CN116331220B - Lane departure early warning method and early warning system for automatic driving vehicle - Google Patents
Lane departure early warning method and early warning system for automatic driving vehicle Download PDFInfo
- Publication number
- CN116331220B CN116331220B CN202310534729.6A CN202310534729A CN116331220B CN 116331220 B CN116331220 B CN 116331220B CN 202310534729 A CN202310534729 A CN 202310534729A CN 116331220 B CN116331220 B CN 116331220B
- Authority
- CN
- China
- Prior art keywords
- analysis
- deviation
- abnormal
- lane
- period
- 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
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
- 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
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/146—Display means
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
-
- 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
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/20—Ambient conditions, e.g. wind or rain
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the field of automatic driving, relates to a departure warning technology, and is used for solving the problem that the existing lane departure warning method cannot detect and analyze factors causing lane departure phenomenon, in particular to a lane departure warning method and a warning system of an automatic driving vehicle, comprising a departure warning platform, wherein the departure warning platform is in communication connection with a departure analysis module, a departure warning module, an abnormality analysis module and a storage module; the deviation analysis module is used for carrying out lane deviation analysis on the automatic driving vehicle: obliquely shooting a lane in an analysis period through a camera arranged on the side surface of the vehicle and marking the shot image as an analysis image; the invention can analyze lane departure of the automatic driving vehicle, and obtain the included angle value and the length value by analyzing the image of the analysis image of the automatic driving vehicle in the running process, thereby forming auxiliary parameters through the included angle value and the length value.
Description
Technical Field
The invention belongs to the field of automatic driving, relates to a departure warning technology, and particularly relates to a lane departure warning method and a lane departure warning system for an automatic driving vehicle.
Background
The lane departure early warning system mainly comprises a HUD head-up display, a camera, a controller and a sensor, when the lane departure system is started, the camera can acquire the identification line of a driving lane at any time, the position parameters of an automobile in a current lane are obtained through image processing, and when the automobile departure lane is detected, the sensor can collect the vehicle data and the operation state of a driver in time.
The reasons for the lane departure phenomenon of the automatic driving vehicle are various, the most common is that the recognition precision of environmental influence and the system are out of control, and the correction processing is carried out by taking different measures aiming at the lane departure caused by different reasons, the existing lane departure early warning method can only carry out departure early warning analysis, but cannot detect and analyze the factors causing the lane departure phenomenon, so that the correction processing cannot be carried out in a correct mode, and the automatic driving safety is reduced.
Aiming at the technical problems, the application provides a solution.
Disclosure of Invention
The invention aims to provide a lane departure warning method and a lane departure warning system for an automatic driving vehicle, which are used for solving the problem that the existing lane departure warning method cannot detect and analyze factors causing lane departure phenomenon;
the technical problems to be solved by the invention are as follows: how to provide a lane departure warning method and a warning system for an automatic driving vehicle, which can detect and analyze factors causing lane departure.
The aim of the invention can be achieved by the following technical scheme:
the lane departure warning method and the warning system of the automatic driving vehicle comprise a departure warning platform, wherein the departure warning platform is in communication connection with a departure analysis module, a departure warning module, an abnormality analysis module and a storage module;
the deviation analysis module is used for carrying out lane deviation analysis on the automatic driving vehicle: marking an automatic driving vehicle as an analysis object, generating an analysis period, dividing the analysis period into a plurality of analysis periods, obliquely shooting a lane in the analysis periods through a camera arranged on the side surface of the vehicle, marking the shot image as an analysis image, and acquiring auxiliary parameters of the analysis image; the auxiliary parameters of the analysis images in the analysis period are sent to the deviation early warning module in real time through the deviation early warning platform;
the deviation early warning module is used for monitoring and analyzing the lane deviation state of the automatic driving vehicle through the auxiliary parameters of the lane area, acquiring a deviation coefficient PL of an analysis object in an analysis period and judging whether the deviation state of the analysis object in the analysis period is abnormal or not through the numerical value of the deviation coefficient PL;
the abnormality analysis module is used for analyzing abnormal factors of the deviation state of the automatic driving vehicle: and acquiring fog data WQ, rainfall data YL and wind power data FL in an abnormal period, performing numerical calculation to obtain a ring difference coefficient HY, and marking the deviation state abnormal factors of the analysis object according to the numerical value of the ring difference coefficient HY.
As a preferred embodiment of the present invention, the process of acquiring the auxiliary parameter of the analysis image includes: the contrast of the analysis image is adjusted to a preset standard contrast, the analysis image is amplified to a pixel grid image and subjected to gray level conversion, a gray level range is obtained through a storage module, the pixel grid with a gray level value within the gray level range is marked as a lane grid, the analysis image is divided into a plurality of lane areas, the pixel grids in the lane areas are all lane grids, and the pixel grids adjacent to the lane areas are not lane grids; and connecting the central point of the lane area with the central point of the analysis image to obtain an auxiliary line, marking an angle value of an acute angle formed by an extension line of the auxiliary line and the bottom edge of the analysis image as an included angle value of the lane area, and forming auxiliary parameters of the lane area by the included angle value of the lane area and the length value of the auxiliary line.
As a preferred embodiment of the present invention, the acquisition process of the deviation coefficient PL of the analysis object in the analysis period includes: marking the maximum value and the minimum value of the length values of the lane areas in all the analysis images in the analysis period as a large value and a small value respectively, marking the maximum value and the minimum value of the included angle values of the lane areas in all the analysis images in the analysis period as a large value and a small value respectively, marking the difference value of the large value and the small value as a long difference value CC, and marking the difference value of the large value and the small value as a small difference value JC; the deviation coefficient PL of the analysis object in the analysis period is obtained by performing numerical calculation on the long difference CC and the pinch difference JC.
As a preferred embodiment of the present invention, the specific process of determining whether the deviation state of the analysis object is abnormal in the analysis period includes: the deviation threshold PLmax is acquired by the storage module, and the deviation coefficient PL of the analysis object in the analysis period is compared with the deviation threshold PLmax: if the deviation coefficient PL is greater than or equal to the deviation threshold PLmax, judging that the deviation state of the analysis object in the analysis period is abnormal, marking the corresponding analysis period as an abnormal period, carrying out abnormal characteristic analysis on the abnormal period, generating a driving abnormal signal and sending the driving abnormal signal to a vehicle-mounted display screen and a mobile phone terminal of a driver through a deviation early warning platform; if the deviation coefficient PL is smaller than the deviation threshold PLmax, it is determined that the deviation state of the analysis object in the analysis period is normal, and the corresponding analysis period is marked as normal.
As a preferred embodiment of the present invention, the specific process of performing the abnormality characteristic analysis on the abnormal period includes: forming a length set by the length values of the lane areas in all analysis images in the abnormal time period, performing variance calculation on the length set to obtain a long amplitude value CF, forming an included angle set by the included angle values of the lane areas in all analysis images in the abnormal time period, performing variance calculation on the included angle set to obtain a clipping amplitude value JF, and performing numerical calculation on the long amplitude value CF and the clipping amplitude value JF to obtain a deviation coefficient PF of the abnormal time period; the method comprises the steps of obtaining a deviation threshold value PFmax through a storage module, comparing the deviation coefficient PF with the deviation threshold value PFmax, and marking abnormal characteristics of an abnormal period through a comparison result.
As a preferred embodiment of the present invention, the specific process of comparing the deviation factor PF with the deviation threshold PFmax includes: if the deviation coefficient PF is smaller than the deviation threshold PFmax, marking the abnormal characteristic of the abnormal period as deviation, generating an abnormal analysis signal and sending the abnormal analysis signal to an abnormal analysis module; if the deviation coefficient PF is larger than or equal to the deviation threshold PFmax, the abnormal characteristic of the abnormal period is marked as out of control, a system optimization signal is generated, and the system optimization signal is sent to a mobile phone terminal of a manager.
As a preferred embodiment of the present invention, the mist data WQ is a maximum value of the mist concentration in the abnormal period, the rain amount data YL is a rainfall in the abnormal period, and the wind force data FL is a maximum value of the wind force outside the autonomous vehicle in the abnormal period.
As a preferred embodiment of the present invention, the specific process of marking the deviation state abnormality factor of the analysis object includes: the method comprises the steps of obtaining a ring difference threshold HYmax through a storage module, and comparing the ring difference coefficient HY with the ring difference threshold HYmax: if the ring deviation coefficient HY is smaller than the ring deviation threshold HYmax, determining that the deviation state abnormality factor of the automatic driving vehicle is a system fault, generating a system upgrading signal and sending the system upgrading signal to a mobile phone terminal of a manager through a deviation early warning platform; if the ring deviation coefficient HY is greater than or equal to the ring deviation threshold HYmax, determining that the deviation state abnormality factor of the automatic driving vehicle is environmental influence, generating an environment abnormality signal, and sending the environment abnormality signal to a vehicle-mounted display screen and a mobile phone terminal of a driver through a deviation early warning platform.
A lane departure warning method of an autonomous vehicle, comprising the steps of:
step one: lane departure analysis for an autonomous vehicle: marking an automatic driving vehicle as an analysis object, generating an analysis period, dividing the analysis period into a plurality of analysis periods, and transmitting auxiliary parameters of a lane region of an analysis image in the analysis periods to a deviation early warning module in real time through a deviation early warning platform;
step two: monitoring and analyzing the lane departure state of the automatic driving vehicle through the auxiliary parameters of the lane area, acquiring a departure coefficient PL of an analysis period, and judging whether the departure state in the analysis period is abnormal or not through the value of the departure coefficient PL;
step three: carrying out abnormal characteristic analysis on the abnormal time period, obtaining a deviation coefficient PF, and marking the abnormal characteristic of the abnormal time period through the numerical value of the deviation coefficient PF;
step four: and analyzing the abnormal factors of the deviation state of the automatic driving vehicle, obtaining the ring difference coefficient HY, and judging the abnormal factors of the deviation state of the automatic driving vehicle through the numerical value of the ring difference coefficient HY.
The invention has the following beneficial effects:
1. the lane departure analysis can be carried out on the automatic driving vehicle through the departure analysis module, the included angle value and the length value are obtained through image analysis on an analysis image of the automatic driving vehicle in the driving process, so that auxiliary parameters are formed through the included angle value and the length value, and data support is provided for the departure early warning analysis process through the auxiliary parameters;
2. the lane departure state of the automatic driving vehicle can be monitored and analyzed through the departure warning module, the departure coefficient is obtained through comprehensive analysis of auxiliary parameters of all analysis images in the analysis period, so that the departure state of an analysis object in the analysis period is fed back according to the departure coefficient, meanwhile, the fault type of the departure state abnormality is analyzed through an abnormal characteristic analysis result, and therefore correction processing can be carried out through targeted measures through an abnormal characteristic marking result;
3. the abnormal analysis module can analyze abnormal factors of the deviation state of the automatic driving vehicle, and the environment abnormal coefficient is obtained by comprehensively analyzing and calculating the external environment parameters of the automatic driving vehicle, so that the environment abnormal degree is fed back according to the numerical value of the environment abnormal coefficient, and further, the factors causing the abnormal lane deviation state are fed back.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system block diagram of a first embodiment of the present invention;
fig. 2 is a flowchart of a method according to a second embodiment of the invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one: as shown in fig. 1, the lane departure warning system of the automatic driving vehicle comprises a departure warning platform, wherein the departure warning platform is in communication connection with a departure analysis module, a departure warning module, an abnormality analysis module and a storage module.
The deviation analysis module is used for carrying out lane deviation analysis on the automatic driving vehicle: marking an automatic driving vehicle as an analysis object, generating an analysis period, dividing the analysis period into a plurality of analysis periods, obliquely shooting a lane in the analysis period through a camera arranged on the side surface of the vehicle, marking the shot image as an analysis image, adjusting the contrast of the analysis image to a preset standard contrast, amplifying the analysis image as a pixel grid image, carrying out gray level conversion, obtaining a gray level range through a storage module, marking the pixel grid with a gray level within the gray level range as a lane grid, dividing the analysis image into a plurality of lane areas, wherein the pixel grids in the lane areas are all lane grids, and the pixel grids adjacent to the lane areas are not lane grids; connecting the central point of the lane area with the central point of the analysis image to obtain an auxiliary line, marking an angle value of an acute angle formed by an extension line of the auxiliary line and the bottom edge of the analysis image as an included angle value of the lane area, and forming auxiliary parameters of the lane area by the included angle value of the lane area and the length value of the auxiliary line; auxiliary parameters of the lane region of the analysis image in the analysis period are sent to the deviation early warning module in real time through the deviation early warning platform; the method comprises the steps of carrying out lane departure analysis on an automatic driving vehicle, carrying out image analysis on an analysis image of the automatic driving vehicle in the driving process to obtain an included angle value and a length value, forming auxiliary parameters through the included angle value and the length value, and providing data support for the departure early warning analysis process through the auxiliary parameters.
The departure early warning module is used for monitoring and analyzing the lane departure state of the automatic driving vehicle through the auxiliary parameters of the lane area: marking the maximum value and the minimum value of the length values of the lane areas in all the analysis images in the analysis period as a large value and a small value respectively, marking the maximum value and the minimum value of the included angle values of the lane areas in all the analysis images in the analysis period as a large value and a small value respectively, marking the difference value of the large value and the small value as a long difference value CC, marking the difference value of the large value and the small value as a difference value JC, and obtaining the deviation coefficient PL of the analysis object in the analysis period through a formula PL=α1xCC+α2xJC, wherein α1 and α2 are both proportional coefficients, and α1 and α2 are both proportional coefficients; the deviation threshold PLmax is acquired by the storage module, and the deviation coefficient PL of the analysis object in the analysis period is compared with the deviation threshold PLmax: if the deviation coefficient PL is greater than or equal to the deviation threshold PLmax, judging that the deviation state of the analysis object in the analysis period is abnormal, marking the corresponding analysis period as an abnormal period, carrying out abnormal characteristic analysis on the abnormal period, generating a driving abnormal signal and sending the driving abnormal signal to a vehicle-mounted display screen and a mobile phone terminal of a driver through a deviation early warning platform; if the deviation coefficient PL is smaller than the deviation threshold PLmax, judging that the deviation state of the analysis object in the analysis period is normal, and marking the corresponding analysis period as normal; the specific process for carrying out the abnormal characteristic analysis on the abnormal time period comprises the following steps: forming a length set by length values of lane areas in all analysis images in an abnormal period, performing variance calculation on the length set to obtain a long amplitude CF, forming an included angle set by included angle values of the lane areas in all analysis images in the abnormal period, performing variance calculation on the included angle set to obtain an included angle JF, and obtaining a deviation coefficient PF of the abnormal period through a formula PF=β1xCF+β2xJF, wherein β1 and β2 are both proportional coefficients, and β1 > β2 > 1; the method comprises the steps of obtaining a deviation threshold value PFmax through a storage module, and comparing a deviation coefficient PF with the deviation threshold value PFmax: if the deviation coefficient PF is smaller than the deviation threshold PFmax, marking the abnormal characteristic of the abnormal period as deviation, generating an abnormal analysis signal and sending the abnormal analysis signal to an abnormal analysis module; if the deviation coefficient PF is larger than or equal to the deviation threshold PFmax, marking the abnormal characteristic of the abnormal period as out of control, generating a system optimization signal and sending the system optimization signal to a mobile phone terminal of a manager; the method comprises the steps of monitoring and analyzing the lane departure state of an automatic driving vehicle, comprehensively analyzing auxiliary parameters of all analysis images in an analysis period to obtain departure coefficients, feeding back the departure state of an analysis object in the analysis period according to the departure coefficients, and analyzing the fault type of abnormality of the departure state according to an abnormality characteristic analysis result, so that correction processing can be carried out by taking targeted measures through the abnormality characteristic marking result.
The abnormality analysis module is used for analyzing abnormal factors of the deviation state of the automatic driving vehicle: acquiring fog data WQ, rainfall data YL and wind power data FL in an abnormal period, wherein the fog data WQ is the maximum value of fog concentration in the abnormal period, the rainfall data YL is the rainfall in the abnormal period, the wind power data FL is the maximum value of wind power outside an automatic driving vehicle in the abnormal period, and the ring difference coefficient HY in the abnormal period is obtained through a formula HY=γ1×WQ+γ2×YL+γ3×FL, wherein γ1, γ2 and γ3 are proportionality coefficients, and γ1 > γ2 > γ3 > 1; the method comprises the steps of obtaining a ring difference threshold HYmax through a storage module, and comparing the ring difference coefficient HY with the ring difference threshold HYmax: if the ring deviation coefficient HY is smaller than the ring deviation threshold HYmax, determining that the deviation state abnormality factor of the automatic driving vehicle is a system fault, generating a system upgrading signal and sending the system upgrading signal to a mobile phone terminal of a manager through a deviation early warning platform; if the environment deviation coefficient HY is greater than or equal to the environment deviation threshold HYmax, determining that the deviation state abnormality factor of the automatic driving vehicle is environmental influence, generating an environment abnormality signal and sending the environment abnormality signal to a vehicle-mounted display screen and a mobile phone terminal of a driver through a deviation early warning platform; the method comprises the steps of analyzing abnormal factors of the deviation state of the automatic driving vehicle, comprehensively analyzing and calculating external environment parameters of the automatic driving vehicle to obtain a circular difference coefficient, feeding back the environment abnormality degree according to the numerical value of the circular difference coefficient, and feeding back factors causing the abnormal lane deviation state.
Embodiment two: as shown in fig. 2, a lane departure warning method for an autonomous vehicle includes the steps of:
step one: lane departure analysis for an autonomous vehicle: marking an automatic driving vehicle as an analysis object, generating an analysis period, dividing the analysis period into a plurality of analysis periods, and transmitting auxiliary parameters of a lane region of an analysis image in the analysis periods to a deviation early warning module in real time through a deviation early warning platform;
step two: monitoring and analyzing the lane departure state of the automatic driving vehicle through the auxiliary parameters of the lane area, acquiring a departure coefficient PL of an analysis period, and judging whether the departure state in the analysis period is abnormal or not through the value of the departure coefficient PL;
step three: carrying out abnormal characteristic analysis on the abnormal time period, obtaining a deviation coefficient PF, and marking the abnormal characteristic of the abnormal time period through the numerical value of the deviation coefficient PF;
step four: and analyzing the abnormal factors of the deviation state of the automatic driving vehicle, obtaining the ring difference coefficient HY, and judging the abnormal factors of the deviation state of the automatic driving vehicle through the numerical value of the ring difference coefficient HY.
The lane departure warning method and the warning system of the automatic driving vehicle are characterized in that the automatic driving vehicle is marked as an analysis object to generate an analysis period, the analysis period is divided into a plurality of analysis periods, and auxiliary parameters of a lane region of an analysis image in the analysis periods are sent to a departure warning module in real time through a departure warning platform; monitoring and analyzing the lane departure state of the automatic driving vehicle through the auxiliary parameters of the lane area, acquiring a departure coefficient PL of an analysis period, and judging whether the departure state in the analysis period is abnormal or not through the value of the departure coefficient PL; carrying out abnormal characteristic analysis on the abnormal time period, obtaining a deviation coefficient PF, and marking the abnormal characteristic of the abnormal time period through the numerical value of the deviation coefficient PF; and analyzing the abnormal factors of the deviation state of the automatic driving vehicle, obtaining the ring difference coefficient HY, and judging the abnormal factors of the deviation state of the automatic driving vehicle through the numerical value of the ring difference coefficient HY.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.
The formulas are all formulas obtained by collecting a large amount of data for software simulation and selecting a formula close to a true value, and coefficients in the formulas are set by a person skilled in the art according to actual conditions; such as: the formula hy=γ1×wq+γ2×yl+γ3×fl; collecting a plurality of groups of sample data by a person skilled in the art and setting a corresponding ring difference coefficient for each group of sample data; substituting the set ring difference coefficient and the acquired sample data into a formula, forming a ternary one-time equation set by any three formulas, screening the calculated coefficient, and taking an average value to obtain values of gamma 1, gamma 2 and gamma 3 of 4.69, 3.58 and 2.32 respectively;
the size of the coefficient is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, and the size of the coefficient depends on the number of sample data and the corresponding circular different coefficient is preliminarily set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected, for example, the ring difference coefficient is in direct proportion to the value of the fog data.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (7)
1. The lane departure warning system of the automatic driving vehicle is characterized by comprising a departure warning platform, wherein the departure warning platform is in communication connection with a departure analysis module, a departure warning module, an abnormality analysis module and a storage module;
the deviation analysis module is used for carrying out lane deviation analysis on the automatic driving vehicle: marking an automatic driving vehicle as an analysis object, generating an analysis period, dividing the analysis period into a plurality of analysis periods, obliquely shooting a lane in the analysis periods through a camera arranged on the side surface of the vehicle, marking the shot image as an analysis image, and acquiring auxiliary parameters of the analysis image; the auxiliary parameters of the analysis images in the analysis period are sent to the deviation early warning module in real time through the deviation early warning platform;
the deviation early warning module is used for monitoring and analyzing the lane deviation state of the automatic driving vehicle through the auxiliary parameters of the lane area, acquiring a deviation coefficient PL of an analysis object in an analysis period and judging whether the deviation state of the analysis object in the analysis period is abnormal or not through the numerical value of the deviation coefficient PL;
the abnormality analysis module is used for analyzing abnormal factors of the deviation state of the automatic driving vehicle: acquiring fog data WQ, rainfall data YL and wind power data FL in an abnormal period, performing numerical calculation to obtain a ring difference coefficient HY, and marking an abnormal deviation state factor of an analysis object according to the numerical value of the ring difference coefficient HY;
the acquisition process of the deviation coefficient PL of the analysis object in the analysis period includes: marking the maximum value and the minimum value of the length values of the lane areas in all the analysis images in the analysis period as a large value and a small value respectively, marking the maximum value and the minimum value of the included angle values of the lane areas in all the analysis images in the analysis period as a large value and a small value respectively, marking the difference value of the large value and the small value as a long difference value CC, and marking the difference value of the large value and the small value as a small difference value JC; the deviation coefficient PL of the analysis object in the analysis period is obtained by performing numerical calculation on the long difference CC and the pinch difference JC.
2. The lane departure warning system of claim 1, wherein the process of obtaining the auxiliary parameter of the analysis image comprises: the contrast of the analysis image is adjusted to a preset standard contrast, the analysis image is amplified to a pixel grid image and subjected to gray level conversion, a gray level range is obtained through a storage module, the pixel grid with a gray level value within the gray level range is marked as a lane grid, the analysis image is divided into a plurality of lane areas, the pixel grids in the lane areas are all lane grids, and the pixel grids adjacent to the lane areas are not lane grids; and connecting the central point of the lane area with the central point of the analysis image to obtain an auxiliary line, marking an angle value of an acute angle formed by an extension line of the auxiliary line and the bottom edge of the analysis image as an included angle value of the lane area, and forming auxiliary parameters of the lane area by the included angle value of the lane area and the length value of the auxiliary line.
3. The lane departure warning system for an automatically driven vehicle according to claim 2, wherein the specific process of determining whether the departure state of the analysis object is abnormal in the analysis period comprises: the deviation threshold PLmax is acquired by the storage module, and the deviation coefficient PL of the analysis object in the analysis period is compared with the deviation threshold PLmax: if the deviation coefficient PL is greater than or equal to the deviation threshold PLmax, judging that the deviation state of the analysis object in the analysis period is abnormal, marking the corresponding analysis period as an abnormal period, carrying out abnormal characteristic analysis on the abnormal period, generating a driving abnormal signal and sending the driving abnormal signal to a vehicle-mounted display screen and a mobile phone terminal of a driver through a deviation early warning platform; if the deviation coefficient PL is smaller than the deviation threshold PLmax, it is determined that the deviation state of the analysis object in the analysis period is normal, and the corresponding analysis period is marked as normal.
4. A lane departure warning system for an autonomous vehicle according to claim 3, wherein the specific process of performing the abnormality feature analysis for the abnormal period comprises: forming a length set by the length values of the lane areas in all analysis images in the abnormal time period, performing variance calculation on the length set to obtain a long amplitude value CF, forming an included angle set by the included angle values of the lane areas in all analysis images in the abnormal time period, performing variance calculation on the included angle set to obtain a clipping amplitude value JF, and performing numerical calculation on the long amplitude value CF and the clipping amplitude value JF to obtain a deviation coefficient PF of the abnormal time period; the method comprises the steps of obtaining a deviation threshold value PFmax through a storage module, comparing the deviation coefficient PF with the deviation threshold value PFmax, and marking abnormal characteristics of an abnormal period through a comparison result.
5. The lane departure warning system for an autonomous vehicle of claim 4, wherein comparing the deviation factor PF to the deviation threshold PFmax comprises: if the deviation coefficient PF is smaller than the deviation threshold PFmax, marking the abnormal characteristic of the abnormal period as deviation, generating an abnormal analysis signal and sending the abnormal analysis signal to an abnormal analysis module; if the deviation coefficient PF is larger than or equal to the deviation threshold PFmax, the abnormal characteristic of the abnormal period is marked as out of control, a system optimization signal is generated, and the system optimization signal is sent to a mobile phone terminal of a manager.
6. The lane departure warning system of an autonomous vehicle according to claim 5, wherein the mist data WQ is a maximum value of the mist concentration during an abnormal period, the rain amount data YL is a rainfall during the abnormal period, and the wind force data FL is a maximum value of the wind force outside the autonomous vehicle during the abnormal period.
7. The lane departure warning system for an autonomous vehicle according to claim 1, wherein the specific process of marking the departure status abnormality factor of the analysis object comprises: the method comprises the steps of obtaining a ring difference threshold HYmax through a storage module, and comparing the ring difference coefficient HY with the ring difference threshold HYmax: if the ring deviation coefficient HY is smaller than the ring deviation threshold HYmax, determining that the deviation state abnormality factor of the automatic driving vehicle is a system fault, generating a system upgrading signal and sending the system upgrading signal to a mobile phone terminal of a manager through a deviation early warning platform; if the ring deviation coefficient HY is greater than or equal to the ring deviation threshold HYmax, determining that the deviation state abnormality factor of the automatic driving vehicle is environmental influence, generating an environment abnormality signal, and sending the environment abnormality signal to a vehicle-mounted display screen and a mobile phone terminal of a driver through a deviation early warning platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310534729.6A CN116331220B (en) | 2023-05-12 | 2023-05-12 | Lane departure early warning method and early warning system for automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310534729.6A CN116331220B (en) | 2023-05-12 | 2023-05-12 | Lane departure early warning method and early warning system for automatic driving vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116331220A CN116331220A (en) | 2023-06-27 |
| CN116331220B true CN116331220B (en) | 2023-08-04 |
Family
ID=86895160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310534729.6A Active CN116331220B (en) | 2023-05-12 | 2023-05-12 | Lane departure early warning method and early warning system for automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116331220B (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010032064A1 (en) * | 2010-07-23 | 2011-05-12 | Daimler Ag | Method for assisting driver of vehicle during transverse control of vehicle, involves determining relevance distances between vehicle and objects, and decreasing relevance of objects for transverse control with relevance distances |
| KR101472615B1 (en) * | 2010-12-21 | 2014-12-16 | 삼성전기주식회사 | System and method for warning lane departure |
| KR101473866B1 (en) * | 2014-01-23 | 2014-12-17 | 주식회사 지티 | Image processing system for vehicle and image processing method of using the same |
| KR20170008190A (en) * | 2016-08-04 | 2017-01-23 | 김구현 | Driver Assistance System And Method Thereof |
| WO2020191543A1 (en) * | 2019-03-22 | 2020-10-01 | SZ DJI Technology Co., Ltd. | System and method for lane monitoring and providing lane departure warnings |
| CN210234809U (en) * | 2019-07-05 | 2020-04-03 | 河南护航实业股份有限公司 | Lane departure early warning system |
| CN110487562B (en) * | 2019-08-21 | 2020-04-14 | 北京航空航天大学 | Driveway keeping capacity detection system and method for unmanned driving |
| CN112149560B (en) * | 2020-09-22 | 2024-03-01 | 深圳市达程科技开发有限公司 | Lane departure detection method |
| CN112233273A (en) * | 2020-10-10 | 2021-01-15 | 苏州智加科技有限公司 | Data transmission method and device, vehicle-mounted equipment and storage medium |
| CN112519796A (en) * | 2020-11-20 | 2021-03-19 | 安徽网思科技有限公司 | Lane departure early warning system for automatic driving |
-
2023
- 2023-05-12 CN CN202310534729.6A patent/CN116331220B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 基于小波分解的车道偏离预警算法研究;高岩;舒强;郑楚清;;公路与汽运(第05期);第48-50页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116331220A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949372B (en) | Laser radar and vision combined calibration method | |
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN110458157B (en) | Intelligent monitoring system for power cable production process | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| CN115171361B (en) | Dangerous behavior intelligent detection and early warning method based on computer vision | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| CN112769877A (en) | Group fog early warning method, cloud server, vehicle and medium | |
| CN111610191B (en) | Road detection and repair system | |
| CN107832788B (en) | Vehicle distance measuring method based on monocular vision and license plate recognition | |
| CN116331220B (en) | Lane departure early warning method and early warning system for automatic driving vehicle | |
| CN107150689A (en) | A kind of automobile assistant driving method and system | |
| CN111332306A (en) | Traffic road perception auxiliary driving early warning device based on machine vision | |
| CN115994901A (en) | Automatic road disease detection method and system | |
| CN113408396B (en) | Bridge intelligent sensing system based on cloud computing | |
| CN112083693B (en) | Paint production line information management system based on internet of things technology | |
| CN112990117B (en) | Installation data processing method and device based on intelligent driving system | |
| CN112487925B (en) | Bridge load damage identification method and system | |
| CN114757905A (en) | Vision-based rope winding abnormity detection device and method | |
| CN114169404A (en) | Method for intelligently acquiring quantitative information of slope diseases based on images | |
| CN113301327A (en) | Performance determination method and device of image collector, medium and electronic equipment | |
| CN114359223A (en) | Material level height detection method, device and system and operation machine | |
| CN112686203A (en) | Vehicle safety warning device detection method based on space prior | |
| CN110781758A (en) | Dynamic video monitoring method and device for abnormal pantograph structure | |
| CN115619748A (en) | Method for monitoring glue color abnormity in gluing process of wind power blade | |
| CN110177222A (en) | A kind of the camera exposure parameter method of adjustment and device of the unused resource of combination vehicle device |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 201, 202, 301, No. 56-4 Fenghuang South Road, Huadu District, Guangzhou City, Guangdong Province, 510806 Patentee after: Heduo Technology (Guangzhou) Co.,Ltd. Address before: 100095 101-15, 3rd floor, building 9, yard 55, zique Road, Haidian District, Beijing Patentee before: HOLOMATIC TECHNOLOGY (BEIJING) Co.,Ltd. |