CN116625375A - Vehicle positioning method based on wheel parameter calibration and monocular lane line detection - Google Patents
Vehicle positioning method based on wheel parameter calibration and monocular lane line detection Download PDFInfo
- Publication number
- CN116625375A CN116625375A CN202310596655.9A CN202310596655A CN116625375A CN 116625375 A CN116625375 A CN 116625375A CN 202310596655 A CN202310596655 A CN 202310596655A CN 116625375 A CN116625375 A CN 116625375A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- wheel
- odometer
- lane line
- lane
- 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 32
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 238000006073 displacement reaction Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000012546 transfer Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000003702 image correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle positioning method based on wheel parameter calibration and monocular lane line detection, and belongs to the field of intelligent driving positioning. The positioning method can be divided into two parts, namely a vehicle kinematic odometer and transverse positioning based on lane line detection. The specific method of the kinematic odometer is as follows: and recalibrating parameters such as perimeter and the like in actual running of the wheels based on dynamic wheel assumption through Gauss Newton method and integrated Kalman filtering, and reducing errors of the kinematic odometer. The specific method for transverse positioning comprises the following steps: and detecting lane lines by thresholding, curve fitting and other methods, and calculating the transverse displacement of the vehicle according to the lane line detection result. And finally, fusing the odometer and the transverse positioning result, and outputting the current position of the vehicle. The method has the advantages of low price of the device and low consumption of calculation resources, and can provide the positioning information of the vehicle for the intelligent driving of the automobile when the GNSS signal is lost or the signal quality is poor.
Description
Technical Field
The invention relates to a vehicle positioning method based on wheel parameter calibration and monocular lane line detection, and belongs to the field of intelligent driving positioning.
Background
The three core technologies of intelligent driving are perception, planning and control respectively, wherein a perception layer is used for understanding the position around the vehicle and the driving environment. The positioning system aims at determining the position of the vehicle on the global coordinate system and is considered one of the most critical parts in the stack, as its accuracy and robustness influence the perception layer follow-up algorithm and the follow-up planning and action layer.
To accurately position the vehicle, three techniques are currently commonly used. 1. Signal positioning: such as Global Navigation Satellite Systems (GNSS), ultra wideband positioning technology (UWB); 2. dead reckoning: after knowing the initial position of the vehicle, accumulating displacement vectors to calculate the current position based on an Inertial Measurement Unit (IMU) technology; 3. and (3) environmental characteristic matching: based on the positioning of the lidar or vision sensor, i.e. matching features stored in a database, to learn about the location and environment of the vehicle.
The above techniques have their own drawbacks. The situation that the positioning signals cannot be received may occur when the signals are positioned in urban canyons, tunnels, under-overhead bridges and other road sections; dead reckoning is affected by errors of the sensor, and serious track drift can be caused by long-time integration process; the SLAM positioning algorithm for lidar or vision requires more computational resources and the sensor itself is expensive.
In view of the above, the present invention proposes a vehicle positioning method based on wheel parameter calibration and monocular lane line detection to solve the disadvantages in the above method.
Disclosure of Invention
The invention aims to provide a vehicle positioning method based on wheel parameter calibration and monocular lane line detection, which aims to solve the problem of stable vehicle positioning when GNSS signals are poor.
In order to achieve the above purpose, the invention provides a vehicle positioning method based on wheel parameter calibration and monocular lane line detection, which mainly comprises the following steps:
step 1: establishing a kinematic odometer model based on a kinematic model of the vehicle: the yaw angle and the non-optimized speed are calculated through the actual radius of the wheels and the pulse numbers of the left and right wheels of the rear axle, an odometer model of the vehicle is built, and the odometer model comprises parameters of the circumference of the left rear wheel to be optimized, the circumference difference of the left and right rear wheels, the wheel distance of the rear axle and the load transfer coefficient.
Step 2: the method comprises the steps of calibrating wheel parameters according to dynamic wheel hypothesis and applying the wheel parameters to a kinematic odometer: the radius of the wheel is regarded as dynamic in the running process of the vehicle, the theoretical radius of the wheel is corrected by introducing state coefficients, the circumference of the left rear wheel, the circumference difference of the left rear wheel and the right rear wheel is optimized by the previously recorded vehicle track, the wheel distance of the rear axle and the load transfer coefficient are optimized, and corresponding parameters in the odometer model are updated.
Step 3: identifying and detecting adjacent lane lines through a camera: and processing the image acquired by the camera by means of image correction, thresholding, curve fitting and the like, and detecting and extracting lane line information.
Step 4: determining a lateral displacement of the vehicle within the lane: and identifying left and right lane lines of a lane where the vehicle is located in the running process of the vehicle according to the set distance threshold value, and recovering the real scale of the transverse displacement of the vehicle in the lane by taking the standard width of the lane and the lane lines as a reference scale.
Step 5: and carrying out weighted correction on the lateral displacement of the vehicle detected and identified based on the lane line detection and the lateral displacement obtained by the kinematic odometer after parameter updating according to the corresponding confidence coefficient to obtain a final positioning result, and outputting position information.
The beneficial effects of the invention are as follows: the method provided by the invention has the advantages of low price of the required device and low consumption of calculation resources, and can solve the problem of how to connect stably when GNSS signals are lost or the signal quality is poor, and provide the positioning information of the vehicle for the intelligent driving automobile.
Drawings
FIG. 1 is a flow chart of a vehicle positioning method based on wheel parameter calibration and monocular lane line detection according to the present invention.
Fig. 2 is a diagram of a vehicle kinematic odometer model constructed in accordance with the present invention.
FIG. 3 is a flow chart of the calibration of the wheel parameters of the present invention.
FIG. 4 is a flow chart of lane line detection according to the present invention.
FIG. 5 is a flow chart for determining lateral displacement of a vehicle in accordance with the present invention.
Fig. 6 is a data fusion correction flow chart.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
The invention provides a vehicle positioning method based on wheel parameter calibration and monocular lane line detection, which mainly comprises the following steps:
step 1: a kinematic odometer model is established based on a kinematic model of the vehicle.
Step 2: the wheel parameters are calibrated according to the dynamic wheel hypothesis and are applied to the kinematic odometer.
Step 3: and identifying and detecting the adjacent lane lines through the camera.
Step 4: a lateral displacement of the vehicle within the lane is determined.
Step 5: and correcting the calculation result of the kinematic odometer according to the transverse displacement and outputting the final vehicle position.
The steps 1 to 5 will be specifically described below.
As shown in fig. 2, in step 1, firstly, vehicle fixed parameters and vehicle running data are inputted and processed, the yaw angle and the non-optimized vehicle speed are calculated according to the pulse number input, and an odometer model is built by considering the tire circumference waiting optimization parameters.
As shown in fig. 3, in step 2, the wheel radius is regarded as dynamic during the running of the vehicle, the theoretical radius of the wheel is corrected by introducing state coefficients, the circumference of the left rear wheel is changed according to the previously recorded vehicle track, the circumference difference of the left rear wheel and the right rear wheel is changed, the wheel distance of the rear axle and the load transfer coefficient are optimized, and the corresponding parameters in the odometer model are updated.
As shown in fig. 4, in step 3, the image acquired by the camera is processed by means of image correction, thresholding, edge detection, curve fitting and the like, and lane line information is detected and extracted.
As shown in fig. 5, in step 4, the left and right lane lines of the lane where the vehicle is in are identified according to the distance threshold set by the lane line detection information, and the standard width of the lane and the lane lines is taken as the reference scale, so as to recover the real scale of the lateral displacement of the vehicle in the lane.
As shown in fig. 6, in step 5, different weights are set according to the corresponding confidence degrees for the lateral displacement of the vehicle identified by lane line detection and the lateral displacement obtained by the kinematic odometer after parameter updating, and the final positioning result is obtained by performing weighted correction, and the position information is output.
In summary, the method provided by the invention has the advantages of low price of the device and low consumption of calculation resources, and can solve the problem of how to connect stably when GNSS signals are lost or the signal quality is poor, and provide the positioning information of the vehicle for the intelligent driving automobile.
Claims (6)
1. A vehicle positioning method based on wheel parameter calibration and monocular lane line detection mainly comprises the following steps:
step 1: establishing a kinematic odometer model based on a kinematic model of the vehicle;
step 2: calibrating wheel parameters according to dynamic wheel hypothesis, and applying the wheel parameters to a kinematic odometer;
step 3: identifying and detecting adjacent lane lines through a camera;
step 4: determining a lateral displacement of the vehicle within the lane;
step 5: and correcting the calculation result of the kinematic odometer according to the transverse displacement and outputting the final vehicle position.
2. The vehicle positioning method based on wheel parameter calibration and monocular lane line detection according to claim 1, characterized in that: in the step 1, based on a kinematic model of the vehicle, the yaw angle and the non-optimized vehicle speed are calculated through the actual radius of the wheels and the pulse numbers of the left and right wheels of the rear axle, an odometer model of the vehicle is built, and the odometer model comprises parameters of the left and right rear wheel circumference difference to be optimized, the rear axle wheel distance and the load transfer coefficient.
3. The vehicle positioning method based on wheel parameter calibration and monocular lane line detection according to claim 1, characterized in that: in the step 2, the radius of the wheel is regarded as dynamic in the running process of the vehicle, a dynamic coefficient is introduced to correct the theoretical radius of the wheel, the circumference of the left rear wheel is changed by using a Gauss Newton method and an integrated Kalman filter through the previously recorded vehicle track, the circumference difference of the left rear wheel and the right rear wheel is optimized, the wheel distance of the rear axle and the load transfer coefficient are optimized, and the corresponding parameters in the odometer model are updated.
4. The vehicle positioning method based on wheel parameter calibration and monocular lane line detection according to claim 1, characterized in that: and 3, performing image correction, thresholding, curve fitting and other means on the image acquired by the camera, and detecting and extracting lane line information.
5. The vehicle positioning method based on wheel parameter calibration and monocular lane line detection according to claim 1, characterized in that: and 4, identifying left and right lane lines of a lane where the vehicle runs according to the set distance threshold value, and recovering the real scale of the transverse displacement of the vehicle in the lane by taking the standard width of the lane and the lane lines as a reference scale.
6. The vehicle positioning method based on wheel parameter calibration and monocular lane line detection according to claim 1, characterized in that: and 5, carrying out weighted correction on the lateral displacement of the vehicle detected and identified based on the lane line and the lateral displacement obtained by the kinematic odometer after parameter updating according to the corresponding confidence coefficient to obtain a final positioning result, and outputting position information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310596655.9A CN116625375A (en) | 2023-05-25 | 2023-05-25 | Vehicle positioning method based on wheel parameter calibration and monocular lane line detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310596655.9A CN116625375A (en) | 2023-05-25 | 2023-05-25 | Vehicle positioning method based on wheel parameter calibration and monocular lane line detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116625375A true CN116625375A (en) | 2023-08-22 |
Family
ID=87609433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310596655.9A Pending CN116625375A (en) | 2023-05-25 | 2023-05-25 | Vehicle positioning method based on wheel parameter calibration and monocular lane line detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116625375A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117818665A (en) * | 2024-03-05 | 2024-04-05 | 智道网联科技(北京)有限公司 | Automatic driving vehicle control method and device, electronic equipment and storage medium |
| CN117818665B (en) * | 2024-03-05 | 2024-05-31 | 智道网联科技(北京)有限公司 | Automatic driving vehicle control method and device, electronic equipment and storage medium |
-
2023
- 2023-05-25 CN CN202310596655.9A patent/CN116625375A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117818665A (en) * | 2024-03-05 | 2024-04-05 | 智道网联科技(北京)有限公司 | Automatic driving vehicle control method and device, electronic equipment and storage medium |
| CN117818665B (en) * | 2024-03-05 | 2024-05-31 | 智道网联科技(北京)有限公司 | Automatic driving vehicle control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109946732B (en) | Unmanned vehicle positioning method based on multi-sensor data fusion | |
| US11802769B2 (en) | Lane line positioning method and apparatus, and storage medium thereof | |
| EP2926330B1 (en) | Vehicle location estimation apparatus and vehicle location estimation method | |
| US9208389B2 (en) | Apparatus and method for recognizing current position of vehicle using internal network of the vehicle and image sensor | |
| Goldbeck et al. | Lane following combining vision and DGPS | |
| US20210229280A1 (en) | Positioning method and device, path determination method and device, robot and storage medium | |
| CN110332945B (en) | Vehicle navigation method and device based on traffic road marking visual identification | |
| CN113920198B (en) | Coarse-to-fine multi-sensor fusion positioning method based on semantic edge alignment | |
| US10990111B2 (en) | Position determination apparatus and method for vehicle | |
| CN111649740B (en) | Method and system for high-precision positioning of vehicle based on IMU | |
| CN112904395A (en) | Mining vehicle positioning system and method | |
| CN111381248A (en) | Obstacle detection method and system considering vehicle bump | |
| CN113175938B (en) | Vehicle positioning enhancement system and method based on high-precision map | |
| EP4345421A2 (en) | Method for calibrating sensor parameters based on autonomous driving, apparatus, storage medium, and vehicle | |
| CN115792894A (en) | Multi-sensor fusion vehicle target tracking method, system and storage medium | |
| CN110986966A (en) | Automatic driving positioning method and system for long-distance tunnel | |
| KR102618247B1 (en) | Device for correcting localization heading error in autonomous car and operating methdo thereof | |
| CN111103578B (en) | Laser radar online calibration method based on deep convolutional neural network | |
| CN112987717A (en) | Method and system for identifying vehicle ramp and curve | |
| CN116625375A (en) | Vehicle positioning method based on wheel parameter calibration and monocular lane line detection | |
| CN115379408B (en) | Scene perception-based V2X multi-sensor fusion method and device | |
| EP3828583A1 (en) | Analysis of localization errors in a mobile object | |
| CN114396958B (en) | Lane positioning method and system based on multiple lanes and multiple sensors and vehicle | |
| CN115046546A (en) | Automatic driving automobile positioning system and method based on lane line identification | |
| CN112611377B (en) | State prediction method, device and storage medium for car outdoor navigation |
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 |