screened to obtain the points on the ground hit by the laser radar.
When the traveling speed of the vehicle is greater than 40km/h, the area right in front of the vehicle is a ground area, at the moment, points of the laser radar on the ground are obtained through screening according to a denoising strategy, and then the points of the laser radar on the ground are used as reference data to estimate the pitch angle of the laser radar in real time.
In this embodiment, the denoising strategy specifically includes the following steps:
acquiring original data of point cloud points through laser radar;
selecting an ROI (region of interest);
and selecting n point cloud point ground data in the ROI area to respectively obtain the horizontal and vertical coordinates of the n point cloud point ground data.
In the embodiment, further, the ROI area is set as x e (0,15), y e (-0.5, 0.5), when the traveling speed of the vehicle is greater than 40km/h, the area right in front of the vehicle is the ground area, at this time, the points of the laser radar on the ground are obtained through screening according to a denoising strategy, so that x e (0,15) and y e (-0.5, 0.5) are selected as ROI areas of interest, the ground data of the point cloud points selected from the ROI areas are the original data of n point cloud points belonging to x e (0,15), and the original data of the n point cloud points in the range of y e (-0.5, 0.5) are respectively obtained to obtain coordinate data (x e, 15) corresponding to the original data of the n point cloud points1，y1)，(x2，y2)……(xn，yn)。
In this embodiment, further, the ground fitting strategy specifically includes the following steps:
establishing a pitch angle linear equation y which is kx + b according to the point cloud point ground data, wherein k represents the slope of a point cloud point ground data fitting straight line, and b represents the distance between the laser radar and the ground;
using fitting slope formula according to pitch angle linear equation
And solving to obtain the current pitch angle k.
In this embodiment, further, the updating policy specifically includes the following steps:
calculating the current pitch angle according to an error measurement strategy to obtain a deviation pitch angle gt；
According to kt＝β1kt-1+(1-β1)gtGet the updated pitch angle ktWherein, β1The learning rate is expressed, and the learning rate can reduce the proportion of wrong estimation, thereby weakening the adverse effect caused by the occurrence of estimation errors.
In this embodiment, further, the error measure strategy is to make a difference g between the current pitch angle and the previous pitch anglet＝k-kt-1Where k denotes the current pitch angle, kt-1The pitch angle at the previous moment is indicated.
In the present embodiment, further, β in the policy is updated1Set to 0.99.
In this embodiment, further, after updating the current pitch angle, a correction step is performed on the point cloud data.
In this embodiment, further, the correcting step is to project all the point cloud point raw data collected by the laser radar onto a plane with a slope of zero.
When the laser radar works, pulse light is emitted towards a target direction, part of the measurement light returns to the sensor after being reflected or scattered after contacting the target, the distance from the target to the laser radar is calculated by measuring the time length required by the light returning to the sensor, and three-dimensional imaging is to map an object and describe the object into point cloud in the form of an x, y and z coordinate system. In contrast to two-dimensional imaging systems, three-dimensional imaging provided by lidar has the ability to analyze a targetThe advantages of geometric characteristics and absolute scale information, and the distance between the laser radar and the observed object
The method is characterized in that L represents the distance from a sensor to a certain point on an observed object, c represents the light speed, t represents the laser flight time, and the pulse width of the laser can reach the subnanosecond order, so that the distance resolution with decimeter precision can be realized.
The working principle and the working process of the invention are as follows: the method comprises the steps of acquiring point cloud point original data of a three-dimensional point cloud point by a laser radar, projecting the three-dimensional point cloud point original data to the ground to obtain two-dimensional point cloud point data, calculating the current pitch angle of the laser radar for the points on the ground according to a ground fitting strategy, wherein the ground fitting strategy adopts a least square method, and specifically as shown in figure 3, the fitting slope is
Wherein the content of the first and second substances,
respectively calculating the product of the abscissa and the ordinate of the cloud point ground data of n points, then calculating the average value of the n products,
the method comprises averaging the abscissa of the ground data of the cloud points of n points, averaging the ordinate of the ground data of the cloud points of n points, and multiplying the two averages,
which means averaging the squares of the abscissas of the n point cloud point ground data,
the abscissa representing the ground data of the cloud points of n points is firstly averaged and then squared to obtain a current pitch angle k, and then the current pitch angle k is calculated according to an error measurement strategy to obtain a deviation pitch angle gtThe error measurement strategy specifically refers to the difference between the current pitch angle and the previous pitch angle according to the formula kt＝β1kt-1+(1-β1)gtGet the updated pitch angle ktWherein, β1The learning rate is represented, the value of the learning rate is set to be 0.99, the initial purpose of the setting is to consider that if the fitting slope estimation fails, the final updating result is not influenced, the function of a single frame is not obvious, and the updating pitch angle k obtained through the updating strategy is enabled to be not obvioustThe method is correct, and particularly comprises the steps of selecting an ROI (region of interest), selecting ground data of n points in the ROI, performing ground fitting according to the n points extracted from the ROI, fitting the ground to obtain a fitting straight line for ground data distribution of the point cloud points, estimating to obtain a current pitch angle of the laser radar, correcting the current pitch angle according to an updating strategy, and finally projecting the point cloud point original data onto a plane with zero slope to realize correction operation of all point cloud point original data acquired by the laser radar before delivery of a vehicle, so that when calibration is completed before delivery of the vehicle, a pitch angle parameter of the laser radar is fixed and is not changed any more along with delivery of the vehicle, and further, when the pitch angle of the laser radar is different due to initial installation or ground bumpiness, the condition that the measured and calculated target of the pitch angle is dispersed on the z axis by the lidar3D detection algorithm based on deep learning is caused, and particularly as shown in fig. 4, the problem that the distribution of the pitch angle on the z axis is very dispersed, so that the model detection rate is greatly reduced is solved; in addition, straight line fitting is carried out on the point cloud point ground data subjected to data denoising according to a ground fitting strategy, and the current pitch angle is estimated and obtained, so that the calculation amount is small, and the occupied calculation resources are less; pitching caused by laser radar position movement after the vehicle leaves factory can be solved through an updating strategyThe angular change, as shown in fig. 5 in particular, it can be seen that the distribution of the processed measurement target of the pitch angle on the z axis becomes concentrated by the lidar3D detection algorithm based on deep learning, in the registration process from the point cloud to be registered to the target point cloud, a conversion parameter matrix is obtained by establishing a corresponding relationship between two frames of point cloud three-dimensional coordinate data, the point cloud data acquired at different frame rates are unified into a common mapping coordinate system, the point cloud registration process needs to be completed, and all the point cloud point raw data corrected by the update strategy are mapped onto a plane with a zero slope, so that the correction process is completed.
The embodiments of the present invention have been described in detail, but the present invention is only the preferred embodiments of the present invention, and is not to be considered as limiting the scope of the present invention. All equivalent changes and modifications made within the scope of the present invention should be covered by the present patent.
Claims (9)
1. A vehicle-mounted laser radar pitch angle automatic correction method is characterized by comprising the following steps:
screening and obtaining points of the laser radar on the ground according to a denoising strategy;
calculating the current pitch angle of the laser radar for the points on the ground according to a ground fitting strategy;
and correcting the current pitch angle by adopting an updating strategy.
2. The method for automatically correcting the pitch angle of the vehicle-mounted laser radar according to claim 1, wherein the denoising strategy specifically comprises the following steps:
acquiring original data of point cloud points through laser radar;
selecting an ROI (region of interest);
and selecting n point cloud point ground data in the ROI area to respectively obtain the horizontal and vertical coordinates of the n point cloud point ground data.
3. The automatic vehicle-mounted lidar pitch angle correction method according to claim 2, wherein the ROI area is set to x e (0,15), and y e (-0.5, 0.5).
4. The method for automatically correcting the pitch angle of the vehicle-mounted laser radar according to claim 1, wherein the ground fitting strategy specifically comprises the following steps:
establishing a pitch angle linear equation y which is kx + b according to the point cloud point ground data, wherein k represents the slope of a point cloud point ground data fitting straight line, and b represents the distance between the laser radar and the ground;
using fitting slope formula according to pitch angle linear equation
And solving to obtain the current pitch angle k.
5. The method for automatically correcting the pitch angle of the vehicle-mounted laser radar according to claim 1, wherein the updating strategy specifically comprises the following steps:
calculating the current pitch angle according to an error measurement strategy to obtain a deviation pitch angle gt；
According to kt＝β1kt-1+(1-β1)gtGet the updated pitch angle ktWherein, β1Indicating the learning rate.
6. The method of claim 5, wherein the error measure strategy is a difference g between a current pitch angle and a previous pitch anglet＝k-kt-1Where k denotes the current pitch angle, kt-1The pitch angle at the previous moment is indicated.
7. The method for automatically correcting vehicle-mounted laser radar pitch angle according to claim 5, wherein β in the updating strategy1Set to 0.99.
8. The method for automatically correcting the pitch angle of the vehicle-mounted laser radar according to claim 1, wherein a correction step is performed on point cloud data after the current pitch angle is updated.
9. The method according to claim 8, wherein the correcting step is to project the point cloud point raw data onto a plane with zero slope.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011353527.4A CN112558044A (en) | 2020-11-26 | 2020-11-26 | Automatic correction method for vehicle-mounted laser radar pitch angle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011353527.4A CN112558044A (en) | 2020-11-26 | 2020-11-26 | Automatic correction method for vehicle-mounted laser radar pitch angle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112558044A true CN112558044A (en) | 2021-03-26 |
Family
ID=75046913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011353527.4A Pending CN112558044A (en) | 2020-11-26 | 2020-11-26 | Automatic correction method for vehicle-mounted laser radar pitch angle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112558044A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113625237A (en) * | 2021-08-11 | 2021-11-09 | 南京隼眼电子科技有限公司 | Vehicle-mounted millimeter wave radar pitch angle error calibration method and device and electronic equipment |
| CN115079128A (en) * | 2022-08-23 | 2022-09-20 | 深圳市欢创科技有限公司 | Method and device for distortion removal of laser radar point cloud data and robot |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717498A (en) * | 2016-02-04 | 2016-06-29 | 杭州南江机器人股份有限公司 | Pitch angle measuring and correcting system and method of laser range finder |
| CN109696663A (en) * | 2019-02-21 | 2019-04-30 | 北京大学 | A kind of vehicle-mounted three-dimensional laser radar scaling method and system |
| CN111060131A (en) * | 2019-11-27 | 2020-04-24 | 四川阿泰因机器人智能装备有限公司 | Laser radar-based robot accurate posture correction method and device |
| CN111368706A (en) * | 2020-03-02 | 2020-07-03 | 南京航空航天大学 | Data fusion dynamic vehicle detection method based on millimeter wave radar and machine vision |
| CN111427026A (en) * | 2020-02-21 | 2020-07-17 | 深圳市镭神智能系统有限公司 | Laser radar calibration method and device, storage medium and self-moving equipment |
-
2020
- 2020-11-26 CN CN202011353527.4A patent/CN112558044A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717498A (en) * | 2016-02-04 | 2016-06-29 | 杭州南江机器人股份有限公司 | Pitch angle measuring and correcting system and method of laser range finder |
| CN109696663A (en) * | 2019-02-21 | 2019-04-30 | 北京大学 | A kind of vehicle-mounted three-dimensional laser radar scaling method and system |
| CN111060131A (en) * | 2019-11-27 | 2020-04-24 | 四川阿泰因机器人智能装备有限公司 | Laser radar-based robot accurate posture correction method and device |
| CN111427026A (en) * | 2020-02-21 | 2020-07-17 | 深圳市镭神智能系统有限公司 | Laser radar calibration method and device, storage medium and self-moving equipment |
| CN111368706A (en) * | 2020-03-02 | 2020-07-03 | 南京航空航天大学 | Data fusion dynamic vehicle detection method based on millimeter wave radar and machine vision |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113625237A (en) * | 2021-08-11 | 2021-11-09 | 南京隼眼电子科技有限公司 | Vehicle-mounted millimeter wave radar pitch angle error calibration method and device and electronic equipment |
| CN115079128A (en) * | 2022-08-23 | 2022-09-20 | 深圳市欢创科技有限公司 | Method and device for distortion removal of laser radar point cloud data and robot |
| CN115079128B (en) * | 2022-08-23 | 2022-12-09 | 深圳市欢创科技有限公司 | Method and device for distortion removal of laser radar point cloud data and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109001711B (en) | Multi-line laser radar calibration method | |
| CN111208492B (en) | Vehicle-mounted laser radar external parameter calibration method and device, computer equipment and storage medium | |
| CN107632308B (en) | Method for detecting contour of obstacle in front of vehicle based on recursive superposition algorithm | |
| CN108509972A (en) | A kind of barrier feature extracting method based on millimeter wave and laser radar | |
| US20100235129A1 (en) | Calibration of multi-sensor system | |
| CN112558044A (en) | Automatic correction method for vehicle-mounted laser radar pitch angle | |
| CN110764110B (en) | Path navigation method, device and computer readable storage medium | |
| CN112711027B (en) | Tunnel inner transverse positioning method based on laser radar point cloud data | |
| CN111382591B (en) | Binocular camera ranging correction method and vehicle-mounted equipment | |
| CN113327296A (en) | Laser radar and camera online combined calibration method based on depth weighting | |
| CN112098960A (en) | Method for determining an alignment angle of a radar sensor for a road vehicle radar auto-alignment controller | |
| US11677931B2 (en) | Automated real-time calibration | |
| CN115079143B (en) | Multi-radar external parameter quick calibration method and device for double-bridge steering mine card | |
| CN112710339A (en) | Method and apparatus for calibrating vehicle sensors | |
| CN113935904A (en) | Laser odometer error correction method, system, storage medium and computing equipment | |
| JP7137464B2 (en) | Camera calibration device, camera calibration method, and program | |
| DE102022108712A1 (en) | Joint estimation and correction of an alignment error of a LIDAR centerline and a localization error of a host vehicle | |
| US20220187832A1 (en) | Sensor fusion in agricultural vehicle steering | |
| Jeong et al. | LiDAR intensity calibration for road marking extraction | |
| CN117590362B (en) | Multi-laser radar external parameter calibration method, device and equipment | |
| CN113296120B (en) | Obstacle detection method and terminal | |
| US20130057658A1 (en) | Method for Detection of Targets in Stereoscopic Images | |
| CN114442073A (en) | Laser radar calibration method and device, vehicle and storage medium | |
| CN114527452A (en) | Laser radar external parameter online calibration method | |
| CN112835029A (en) | Unmanned-vehicle-oriented multi-sensor obstacle detection data fusion method 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 |