CN113870359A - Laser radar external parameter calibration method and device based on random gradient descent - Google Patents
Laser radar external parameter calibration method and device based on random gradient descent Download PDFInfo
- Publication number
- CN113870359A CN113870359A CN202111117477.4A CN202111117477A CN113870359A CN 113870359 A CN113870359 A CN 113870359A CN 202111117477 A CN202111117477 A CN 202111117477A CN 113870359 A CN113870359 A CN 113870359A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- gradient descent
- random gradient
- laser radar
- external
- 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 47
- 239000013643 reference control Substances 0.000 claims abstract description 85
- 238000011478 gradient descent method Methods 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 20
- 238000012795 verification Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 11
- 238000012986 modification Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 239000000463 material Substances 0.000 abstract description 11
- 230000006870 function Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention discloses a laser radar external reference calibration method, medium and device based on random gradient descent, wherein the method comprises the following steps: scanning an image area to be built through radar equipment to obtain reference point cloud data; screening the datum point cloud data to select a plurality of datum control points and extracting point cloud coordinate values of the datum control points; measuring each reference control point to obtain an actual coordinate value of each reference control point; correcting laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration; the efficiency and the accuracy of laser radar external parameter calibration can be effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
Description
Technical Field
The invention relates to the technical field of radar measurement, in particular to a laser radar external reference calibration method based on random gradient descent, a computer-readable storage medium and a laser radar external reference calibration device based on random gradient descent.
Background
The laser radar has the advantages of high precision, large range finding range, no influence of light and the like, and is widely applied to the environment perception fields of obstacle detection, instant positioning, map construction and the like of intelligent driving vehicles. In the actual use process, in order to unify the information of multiple sensors to realize accurate positioning, data acquired by a laser radar under a local coordinate system of the laser radar needs to be converted into a world coordinate system, namely point cloud coordinate data is converted through a coordinate transformation matrix. Therefore, the laser radar needs to be calibrated in advance to obtain an accurate transformation matrix.
In the related art, a manual calibration method or a calibration object measurement method is mostly adopted in the process of external reference calibration of the laser radar, however, the manual calibration method has high requirements on the operation precision of an operator, and is not strong in popularization and unstable in measurement precision. The calibration object measuring method needs to move the calibration object, and consumes a large amount of manpower, so that the calibration efficiency of the method is low.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, one purpose of the invention is to provide a laser radar external reference calibration method based on random gradient descent, which can effectively improve the laser radar external reference calibration efficiency and accuracy; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
A second object of the invention is to propose a computer-readable storage medium.
The third purpose of the invention is to provide a laser radar external reference calibration device based on random gradient descent.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for calibrating an external parameter of a laser radar based on random gradient descent, including the following steps: scanning an image area to be built through radar equipment to obtain reference point cloud data; screening the datum point cloud data to select a plurality of datum control points and extracting point cloud coordinate values of the datum control points; measuring each reference control point to obtain an actual coordinate value of each reference control point; and correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration.
According to the laser radar external reference calibration method based on random gradient descent, firstly, a region to be mapped is scanned through radar equipment to obtain reference point cloud data; then, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points; then, measuring each reference control point to obtain an actual coordinate value of each reference control point; then, correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration; therefore, the efficiency and the accuracy of laser radar external parameter calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
In addition, the laser radar external reference calibration method based on random gradient descent proposed by the above embodiment of the present invention may further have the following additional technical features:
optionally, the screening the reference point cloud data to select a plurality of reference control points includes: segmenting the reference point cloud data to generate a plurality of reference point cloud areas, and calculating a shielding coefficient, a reflection intensity value and a definition value corresponding to each reference point cloud area; and calculating a comprehensive value corresponding to each reference point cloud area according to the shielding coefficient, the reflection intensity value and the definition value, and determining a reference control point according to the comprehensive value.
Optionally, the modifying the laser radar external parameter according to the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by using a random gradient descent method includes: calculating an error between an actual coordinate value of the reference control point and a corresponding point cloud coordinate value according to the loss function so as to preprocess the data and obtain a sample set; randomly selecting samples in the sample set to obtain a training sample set verification sample set; training according to the training sample by using a random gradient descent method to correct the external parameters of the laser radar; and verifying the corrected radar external parameters by using a verification sample set.
Optionally, the loss function is expressed by the following formula:
L＝α*h1+h2
where L represents a loss function, α represents an adjustable weight, h1 represents a horizontal distance error, and h2 represents an elevation distance error.
In order to achieve the above object, a second aspect of the present invention provides a computer-readable storage medium, on which a random gradient descent-based lidar external reference calibration program is stored, where the random gradient descent-based lidar external reference calibration program is executed by a processor to implement the random gradient descent-based lidar external reference calibration method as described above.
According to the computer-readable storage medium of the embodiment of the invention, the laser radar external reference calibration program based on the random gradient descent is stored, so that when the processor executes the laser radar external reference calibration program based on the random gradient descent, the laser radar external reference calibration method based on the random gradient descent is realized, and the efficiency and the accuracy of laser radar external reference calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
In order to achieve the above object, a third embodiment of the present invention provides a lidar external reference calibration apparatus based on random gradient descent, including: a processor and a measurement unit, wherein: the processor is used for acquiring reference point cloud data obtained by scanning of radar equipment, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points; the measuring unit is used for measuring each reference control point to obtain an actual coordinate value of each reference control point; and the processor is also used for correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values so as to finish external parameter calibration.
According to the laser radar external reference calibration device based on random gradient descent, provided by the embodiment of the invention, the processor and the measurement unit are arranged, wherein: the processor is used for acquiring reference point cloud data obtained by scanning of radar equipment, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points; the measuring unit is used for measuring each reference control point to obtain an actual coordinate value of each reference control point; the processor is also used for correcting the laser radar external parameters according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values by using a random gradient descent method so as to finish external parameter calibration; therefore, the efficiency and the accuracy of laser radar external parameter calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
In addition, the lidar external reference calibration device based on random gradient descent proposed by the above embodiment of the present invention may further have the following additional technical features:
optionally, the measurement unit comprises a lidar and an inertial measurer.
Optionally, the screening the reference point cloud data to select a plurality of reference control points includes: segmenting the reference point cloud data to generate a plurality of reference point cloud areas, and calculating a shielding coefficient, a reflection intensity value and a definition value corresponding to each reference point cloud area; and calculating a comprehensive value corresponding to each reference point cloud area according to the shielding coefficient, the reflection intensity value and the definition value, and determining a reference control point according to the comprehensive value.
Optionally, the modifying the laser radar external parameter according to the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by using a random gradient descent method includes: calculating an error between an actual coordinate value of the reference control point and a corresponding point cloud coordinate value according to the loss function so as to preprocess the data and obtain a sample set; randomly selecting samples in the sample set to obtain a training sample set verification sample set; training according to the training sample by using a random gradient descent method to correct the external parameters of the laser radar; and verifying the corrected radar external parameters by using a verification sample set.
Optionally, the loss function is expressed by the following formula:
L＝α*h1+h2
where L represents a loss function, α represents an adjustable weight, h1 represents a horizontal distance error, and h2 represents an elevation distance error.
Drawings
FIG. 1 is a schematic flow chart of a lidar external reference calibration method based on random gradient descent according to an embodiment of the invention;
fig. 2 is a block diagram illustrating a lidar external reference calibration apparatus based on random gradient descent according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the related art, a manual calibration method or a calibration object measurement method is mostly adopted in the process of external reference calibration of the laser radar, however, the manual calibration method has high requirements on the operation precision of an operator, and is not strong in popularization and unstable in measurement precision. The calibration object measuring method needs to move the calibration object, and consumes a large amount of manpower, so that the calibration efficiency of the method is low. According to the laser radar external reference calibration method based on random gradient descent, firstly, a region to be mapped is scanned through radar equipment to obtain reference point cloud data; then, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points; then, measuring each reference control point to obtain an actual coordinate value of each reference control point; then, correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration; therefore, the efficiency and the accuracy of laser radar external parameter calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a schematic flow chart of a lidar external reference calibration method based on random gradient descent according to an embodiment of the present invention, and as shown in fig. 1, the lidar external reference calibration method based on random gradient descent includes the following steps:
s101, scanning an area to be mapped through radar equipment to obtain reference point cloud data.
S102, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points.
That is, the obtained reference point cloud data is screened to select a proper point location as a reference control point; wherein, the suitable reference control point is a point position which has no shielding environment, strong reflectivity and clear and identifiable point cloud inside.
In some embodiments, the filtering the reference point cloud data to select a plurality of reference control points includes: segmenting the reference point cloud data to generate a plurality of reference point cloud areas, and calculating a shielding coefficient, a reflection intensity value and a definition value corresponding to each reference point cloud area; and calculating a comprehensive value corresponding to each reference point cloud area according to the shielding coefficient, the reflection intensity value and the definition value, and determining a reference control point according to the comprehensive value.
And S103, measuring each reference control point to obtain an actual coordinate value of each reference control point.
That is, the measuring device is placed at the selected reference control point to measure each reference control point, and the actual coordinate value of each reference control point is obtained.
And S104, correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration.
That is, the laser radar external parameter is corrected according to the difference between the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by a random gradient descent method, so as to complete the calibration of the external parameter.
In some embodiments, the laser radar external parameter is corrected according to the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by using a random gradient descent method, which comprises the following steps: calculating an error between an actual coordinate value of the reference control point and a corresponding point cloud coordinate value according to the loss function so as to preprocess the data and obtain a sample set; randomly selecting samples in the sample set to obtain a training sample set verification sample set; training according to the training sample by using a random gradient descent method to correct the external parameters of the laser radar; and verifying the corrected radar external parameters by using a verification sample set.
As an example, assume that the number of selected reference control points is 70; after the initial data preprocessing is completed, 50 of the initial data are randomly selected as training samples, and 20 of the initial data are randomly selected as verification samples; then, correcting the laser radar external parameters according to 50 training samples by a random gradient descent method; and verified after completion by 20 verification samples to complete the calibration.
In some embodiments, because it was found during the actual study: the initial horizontal distance error is much higher than the elevation distance error, so to improve the accuracy of the final calibration result, the loss function is expressed by the following formula:
L＝α*h1+h2
where L represents a loss function, α represents an adjustable weight, h1 represents a horizontal distance error, and h2 represents an elevation distance error.
In summary, according to the laser radar external reference calibration method based on random gradient descent in the embodiment of the present invention, firstly, a region to be mapped is scanned by a radar device to obtain reference point cloud data; then, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points; then, measuring each reference control point to obtain an actual coordinate value of each reference control point; then, correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration; therefore, the efficiency and the accuracy of laser radar external parameter calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
In order to implement the foregoing embodiment, an embodiment of the present invention provides a computer-readable storage medium, on which a laser radar external reference calibration program based on random gradient descent is stored, and when executed by a processor, the laser radar external reference calibration program based on random gradient descent implements the laser radar external reference calibration method based on random gradient descent as described above.
According to the computer-readable storage medium of the embodiment of the invention, the laser radar external reference calibration program based on the random gradient descent is stored, so that when the processor executes the laser radar external reference calibration program based on the random gradient descent, the laser radar external reference calibration method based on the random gradient descent is realized, and the efficiency and the accuracy of laser radar external reference calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
In order to implement the foregoing embodiment, an embodiment of the present invention provides a lidar external reference calibration apparatus based on random gradient descent, and as shown in fig. 2, the lidar external reference calibration apparatus based on random gradient descent includes: a processor 10 and a measurement unit 20.
The processor 10 is configured to acquire reference point cloud data obtained by scanning of the radar device, screen the reference point cloud data to select a plurality of reference control points, and extract point cloud coordinate values of the reference control points;
the measuring unit 20 is configured to measure each reference control point to obtain an actual coordinate value of each reference control point;
the processor 10 is further configured to perform laser radar external reference correction according to the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by using a random gradient descent method, so as to complete external reference calibration.
In some embodiments, the measurement unit 20 includes a lidar and an inertial measurer.
In some embodiments, the filtering the reference point cloud data to select a plurality of reference control points includes: segmenting the reference point cloud data to generate a plurality of reference point cloud areas, and calculating a shielding coefficient, a reflection intensity value and a definition value corresponding to each reference point cloud area; and calculating a comprehensive value corresponding to each reference point cloud area according to the shielding coefficient, the reflection intensity value and the definition value, and determining a reference control point according to the comprehensive value.
In some embodiments, the laser radar external parameter is corrected according to the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by using a random gradient descent method, which comprises the following steps: calculating an error between an actual coordinate value of the reference control point and a corresponding point cloud coordinate value according to the loss function so as to preprocess the data and obtain a sample set; randomly selecting samples in the sample set to obtain a training sample set verification sample set; training according to the training sample by using a random gradient descent method to correct the external parameters of the laser radar; and verifying the corrected radar external parameters by using a verification sample set.
In some embodiments, the loss function is expressed by the following formula:
L＝α*h1+h2
where L represents a loss function, α represents an adjustable weight, h1 represents a horizontal distance error, and h2 represents an elevation distance error.
It should be noted that the above description about the laser radar external reference calibration method based on random gradient descent in fig. 1 is also applicable to the laser radar external reference calibration device based on random gradient descent, and is not repeated herein.
In summary, according to the laser radar external reference calibration apparatus based on random gradient descent in the embodiment of the present invention, by setting the processor and the measurement unit, wherein: the processor is used for acquiring reference point cloud data obtained by scanning of radar equipment, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points; the measuring unit is used for measuring each reference control point to obtain an actual coordinate value of each reference control point; the processor is also used for correcting the laser radar external parameters according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values by using a random gradient descent method so as to finish external parameter calibration; therefore, the efficiency and the accuracy of laser radar external parameter calibration are effectively improved; meanwhile, the manpower and material resources consumed by laser radar external parameter calibration are reduced, and the method is suitable for popularization.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above should not be understood to necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A laser radar external reference calibration method based on random gradient descent is characterized by comprising the following steps:
scanning an image area to be built through radar equipment to obtain reference point cloud data;
screening the datum point cloud data to select a plurality of datum control points and extracting point cloud coordinate values of the datum control points;
measuring each reference control point to obtain an actual coordinate value of each reference control point;
and correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values to finish external parameter calibration.
2. The lidar external reference calibration method based on random gradient descent of claim 1, wherein the step of screening the reference point cloud data to select a plurality of reference control points comprises:
segmenting the reference point cloud data to generate a plurality of reference point cloud areas, and calculating a shielding coefficient, a reflection intensity value and a definition value corresponding to each reference point cloud area;
and calculating a comprehensive value corresponding to each reference point cloud area according to the shielding coefficient, the reflection intensity value and the definition value, and determining a reference control point according to the comprehensive value.
3. The method for calibrating laser radar external parameters based on random gradient descent as claimed in claim 1, wherein the step of correcting the laser radar external parameters according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values by using the random gradient descent method comprises:
calculating an error between an actual coordinate value of the reference control point and a corresponding point cloud coordinate value according to the loss function so as to preprocess the data and obtain a sample set;
randomly selecting samples in the sample set to obtain a training sample set verification sample set;
training according to the training sample by using a random gradient descent method to correct the external parameters of the laser radar;
and verifying the corrected radar external parameters by using a verification sample set.
4. The lidar external reference calibration method based on random gradient descent of claim 3, wherein the loss function is expressed by the following formula:
L＝α*h1+h2
where L represents a loss function, α represents an adjustable weight, h1 represents a horizontal distance error, and h2 represents an elevation distance error.
5. A computer-readable storage medium, on which a random gradient descent-based lidar external reference calibration program is stored, which, when executed by a processor, implements the random gradient descent-based lidar external reference calibration method of any one of claims 1-4.
6. The laser radar external reference calibration device based on random gradient descent is characterized by comprising the following components: a processor and a measurement unit, wherein:
the processor is used for acquiring reference point cloud data obtained by scanning of radar equipment, screening the reference point cloud data to select a plurality of reference control points and extracting point cloud coordinate values of the reference control points;
the measuring unit is used for measuring each reference control point to obtain an actual coordinate value of each reference control point;
and the processor is also used for correcting the laser radar external parameters by using a random gradient descent method according to the actual coordinate values of the reference control points and the corresponding point cloud coordinate values so as to finish external parameter calibration.
7. The lidar external reference calibration apparatus based on random gradient descent of claim 6, wherein the measurement unit comprises a lidar and an inertial measurer.
8. The lidar external reference calibration apparatus for random gradient descent according to claim 6, wherein the step of screening the reference point cloud data to select a plurality of reference control points comprises:
segmenting the reference point cloud data to generate a plurality of reference point cloud areas, and calculating a shielding coefficient, a reflection intensity value and a definition value corresponding to each reference point cloud area;
and calculating a comprehensive value corresponding to each reference point cloud area according to the shielding coefficient, the reflection intensity value and the definition value, and determining a reference control point according to the comprehensive value.
9. The lidar external reference calibration device based on random gradient descent of claim 6, wherein the modification of the lidar external reference according to the actual coordinate value of the reference control point and the corresponding point cloud coordinate value by using the random gradient descent method comprises:
calculating an error between an actual coordinate value of the reference control point and a corresponding point cloud coordinate value according to the loss function so as to preprocess the data and obtain a sample set;
randomly selecting samples in the sample set to obtain a training sample set verification sample set;
training according to the training sample by using a random gradient descent method to correct the external parameters of the laser radar;
and verifying the corrected radar external parameters by using a verification sample set.
10. The lidar external reference calibration apparatus for random gradient descent of claim 8, wherein the loss function is expressed by the following formula:
L＝α*h1+h2
where L represents a loss function, α represents an adjustable weight, h1 represents a horizontal distance error, and h2 represents an elevation distance error.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111117477.4A CN113870359A (en) | 2021-09-23 | 2021-09-23 | Laser radar external parameter calibration method and device based on random gradient descent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111117477.4A CN113870359A (en) | 2021-09-23 | 2021-09-23 | Laser radar external parameter calibration method and device based on random gradient descent |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870359A true CN113870359A (en) | 2021-12-31 |
Family
ID=78993648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111117477.4A Pending CN113870359A (en) | 2021-09-23 | 2021-09-23 | Laser radar external parameter calibration method and device based on random gradient descent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870359A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109871850A (en) * | 2019-01-21 | 2019-06-11 | 北京大学 | A kind of classification method of the mobile lidar data based on neural network model |
| CN112924955A (en) * | 2021-01-29 | 2021-06-08 | 同济大学 | Dynamic correction method for point cloud coordinates of roadside laser radar |
| CN112949380A (en) * | 2021-01-08 | 2021-06-11 | 浙江大学 | Intelligent underwater target identification system based on laser radar point cloud data |
| WO2021174507A1 (en) * | 2020-03-05 | 2021-09-10 | 深圳市大疆创新科技有限公司 | Parameter calibration method, device, and system, and storage medium |
-
2021
- 2021-09-23 CN CN202111117477.4A patent/CN113870359A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109871850A (en) * | 2019-01-21 | 2019-06-11 | 北京大学 | A kind of classification method of the mobile lidar data based on neural network model |
| WO2021174507A1 (en) * | 2020-03-05 | 2021-09-10 | 深圳市大疆创新科技有限公司 | Parameter calibration method, device, and system, and storage medium |
| CN112949380A (en) * | 2021-01-08 | 2021-06-11 | 浙江大学 | Intelligent underwater target identification system based on laser radar point cloud data |
| CN112924955A (en) * | 2021-01-29 | 2021-06-08 | 同济大学 | Dynamic correction method for point cloud coordinates of roadside laser radar |
Non-Patent Citations (1)
| Title |
|---|
| 康国华;张琪;张晗;徐伟证;张文豪;: "基于点云中心的激光雷达与相机联合标定方法研究", 仪器仪表学报, no. 12, 15 December 2019 (2019-12-15), pages 121 - 129 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961468B (en) | Volume measurement method and device based on binocular vision and storage medium | |
| CN109725303B (en) | Coordinate system correction method and device, and storage medium | |
| CN103513029A (en) | Immunochromatographic analyzer calibration method | |
| CN111750804B (en) | Object measuring method and device | |
| CN111383285A (en) | Millimeter wave radar and camera sensor fusion calibration method and system | |
| JP2022528301A (en) | Calibration method, positioning method, equipment, electronic devices and storage media | |
| CN111508011A (en) | Depth data calibration method of flight time camera | |
| CN111398938B (en) | Laser radar calibration method and system | |
| CN108961184A (en) | A kind of bearing calibration of depth image, device and equipment | |
| CN115840196B (en) | Laser radar inter-calibration method and device based on entity calibration | |
| CN109903245A (en) | The non-uniform correction method of infrared image | |
| CN112558027A (en) | Radar verification method, device, equipment and storage medium | |
| CN116543056A (en) | Linear camera calibration and calibration method, device and storage medium | |
| CN116399820A (en) | Method, device, equipment and medium for verifying authenticity of vegetation remote sensing product | |
| CN108875184B (en) | Shale organic carbon content prediction method and device based on digital outcrop model | |
| CN113702927A (en) | Vehicle sensor calibration method and device and storage medium | |
| CN116660873B (en) | Precision compensation method, device and equipment for laser sensor and storage medium | |
| CN113032272A (en) | Automatic parking system test evaluation method, device, equipment and storage medium | |
| CN112734858A (en) | Binocular calibration precision online detection method and device | |
| CN113870359A (en) | Laser radar external parameter calibration method and device based on random gradient descent | |
| CN107741220B (en) | Image processing method and device and electronic equipment | |
| CN110058211B (en) | Method and device for acquiring calibration initial value of vehicle-mounted LiDAR measurement system | |
| CN111669573A (en) | Motor stability detection method and device | |
| JP2021518951A (en) | Correction method and device for correcting image data | |
| CN115166701B (en) | System calibration method and device for RGB-D camera and laser radar |
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 |