CN117523517A - Method and device for measuring lane line precision, vehicle and storage medium - Google Patents
Method and device for measuring lane line precision, vehicle and storage medium Download PDFInfo
- Publication number
- CN117523517A CN117523517A CN202311524534.XA CN202311524534A CN117523517A CN 117523517 A CN117523517 A CN 117523517A CN 202311524534 A CN202311524534 A CN 202311524534A CN 117523517 A CN117523517 A CN 117523517A
- Authority
- CN
- China
- Prior art keywords
- target
- lane line
- point set
- value
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005259 measurement Methods 0.000 claims abstract description 48
- 230000006870 function Effects 0.000 claims description 53
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 9
- 238000009795 derivation Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000000691 measurement method Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 abstract description 15
- 238000007405 data analysis Methods 0.000 abstract description 4
- 238000001914 filtration Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 description 29
- 238000004891 communication Methods 0.000 description 8
- 238000010187 selection method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/72—Data preparation, e.g. statistical preprocessing of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/776—Validation; Performance evaluation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/10—Historical data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to the technical field of automatic driving, in particular to a lane line precision measuring method, a lane line precision measuring device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring current observation data and historical observation data of a vehicle on a lane line; solving the current observation data and the historical observation data to generate a target true value and a target curve solution set; and calculating all curves in the target curve solution set, obtaining a target parameter point set of all the curves, and calculating the accuracy measurement value of the lane line by utilizing the difference value between the true value and the corresponding parameter point in the target parameter point set. According to the method and the device for measuring the lane line accuracy, the approximate true value of the intercept between the vehicle and the lane line can be obtained through optimization or filtering fusion solution, the statistic data analysis of multi-frame historical fusion lane line data and the approximate true value is carried out, the quantized lane line accuracy measurement value is obtained, the reference true value of the lane line in the measurement process is obtained, and therefore the efficiency and the accuracy of the lane line accuracy measurement are improved, and the practicability is higher.
Description
Technical Field
The present disclosure relates to the field of automatic driving technologies, and in particular, to a lane line accuracy measurement method, a lane line accuracy measurement device, a vehicle, and a storage medium.
Background
In intelligent driving, lane lines on a road can be detected through a vehicle camera and a sensor, intelligent simulation of actual road lane lines is realized, and more visual and clear visual references are provided.
In the related art, the accuracy of the detected lane line directly influences the safety and accuracy of intelligent driving, and the overall performance detection and evaluation of the lane line can be obtained by comparing the 2D lane line result after deep learning processing with the image labeling result.
However, in the related art, only an offline evaluation result of a single-frame 2D image can be obtained for a vehicle lane line, an evaluation result of the lane line cannot be obtained in real time, verification on the accuracy of the 3D lane line is difficult, accurate evaluation on an optimal lane line obtained by multi-frame observation fusion solution in the actual driving process of the vehicle cannot be realized, and a selection method of a true value of the lane line in an evaluation system is not clear, so that the efficiency and accuracy of calculation of the lane line accuracy measurement value are reduced, and the need to be solved is overcome.
Disclosure of Invention
The application provides a method, a device, a vehicle and a storage medium for measuring lane line precision, which are used for solving the problems that in the related technology, the vehicle lane line can only acquire an offline evaluation result of a single-frame 2D image, the evaluation result of the lane line cannot be acquired in real time, the precision of a 3D lane line is difficult to verify, the accurate evaluation of an optimal lane line obtained by multi-frame observation fusion calculation in the actual driving process of the vehicle cannot be realized, the selection method of the lane line true value in a system is not clear, the calculation efficiency and accuracy of the lane line precision measurement value are reduced, and the like.
An embodiment of a first aspect of the present application provides a method for measuring lane line accuracy, including the following steps: acquiring current observation data and historical observation data of a vehicle on a lane line; resolving the current observation data and the historical observation data to generate a target true value and a target curve solution set; and calculating all curves in the target curve solution set, obtaining a target parameter point set of all the curves, and calculating the accuracy measurement value of the lane line by utilizing the difference value between the true value and the corresponding parameter point in the target parameter point set.
Optionally, in an embodiment of the present application, the calculating the current observation data and the historical observation data generates a target truth value and a target curve solution set, including: fitting based on the current observation data to obtain a current lane line optimal solution, and calculating the target true value according to the current lane line optimal solution; and sampling the historical observation data to obtain a target historical lane line point set, and converting the positions of all the point sets in the target historical lane line point set into vehicle positions corresponding to the current observation data to obtain the target curve solution set.
Optionally, in an embodiment of the present application, the calculating all curves in the target curve solution set, and obtaining a target parameter point set of all the curves includes: deriving the original functions corresponding to all the curves, and obtaining a first order derivative function and a second order derivative function of all the curves; and calculating a target intercept point set of all curves by using the primitive function, calculating a target orientation point set by using the first order derivative function, calculating a target curvature point set by using the second order derivative function, and constructing the target parameter point set based on the target intercept point set, the target orientation point set and the target curvature point set.
Optionally, in an embodiment of the present application, the calculating the accuracy metric value of the lane line using the difference between the true value and the corresponding parameter point in the target parameter point set includes: calculating the statistical value of each point set in the target parameter point set based on the difference value to obtain a statistical value set of the target parameter point set, wherein the statistical value of each point set is a precision measurement value of a curve corresponding to each target parameter point set; extracting a plurality of continuous sets in the statistic value set, and calculating the average value of the plurality of continuous sets to obtain a statistic average value set of the target parameter point set, wherein the statistic average value set is an accuracy measurement average value of all curves in a continuous time period corresponding to the plurality of continuous sets; and generating the precision measurement value of the lane line by the statistic value set of the target parameter point set and the statistic mean value set of the target parameter point set.
An embodiment of a second aspect of the present application provides a measurement device for lane line accuracy, including: the acquisition module is used for acquiring current observation data and historical observation data of the vehicle on the lane line; the generation module is used for resolving the current observation data and the historical observation data to generate a target true value and a target curve solution set; and the measurement module is used for calculating all curves in the target curve solution set, obtaining a target parameter point set of all the curves, and calculating the accuracy measurement value of the lane line by utilizing the difference value between the true value and the corresponding parameter point in the target parameter point set.
Optionally, in one embodiment of the present application, the generating module includes: the fitting unit is used for fitting based on the current observation data to obtain a current lane line optimal solution, and calculating the target true value according to the current lane line optimal solution; the conversion unit is used for sampling the historical observation data to obtain a target historical lane line point set, converting the positions of all the point sets in the target historical lane line point set into the positions of the vehicles corresponding to the current observation data, and obtaining the target curve solution set.
Optionally, in one embodiment of the present application, the metric module includes: the derivation unit is used for deriving the original functions corresponding to all the curves and obtaining a first order derivation function and a second order derivation function of all the curves; the construction unit is used for calculating a target intercept point set of all curves by using the original function, calculating a target orientation point set by using the first order derivative function, calculating a target curvature point set by using the second order derivative function, and constructing the target parameter point set based on the target intercept point set, the target orientation point set and the target curvature point set.
Optionally, in one embodiment of the present application, the metric module includes: the first calculation unit is used for calculating the statistical value of each point set in the target parameter point set based on the difference value to obtain a statistical value set of the target parameter point set, wherein the statistical value of each point set is a precision metric value of a curve corresponding to each target parameter point set; the second calculation unit is used for extracting a plurality of continuous sets in the statistic value set, calculating the average value of the plurality of continuous sets and obtaining a statistic average value set of the target parameter point set, wherein the statistic average value set is an accuracy measurement average value of all curves in a continuous time period corresponding to the plurality of continuous sets; and the generating unit is used for generating the precision measurement value of the lane line from the statistic value set of the target parameter point set and the statistic mean value set of the target parameter point set.
An embodiment of a third aspect of the present application provides a vehicle, including: the lane line accuracy measuring device comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the program to realize the lane line accuracy measuring method according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements a method of measuring lane line accuracy as above.
According to the method and the device for measuring the lane line accuracy, the approximate true value of the intercept between the vehicle and the lane line can be obtained through optimization or filtering fusion solution, the statistic data analysis of multi-frame historical fusion lane line data and the approximate true value is carried out, the quantized lane line accuracy measurement value is obtained, the reference true value of the lane line in the measurement process is obtained, and therefore the efficiency and the accuracy of the lane line accuracy measurement are improved, and the practicability is higher. Therefore, the method solves the problems that in the related technology, only an offline evaluation result of a single-frame 2D image can be obtained for a vehicle lane line, an evaluation result of the lane line cannot be obtained in real time, verification on the accuracy of the 3D lane line is difficult, accurate evaluation on an optimal lane line obtained by multi-frame observation fusion solution in the actual driving process of the vehicle cannot be realized, a selection method of a lane line true value in an evaluation system is not clear, and the calculation efficiency and accuracy of a lane line accuracy measurement value are reduced.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of a method for measuring lane line accuracy according to an embodiment of the present application;
FIG. 2 is a flow chart of a lane line accuracy measurement process according to one embodiment of the present application;
FIG. 3 is a schematic structural view of a lane line accuracy measuring device according to an embodiment of the present application;
fig. 4 is a schematic structural view of a vehicle according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.
The following describes a method, an apparatus, a vehicle, and a storage medium for measuring lane line accuracy according to an embodiment of the present application with reference to the accompanying drawings. Aiming at the problems that in the related art mentioned in the background art, only an offline evaluation result of a single-frame 2D image can be obtained for a vehicle lane line, an evaluation result of the lane line cannot be obtained in real time, the accuracy of the 3D lane line cannot be verified, the accurate evaluation of an optimal lane line obtained by multi-frame observation fusion solution in the actual driving process of the vehicle cannot be realized, and the selection method of a lane line true value in a system is not explicitly evaluated, so that the calculation efficiency and accuracy of the lane line accuracy measurement value are reduced. Therefore, the method solves the problems that in the related technology, only an offline evaluation result of a single-frame 2D image can be obtained for a vehicle lane line, an evaluation result of the lane line cannot be obtained in real time, verification on the accuracy of the 3D lane line is difficult, accurate evaluation on an optimal lane line obtained by multi-frame observation fusion solution in the actual driving process of the vehicle cannot be realized, a selection method of a lane line true value in an evaluation system is not clear, and the calculation efficiency and accuracy of a lane line accuracy measurement value are reduced.
Specifically, fig. 1 is a flow chart of a method for measuring lane line accuracy according to an embodiment of the present application.
As shown in fig. 1, the method for measuring the lane line accuracy includes the following steps:
in step S101, current observation data and historical observation data of a vehicle on a lane line are acquired.
It can be appreciated that in the embodiment of the present application, the current observation data of the lane line may be based on the road image obtained by the vehicle captured by the camera in real time, and the 2D lane line may be calculated by the deep learning neural network, so as to project the obtained 3D lane line data. The historical observation data is the observation data of the vehicle on the lane lines in the historical driving process.
In step S102, the current observation data and the historical observation data are resolved, and a target true value and a target curve solution set are generated.
It can be understood that in the embodiment of the present application, the current observation data and the historical observation data obtained in the above steps may be calculated, so as to obtain a target true value as an evaluation reference under the current observation data, where the target curve solution set is a set to be evaluated after the historical observation data is preprocessed.
Optionally, in one embodiment of the present application, resolving the current observation data and the historical observation data to generate a target truth value and a target curve solution set includes: fitting is carried out based on the current observation data to obtain a current lane line optimal solution, and a target true value is calculated according to the current lane line optimal solution; sampling historical observation data to obtain a target historical lane line point set, and converting the positions of all the point sets in the target historical lane line point set into vehicle positions corresponding to the current observation data to obtain a target curve solution set.
In the actual execution process, the 3D lane line data can be fitted through sampling points to obtain a 3-order curve f (x) =c 0 +c 1 x+c 2 x 2 +c 3 x 3 Wherein c 0 、c 1 、c 2 、c 3 The three-dimensional curve equation coefficients are the three-dimensional curve equation coefficients of the lane line equation, and x is the independent variable x under the vehicle body coordinate system. And (3) comprehensively solving a 3D lane line point set by utilizing the current observation and the historical observation to obtain a current lane line optimal solution, taking x=0 from a primary function, a first derivative and a second derivative of the current lane line optimal solution, and sequentially and respectively obtaining the transverse intercept, the direction and the curvature of the current vehicle as target true values. And simultaneously taking the current moment as an anchor point, taking a history n-frame calculation lane line 3D lane line from the history observation data, sampling the history n-frame calculation lane line, discretizing, converting the discretized lane line point set into a current vehicle system corresponding to the current observation data through pose, obtaining a history observation data point set under the current vehicle system, and re-fitting all the history lane line point sets transferred into the current vehicle system into a cubic curve to obtain all curve coefficients, thereby obtaining a target curve solution set.
In step S103, all curves in the target curve solution set are calculated, a target parameter point set of all curves is obtained, and a precision metric value of the lane line is calculated by using the difference between the true value and the corresponding parameter point in the target parameter point set.
It may be understood that in the embodiment of the present application, all curves in the target curve solution set may be calculated to obtain a target parameter point set corresponding to all history curves, that is, a transverse intercept, an orientation, and a curvature of the vehicle included in the target truth value are target parameters required to be obtained in the history observation data, and finally, the difference value between the target truth value and the corresponding parameter point in the target parameter point set is used to calculate the accuracy metric value of the lane line.
In particular, when the historical observation data is the original observation data at the current moment, the evaluation method of the steps can be used in a similar way to acquire the accuracy measurement value of the lane line in real time.
Optionally, in one embodiment of the present application, calculating all curves in the target curve solution set, and obtaining a target parameter point set of all curves includes: deriving the original functions corresponding to all the curves, and obtaining a first order derivative function and a second order derivative function of all the curves; and calculating a target intercept point set of all curves by using the original function, calculating a target orientation point set by using a first order derivative function, calculating a target curvature point set by using a second order derivative function, and constructing a target parameter point set based on the target intercept point set, the target orientation point set and the target curvature point set.
Specifically, the primitive function corresponding to all curves is f (x) =c 0 +c 1 x+c 2 x 2 +c 3 x 3 Obtaining a first order derivative function f' (x) =c after derivative 1 +2c 2 x+3c 3 x 2 Second derivative function f "(x) =2c 2 +6c 3 x. The current vehicle position point set A { (0, c) is obtained by taking x=0 for the original function, the first order derivative function and the second order derivative function 1 ) Second order derivative set C { (0, 2×c) 2 ) And respectively obtaining a target intercept point set, a target orientation point set and a target curvature point set, thereby constructing and obtaining a target parameter point set.
Optionally, in one embodiment of the present application, calculating the accuracy metric value of the lane line using the difference between the true value and the corresponding parameter point in the target parameter point set includes: calculating the statistical value of each point set in the target parameter point set based on the difference value to obtain a statistical value set of the target parameter point set, wherein the statistical value of each point set is the precision metric value of the curve corresponding to each target parameter point set; extracting a plurality of continuous sets in the statistical value sets, and calculating the average value of the plurality of continuous sets to obtain a statistical average value set of the target parameter point set, wherein the statistical average value set is the precision measurement average value of all curves in a continuous time period corresponding to the plurality of continuous sets; and generating the precision measurement value of the lane line by the statistic value set of the target parameter point set and the statistic mean value set of the target parameter point set.
In the actual execution process, the y values in all the target intercept point set, the target orientation point set and the target curvature point set can be statistically calculated with the difference from the target true value to respectively obtain the transverse position, the orientation and the curvature distribution maximum E max =max, where c 0 The optimal solution result coefficient of the lane line at the current moment is indicated,the optimal solution result c of the pointed historical n frames 0 Coefficient, fabs, refers to absolute value solving function, max only solves the function name of the maximum value, E max C is 0 A coefficient difference maximum value result; mean->Sigma is the sum symbol, c 0 Indicating the optimal solution result coefficient of the lane line at the current moment, < + >>The optimal solution result c of the pointed historical n frames 0 Coefficient, n is the historical frame parameter set, AVG is c 0 Coefficient average value; variance ofWherein std is the standard deviation calculation result, sigma sum symbol, AVG is c 0 Coefficient mean value->The optimal solution result c of the pointed historical n frames 0 Coefficients. The maximum value and the average value are the calculation results of the accuracy measurement of the historical n-frame optimal solution lane lines at the current position, namely the statistical value set. Further taking m frame measurement calculation results, and further carrying out statistical calculation to obtain AVG peri Maximum->The two calculated values are lane line accuracy measurement results, namely a statistical mean value set, in the current time period.
As shown in fig. 2, the working contents of the embodiment of the present application are described in detail below with a specific embodiment.
In step S201, road images are acquired through a camera, and 2D lane lines are obtained through a neural network.
The road image is obtained through a camera, and the image obtains a 2D lane line through a deep learning neural network.
In step S202: the 2D lane lines are projected to 3D.
The 2D lane line is projected to be a 3D lane line, and current observation data of the vehicle on the lane line is obtained
In step S203, the optimal solution of the lane line is calculated, and the true value is considered by the approximate left and right points of the vehicle.
And solving the current observation data to obtain an optimal solution of the lane line, and approximating the true value considered by the left and right points of the vehicle to obtain a target true value.
In step S204, the optimal solution of the historical n frames is obtained and transferred to a lane line set under the current vehicle system.
And sampling the historical observation data to obtain a historical n-frame optimal solution to obtain a target historical lane line point set, and converting the positions of all the point sets in the target historical lane line point set into the vehicle positions corresponding to the current observation data to obtain a lane line set under the current vehicle system, namely a target curve solution set.
In step S205, the zero point position, the first derivative and the second derivative point set of the vehicle are calculated.
And deriving the original functions corresponding to all the curves, and obtaining a first derivative function and a second derivative function of all the curves to obtain a zero point position, a first derivative and a second derivative point set.
In step S206, the point set distribution mean, variance and maximum value are calculated statistically.
And calculating the distribution mean value, variance and maximum value of the point set by statistics to obtain a statistical value set of the target parameter point set.
In step S207, the mean, variance and maximum value of m frames are obtained for further statistics.
Wherein, the average value, variance and maximum value of m frames are obtained for further statistics to obtain a statistical average value set of a target parameter point set
And step S208, obtaining a real-time lane line precision quantization result and a quantization result in time.
And acquiring a precision measurement value set of the lane line.
According to the method for measuring the lane line precision, which is provided by the embodiment of the application, the approximate true value of the intercept between the vehicle and the lane line can be obtained through optimization or filtering fusion, the statistical data analysis of multi-frame historical fusion lane line data and the approximate true value is carried out, the quantized lane line precision measurement value is obtained, and the reference true value of the lane line in the measurement process is obtained, so that the efficiency and the accuracy of the lane line precision measurement are improved, and the practicability is higher. Therefore, the method solves the problems that in the related technology, only an offline evaluation result of a single-frame 2D image can be obtained for a vehicle lane line, an evaluation result of the lane line cannot be obtained in real time, verification on the accuracy of the 3D lane line is difficult, accurate evaluation on an optimal lane line obtained by multi-frame observation fusion solution in the actual driving process of the vehicle cannot be realized, a selection method of a lane line true value in an evaluation system is not clear, and the calculation efficiency and accuracy of a lane line accuracy measurement value are reduced.
Next, a measurement device for lane line accuracy according to an embodiment of the present application will be described with reference to the accompanying drawings.
Fig. 3 is a schematic structural diagram of a lane line accuracy measuring apparatus according to an embodiment of the present application.
As shown in fig. 3, the lane line accuracy measuring apparatus 10 includes: an acquisition module 100, a generation module 200 and a metrics module 300.
The acquiring module 100 is configured to acquire current observation data and historical observation data of a lane line of a vehicle.
The generating module 200 is configured to solve the current observation data and the historical observation data, and generate a target true value and a target curve solution set.
The measurement module 300 is configured to calculate all curves in the target curve solution set, obtain a target parameter point set of all curves, and calculate a precision measurement value of the lane line by using a difference value between the true value and a corresponding parameter point in the target parameter point set.
Optionally, in one embodiment of the present application, the generating module 200 includes: fitting unit and conversion unit.
And the fitting unit is used for fitting based on the current observation data to obtain a current lane line optimal solution, and calculating a target true value according to the current lane line optimal solution.
The conversion unit is used for sampling the historical observation data to obtain a target historical lane line point set, and converting the positions of all the point sets in the target historical lane line point set into the positions of the vehicle corresponding to the current observation data to obtain a target curve solution set.
Optionally, in one embodiment of the present application, the metric module 300 includes: and the derivation unit and the construction unit.
The derivation unit is used for deriving the original functions corresponding to all the curves and obtaining a first order derivative function and a second order derivative function of all the curves.
The construction unit is used for calculating a target intercept point set of all curves by utilizing the original function, calculating a target orientation point set by utilizing the first order derivative function, calculating a target curvature point set by utilizing the second order derivative function, and constructing a target parameter point set based on the target intercept point set, the target orientation point set and the target curvature point set.
Optionally, in one embodiment of the present application, the metric module 300 includes: the first calculating unit, the second calculating unit and the generating unit.
The first calculation unit is used for calculating the statistical value of each point set in the target parameter point set based on the difference value to obtain a statistical value set of the target parameter point set, wherein the statistical value of each point set is the precision metric value of the curve corresponding to each target parameter point set.
The second calculation unit is used for extracting a plurality of continuous sets in the statistic value set, calculating the average value of the plurality of continuous sets, and obtaining a statistic average value set of the target parameter point set, wherein the statistic average value set is an average value of precision measurement of all curves in a continuous time period corresponding to the plurality of continuous sets.
And the generating unit is used for generating the precision measurement value of the lane line from the statistic value set of the target parameter point set and the statistic mean value set of the target parameter point set.
It should be noted that the foregoing explanation of the embodiment of the lane line accuracy measuring method is also applicable to the lane line accuracy measuring device of this embodiment, and will not be repeated here.
According to the lane line precision measuring device provided by the embodiment of the application, the approximate true value of the intercept between the vehicle and the lane line can be obtained through optimization or filtering fusion, the statistic data analysis of multi-frame historical fusion lane line data and the approximate true value is carried out, the quantized lane line precision measuring value is obtained, the reference true value of the lane line in the measuring process is obtained, the efficiency and the accuracy of the lane line precision measuring are improved, and the practicability is higher. Therefore, the method solves the problems that in the related technology, only an offline evaluation result of a single-frame 2D image can be obtained for a vehicle lane line, an evaluation result of the lane line cannot be obtained in real time, verification on the accuracy of the 3D lane line is difficult, accurate evaluation on an optimal lane line obtained by multi-frame observation fusion solution in the actual driving process of the vehicle cannot be realized, a selection method of a lane line true value in an evaluation system is not clear, and the calculation efficiency and accuracy of a lane line accuracy measurement value are reduced.
Fig. 4 is a schematic structural diagram of a vehicle according to an embodiment of the present application. The vehicle may include:
memory 401, processor 402, and a computer program stored on memory 401 and executable on processor 402.
The processor 402 implements the lane line accuracy measurement method provided in the above-described embodiment when executing a program.
Further, the vehicle further includes:
a communication interface 403 for communication between the memory 401 and the processor 402.
A memory 401 for storing a computer program executable on the processor 402.
Memory 401 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 may be connected to each other by a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component Interconnect, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 401, the processor 402, and the communication interface 403 are integrated on a chip, the memory 401, the processor 402, and the communication interface 403 may complete communication with each other through internal interfaces.
The processor 402 may be a central processing unit (Central Processing Unit, abbreviated as CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or one or more integrated circuits configured to implement embodiments of the present application.
The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the lane line accuracy measurement method as above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means 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 application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. The method for measuring the lane line precision is characterized by comprising the following steps of:
acquiring current observation data and historical observation data of a vehicle on a lane line;
resolving the current observation data and the historical observation data to generate a target true value and a target curve solution set;
and calculating all curves in the target curve solution set, obtaining a target parameter point set of all the curves, and calculating the accuracy measurement value of the lane line by utilizing the difference value between the true value and the corresponding parameter point in the target parameter point set.
2. The method of claim 1, wherein said resolving said current observations with said historical observations to generate a target truth and target curve solution set comprises:
fitting based on the current observation data to obtain a current lane line optimal solution, and calculating the target true value according to the current lane line optimal solution;
and sampling the historical observation data to obtain a target historical lane line point set, and converting the positions of all the point sets in the target historical lane line point set into vehicle positions corresponding to the current observation data to obtain the target curve solution set.
3. The method of claim 1, wherein said calculating all curves in said target curve solution set, obtaining a target parameter point set for said all curves, comprises:
deriving the original functions corresponding to all the curves, and obtaining a first order derivative function and a second order derivative function of all the curves;
and calculating a target intercept point set of all curves by using the primitive function, calculating a target orientation point set by using the first order derivative function, calculating a target curvature point set by using the second order derivative function, and constructing the target parameter point set based on the target intercept point set, the target orientation point set and the target curvature point set.
4. The method of claim 1, wherein calculating the measure of accuracy of the lane line using the difference between the true value and the corresponding parameter point in the set of target parameter points comprises:
calculating the statistical value of each point set in the target parameter point set based on the difference value to obtain a statistical value set of the target parameter point set, wherein the statistical value of each point set is a precision measurement value of a curve corresponding to each target parameter point set;
extracting a plurality of continuous sets in the statistic value set, and calculating the average value of the plurality of continuous sets to obtain a statistic average value set of the target parameter point set, wherein the statistic average value set is an accuracy measurement average value of all curves in a continuous time period corresponding to the plurality of continuous sets;
and generating the precision measurement value of the lane line by the statistic value set of the target parameter point set and the statistic mean value set of the target parameter point set.
5. A lane line accuracy measuring apparatus, comprising:
the acquisition module is used for acquiring current observation data and historical observation data of the vehicle on the lane line;
the generation module is used for resolving the current observation data and the historical observation data to generate a target true value and a target curve solution set;
and the measurement module is used for calculating all curves in the target curve solution set, obtaining a target parameter point set of all the curves, and calculating the accuracy measurement value of the lane line by utilizing the difference value between the true value and the corresponding parameter point in the target parameter point set.
6. The apparatus of claim 5, wherein the generating module comprises:
the fitting unit is used for fitting based on the current observation data to obtain a current lane line optimal solution, and calculating the target true value according to the current lane line optimal solution;
the conversion unit is used for sampling the historical observation data to obtain a target historical lane line point set, converting the positions of all the point sets in the target historical lane line point set into the positions of the vehicles corresponding to the current observation data, and obtaining the target curve solution set.
7. The apparatus of claim 5, wherein the metrics module comprises:
the derivation unit is used for deriving the original functions corresponding to all the curves and obtaining a first order derivation function and a second order derivation function of all the curves;
the construction unit is used for calculating a target intercept point set of all curves by using the original function, calculating a target orientation point set by using the first order derivative function, calculating a target curvature point set by using the second order derivative function, and constructing the target parameter point set based on the target intercept point set, the target orientation point set and the target curvature point set.
8. The apparatus of claim 5, wherein the metrics module comprises:
the first calculation unit is used for calculating the statistical value of each point set in the target parameter point set based on the difference value to obtain a statistical value set of the target parameter point set, wherein the statistical value of each point set is a precision metric value of a curve corresponding to each target parameter point set;
the second calculation unit is used for extracting a plurality of continuous sets in the statistic value set, calculating the average value of the plurality of continuous sets and obtaining a statistic average value set of the target parameter point set, wherein the statistic average value set is an accuracy measurement average value of all curves in a continuous time period corresponding to the plurality of continuous sets;
and the generating unit is used for generating the precision measurement value of the lane line from the statistic value set of the target parameter point set and the statistic mean value set of the target parameter point set.
9. A vehicle, characterized by comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the lane line accuracy measurement method according to any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing a method of measuring lane line accuracy according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311524534.XA CN117523517A (en) | 2023-11-13 | 2023-11-13 | Method and device for measuring lane line precision, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311524534.XA CN117523517A (en) | 2023-11-13 | 2023-11-13 | Method and device for measuring lane line precision, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117523517A true CN117523517A (en) | 2024-02-06 |
Family
ID=89765864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311524534.XA Pending CN117523517A (en) | 2023-11-13 | 2023-11-13 | Method and device for measuring lane line precision, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117523517A (en) |
-
2023
- 2023-11-13 CN CN202311524534.XA patent/CN117523517A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111009153B (en) | Training method, device and equipment of trajectory prediction model | |
| CN107481292B (en) | Attitude error estimation method and device for vehicle-mounted camera | |
| JP6670071B2 (en) | Vehicle image recognition system and corresponding method | |
| JP4943034B2 (en) | Stereo image processing device | |
| CN109532662B (en) | Method and device for calculating distance between vehicles and collision time | |
| CN109360239B (en) | Obstacle detection method, obstacle detection device, computer device, and storage medium | |
| CN109598264B (en) | Object grabbing method and device | |
| CN111144330B (en) | Deep learning-based lane line detection method, device and equipment | |
| CN114930401A (en) | Point cloud-based three-dimensional reconstruction method and device and computer equipment | |
| CN110659545B (en) | Training method of vehicle identification model, vehicle identification method, device and vehicle | |
| US20220080980A1 (en) | Device for predicting speed of vehicle and method thereof | |
| CN114943952A (en) | Method, system, device and medium for obstacle fusion under multi-camera overlapped view field | |
| CN110751040B (en) | Three-dimensional object detection method and device, electronic equipment and storage medium | |
| CN116543361A (en) | Multi-mode fusion sensing method and device for vehicle, vehicle and storage medium | |
| CN115097419A (en) | External parameter calibration method and device for laser radar IMU | |
| CN114919584A (en) | Motor vehicle fixed point target distance measuring method and device and computer readable storage medium | |
| CN117523517A (en) | Method and device for measuring lane line precision, vehicle and storage medium | |
| CN116385369A (en) | Depth image quality evaluation method and device, electronic equipment and storage medium | |
| JP2021051347A (en) | Distance image generation apparatus and distance image generation method | |
| EP4152274A1 (en) | System and method for predicting an occupancy probability of a point in an environment, and training method thereof | |
| CN113624223B (en) | Indoor parking lot map construction method and device | |
| CN112477868B (en) | Collision time calculation method and device, readable storage medium and computer equipment | |
| CN114936423A (en) | Tire quasi-steady state data processing method and device | |
| CN111832347B (en) | Method and device for dynamically selecting region of interest | |
| JP7031625B2 (en) | Graph structure estimation device, SLAM device, graph structure estimation method, computer program, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |