CN115620254A - Method, device, equipment and storage medium for evaluating lane line detection - Google Patents
Method, device, equipment and storage medium for evaluating lane line detection Download PDFInfo
- Publication number
- CN115620254A CN115620254A CN202211327574.0A CN202211327574A CN115620254A CN 115620254 A CN115620254 A CN 115620254A CN 202211327574 A CN202211327574 A CN 202211327574A CN 115620254 A CN115620254 A CN 115620254A
- Authority
- CN
- China
- Prior art keywords
- lane line
- sensing module
- matching
- lane
- position point
- 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 44
- 238000001514 detection method Methods 0.000 title claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 41
- 230000008447 perception Effects 0.000 claims abstract description 7
- 239000002699 waste material Substances 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a method, a device, equipment and a storage medium for evaluating lane line detection, wherein the method comprises the following steps: acquiring each positioning data point of any lane line detected by a lane line sensing module of a vehicle, and taking each positioning data point of any lane line of the lane line sensing module as a first position point; acquiring each positioning data point of a lane line of a high-precision map corresponding to any lane line of the lane line sensing module, and taking each positioning data point corresponding to the high-precision map as a second position point; calculating a matching score of a lane line based on the first location point and the second location point; determining an evaluation result of the any lane line detected by the lane line perception module based on the matching score. The method and the device can accurately and efficiently evaluate the detection result of the lane line, improve the accuracy of lane line evaluation and save the marking resources.
Description
Technical Field
The present application relates to the field of automatic driving technologies, and in particular, to a method, an apparatus, a device, and a storage medium for evaluating lane line detection.
Background
At present, the field of automatic driving is rapidly developed, and automatic driving of automobiles becomes an important development trend of automobile technology and industry. Lane lines are very important components in the vision system of the autonomous vehicle, and when evaluating the detection result of the lane lines, a method generally adopted in the prior art is to mark the lane lines in the camera image and use the marked lane lines for matching.
However, this method requires marking on a two-dimensional image and projecting the label from the two-dimensional image coordinate system to a three-dimensional vehicle coordinate system, followed by matching of lane lines. Additional errors caused by camera calibration errors and fluctuating ground plane are introduced, easily giving distortion effects. In addition, projecting the results in the two-dimensional image coordinate system to the three-dimensional vehicle coordinate system wastes a large amount of annotation resources.
Disclosure of Invention
Based on this, the application provides an evaluation method, an evaluation device, a device and a storage medium for lane line detection, so as to solve the problems in the prior art.
In a first aspect, a method for evaluating lane line detection is provided, the method including:
acquiring each positioning data point of any lane line detected by a lane line sensing module of a vehicle, and taking each positioning data point of any lane line of the lane line sensing module as a first position point;
acquiring each positioning data point of a lane line of a high-precision map corresponding to any lane line of the lane line sensing module, and taking each positioning data point corresponding to the high-precision map as a second position point;
calculating a matching score of a lane line based on the first location point and the second location point;
determining an evaluation result of the any lane line detected by the lane line perception module based on the matching score.
According to one implementation manner in the embodiment of the present application, the calculating a matching score of the lane line based on the first location point and the second location point includes:
calculating the average distance between each first position point and the corresponding second position point;
calculating the maximum distance in the distances from each first position point to the corresponding second position point;
calculating the matching score based on the average distance and the maximum distance.
According to an implementable aspect of an embodiment of the present application, said calculating the matching score based on the average distance and the maximum distance comprises:
by MS = BS-k 1 *d avg -k 2 *d max Calculating the matching score by a formula;
wherein MS is a matching score; BS is a benchmark score which is a constant; k is a radical of formula 1 And k 2 Is a constant; d avg Is the average distance; d max Is the maximum distance.
According to an implementable manner in an embodiment of the present application, the determining an evaluation result of the any lane line detected by the lane line perception module based on the matching score includes:
when the matching score meets a set condition, determining that the matching of any lane line detected by the lane line sensing module is successful;
when the matching score does not meet a set condition, determining that the matching of any lane line detected by the lane line sensing module fails;
wherein the evaluation result comprises the matching success and the matching failure.
According to an implementable manner in an embodiment of the present application, the method further comprises:
when the lane line sensing module detects that any lane line is successfully matched, a matching index is calculated according to the lane line sensed by the lane line sensing module and the corresponding lane line of the high-precision map, wherein the matching index comprises one or more of a detection distance, an average distance, a maximum distance and a maximum weighted distance.
According to an implementable manner of an embodiment of the present application, the detection distance represents a euclidean distance between two first location points;
the average distance represents the average distance between each first position point and the corresponding second position point;
the maximum distance represents the maximum value of the distance from each first position point to the corresponding second position point;
the maximum weighted distance represents the maximum of the weighted distances between each first location point and the corresponding second location point.
According to an implementable manner in an embodiment of the present application, the method further comprises:
acquiring the number of lane lines which are successfully matched and the number of lane lines which are unsuccessfully matched in all the lane lines detected by the lane line sensing module;
and calculating the matching success rate based on the number of the lane lines which are successfully matched and the number of all the lane lines.
In a second aspect, there is provided an evaluation device for lane line detection, the device including:
a first obtaining module: the system comprises a lane line sensing module, a first position point and a second position point, wherein the lane line sensing module is used for sensing the lane lines of a vehicle;
a second obtaining module: the system comprises a lane line sensing module, a lane line positioning module, a second position point and a third position point, wherein the lane line sensing module is used for sensing a lane line of a high-precision map;
a matching module: a matching score for calculating a lane line based on the first location point and the second location point;
an evaluation module: and the evaluation result is used for determining the any lane line detected by the lane line perception module based on the matching score.
In a third aspect, a computer device is provided, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer instructions executable by the at least one processor to enable the at least one processor to perform the method referred to in the first aspect above.
In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored, wherein the computer instructions are configured to cause a computer to perform the method of the first aspect.
According to the technical content provided by the embodiment of the application, the matching score of the lane line is calculated by acquiring each positioning data point of the lane line detected by the lane line sensing module of the vehicle and each positioning data point of the corresponding high-precision map lane line, so that the lane line detected by the lane line sensing module is evaluated according to the matching score, and the evaluation result is determined. Because the high-precision map is a three-dimensional image, the lane line data corresponding to the high-precision map and the lane line data of the lane line sensing module are three-dimensional data, and the lane line data of the high-precision map and the lane line data of the lane line sensing module are matched, the problems of error distortion, marking resource waste and the like caused by marking the lane line under a two-dimensional image coordinate system obtained by a camera and projecting the lane line under the three-dimensional vehicle coordinate system for lane line matching in the prior art are solved.
The method can accurately and efficiently evaluate the detection result of the lane line, improve the accuracy of lane line evaluation and save marking resources. By acquiring the lane line data of the high-precision map and matching the lane line data of the lane line sensing module, the problems of error distortion, marking resource waste and the like caused by marking the lane line under a two-dimensional image coordinate system obtained by a camera and projecting the lane line under a three-dimensional vehicle coordinate system for lane line matching in the prior art are solved.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for evaluating lane line detection according to an embodiment;
FIG. 2 is a diagram illustrating an evaluation method for lane marking detection in one embodiment;
FIG. 3 is a block diagram showing an example of the structure of an evaluation device for lane line detection;
FIG. 4 is a schematic block diagram of a computer apparatus in one embodiment.
Detailed Description
The present application will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
Fig. 1 is a flowchart of an evaluation method for lane line detection according to an embodiment of the present disclosure, and as shown in fig. 1, the method may include the following steps:
step 101: and acquiring each positioning data point of any lane line detected by a lane line sensing module of the vehicle, and taking each positioning data point of any lane line of the lane line sensing module as a first position point.
Specifically, the lane line sensing module is a basic module in automatic driving, and can detect and generate a three-dimensional lane line, and in the VCS vehicle coordinate system, any one of the lane lines detected by the lane line sensing module can be represented as y = f (x), and as shown in fig. 2, each positioning data point of the lane line y = f (x) detected by the lane line sensing module is (x 0, y 0), (x 1, y 1), (x 2, y 2), and the like. The first position point is a location data point such as (x 0, y 0), (x 1, y 1), and (x 2, y 2) of the lane line y = f (x).
Step 102: and acquiring each positioning data point of the lane line of the high-precision map corresponding to any lane line of the lane line sensing module, and taking each positioning data point corresponding to the high-precision map as a second position point.
Specifically, the high-precision map is a three-dimensional map, the three-dimensional lane line data of the high-precision map are acquired and matched with the three-dimensional lane lines of the lane line sensing module, and the problems that in the prior art, lane lines in a two-dimensional image coordinate system acquired by a camera need to be marked and projected to a three-dimensional vehicle coordinate system for lane line matching, error distortion, marking resource waste and the like are caused are solved. As shown in fig. 2, the lane line sensing module detects any lane line y = f (x), acquires each positioning data point A, B, C, D, E and the like of the lane line corresponding to y = f (x) on the high-precision map, and takes each positioning data point A, B, C, D, E and the like corresponding to the high-precision map as the second position point.
Step 103: a matching score of the lane line is calculated based on the first location point and the second location point.
Specifically, the first position point is each positioning data point of any lane line detected by the lane line sensing module, the second position point is a positioning data point of the high-precision map corresponding to the first position point, and the first position point and the second position point are in a corresponding relationship. Whether the first position point and the second position point are matched or not represents whether any lane line detected by the lane line sensing module is matched with the lane line of the high-precision map or not. The matching score of the lane line is calculated based on the first position point and the second position point, for example, the matching score of the lane line can be calculated through the average distance between the first position point and the second position point, and the matching score is used for representing the matching degree of any lane line detected by the lane line sensing module and the lane line of the high-precision map.
Step 104: and determining the evaluation result of any lane line detected by the lane line sensing module based on the matching score.
Specifically, the matching score is used to represent the matching degree of any lane line detected by the lane line sensing module with the lane line of the high-precision map, for example, the lower the matching score, the lower the matching degree, the higher the matching score, the higher the matching degree. The matching degree of any lane line detected by the lane line sensing module and the lane line of the high-precision map can be determined based on the matching score, so that the evaluation result of any lane line detected by the lane line sensing module is determined, and the detection result of the lane line sensing module is evaluated.
In some embodiments, determining the evaluation result of any lane line detected by the lane line sensing module based on the matching score in step 104 includes: when the matching score meets the set condition, determining that any lane line detected by the lane line sensing module is successfully matched; when the matching score does not meet the set condition, determining that any lane line detected by the lane line sensing module fails to be matched; wherein, the evaluation result comprises matching success and matching failure.
Specifically, the lane lines detected by the lane line sensing module are successfully matched and represent the lane lines of the matched high-precision map; the matching failure represents that the lane lines detected by the lane line sensing module do not have the lane lines of the matched high-precision map. When the matching score meets a set condition, for example, when the matching score reaches a set threshold, determining that any lane line detected by the lane line sensing module is successfully matched; when the matching score does not meet the set condition, for example, when the matching score does not reach the set threshold, it is determined that any lane line detected by the lane line sensing module fails to match. And according to the evaluation result, the matching is successful or failed, and the detection result of the lane line sensing module can be measured.
It can be seen that in the embodiment of the application, the matching score of the lane line is calculated by acquiring each positioning data point of the lane line detected by the lane line sensing module of the vehicle and each positioning data point of the corresponding high-precision map lane line, so that the lane line detected by the lane line sensing module is evaluated according to the matching score, and the evaluation result is determined. The method can accurately and efficiently evaluate the detection result of the lane line, improve the accuracy of lane line evaluation and save marking resources. By acquiring the lane line data of the high-precision map and matching the lane line data of the lane line sensing module, the problems of error distortion, marking resource waste and the like caused by marking the lane line under a two-dimensional image coordinate system obtained by a camera and projecting the lane line under a three-dimensional vehicle coordinate system for matching the lane line in the prior art are solved.
In some embodiments, calculating a matching score for the lane line based on the first location point and the second location point comprises: calculating the average distance between each first position point and the corresponding second position point; calculating the maximum distance in the distances from each first position point to the corresponding second position point; a matching score is calculated based on the average distance and the maximum distance.
Specifically, the average distance between each first position point and the corresponding second position point represents the distance of the lane line sensing module deviating from the lane line of the high-precision map. As shown in fig. 2, for high-precision map lane linesThe second location point includes A (x) a ,y a )、B(x b ,y b )、C(x c ,y c )、D(x d ,y d )、E(x e ,y e ) Calculating the distance between each first location point to the corresponding second location point, which may be denoted as d a ＝|y a -f(x a )|,d b ＝|y b -f(x b )|,...,d n ＝|y n -f(x n ) L. As shown in fig. 2, five points a (x) a ,y a )、B(x b ,y b )、C(x c ,y c )、D(x d ,y d )、E(x e ,y e ) On the high-precision map lane line, N =5 in this case. The average distance d between each first position point and the corresponding second position point can be obtained by the following formula avg And a maximum distance d max ：
Wherein N is the number of second location points, (x) i ,y i ) F (x) is the lane line detected by the lane line sensing module, d is the coordinates of each second position point avg Is the average distance, d max Is the maximum distance. A matching score is calculated based on the average distance and the maximum distance. The matching score is used for representing the matching degree of any lane line detected by the lane line sensing module and the lane line of the high-precision map, and understandably, if the average distance between each first position point and the corresponding second position point is larger, the matching degree of the lane line detected by the lane line sensing module and the lane line of the high-precision map is lower; and if the average distance between each first position point and the corresponding second position point is smaller, the matching degree of the lane line detected by the lane line sensing module and the lane line of the high-precision map is higher.
In some embodiments, calculating a match score based on the average distance and the maximum distance comprises: by MS = BS-k 1 *d avg -k 2 *d max Calculating the matching score by a formula; wherein MS is a matching score; BS is a benchmark score which is a constant; k is a radical of formula 1 And k 2 Is a constant; d avg Is the average distance; d is a radical of max Is the maximum distance.
Specifically, k 1 And k 2 The coefficients are respectively the preset average distance and the maximum distance, the reference score BS is a preset constant, and the size of the specific value is not limited in the present application. And substituting the average distance and the maximum distance between each first position point and the corresponding second position point into a formula to calculate the matching score. When the average distance or the maximum distance is larger, the matching score is lower; the smaller the average or maximum distance, the higher the matching score. The matching degree of any lane line detected by the lane line sensing module and the lane line of the high-precision map can be determined based on the matching score.
In some embodiments, the method for evaluating lane line detection provided in the embodiments of the present application further includes: and when any lane line detected by the lane line sensing module is successfully matched, calculating a matching index according to any lane line detected by the lane line sensing module and the corresponding lane line of the high-precision map, wherein the matching index comprises one or more of a detection distance, an average distance, a maximum distance and a maximum weighted distance.
Specifically, in step 104, the evaluation result of any lane line detected by the lane line sensing module is determined based on the matching score, and when the matching score satisfies the set condition, it is determined that any lane line detected by the lane line sensing module is successfully matched. And when any lane line detected by the lane line sensing module is successfully matched, calculating a matching index according to any lane line detected by the lane line sensing module and the corresponding lane line of the high-precision map, wherein the matching index comprises one or more of a detection distance, an average distance, a maximum distance and a maximum weighted distance. The matching index is used for measuring the matching effect of the lane line.
According to the embodiment of the application, when any lane line detected by the lane line sensing module is successfully matched, the matching index is calculated according to the lane line detected by the lane line sensing module and the corresponding lane line of the high-precision map, the matching index comprises one or more of a detection distance, an average distance, a maximum distance and a maximum weighted distance, the matching effect can be measured from different dimensions, and therefore the matching accuracy is improved.
In some embodiments, the detected distance is indicative of a euclidean distance between two first location points; the average distance represents the average distance between each first position point and the corresponding second position point; the maximum distance represents the maximum value of the distance from each first position point to the corresponding second position point; the maximum weighted distance represents the maximum of the weighted distances between each first location point to the corresponding second location point.
Specifically, in the VCS vehicle coordinate system, any lane line detected by the lane line sensing module is represented in a form of y = f (x), and since the detected lane line is a curved line segment, two first position points of the lane line, i.e., E0 (x 0, y 0) and E1 (x 1, y 1), can be found as ends, and then the detection distance D can be defined as the euclidean distance between the two end points, where the formula is as follows:
the lane line detection distance index can be generally evaluated by the detection distance defined by the above method.
In addition, on the basis of the above-described embodiment, the average distance d between each first position point and the corresponding second position point may be obtained by the following formula avg And a maximum distance d max ：
On the basis of the above-described embodiment, the maximum weighted distance d between each first position point and the corresponding second position point can be obtained by the following formula mw ：
Wherein N is the number of second location points, (x) i ,y i ) F (x) is the lane line detected by the lane line sensing module as the coordinates of each second position point.
In some embodiments, the method for evaluating lane line detection provided by the embodiments of the present application further includes: acquiring the number of successfully matched lane lines and the number of unsuccessfully matched lane lines in all the lane lines detected by the lane line sensing module; and calculating the matching success rate based on the number of the successfully matched lane lines and the number of all the lane lines.
Specifically, in step 104, an evaluation result of any lane line detected by the lane line sensing module is determined based on the matching score, and when the matching score meets a set condition, it is determined that any lane line detected by the lane line sensing module is successfully matched; and when the matching score does not meet the set condition, determining that any lane line detected by the lane line sensing module fails to be matched. And further acquiring the number of successfully matched lane lines and the number of unsuccessfully matched lane lines in all the lane lines detected by the lane line sensing module, and calculating the matching success rate based on the number of successfully matched lane lines and the number of all the lane lines, thereby further measuring the effect of lane line detection.
According to the embodiment of the application, the matching score of the lane line is calculated by acquiring each positioning data point of the lane line detected by the lane line sensing module of the vehicle and each positioning data point of the corresponding high-precision map lane line, so that the lane line detected by the lane line sensing module is evaluated according to the matching score, and the evaluation result is determined. The method can accurately and efficiently evaluate the detection result of the lane line, improve the accuracy of lane line evaluation and save the labeling resource. By acquiring the lane line data of the high-precision map and matching the lane line data of the lane line sensing module, the problems of error distortion, marking resource waste and the like caused by marking the lane line under a two-dimensional image coordinate system obtained by a camera and projecting the lane line under a three-dimensional vehicle coordinate system for matching the lane line in the prior art are solved.
According to the embodiment of the application, when any lane line detected by the lane line sensing module is successfully matched, the matching index is calculated according to any lane line detected by the lane line sensing module and the corresponding lane line of the high-precision map, the matching effect can be measured from different dimensions, and therefore the matching accuracy is improved. The matching success rate is calculated by obtaining the number of the successfully matched lane lines and the number of the unsuccessfully matched lane lines in all the lane lines detected by the lane line sensing module, so that the effect and the accuracy of lane line detection are measured.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in a strict order unless explicitly stated in the application, and may be performed in other orders. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
Fig. 3 is a schematic structural diagram of an evaluation device for lane line detection according to an embodiment of the present application, and as shown in fig. 3, the device may include: a first obtaining module 301, a second obtaining module 302, a matching module 303, and an evaluating module 304. The main functions of each component module are as follows:
the first obtaining module 301: the system comprises a lane line sensing module, a first position point and a second position point, wherein the lane line sensing module is used for sensing the lane lines of a vehicle, and the first position point is used for acquiring each positioning data point of any lane line detected by the lane line sensing module of the vehicle and using each positioning data point of any lane line of the lane line sensing module as the first position point.
The second obtaining module 302: and the positioning data points are used for acquiring each positioning data point of a lane line corresponding to any lane line of the lane line sensing module of the high-precision map, and each positioning data point corresponding to the high-precision map is used as a second position point.
The matching module 303: for calculating a matching score for a lane line based on the first location point and the second location point.
The evaluation module 304: for determining an evaluation result of the any lane line detected by the lane line perception module based on the matching score.
In some embodiments, the matching module 303 is further configured to: calculating the average distance between each first position point and the corresponding second position point; calculating the maximum distance in the distances from each first position point to the corresponding second position point; calculating the matching score based on the average distance and the maximum distance.
In some embodiments, said calculating said match score based on said average distance and said maximum distance comprises: by MS = BS-k 1 *d avg -k 2 *d max Calculating the matching score by a formula; wherein MS is a matching score; BS is a benchmark score which is a constant; k is a radical of 1 And k 2 Is a constant; d avg Is the average distance; d is a radical of max Is the maximum distance.
In some embodiments, the evaluation module 304 is further configured to: when the matching score meets a set condition, determining that the matching of any lane line detected by the lane line sensing module is successful; when the matching score does not meet a set condition, determining that the matching of any lane line detected by the lane line sensing module fails; wherein the evaluation result comprises the matching success and the matching failure.
In some embodiments, the evaluation apparatus for lane line detection provided by the embodiment of the present application further includes an index calculation module 305: and the matching index calculation module is used for calculating a matching index according to the any lane line detected by the lane line sensing module and the corresponding lane line of the high-precision map when the any lane line detected by the lane line sensing module is successfully matched, wherein the matching index comprises one or more of a detection distance, an average distance, a maximum distance and a maximum weighted distance.
In some embodiments, the detected distance characterizes a euclidean distance between two first location points; the average distance represents the average distance between each first position point and the corresponding second position point; the maximum distance represents the maximum value of the distance from each first position point to the corresponding second position point; the maximum weighting distance represents the maximum value of the weighting distance between each first position point and the corresponding second position point.
In some embodiments, the device for evaluating lane line detection provided in the embodiments of the present application further includes a success rate calculation module 306: the lane line sensing module is used for acquiring the number of lane lines which are successfully matched and the number of lane lines which are failed to be matched in all the lane lines detected by the lane line sensing module; and calculating the matching success rate based on the number of the successfully matched lane lines and the number of all the lane lines.
According to the specific embodiment provided by the application, the technical scheme provided by the application can have the following advantages:
the method comprises the steps of calculating the matching score of the lane line by acquiring each positioning data point of the lane line detected by a lane line sensing module of the vehicle and each positioning data point of the corresponding high-precision map lane line, evaluating the lane line detected by the lane line sensing module according to the matching score, and determining an evaluation result. The method can accurately and efficiently evaluate the detection result of the lane line, improve the accuracy of lane line evaluation and save marking resources. By acquiring the lane line data of the high-precision map and matching the lane line data of the lane line sensing module, the problems of error distortion, marking resource waste and the like caused by marking the lane line under a two-dimensional image coordinate system obtained by a camera and projecting the lane line under a three-dimensional vehicle coordinate system for matching the lane line in the prior art are solved.
The same and similar parts among the various embodiments are referred to each other, and each embodiment focuses on differences from other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should be noted that, in the embodiments of the present application, the use of user data may be involved, and in practical applications, the user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations, under the condition of meeting the requirements of applicable laws and regulations in the country (for example, the user explicitly agrees, the user is informed, the user explicitly authorizes, etc.).
According to an embodiment of the present application, a computer device and a computer-readable storage medium are also provided. The application also provides a computer device comprising at least one processor, and a memory communicatively coupled to the at least one processor; wherein the memory stores computer instructions executable by the at least one processor, the computer instructions being executable by the at least one processor to enable the at least one processor to perform the method for assessing lane marking detection as described in any of the above embodiments.
As shown in fig. 4, a block diagram of a computer device according to an embodiment of the present application is shown. Computer apparatus is intended to represent various forms of digital computers or mobile devices. Which may include desktop computers, laptop computers, workstations, personal digital assistants, servers, mainframe computers, and other suitable computers. The mobile device may include a tablet, smartphone, wearable device, and the like.
As shown in fig. 4, the computer apparatus 400 includes a computing unit 401, a ROM 402, a RAM 403, a bus 404, and an input/output (I/O) interface 405, the computing unit 401, the ROM 402, and the RAM 403 being connected to each other via the bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The calculation unit 401 may execute various processes in the method embodiments of the present application according to computer instructions stored in a Read Only Memory (ROM) 402 or computer instructions loaded from a storage unit 408 into a Random Access Memory (RAM) 403. Computing unit 401 may be a variety of general and/or special purpose processing components with processing and computing capabilities. The computing unit 401 may include, but is not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. In some embodiments, the methods provided by embodiments of the present application may be implemented as a computer software program tangibly embodied in a computer-readable storage medium, such as storage unit 408.
The RAM 403 may also store various programs and data necessary for the operation of the device 400. Part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409.
An input unit 406, an output unit 407, a storage unit 408 and a communication unit 409 in the computer device 400 may be connected to the I/O interface 405. The input unit 406 may be, for example, a keyboard, a mouse, a touch screen, a microphone, or the like; the output unit 407 may be, for example, a display, a speaker, an indicator light, or the like. The device 400 is capable of exchanging information, data, etc. with other devices via the communication unit 409.
It should be noted that the device may also include other components necessary to achieve proper operation. It may also contain only the components necessary to implement the solution of the present application and not necessarily all of the components shown in the figures.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof.
Computer instructions for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer instructions may be provided to the computing unit 401 such that the computer instructions, when executed by the computing unit 401 such as a processor, cause the steps involved in the method embodiments of the present application to be performed.
The present application further provides a computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the method for evaluating lane line detection according to any of the above embodiments.
The computer-readable storage medium provided herein may be a tangible medium that may contain, or store, computer instructions for performing the steps involved in the method embodiments of the present application. The computer readable storage medium may include, but is not limited to, storage media in the form of electronic, magnetic, optical, electromagnetic, and the like.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An evaluation method for lane line detection, the method comprising:
acquiring each positioning data point of any lane line detected by a lane line sensing module of a vehicle, and taking each positioning data point of any lane line of the lane line sensing module as a first position point;
acquiring each positioning data point of a lane line of a high-precision map corresponding to any lane line of the lane line sensing module, and taking each positioning data point corresponding to the high-precision map as a second position point;
calculating a matching score of a lane line based on the first location point and the second location point;
determining an evaluation result of the any lane line detected by the lane line perception module based on the matching score.
2. The method of claim 1, wherein the calculating a lane line matching score based on the first location point and the second location point comprises:
calculating the average distance between each first position point and the corresponding second position point;
calculating the maximum distance in the distances from each first position point to the corresponding second position point;
calculating the matching score based on the average distance and the maximum distance.
3. The method of evaluating lane line detection according to claim 2, wherein said calculating the matching score based on the average distance and the maximum distance comprises:
by MS = BS-k 1 *d avg -k 2 *d max Calculating the matching score by a formula;
wherein MS is a matching score; BS is a benchmark score which is a constant; k is a radical of 1 And k 2 Is a constant; d avg Is the average distance; d is a radical of max Is the maximum distance.
4. The method according to claim 1, wherein the determining the evaluation result of any lane line detected by the lane line sensing module based on the matching score includes:
when the matching score meets a set condition, determining that the matching of any lane line detected by the lane line sensing module is successful;
when the matching score does not meet a set condition, determining that any lane line detected by the lane line sensing module fails to be matched;
wherein the evaluation result comprises the matching success and the matching failure.
5. The method of evaluating lane line detection according to claim 4, further comprising:
when the lane line sensing module detects that any lane line is successfully matched, a matching index is calculated according to the lane line detected by the lane line sensing module and the corresponding lane line of the high-precision map, wherein the matching index comprises one or more of a detection distance, an average distance, a maximum distance and a maximum weighted distance.
6. The method of claim 5, wherein the detected distance is indicative of a Euclidean distance between two first location points;
the average distance represents the average distance between each first position point and the corresponding second position point;
the maximum distance represents the maximum value of the distance from each first position point to the corresponding second position point;
the maximum weighted distance represents the maximum of the weighted distances between each first location point and the corresponding second location point.
7. The method of evaluating lane line detection according to claim 4, further comprising:
acquiring the number of successfully matched lane lines and the number of unsuccessfully matched lane lines in all the lane lines detected by the lane line sensing module;
and calculating the matching success rate based on the number of the lane lines which are successfully matched and the number of all the lane lines.
8. An evaluation device for lane line detection, the device comprising:
a first acquisition module: the system comprises a lane line sensing module, a first position point and a second position point, wherein the lane line sensing module is used for sensing lane lines of vehicles;
a second obtaining module: the system comprises a lane line sensing module, a lane line positioning module, a second position point and a third position point, wherein the lane line sensing module is used for sensing a lane line of a high-precision map;
a matching module: a matching score for calculating a lane line based on the first location point and the second location point;
an evaluation module: and the evaluation result is used for determining the any lane line detected by the lane line perception module based on the matching score.
9. A computer device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer instructions executable by the at least one processor to cause the at least one processor to perform the method of any one of claims 1-7.
10. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211327574.0A CN115620254A (en) | 2022-10-27 | 2022-10-27 | Method, device, equipment and storage medium for evaluating lane line detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211327574.0A CN115620254A (en) | 2022-10-27 | 2022-10-27 | Method, device, equipment and storage medium for evaluating lane line detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115620254A true CN115620254A (en) | 2023-01-17 |
Family
ID=84876963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211327574.0A Pending CN115620254A (en) | 2022-10-27 | 2022-10-27 | Method, device, equipment and storage medium for evaluating lane line detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115620254A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117490728A (en) * | 2023-12-28 | 2024-02-02 | 合众新能源汽车股份有限公司 | Lane line positioning fault diagnosis method and system |
-
2022
- 2022-10-27 CN CN202211327574.0A patent/CN115620254A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117490728A (en) * | 2023-12-28 | 2024-02-02 | 合众新能源汽车股份有限公司 | Lane line positioning fault diagnosis method and system |
| CN117490728B (en) * | 2023-12-28 | 2024-04-02 | 合众新能源汽车股份有限公司 | Lane line positioning fault diagnosis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766809B (en) | Electronic device, bill information identification method, and computer-readable storage medium | |
| EP3690700A1 (en) | Image similarity calculation method and device, and storage medium | |
| US9092697B2 (en) | Image recognition system and method for identifying similarities in different images | |
| CN111078908A (en) | Data annotation detection method and device | |
| JP2018524734A (en) | System for recognizing input of multiple objects, method and product therefor | |
| US8458645B2 (en) | Electronic device and method for checking layout of printed circuit board | |
| CN116168041B (en) | Real-time detection method and system applied to laminating device | |
| CN111126268B (en) | Key point detection model training method and device, electronic equipment and storage medium | |
| CN109583505A (en) | A kind of object correlating method, device, equipment and the medium of multisensor | |
| US20150234782A1 (en) | Calculation device and method, and computer program product | |
| CN115620254A (en) | Method, device, equipment and storage medium for evaluating lane line detection | |
| US20210192965A1 (en) | Question correction method, device, electronic equipment and storage medium for oral calculation questions | |
| CN111597993B (en) | Data processing method and device | |
| CN113283233A (en) | Text error correction method and device, electronic equipment and storage medium | |
| CN110162362B (en) | Dynamic control position detection and test method, device, equipment and storage medium | |
| CN114415931A (en) | Electronic whiteboard display method and device, electronic whiteboard and storage medium | |
| JP2017049997A (en) | Apparatus and method for document image orientation detection | |
| CN108153963B (en) | Method for checking connector connection layer number in PCB design | |
| CN112698421A (en) | Evaluation method, device, equipment and storage medium for obstacle detection | |
| US20230096697A1 (en) | Object detection model training apparatus, method, and non-transitory computer readable storage medium thereof | |
| US20240078691A1 (en) | Model alignment method | |
| CN115273116A (en) | Table detection and identification method, device, equipment and storage medium | |
| CN113239717B (en) | Method, apparatus, device, medium and program product for processing topics | |
| US12020446B2 (en) | Offset object alignment operations | |
| CN112528848B (en) | Evaluation method, device, equipment and storage medium for obstacle detection |
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 |