CN112373474B - Lane line fusion and transverse control method, system, vehicle and storage medium - Google Patents
Lane line fusion and transverse control method, system, vehicle and storage medium Download PDFInfo
- Publication number
- CN112373474B CN112373474B CN202011323037.XA CN202011323037A CN112373474B CN 112373474 B CN112373474 B CN 112373474B CN 202011323037 A CN202011323037 A CN 202011323037A CN 112373474 B CN112373474 B CN 112373474B
- Authority
- CN
- China
- Prior art keywords
- lane line
- lane
- millimeter wave
- guardrail
- wave radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 31
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 claims abstract description 33
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 claims abstract description 33
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 claims abstract description 33
- 238000001514 detection method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000007499 fusion processing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a lane line fusion and transverse control method, a system, a vehicle and a storage medium, comprising the following steps: acquiring first guardrail information, first path information and a first lane line detected by a forward-looking camera, and acquiring a first lane line confidence rate; acquiring second road edge information and second guardrail information detected by a forward millimeter wave radar; acquiring third path information and third guardrail information detected by a lateral millimeter wave radar; acquiring the road curvature and the road grade output by the ADAS map; acquiring a second lane line detected by the look-around camera and the confidence rate of the obtained second lane line; fusing lane lines based on the data, and outputting the fused lane lines, the types of the lane lines and fusion confidence rates; and transversely controlling the vehicle according to the fused lane line, the type of the lane line and the fusion confidence rate. When the lane line is lost, the method can virtualize a lane line, and cannot directly exit the system, so that the control continuity can be ensured, and the user experience is friendly.
Description
Technical Field
The invention belongs to the technical field of lane property fusion, and particularly relates to a lane line fusion and transverse control method, a lane line fusion and transverse control system, a vehicle and a storage medium.
Background
Along with the development of the intelligent driving technology of the automobile, more and more driving assistance technologies are produced in mass production on passenger cars, and the integration level of the driving assistance technologies is higher and higher. The driving assistance technology is a safety technology for assisting a driver in driving, and improves driving safety and comfort. As driving support techniques have become popular, the continuity of the driving support techniques has been increasing.
At present, in mainstream driving assistance, after a camera detects that a lane line is lost, a driving assistance system can directly exit, and the driving assistance system is very unfriendly for user experience.
Therefore, it is necessary to develop a lane line fusion and lateral control method, system, vehicle, and storage medium.
Disclosure of Invention
The invention aims to provide a lane line fusion and transverse control method, a lane line fusion and transverse control system, a vehicle and a storage medium.
The invention relates to a method for fusing and transversely controlling a base lane line, which comprises the following steps:
acquiring first guardrail information, first path information and a first lane line detected by a forward-looking camera, and the obtained first lane line confidence rate;
acquiring second road edge information and second guardrail information detected by a forward millimeter wave radar;
acquiring third path information and third guardrail information detected by a lateral millimeter wave radar;
acquiring the road curvature and the road grade output by the ADAS map;
acquiring a second lane line detected by the look-around camera and the confidence rate of the obtained second lane line;
fusing the lane lines based on the first lane line, the second lane line, the first lane line confidence rate, the second lane line confidence rate, the first guardrail information, the second guardrail information, the third guardrail information, the first path information, the second path information, the third path information, the road curvature and the road grade, and outputting the fused lane lines, the types of the lane lines and the fusion confidence rate;
and transversely controlling the vehicle according to the fused lane line, the type of the lane line and the fusion confidence rate.
Further, the method of fusing lane lines based on lane lines, lane line confidence rates, guardrail information, road edge information, road curvature and road grades and outputting the fused lane lines, the types of the lane lines and the fusion confidence rates specifically comprises the following steps:
(1) when the condition 1a and the condition 1b are simultaneously met, directly outputting the lane line detected by the forward-looking camera, wherein the type of the lane line is a detection mode, and the fusion confidence rate is high;
condition 1 a: the road grade output by the ADAS map is a high speed or urban expressway;
condition 1 b: the forward-looking camera detects the lane line of the lane, and the confidence rate of the lane line of the lane is greater than a first preset value;
(2) when the conditions 2a to 2c are simultaneously met, taking the width of the lane before loss as a reference, translating the lane line of the lane according to the lane lines of the left lane and the right lane, outputting a fused lane line, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is high;
condition 2 a: the road grade output by the ADAS map is a high speed or urban expressway;
condition 2 b: the forward-looking camera detects the lane line of the vehicle lane, and the confidence rate of the lane line of the vehicle lane is smaller than a first preset value;
condition 2 c: the front-view camera detects lane lines of the left lane and the right lane, the confidence rate of the lane lines of the left lane and the right lane is greater than a first preset value, and the error between the width of the left lane and the width of the right lane detected by the front-view camera and the width of the left lane and the width of the right lane when the confidence rate of the lane lines of the vehicle is high is smaller than a second preset value;
(3) when the conditions 3a to 3f are met, the width of the lane detected by the all-round-looking camera is used as a reference, the road edge or the guardrail detected by the all-round-looking camera is translated, a fused lane line is output, the type of the lane line is a prediction mode, and the fusion confidence rate is medium;
3 a: the road grade output by the ADAS map is a high speed or urban expressway;
3 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value;
3 c: the forward-looking camera detects a road edge or a guardrail, and the confidence rate of the guardrail or the road edge is greater than a third preset value;
3 d: the front millimeter wave radar or the side rear millimeter wave radar detects a road edge or a guardrail, and the confidence rate of the road edge or the guardrail is greater than a third preset value;
3 e: the all-round-looking camera detects lane lines on two sides, and the confidence rate of the lane lines on the two sides is greater than a third preset value;
3 f: the curvature error of the road edge or the guardrail detected by the forward-looking camera and the forward millimeter wave radar or the lateral millimeter wave radar is within a fourth preset value;
(4) when the conditions 4a to 4f are met, taking the width of the lane detected by the look-around camera as a reference, translating the road edges or guardrails detected by the lateral millimeter wave radar and the forward millimeter wave radar, and outputting a fused lane line, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is medium;
4 a: the road grade output by the ADAS map is a high speed or urban expressway;
4 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value;
4 c: the forward-looking camera cannot detect the road edge or the guardrail, or the confidence rate of the guardrail or the road edge is smaller than a third preset value;
4 d: the front millimeter wave radar and the side rear millimeter wave radar detect the road edge or the guardrail, and the confidence rates of the road edge or the guardrail are both greater than a third preset value;
4 e: the all-round-looking camera can detect lane lines on two sides, and the confidence rate of the lane lines is greater than a third preset value;
4 f: the curvature error of the road edge or the guardrail detected by the forward millimeter wave radar and the lateral millimeter wave radar is within a fourth preset value;
(5) when the conditions 5a to 5g are met, taking the width of the lane before loss as a reference, translating the road edges or guardrails detected by the lateral millimeter wave radar and the forward millimeter wave radar, and outputting a fused lane line, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is low;
5 a: the road grade output by the ADAS map is a high speed or urban expressway;
5 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value;
5 c: the forward-looking camera cannot detect the road edge or the guardrail, or the confidence rate of the guardrail or the road edge is smaller than a third preset value;
5 d: the front millimeter wave radar and the side rear millimeter wave radar detect the road edge or the guardrail, and the confidence rates of the road edge or the guardrail are both greater than a third preset value;
5 e: the all-round-looking camera cannot detect lane lines on two sides, or the confidence rates of the output lane lines are all smaller than a third preset value;
5 f: the curvature error of the road edge or the guardrail detected by the forward millimeter wave radar and the lateral millimeter wave radar is within a fourth preset value;
5 g: and the error between the curvature of the road output by the ADAS map and the curvature output by the lateral millimeter wave radar and the forward millimeter wave radar is smaller than a fifth preset value.
Further, according to the fused lane line, the type of the lane line and the fusion confidence rate, the vehicle is transversely controlled, specifically:
when the fusion lane line is in a detection mode and the fusion confidence rate is high, performing long-time transverse control on the vehicle on the basis of the lane line;
when the fusion lane line is in a prediction mode and the fusion confidence rate is high, performing long-time transverse control on the vehicle on the basis of the lane line;
when the fusion lane line is in the prediction mode and the fusion confidence rate is middle, the vehicle is transversely controlled for a period of time based on the lane line,
when the fusion lane line is in the prediction mode and the fusion confidence rate is low, the vehicle is subjected to short-time lateral control based on the lane line.
Further, the longer time is within 2km of driving or within 50s of driving; the period of time is within 800m of driving or within 20s of driving; the short time is within 150m or within 10m of driving.
Further, the first preset value is 90%; the second preset value is 5%; the third preset value is 95%; the fourth preset value is 10%; the fifth preset value is 20%.
In a second aspect, the present invention provides a lane line fusion and lateral control system, including:
the forward-looking camera is used for detecting first guardrail information, first road edge information and a first lane line;
the forward millimeter wave radar is used for detecting the second road edge information and the second guardrail information;
the lateral millimeter wave radar is used for detecting third path information and third guardrail information;
ADAS maps of road curvature and road grade for output;
the all-round camera is used for detecting a second lane line;
a memory for storing a computer readable program;
the controller is used for receiving data output by the forward-looking camera, the forward millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera, and is respectively and electrically connected with the memory, the forward-looking camera, the forward millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera; the computer readable program when invoked by a controller is capable of performing the steps of the lane-line fusion and lateral control method of claims 1 to 5.
In a third aspect, the invention provides a vehicle, which adopts the lane line fusion and transverse control system.
In a fourth aspect, the present invention provides a storage medium having a computer readable program stored therein, where the computer readable program is capable of executing the steps of the lane line fusion and lateral control method according to the present invention when the computer readable program is called.
The invention has the following advantages: the lane line fusion technology based on the combination of the foresight camera, the forward millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera identifies lane lines, curbs and guardrails through the foresight camera, the curbs and guardrails identified by the forward millimeter wave radar, the curbs and road information provided by the lateral millimeter wave radar, the guardrails and the ADAS map are fused, when the lane line identified by the camera is lost, the relevant curbs, the guardrails and the curbs information are fused, one lane line is virtualized, the system cannot be directly withdrawn, the continuity of control can be guaranteed, and the lane line fusion technology is very friendly to user experience.
Drawings
FIG. 1 is a block diagram of system elements;
FIG. 2 is a process flow diagram of a scenario;
FIG. 3 is a flowchart of a scenario two process;
FIG. 4 is a flow chart of a scenario three process;
FIG. 5 is a flow chart of a scene four process;
FIG. 6 is a scene five process flow diagram;
fig. 7 is a fusion decision flow diagram.
Detailed Description
The invention will be further explained with reference to the drawings.
In this embodiment, a method for merging and laterally controlling a base lane line includes the following steps:
acquiring first guardrail information, first path information and a first lane line detected by a forward-looking camera, and the obtained first lane line confidence rate;
acquiring second road edge information and second guardrail information detected by a forward millimeter wave radar;
acquiring third path information and third guardrail information detected by a lateral millimeter wave radar;
acquiring the road curvature and the road grade output by the ADAS map;
acquiring a second lane line detected by the look-around camera and the confidence rate of the obtained second lane line;
fusing the lane lines based on the first lane line, the second lane line, the first lane line confidence rate, the second lane line confidence rate, the first guardrail information, the second guardrail information, the third guardrail information, the first path information, the second path information, the third path information, the road curvature and the road grade, and outputting the fused lane lines, the types of the lane lines and the fusion confidence rate;
and transversely controlling the vehicle according to the fused lane line, the type of the lane line and the fusion confidence rate.
In this embodiment, the front-view camera includes a high-definition telephoto camera and an image processing chip. The front-view camera is arranged in the front windshield of the vehicle and is used for collecting image information right in front of the vehicle. The image processing chip identifies the original image, identifies lane marking, road edge or guardrail information in the image and transmits an identification result to the controller.
The method is mainly used for making up for the situation that the lane line cannot be well identified in the environments of lane line loss, backlight and shadow. The specific implementation process comprises scene classification, scene processing, fusion decision and the like.
Data scene classification
(1) The forward-looking camera can detect the lane line of the vehicle lane, and when the confidence of the detected lane line is greater than a first preset value (recommended 90%), the situation is scene one (namely the lane line of the vehicle lane is clear).
(2) The forward-looking camera can detect the lane line of the vehicle, but the confidence of the detected lane line is low, and the forward-looking camera can detect the lane line of the left lane and the right lane, and when the confidence is high, the scene is a second scene (namely the lane line of the vehicle is fuzzy, the water is accumulated in the vehicle, the camera part is backlighted, and the ground is reflected).
(3) The forward-looking camera cannot detect the lane line, only can detect the road edge or the guardrail, and when the forward-looking camera can detect the lane line, the scene three is shown (namely partial backlight in front of the camera and ground reflection).
(4) The forward-looking camera cannot detect lane lines and road edges or guardrails, the look-around camera can detect the lane lines, the lateral millimeter wave radar or the front radar can detect the road edges or guardrails, and the scene is four (namely, the camera is backlighted).
(5) When the forward-looking camera cannot detect the lane line, the look-around camera cannot detect the lane line, and the forward millimeter wave radar and the lateral millimeter wave radar can detect the road edge or the guardrail, the situation is a scene five (namely the lane line on the road is lost);
(II) scene processing:
fusing the lane lines based on the lane lines, the lane line confidence rate, the guardrail information, the road edge information, the road curvature and the road grade, and outputting the fused lane lines, the types of the lane lines and the fusion confidence rate, which specifically comprises the following steps:
scene one: as shown in fig. 2, when the condition 1a and the condition 1b are simultaneously satisfied, the lane line detected by the forward-looking camera is directly output, the type of the lane line is a detection mode, and the fusion confidence rate is high;
condition 1 a: the road grade output by the ADAS map is a high speed or urban expressway;
condition 1 b: the front-view camera detects the lane line of the lane, and the confidence rate of the lane line of the lane is larger than a first preset value (for example, 90%);
scene two: as shown in fig. 3, when the conditions 2a to 2c are simultaneously satisfied, the lane line of the own lane is translated according to the lane lines of the left and right lanes on the basis of the width of the own lane before loss, and a fused lane line is output, where the type of the lane line is a prediction mode and the fusion confidence rate is high;
condition 2 a: the road grade output by the ADAS map is a high-speed or urban expressway;
condition 2 b: the forward-looking camera detects the lane line of the vehicle, and the confidence rate of the lane line of the vehicle is smaller than a first preset value (for example, 90%);
condition 2 c: when the confidence rate of the lane lines of the left lane and the right lane is higher than a first preset value (for example: 90 percent), and the error between the width of the left lane and the width of the right lane detected by the forward-looking camera and the width of the left lane and the width of the right lane when the confidence rate of the lane lines of the self-vehicle is high is smaller than a second preset value (for example: 5 percent);
scene three: as shown in fig. 4, when the conditions 3a to 3f are simultaneously satisfied, the road width detected by the look-around camera is used as a reference, the road edge detected by the look-ahead camera (i.e. the curvature equation detected by the look-ahead camera) is translated, and a fused lane line is output, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is medium;
3 a: the road grade output by the ADAS map is a high speed or urban expressway;
3 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value (for example: 90%);
3 c: the forward-looking camera detects a road edge or a guardrail, and the confidence rate of the guardrail or the road edge is greater than a third preset value (for example: 95%);
3 d: the front millimeter wave radar or the side rear millimeter wave radar detects a road edge or a guardrail, and the confidence rate of the road edge or the guardrail is greater than a third preset value (for example, 95%);
3 e: the look-around camera detects lane lines on two sides, and the confidence rate of the lane lines on two sides is greater than a third preset value (for example, 95%);
3 f: the curvature error of the curbs or guardrails detected by the front-looking camera and the front millimeter wave radar or the lateral millimeter wave radar is within a fourth preset value (such as 10%);
scene four: as shown in fig. 5, when the conditions 4a to 4f are simultaneously satisfied, the width of the lane detected by the look-around camera is used as a reference, the road edges or guardrails detected by the lateral millimeter wave radar and the forward millimeter wave radar are translated, and a fused lane line is output, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is medium;
4 a: the road grade output by the ADAS map is a high speed or urban expressway;
4 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value (for example: 90%);
4 c: the forward-looking camera cannot detect the road edge or the guardrail, or the confidence rate of the guardrail or the road edge is less than a third preset value (95%);
4 d: the front millimeter wave radar and the side rear millimeter wave radar detect the road edge or the guardrail, and the confidence rate of the road edge or the guardrail is greater than a third preset value (for example, 95%);
4 e: the all-round-looking camera can detect lane lines on two sides, and the confidence rate of the lane lines is greater than a third preset value (95%);
4 f: the curvature error of the road edge or the guardrail detected by the forward millimeter wave radar and the lateral millimeter wave radar is within a fourth preset value (for example, 10 percent);
scene five: as shown in fig. 6, when the conditions 5a to 5g are simultaneously satisfied, the lane width before loss is taken as a reference, the road edges or guardrails detected by the lateral millimeter wave radar and the forward millimeter wave radar are translated, and a fused lane line is output, the type of the lane line is a prediction mode, and the fusion confidence rate is low;
5 a: the road grade output by the ADAS map is a high speed or urban expressway;
5 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value (for example: 90%);
5 c: the forward-looking camera cannot detect the road edge or the guardrail, or the confidence rate of the guardrail or the road edge is less than a third preset value (for example: 95%);
5 d: the forward millimeter wave radar and the side rear millimeter wave radar detect the road edge or the guardrail, and the confidence rate of the road edge or the guardrail is larger than a third preset value (for example, 95%);
5 e: the all-round-looking camera cannot detect lane lines on two sides, or the confidence rates of the output lane lines are all smaller than a third preset value (for example, 95%);
5 f: the road edge or guardrail curvature error detected by the forward millimeter wave radar and the lateral millimeter wave radar is within a fourth preset value (such as 10 percent);
5 g: the error between the curvature of the road output by the ADAS map and the curvature output by the lateral millimeter wave radar and the forward millimeter wave radar is smaller than a fifth preset value (for example, 20%).
In this embodiment, the first preset value, the second preset value, the third preset value, the fourth preset value and the fifth preset value can be properly adjusted according to actual conditions.
(III) fusion decision:
as shown in fig. 7, the vehicle is controlled laterally according to the fused lane line, the type of the lane line, and the fusion confidence rate, specifically:
when the fusion lane line is in a detection mode and the fusion confidence rate is high, performing long-time transverse control on the vehicle on the basis of the lane line;
when the fusion lane line is in a prediction mode and the fusion confidence rate is high, performing transverse control on the vehicle for a long time (such as running within 2km or running within 50s and properly adjusting according to actual conditions) based on the lane line;
when the fusion lane line is in the prediction mode and the fusion confidence rate is middle, the vehicle is transversely controlled for a period of time (such as running within 800m or running within 20s and being properly adjusted according to actual conditions) based on the lane line,
when the fusion lane line is in a prediction mode and the fusion confidence rate is low, the vehicle is transversely controlled for a short time (such as within 150m of driving or within 10m of driving and properly adjusted according to actual conditions) based on the lane line, and the transverse control is used for the driver to take over the stable control before taking over.
In this embodiment, a lane line fusion and lateral control system includes:
the forward-looking camera is used for detecting first guardrail information, first road edge information and a first lane line;
the forward millimeter wave radar is used for detecting the second road edge information and the second guardrail information;
the lateral millimeter wave radar is used for detecting third path information and third guardrail information;
ADAS maps of road curvature and road grade for output;
the all-round camera is used for detecting a second lane line;
a memory for storing a computer readable program;
a controller (in this embodiment, the controller includes a fusion processing unit and a transverse control unit) for receiving data output by the forward-looking camera, the forward-looking millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera, wherein the controller is electrically connected with the memory, the forward-looking camera, the forward-looking millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera respectively; the computer readable program, when invoked by a controller, is capable of performing the steps of the lane-line fusion and lateral control method as described in this embodiment.
In this embodiment, a vehicle adopts the lane line fusion and lateral control system described in this embodiment.
In this embodiment, a storage medium stores a computer readable program, and the computer readable program can execute the steps of the lane line fusion and lateral control method described in this embodiment when being called.
Claims (7)
1. A lane line fusion and transverse control method is characterized by comprising the following steps:
acquiring first guardrail information, first path information and a first lane line detected by a forward-looking camera, and the obtained first lane line confidence rate;
acquiring second road edge information and second guardrail information detected by a forward millimeter wave radar;
acquiring third path information and third guardrail information detected by a lateral millimeter wave radar;
acquiring the road curvature and the road grade output by the ADAS map;
acquiring a second lane line detected by the look-around camera and the confidence rate of the obtained second lane line;
based on first lane line, second lane line, first lane line confidence rate, second lane line confidence rate, first guardrail information, second guardrail information, third guardrail information, first route information, second route information, third route information, road curvature and road grade, merge lane line to output merged lane line, type of lane line and merge confidence rate, specifically:
(1) when the condition 1a and the condition 1b are simultaneously met, directly outputting the lane line detected by the forward-looking camera, wherein the type of the lane line is a detection mode, and the fusion confidence rate is high;
condition 1 a: the road grade output by the ADAS map is a high speed or urban expressway;
condition 1 b: the forward-looking camera detects the lane line of the lane, and the confidence rate of the lane line of the lane is greater than a first preset value;
(2) when the conditions 2a to 2c are simultaneously met, taking the width of the lane before loss as a reference, translating the lane line of the lane according to the lane lines of the left lane and the right lane, outputting a fused lane line, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is high;
condition 2 a: the road grade output by the ADAS map is a high speed or urban expressway;
condition 2 b: the forward-looking camera detects the lane line of the vehicle lane, and the confidence rate of the lane line of the vehicle lane is smaller than a first preset value;
condition 2 c: the front-view camera detects lane lines of the left lane and the right lane, the confidence rate of the lane lines of the left lane and the right lane is greater than a first preset value, and the error between the width of the left lane and the width of the right lane detected by the front-view camera and the width of the left lane and the width of the right lane when the confidence rate of the lane lines of the vehicle is high is smaller than a second preset value;
(3) when the conditions 3a to 3f are met, the width of the lane detected by the all-round-looking camera is used as a reference, the road edge or the guardrail detected by the all-round-looking camera is translated, a fused lane line is output, the type of the lane line is a prediction mode, and the fusion confidence rate is medium;
3 a: the road grade output by the ADAS map is a high speed or urban expressway;
3 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value;
3 c: the forward-looking camera detects a road edge or a guardrail, and the confidence rate of the guardrail or the road edge is greater than a third preset value;
3 d: the front millimeter wave radar or the side rear millimeter wave radar detects a road edge or a guardrail, and the confidence rate of the road edge or the guardrail is greater than a third preset value;
3 e: the all-round-looking camera detects lane lines on two sides, and the confidence rate of the lane lines on the two sides is greater than a third preset value;
3 f: the curvature error of the road edge or the guardrail detected by the forward-looking camera and the forward millimeter wave radar or the lateral millimeter wave radar is within a fourth preset value;
(4) when the conditions 4a to 4f are met, taking the width of the lane detected by the look-around camera as a reference, translating the road edges or guardrails detected by the lateral millimeter wave radar and the forward millimeter wave radar, and outputting a fused lane line, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is medium;
4 a: the road grade output by the ADAS map is a high speed or urban expressway;
4 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value;
4 c: the forward-looking camera cannot detect the road edge or the guardrail, or the confidence rate of the guardrail or the road edge is smaller than a third preset value;
4 d: the front millimeter wave radar and the side rear millimeter wave radar detect the road edge or the guardrail, and the confidence rates of the road edge or the guardrail are both greater than a third preset value;
4 e: the all-round-looking camera can detect lane lines on two sides, and the confidence rate of the lane lines is greater than a third preset value;
4 f: the curvature error of the road edge or the guardrail detected by the forward millimeter wave radar and the lateral millimeter wave radar is within a fourth preset value;
(5) when the conditions 5a to 5g are met, taking the width of the lane before loss as a reference, translating the road edges or guardrails detected by the lateral millimeter wave radar and the forward millimeter wave radar, and outputting a fused lane line, wherein the type of the lane line is a prediction mode, and the fusion confidence rate is low;
5 a: the road grade output by the ADAS map is a high speed or urban expressway;
5 b: the forward-looking camera cannot detect the lane line or the confidence rate of the output lane line is smaller than a first preset value;
5 c: the forward-looking camera cannot detect the road edge or the guardrail, or the confidence rate of the guardrail or the road edge is smaller than a third preset value;
5 d: the front millimeter wave radar and the side rear millimeter wave radar detect the road edge or the guardrail, and the confidence rates of the road edge or the guardrail are both greater than a third preset value;
5 e: the all-round-looking camera cannot detect lane lines on two sides, or the confidence rates of the output lane lines are all smaller than a third preset value;
5 f: the curvature error of the road edge or the guardrail detected by the forward millimeter wave radar and the lateral millimeter wave radar is within a fourth preset value;
5 g: the error between the road curvature output by the ADAS map and the curvature output by the lateral millimeter wave radar and the forward millimeter wave radar is smaller than a fifth preset value;
and transversely controlling the vehicle according to the fused lane line, the type of the lane line and the fusion confidence rate.
2. The lane line fusion and lateral control method according to claim 1, wherein: according to the fused lane line, the type of the lane line and the fusion confidence rate, the vehicle is transversely controlled, and the method specifically comprises the following steps:
when the fusion lane line is in a detection mode and the fusion confidence rate is high, performing long-time transverse control on the vehicle on the basis of the lane line;
when the fusion lane line is in a prediction mode and the fusion confidence rate is high, performing long-time transverse control on the vehicle on the basis of the lane line;
when the fusion lane line is in the prediction mode and the fusion confidence rate is middle, the vehicle is transversely controlled for a period of time based on the lane line,
when the fusion lane line is in the prediction mode and the fusion confidence rate is low, the vehicle is subjected to short-time lateral control based on the lane line.
3. The lane-line fusion and lateral control method according to claim 2, wherein: the longer time is within 2km of driving or within 50s of driving; the period of time is within 800m of driving or within 20s of driving; the short time is within 150m or within 10m of driving.
4. The lane line fusion and lateral control method according to any one of claims 1 to 3, wherein: the first preset value is 90%; the second preset value is 5%; the third preset value is 95%; the fourth preset value is 10%; the fifth preset value is 20%.
5. The utility model provides a lane line fuses and horizontal control system which characterized in that: the method comprises the following steps:
the forward-looking camera is used for detecting first guardrail information, first road edge information and a first lane line;
the forward millimeter wave radar is used for detecting the second road edge information and the second guardrail information;
the lateral millimeter wave radar is used for detecting third path information and third guardrail information;
ADAS maps of road curvature and road grade for output;
the all-round camera is used for detecting a second lane line;
a memory for storing a computer readable program;
the controller is used for receiving data output by the forward-looking camera, the forward millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera, and is respectively and electrically connected with the memory, the forward-looking camera, the forward millimeter wave radar, the lateral millimeter wave radar, the ADAS map and the look-around camera; the computer readable program when invoked by a controller is capable of performing the steps of the lane-line fusion and lateral control method of any of claims 1 to 4.
6. A vehicle, characterized in that: the lane line fusion and lateral control system of claim 5 is employed.
7. A storage medium having a computer-readable program stored therein, characterized in that: the computer readable program when invoked is capable of performing the steps of the lane line fusion and lateral control method of any of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011323037.XA CN112373474B (en) | 2020-11-23 | 2020-11-23 | Lane line fusion and transverse control method, system, vehicle and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011323037.XA CN112373474B (en) | 2020-11-23 | 2020-11-23 | Lane line fusion and transverse control method, system, vehicle and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112373474A CN112373474A (en) | 2021-02-19 |
CN112373474B true CN112373474B (en) | 2022-05-17 |
Family
ID=74587445
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011323037.XA Active CN112373474B (en) | 2020-11-23 | 2020-11-23 | Lane line fusion and transverse control method, system, vehicle and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112373474B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113401121B (en) * | 2021-07-30 | 2022-11-08 | 驭势(上海)汽车科技有限公司 | Vehicle control method and device, electronic equipment and storage medium |
CN114368393B (en) * | 2021-12-21 | 2023-09-15 | 重庆长安汽车股份有限公司 | Lane line loss early warning method and system on straight road and man-machine co-driving method |
CN114353817B (en) * | 2021-12-28 | 2023-08-15 | 重庆长安汽车股份有限公司 | Multi-source sensor lane line determination method, system, vehicle and computer readable storage medium |
CN114396958B (en) * | 2022-02-28 | 2023-08-18 | 重庆长安汽车股份有限公司 | Lane positioning method and system based on multiple lanes and multiple sensors and vehicle |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016220717A1 (en) * | 2016-10-21 | 2018-05-09 | Volkswagen Aktiengesellschaft | Determining a lane and lateral control for a vehicle |
CN108189838A (en) * | 2017-12-30 | 2018-06-22 | 吉利汽车研究院(宁波)有限公司 | A kind of pattern of fusion adaptive cruise curve control method and device |
CN108764187A (en) * | 2018-06-01 | 2018-11-06 | 百度在线网络技术(北京)有限公司 | Extract method, apparatus, equipment, storage medium and the acquisition entity of lane line |
CN108960183A (en) * | 2018-07-19 | 2018-12-07 | 北京航空航天大学 | A kind of bend target identification system and method based on Multi-sensor Fusion |
CN109492566A (en) * | 2018-10-31 | 2019-03-19 | 奇瑞汽车股份有限公司 | Lane position information acquisition method, device and storage medium |
CN110781816A (en) * | 2019-10-25 | 2020-02-11 | 北京行易道科技有限公司 | Method, device, equipment and storage medium for transverse positioning of vehicle in lane |
CN110969059A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Lane line identification method and system |
TWI694019B (en) * | 2019-06-05 | 2020-05-21 | 國立中正大學 | Lane line detection and tracking method |
WO2020103892A1 (en) * | 2018-11-21 | 2020-05-28 | 北京市商汤科技开发有限公司 | Lane line detection method and apparatus, electronic device, and readable storage medium |
CN111291676A (en) * | 2020-02-05 | 2020-06-16 | 清华大学 | Lane line detection method and device based on laser radar point cloud and camera image fusion and chip |
CN111401446A (en) * | 2020-03-16 | 2020-07-10 | 重庆长安汽车股份有限公司 | Single-sensor and multi-sensor lane line rationality detection method and system and vehicle |
WO2020146983A1 (en) * | 2019-01-14 | 2020-07-23 | 深圳市大疆创新科技有限公司 | Lane detection method and apparatus, lane detection device, and mobile platform |
CN111516673A (en) * | 2020-04-30 | 2020-08-11 | 重庆长安汽车股份有限公司 | Lane line fusion system and method based on intelligent camera and high-precision map positioning |
CN111860155A (en) * | 2020-06-12 | 2020-10-30 | 华为技术有限公司 | Lane line detection method and related equipment |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9090263B2 (en) * | 2010-07-20 | 2015-07-28 | GM Global Technology Operations LLC | Lane fusion system using forward-view and rear-view cameras |
EP2899669A1 (en) * | 2014-01-22 | 2015-07-29 | Honda Research Institute Europe GmbH | Lane relative position estimation method and system for driver assistance systems |
US20200349363A1 (en) * | 2019-05-02 | 2020-11-05 | Miguel Hurtado | Method and system for estimating lane lines in vehicle advanced driver assistance driver assistance systems |
-
2020
- 2020-11-23 CN CN202011323037.XA patent/CN112373474B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102016220717A1 (en) * | 2016-10-21 | 2018-05-09 | Volkswagen Aktiengesellschaft | Determining a lane and lateral control for a vehicle |
CN108189838A (en) * | 2017-12-30 | 2018-06-22 | 吉利汽车研究院(宁波)有限公司 | A kind of pattern of fusion adaptive cruise curve control method and device |
CN108764187A (en) * | 2018-06-01 | 2018-11-06 | 百度在线网络技术(北京)有限公司 | Extract method, apparatus, equipment, storage medium and the acquisition entity of lane line |
CN108960183A (en) * | 2018-07-19 | 2018-12-07 | 北京航空航天大学 | A kind of bend target identification system and method based on Multi-sensor Fusion |
CN110969059A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Lane line identification method and system |
CN109492566A (en) * | 2018-10-31 | 2019-03-19 | 奇瑞汽车股份有限公司 | Lane position information acquisition method, device and storage medium |
WO2020103892A1 (en) * | 2018-11-21 | 2020-05-28 | 北京市商汤科技开发有限公司 | Lane line detection method and apparatus, electronic device, and readable storage medium |
WO2020146983A1 (en) * | 2019-01-14 | 2020-07-23 | 深圳市大疆创新科技有限公司 | Lane detection method and apparatus, lane detection device, and mobile platform |
TWI694019B (en) * | 2019-06-05 | 2020-05-21 | 國立中正大學 | Lane line detection and tracking method |
CN110781816A (en) * | 2019-10-25 | 2020-02-11 | 北京行易道科技有限公司 | Method, device, equipment and storage medium for transverse positioning of vehicle in lane |
CN111291676A (en) * | 2020-02-05 | 2020-06-16 | 清华大学 | Lane line detection method and device based on laser radar point cloud and camera image fusion and chip |
CN111401446A (en) * | 2020-03-16 | 2020-07-10 | 重庆长安汽车股份有限公司 | Single-sensor and multi-sensor lane line rationality detection method and system and vehicle |
CN111516673A (en) * | 2020-04-30 | 2020-08-11 | 重庆长安汽车股份有限公司 | Lane line fusion system and method based on intelligent camera and high-precision map positioning |
CN111860155A (en) * | 2020-06-12 | 2020-10-30 | 华为技术有限公司 | Lane line detection method and related equipment |
Non-Patent Citations (5)
Title |
---|
Lane recognition and tracking based on muli-features fuzzy fusion and particle filter;Huang Haibo等;《2011 International Conference on Consumer Electronics, Communications and Networks (CECNet)》;20110516;全文 * |
Research on lane a compensation methon based on multi-sensor fusion;LiYushan等;《Sensors》;20190402;全文 * |
基于全局与局部模型相互制约及具有模型不确定性评估的车道线检测方法;刘晓龙等;《东南大学学报(自然科学版)》;20130720;全文 * |
基于动态概率网格和贝叶斯决策网络的车辆变道辅助驾驶决策方法;惠飞等;《交通运输工程学报》;20180415(第02期);全文 * |
基于深度学习的复杂环境下车道线检测方法研究;陈洋;《上海工程技术大学硕士论文》;20191201;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112373474A (en) | 2021-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112373474B (en) | Lane line fusion and transverse control method, system, vehicle and storage medium | |
KR102512207B1 (en) | Roadway line fitting method and system | |
CN111383474B (en) | Decision making system and method for automatically driving vehicle | |
CN107389084B (en) | Driving path planning method and storage medium | |
KR20140078436A (en) | Sensor fusion system and method thereof | |
CN110969178A (en) | Data fusion system and method for automatic driving vehicle and automatic driving system | |
WO2023197408A1 (en) | Method and apparatus for determining vehicle speed control model training sample | |
CN110412980A (en) | Automatic driving and line control method | |
CN113460086A (en) | Control system, method, vehicle and storage medium for automatically driving to enter ramp | |
CN115042820A (en) | Autonomous vehicle control method, device, equipment and storage medium | |
CN114802234A (en) | Road edge avoiding method and system in intelligent cruise | |
CN114516327A (en) | Self-learning vehicle following system and method based on driver behavior learning and surrounding environment | |
CN110784680B (en) | Vehicle positioning method and device, vehicle and storage medium | |
CN114842432A (en) | Automobile light control method and system based on deep learning | |
CN117184126A (en) | Automatic driving method and device and computer readable storage medium | |
JP5682302B2 (en) | Traveling road estimation device, method and program | |
CN116279477A (en) | Lane control method and device and electronic equipment | |
WO2021170140A1 (en) | Lane structure detection method and apparatus | |
CN114954452A (en) | Vehicle speed control method and system based on adaptive cruise | |
CN114464005A (en) | Method and system for assisting driving of vehicle | |
CN113386771A (en) | Road model generation method and equipment | |
CN110531347A (en) | Detection method, device and the computer readable storage medium of laser radar | |
CN115431981B (en) | Driving auxiliary identification system based on high-precision map | |
CN111637898B (en) | Processing method and device for high-precision navigation electronic map | |
CN118182473A (en) | Vehicle junction control method, device, equipment and 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |