CN114217277A - Radar camera calibration quality evaluation method and system - Google Patents
Radar camera calibration quality evaluation method and system Download PDFInfo
- Publication number
- CN114217277A CN114217277A CN202111516455.5A CN202111516455A CN114217277A CN 114217277 A CN114217277 A CN 114217277A CN 202111516455 A CN202111516455 A CN 202111516455A CN 114217277 A CN114217277 A CN 114217277A
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- radar
- points
- outliers
- module
- 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 22
- 238000013441 quality evaluation Methods 0.000 title claims description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 11
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims 2
- 238000011156 evaluation Methods 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G01S7/02—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
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a method and a system for evaluating the calibration quality of a radar camera, wherein the method comprises the following steps: step S1: error calculation is carried out on the pixel coordinate system, and outliers are judged; step S2: unifying pixel coordinate system formulas; step S3: unifying a world coordinate system, and selecting outliers; step S4: the pixel domain and world coordinate system results are aggregated. The invention solves the problems of too long calibration time and too much manpower input of an RSU drive test sensing scheme.
Description
Technical Field
The invention relates to the technical field of radar camera shooting, in particular to a method and a system for evaluating calibration quality of a radar camera.
Background
Calibration mainly refers to the fact that whether the accuracy (precision) of a used instrument meets a standard or not is detected by using a standard measuring instrument, and generally, the calibration is mainly used for instruments with high precision. Calibration may also be considered calibration. Therefore, the term "calibration" may be considered to include both of the above meanings.
Patent document No. CN112684424A discloses an automatic calibration method for millimeter wave radar and camera, which includes the following steps: 1) only one moving target is arranged in the cross visual range of the millimeter wave radar and the camera, and the moving target moves in a plurality of positions in the cross visual range; 2) the millimeter wave radar and the camera perform sampling at the same starting time and the same frequency; 3) primarily screening a plurality of target points of the millimeter wave radar and the camera in each sampling period; 4) respectively acquiring target points obtained by a millimeter wave radar and a camera in a plurality of continuous sampling periods, and performing outlier screening; 5) and constructing a neural network for training the radar target point coordinates and the camera target point coordinates of the continuous sampling period after outlier screening, and realizing automatic calibration of the millimeter-wave radar and the camera according to the trained neural network.
In view of the above-mentioned related technologies, the inventor considers that the above-mentioned technologies have problems of too long calibration time and too much manpower input, and therefore, a technical solution is needed to improve the above-mentioned technical problems.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method and a system for evaluating the calibration quality of a radar camera.
According to the invention, the method for evaluating the calibration quality of the radar camera comprises the following steps:
step S1: error calculation is carried out on the pixel coordinate system, and outliers are judged;
step S2: unifying pixel coordinate system formulas;
step S3: unifying a world coordinate system, and selecting outliers;
step S4: the pixel domain and world coordinate system results are aggregated.
Preferably, the step S1 includes the steps of:
step S1.1: respectively carrying out difference operation on the positions of the radar, the camera and the gps coordinates of the N groups of scattered points in the pixel and the true value;
step S1.2: averaging the results obtained by the difference operation, performing descending order arrangement on the N groups of results, and judging the result as an outlier if the obtained error value is greater than a threshold value;
step S1.3: and (4) detecting the outliers of the N groups of values obtained in the step (S2.1) by using a Local Outlier Factor method.
Preferably, in step S3, the pixels, the radar, and the real values of the raw data are mapped into world coordinates, and are displayed on a screen using a map, and the outliers are selected by a bird' S-eye view brush.
Preferably, in step S4, the deviation result of the pixel coordinate system is compared with the result of the map bird' S-eye view, so as to find a calibration outlier, and the calibration staff is notified to collect correction data, thereby evaluating and deploying the calibration quality of the road measuring end.
Preferably, the radar, the camera and the calculated gps world coordinate are mapped to a pixel coordinate system together, the mapping calculation is performed on the acquired N target points, N groups of scattered points are obtained in the pixel coordinate system, the N groups of scattered points are ensured to be located in the ROI road area, the errors of the N groups of points are effectively sorted, the deviation outliers in the scattered points are located, the user is informed of the results, the data points are collected again, and the error points are located.
The invention also provides a radar camera calibration quality evaluation system, which comprises the following modules:
module M1: error calculation is carried out on the pixel coordinate system, and outliers are judged;
module M2: unifying pixel coordinate system formulas;
module M3: unifying a world coordinate system, and selecting outliers;
module M4: the pixel domain and world coordinate system results are aggregated.
Preferably, the module M1 includes the following modules:
module M1.1: respectively carrying out difference operation on the positions of the radar, the camera and the gps coordinates of the N groups of scattered points in the pixel and the true value;
module M1.2: averaging the results obtained by the difference operation, performing descending order arrangement on the N groups of results, and judging the result as an outlier if the obtained error value is greater than a threshold value;
module M1.3: and detecting outliers by using a Local Outlier Factor system on the N groups of values obtained by the module M2.1.
Preferably, the module M3 maps the pixels, radar and true values of the original data into world coordinates, and displays the world coordinates on a map, and selects outliers by bird's-eye view.
Preferably, in the module M4, the deviation result of the pixel coordinate system is compared with the result of the map bird's-eye view, so as to find the calibration outlier, notify the calibration personnel to collect the correction data, and evaluate and deploy the calibration quality of the road measuring end.
Preferably, the radar, the camera and the calculated gps world coordinate are mapped to a pixel coordinate system together, the mapping calculation is performed on the acquired N target points, N groups of scattered points are obtained in the pixel coordinate system, the N groups of scattered points are ensured to be located in the ROI road area, the errors of the N groups of points are effectively sorted, the deviation outliers in the scattered points are located, the user is informed of the results, the data points are collected again, and the error points are located.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention solves the problems of too long calibration time and too much manpower input of an RSU drive test sensing scheme;
2. the method improves the distance sensing precision of the radar and camera combined scheme of the drive test end by 35 percent compared with the prior respective calibration scheme;
3. the invention supports the precision cross validation of a pixel coordinate system and a world coordinate system, and the software display is more visual, convenient and quick.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flow diagram of the present invention;
FIG. 2 is a world coordinate system radar pixel truth map.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
The invention provides a radar camera calibration quality evaluation method, wherein a radar, a camera and calculated gps world coordinates are mapped to a pixel coordinate system together, N collected target points are subjected to mapping calculation, N groups of scattered points are obtained in the pixel coordinate system, the N groups of scattered points are ensured to be positioned in an ROI road area, then errors of the N groups of points are effectively sorted, deviation outliers in the scattered points are quickly positioned, a user is informed of the results, and data points are collected again, so that the effect of quickly positioning the error points is achieved.
A radar camera calibration quality evaluation method comprises the following steps:
step 1: calculating errors of a unified pixel coordinate system; step 1.1: performing difference operation on the positions of the radar, the camera and the gps coordinates of the N groups of scattered points in the pixel and the true value respectively; step 1.2: then, obtaining an average, performing descending order arrangement on the N groups of results, and judging that the obtained error value is greater than a certain threshold value as an outlier; step 1.3: the outliers are detected by the N sets of values obtained in step 2.1 using the Local Outlier Factor method and the user is informed whether the technique lof can be applied for the coordinate system error calculation.
Step 2: unified pixel coordinate system formula and corresponding software presentation:
wherein: rank represents the sorting of N groups of calculation results in brackets;
DO represents descending order (sorted from large to small);
dis represents the Euclidean distance between two points;
P0-PN represents the coordinate value of the origin of the image after calibration, from 0 group to N groups of points;
A0-AN represents the true value of the image of the calibration original data;
R0-RN represents the pixel value of the radar value in the image coordinate system;
G0-GN represents the pixel values of the conversion of GPS data into an image coordinate system
And step 3: unifying a world coordinate system; the pixels, the radar and the original data truth value are uniformly mapped into world coordinates, and a high-precision map is used for displaying pictures, so that outliers can be quickly selected through a bird's-eye view.
And 4, step 4: summarizing pixel domain and world coordinate system results; by comparing the deviation result of the pixel coordinate system with the aerial view result of the map, the calibration outlier can be easily and quickly found, and calibration related personnel are informed to quickly acquire correction data so as to achieve the calibration quality evaluation and quick deployment of the road measuring end.
The invention also provides a radar camera calibration quality evaluation system, which comprises the following modules: module M1: error calculation is carried out on the pixel coordinate system, and outliers are judged; module M1.1: respectively carrying out difference operation on the positions of the radar, the camera and the gps coordinates of the N groups of scattered points in the pixel and the true value; module M1.2: averaging the results obtained by the difference operation, performing descending order arrangement on the N groups of results, and judging the result as an outlier if the obtained error value is greater than a threshold value; module M1.3: and detecting the outliers by applying the N groups of values obtained by the module M2.1 to a Local Outlier Factor system.
Module M2: unifying pixel coordinate system formulas; module M3: unifying a world coordinate system, and selecting outliers; and uniformly mapping the pixels, the radar and the original data truth value into world coordinates, displaying a picture by using a map, and selecting an outlier by a bird's-eye view picture brush.
Module M4: the pixel domain and world coordinate system results are aggregated. And comparing the deviation result of the pixel coordinate system with the bird's-eye view result of the map, finding a calibration outlier, informing calibration personnel to collect correction data, and evaluating and deploying the calibration quality of the road measuring end.
The radar, the camera and the calculated gps world coordinate are mapped to a pixel coordinate system together, the N collected target points are subjected to mapping calculation, N groups of scattered points are obtained in the pixel coordinate system, the N groups of scattered points are ensured to be located in the ROI area, errors of the N groups of points are effectively sequenced, deviation outliers in the scattered points are located, a user is informed of the results, the data points are collected again, and the error points are located.
The invention solves the problems of too long calibration time and too much manpower input of an RSU drive test sensing scheme.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, units provided by the present invention as pure computer readable program code, the system and its various devices, modules, units provided by the present invention can be implemented with the same functionality in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like, all by logically programming method steps. Therefore, the system and the devices, modules and units thereof provided by the present invention can be regarded as a hardware component, and the devices, modules and units included therein for implementing various functions can also be regarded as structures within the hardware component; means, modules, units for performing the various functions may also be regarded as structures within both software modules and hardware components for performing the method.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. A radar camera calibration quality evaluation method is characterized by comprising the following steps:
step S1: error calculation is carried out on the pixel coordinate system, and outliers are judged;
step S2: unifying pixel coordinate system formulas;
step S3: unifying a world coordinate system, and selecting outliers;
step S4: the pixel domain and world coordinate system results are aggregated.
2. The radar camera calibration quality evaluation method according to claim 1, wherein said step S1 includes the steps of:
step S1.1: respectively carrying out difference operation on the positions of the radar, the camera and the gps coordinates of the N groups of scattered points in the pixel and the true value;
step S1.2: averaging the results obtained by the difference operation, performing descending order arrangement on the N groups of results, and judging the result as an outlier if the obtained error value is greater than a threshold value;
step S1.3: and (4) detecting the outliers by applying a Local Outlier Factor method to the N groups of values obtained in the step (S2.1).
3. The radar camera calibration quality evaluation method according to claim 1, wherein in step S3, pixels, radar, and true values of raw data are mapped together into world coordinates, and a map is used for screen display, and outliers are selected by a bird' S-eye view brush.
4. The method for evaluating the calibration quality of the radar camera according to claim 1, wherein in step S4, the calibration outlier is found by comparing the deviation result of the pixel coordinate system with the result of the bird' S eye view of the map, and a calibration person is notified to collect correction data to evaluate and deploy the calibration quality of the road measurement end.
5. The radar camera calibration quality evaluation method according to claim 1, wherein the radar, the camera, and the calculated gps world coordinate are mapped together to a pixel coordinate system, and the mapping calculation is performed on the N collected target points to obtain N sets of scatter points in the pixel coordinate system, and ensure that the N sets of scatter points are all located in the ROI road region, and the N sets of scatter points are error-efficiently sorted, and the deviation outliers in the scatter points are located, and the user is informed of the result, and the data points are recollected, and the error points are located.
6. A radar camera calibration quality evaluation system, characterized in that the system comprises the following modules:
module M1: error calculation is carried out on the pixel coordinate system, and outliers are judged;
module M2: unifying pixel coordinate system formulas;
module M3: unifying a world coordinate system, and selecting outliers;
module M4: the pixel domain and world coordinate system results are aggregated.
7. The radar camera calibration quality evaluation system of claim 6, wherein said module M1 comprises the following modules:
module M1.1: respectively carrying out difference operation on the positions of the radar, the camera and the gps coordinates of the N groups of scattered points in the pixel and the true value;
module M1.2: averaging the results obtained by the difference operation, performing descending order arrangement on the N groups of results, and judging the result as an outlier if the obtained error value is greater than a threshold value;
module M1.3: and detecting the outliers by using the N groups of values obtained by the module M2.1 through a Local Outlier Factor system.
8. The radar camera calibration quality evaluation system according to claim 6, wherein in the module M3, pixels, radar, and raw data truth values are mapped together into world coordinates, and are displayed on a screen using a map, and outliers are selected by a bird's eye view brush.
9. The radar camera calibration quality evaluation system according to claim 6, wherein in the module M4, calibration outliers are found by comparing the deviation result of the pixel coordinate system with the result of the map bird's eye view, calibration personnel are notified to collect correction data, and the quality of calibration evaluation and deployment are performed on the road measurement end.
10. The radar camera calibration quality evaluation system of claim 6, wherein the radar, the camera, and the calculated gps world coordinates are mapped together to a pixel coordinate system, and the mapping calculation is performed on the N collected target points to obtain N sets of scatter points in the pixel coordinate system, ensure that the N sets of scatter points are all located in the ROI road region, perform error-efficient ranking on the N sets of points, locate the deviation outliers in the scatter points, and inform the user of the results to perform the recollection of the data points and locate the error points.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111516455.5A CN114217277A (en) | 2021-12-09 | 2021-12-09 | Radar camera calibration quality evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111516455.5A CN114217277A (en) | 2021-12-09 | 2021-12-09 | Radar camera calibration quality evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114217277A true CN114217277A (en) | 2022-03-22 |
Family
ID=80701229
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111516455.5A Pending CN114217277A (en) | 2021-12-09 | 2021-12-09 | Radar camera calibration quality evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114217277A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200232800A1 (en) * | 2019-01-17 | 2020-07-23 | GM Global Technology Operations LLC | Method and apparatus for enabling sequential groundview image projection synthesis and complicated scene reconstruction at map anomaly hotspot |
CN111986162A (en) * | 2020-07-28 | 2020-11-24 | 西安理工大学 | Hyperspectral abnormal point rapid detection method based on rough positioning and collaborative representation |
KR102206314B1 (en) * | 2019-10-08 | 2021-01-22 | 전남대학교산학협력단 | Apparatus and method for processing outlier |
CN112684424A (en) * | 2020-12-30 | 2021-04-20 | 同济大学 | Automatic calibration method for millimeter wave radar and camera |
-
2021
- 2021-12-09 CN CN202111516455.5A patent/CN114217277A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200232800A1 (en) * | 2019-01-17 | 2020-07-23 | GM Global Technology Operations LLC | Method and apparatus for enabling sequential groundview image projection synthesis and complicated scene reconstruction at map anomaly hotspot |
KR102206314B1 (en) * | 2019-10-08 | 2021-01-22 | 전남대학교산학협력단 | Apparatus and method for processing outlier |
CN111986162A (en) * | 2020-07-28 | 2020-11-24 | 西安理工大学 | Hyperspectral abnormal point rapid detection method based on rough positioning and collaborative representation |
CN112684424A (en) * | 2020-12-30 | 2021-04-20 | 同济大学 | Automatic calibration method for millimeter wave radar and camera |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111598913B (en) | Image segmentation method and system based on robot vision | |
CN112465880B (en) | Target detection method based on multi-source heterogeneous data cognitive fusion | |
CN108537834A (en) | A kind of volume measuring method, system and depth camera based on depth image | |
KR20200100806A (en) | Analysis of captured images to determine test results | |
CN107274450B (en) | Information processing apparatus and control method thereof | |
CN108520514A (en) | Printed circuit board electronics member device consistency detecting method based on computer vision | |
CN114066857A (en) | Infrared image quality evaluation method and device, electronic equipment and readable storage medium | |
CN110377670B (en) | Method, device, medium and equipment for determining road element information | |
CN109035230B (en) | Round hole diameter visual measurement method | |
CN106931976B (en) | A kind of method and device of navigation information updating | |
CN106954054A (en) | A kind of image correction method, device and projecting apparatus | |
Kucheruk et al. | Definition of dynamic characteristics of pointer measuring devices on the basis of automatic indications determination | |
CN113198166A (en) | Long jump detection method and detection device | |
CN110895543B (en) | Population migration tracking display method and device and storage medium | |
CN117710756B (en) | Target detection and model training method, device, equipment and medium | |
CN108830881B (en) | Video tracking method and device for moving creature | |
CN114217277A (en) | Radar camera calibration quality evaluation method and system | |
TW201523459A (en) | Object tracking method and electronic apparatus | |
CN105427315B (en) | Digital instrument image position testing method and device | |
CN109357697B (en) | Medical instrument calibration method, system and device based on quality evaluation target value calculation | |
CN109470269B (en) | Calibration method, calibration equipment and calibration system for space target measuring mechanism | |
CN114578341A (en) | Radar tracking method, noise elimination method, device and equipment | |
CN109682395B (en) | Star sensor dynamic noise equivalent angle evaluation method and system | |
CN104933047B (en) | Method and device for determining value of search term | |
CN112329596B (en) | Target damage assessment method and device, electronic equipment and computer-readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |