CN110045354B - Method and device for evaluating radar performance - Google Patents
Method and device for evaluating radar performance Download PDFInfo
- Publication number
- CN110045354B CN110045354B CN201910319623.8A CN201910319623A CN110045354B CN 110045354 B CN110045354 B CN 110045354B CN 201910319623 A CN201910319623 A CN 201910319623A CN 110045354 B CN110045354 B CN 110045354B
- Authority
- CN
- China
- Prior art keywords
- test
- radar
- points
- scanning
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/497—Means for monitoring or calibrating
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application discloses a method and a device for evaluating radar performance. The method comprises the steps of obtaining image data corresponding to a radar to be tested, wherein the image data is obtained by scanning a test material by the radar to be tested; performing characteristic analysis on the image data to determine an index value corresponding to a test index; calculating the test score of the radar to be tested according to the index value; and evaluating the performance of the radar to be tested according to the test score. The method and the device solve the problem that related single-line laser radar evaluation is unscientific and has no theoretical basis.
Description
Technical Field
The application relates to the technical field of robots, in particular to a method and a device for evaluating radar performance.
Background
In the field of intelligent robot technology, the application of single-line laser radar is very wide. When a user selects a single-line laser radar, the quality of the single-line laser radar is generally evaluated based on hardware parameters given by a laser radar manufacturer and the using effect in the trial process. The evaluation mode is mainly to judge the quality of the single-line laser radar according to the noise by the subjective method, and a scientific method and a theoretical basis are not used as a support to evaluate the single-line laser radar.
Disclosure of Invention
The main purpose of the present application is to provide a method for evaluating radar performance, so as to solve the problem that the related evaluation of a single-line laser radar is unscientific and has no theoretical basis.
In order to achieve the above object, according to a first aspect of the present application, a method of radar performance evaluation is provided.
The method for evaluating the performance of the radar comprises the following steps:
acquiring image data corresponding to a radar to be tested, wherein the image data is obtained by scanning a test material by the radar to be tested;
performing characteristic analysis on the image data to determine an index value corresponding to a test index;
calculating the test score of the radar to be tested according to the index value;
and evaluating the performance of the radar to be tested according to the test score.
Further, the performing feature analysis on the image data and determining an index value corresponding to the test index includes:
extracting a preset number of image frames in the image data and performing feature analysis on the preset number of image frames;
and respectively determining the material type recognition rate, the close range noise point occupation ratio, the effective point occupation ratio and the mean square error of straight line fitting of the radar to be detected according to the analysis result of the image frame.
Further, the performing feature analysis on a preset number of image frames includes:
extracting all scanning points of a test board from a preset number of image frames, wherein all the scanning points comprise line segment characteristics and noise points between a radar to be tested and the test board, and the test board is formed by multiple test materials;
and filtering the noise points to obtain effective scanning points of the test board.
Further, the filtering the noise to obtain the effective scanning point of the test board includes:
removing isolated noise points in the noise points;
performing linear fitting on other scanning points except the isolated noise points to obtain a testing line segment corresponding to the testing board;
classifying scanning points outside the test line segment according to the test line segment to obtain a long-distance noise point and a short-distance noise point;
and removing the long-distance noise points to obtain effective scanning points.
Further, the determining the index value corresponding to the test index includes:
calculating to obtain the short-distance noise ratio according to the number of the short-distance noise points and the theoretical scanning point number of the test board;
calculating to obtain the effective point ratio according to the number of the effective scanning points and the theoretical scanning point number of the test board;
calculating the mean square error of straight line fitting according to the effective scanning points and the new testing line section determined by re-fitting the effective scanning points;
and determining the material type recognition rate according to the effective scanning point corresponding to each test material on the test board and the corresponding theoretical scanning point.
Further, the determining the material type recognition rate according to the effective scanning point and the corresponding theoretical scanning point corresponding to each test material on the test board includes:
dividing the new test line segment according to different test materials, and calculating an effective scanning point corresponding to each test material;
and calculating the material type recognition rate according to the effective scanning point corresponding to each test material and the theoretical scanning point corresponding to each test material.
Further, the calculating the test score of the radar to be tested according to the index value includes:
and performing combined calculation on the material type identification rate, the close-range noise point ratio, the effective point ratio and the mean square error of straight line fitting according to preset weights to obtain the test score of the radar to be tested.
In order to achieve the above object, according to a second aspect of the present application, there is provided an apparatus for radar performance evaluation.
The device for evaluating the performance of the radar comprises:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring image data corresponding to a radar to be tested, and the image data is obtained by scanning a test material by the radar to be tested;
the determining unit is used for carrying out feature analysis on the image data and determining an index value corresponding to the test index;
the calculation unit is used for calculating the test score of the radar to be tested according to the index value;
and the evaluation unit is used for evaluating the performance of the radar to be tested according to the test score.
Further, the determining unit includes:
the extraction module is used for extracting a preset number of image frames in the image data and performing feature analysis on the preset number of image frames;
and the determining module is used for respectively determining the material type recognition rate, the short-distance noise point occupation ratio, the effective point occupation ratio and the mean square error of straight line fitting of the radar to be detected according to the analysis result of the image frame.
Further, the extraction module is configured to:
extracting all scanning points of a test board from a preset number of image frames, wherein all the scanning points comprise line segment characteristics and noise points between a radar to be tested and the test board, and the test board is formed by multiple test materials;
and filtering the noise points to obtain effective scanning points of the test board.
Further, the extraction module is further configured to:
removing isolated noise points in the noise points;
performing linear fitting on other scanning points except the isolated noise points to obtain a testing line segment corresponding to the testing board;
classifying scanning points outside the test line segment according to the test line segment to obtain a long-distance noise point and a short-distance noise point;
and removing the long-distance noise points to obtain effective scanning points.
Further, the determining module is configured to:
calculating to obtain the short-distance noise ratio according to the number of the short-distance noise points and the theoretical scanning point number of the test board;
calculating to obtain the effective point ratio according to the number of the effective scanning points and the theoretical scanning point number of the test board;
calculating the mean square error of straight line fitting according to the effective scanning points and the new testing line section determined by re-fitting the effective scanning points;
and determining the material type recognition rate according to the effective scanning point corresponding to each test material on the test board and the corresponding theoretical scanning point.
Further, the determining module is further configured to:
dividing the new test line segment according to different test materials, and calculating an effective scanning point corresponding to each test material;
and calculating the material type recognition rate according to the effective scanning point corresponding to each test material and the theoretical scanning point corresponding to each test material.
Further, the computing unit is configured to:
and performing combined calculation on the material type identification rate, the close-range noise point ratio, the effective point ratio and the mean square error of straight line fitting according to preset weights to obtain the test score of the radar to be tested.
Further, according to a third aspect of the present application, there is provided a computer-readable storage medium storing computer code which, when executed, performs the method of radar performance evaluation as described in the first aspect above.
Further, according to a fourth aspect of the present application, there is provided a computer apparatus comprising:
one or more processors;
a memory for storing one or more computer programs;
the one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method of radar performance profiling as described in the first aspect above.
In the embodiment of the application, the method and the device for evaluating the performance of the radar can determine the index value corresponding to the test index by analyzing the image data scanned by the radar to be tested, and then calculate the test score of the radar to be tested according to the index value.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a flow diagram of a method for radar performance evaluation according to one embodiment of the present application;
FIG. 2 is a flow diagram of a method for radar performance evaluation according to another embodiment of the present application;
FIG. 3 is a block diagram of the components of an apparatus for radar performance evaluation according to one embodiment of the present application;
FIG. 4 is a block diagram of the radar performance evaluation apparatus according to another embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present application, a method for evaluating radar performance is provided, as shown in fig. 1, the method includes steps S101 to S104 as follows:
s101, obtaining image data corresponding to the radar to be detected.
The image data is obtained by scanning the test material by the radar to be tested. The radar to be tested in the embodiment of the invention mainly refers to a laser radar (such as a single line laser radar), and in an actual application scene, the types of materials to be scanned by the laser radar are various, so that in order to evaluate the performance of the laser radar more comprehensively, multiple types of test materials need to be set for the corresponding test materials, and the test materials comprise various materials, different colors, different lines and other materials with different characteristics, which are usually encountered by the laser radar in the scanning process. In order to more conveniently and rapidly analyze the image data, preferably, different types of test materials are grouped, and different groups of test materials form different test boards, so that the radar to be tested scans the different test boards.
In order to avoid the error of evaluation caused by the fact that materials at two ends of the test board cannot be identified, two pieces of common materials which are consistent in shape and size and can be identified are placed on two sides of the test board in the measuring process.
And S102, performing characteristic analysis on the image data to determine an index value corresponding to the test index.
In this embodiment, the test indexes include a plurality of test indexes for evaluating the scanning result of the radar to be tested, and the test indexes are defined by comprehensively considering whether the radar can work in a complex environment, whether the radar is mistakenly identified in an unfamiliar environment, the accuracy of radar scanning, the accuracy of radar feature depiction on obstacles, and other factors. The performance of the radar can be comprehensively and scientifically evaluated by the determined test index.
The characteristic analysis of the image data is to perform characteristic analysis of the scanning points in the image data, and specifically includes analyzing the position and the number of the scanning points, the linear law of the scanning points and other characteristics, and then determining the index value of the test index according to the analysis result.
And S103, calculating the test score of the radar to be tested according to the index value.
Step S102 shows that the test index includes multiple indexes, and index values of all the test indexes need to be considered comprehensively when calculating the test score of the radar to be tested, and specifically, a suitable calculation method may be selected according to the influence degree of different test indexes on radar performance evaluation to obtain the test score of the radar to be tested.
And S104, evaluating the performance of the radar to be tested according to the test score.
Specifically, the radar performance may be divided into multiple levels, with different levels corresponding to different test score ranges. Therefore, after the test score of the radar to be tested is determined, the test score can be matched with the test score range, the test score range corresponding to the test score of the radar to be tested is determined, then the performance grade of the radar to be tested is determined according to the corresponding relation between the test score range and the performance grade, and finally the performance evaluation of the radar to be tested is completed. The grade division can be freely defined according to actual needs, such as three grades of good, good and poor or A, B, C, D four grades.
From the above description, it can be seen that, in the method for evaluating radar performance in the embodiment of the present application, the index value corresponding to the test index can be determined by analyzing the image data scanned by the radar to be tested, and then the test score of the radar to be tested is calculated according to the index value
According to another embodiment of the present application, there is provided a method for radar performance evaluation, as shown in fig. 2, the method including:
s201, obtaining image data corresponding to the radar to be detected.
The implementation of this step is the same as that in step S101 in fig. 1, and is not described here again.
S202, extracting a preset number of image frames in the image data and carrying out feature analysis on the preset number of image frames.
The image data includes all image frames of all test boards scanned by the radar to be detected in the scanning process, and a preset number of image frames of each test board are respectively extracted, and the preset number can be freely set by a user according to actual requirements, for example, the preset number can be set to be 10 or other values.
The specific process of feature analysis comprises the following steps:
firstly, all scanning points of the test board are extracted from a preset number of image frames, and all the scanning points comprise scanning points contained in line segment characteristics and noise points between a radar to be tested and the test board.
Secondly, the noise point is filtered to obtain the effective scanning point of the test board.
1) Removing isolated noise points in the noise points;
the isolated noise point is a noise point, and the distance between the isolated noise point and two adjacent scanning points is larger than a first preset threshold value. The first preset threshold is a preset value, and may be other values such as 2mm and 3 mm.
2) Performing linear fitting on other scanning points except the isolated noise points to obtain a testing line segment corresponding to the testing board;
principle of straight line fitting: a straight line is found for the discrete points, passing through as many points as possible, the straight line representing a linear law between data points.
The process of line fitting in this embodiment is specifically: and performing linear fitting on other scanning points except the isolated noise points according to a linear fitting method to obtain a testing line segment corresponding to the testing board. The straight line fitting method can be least square fitting, gradient descent method, gauss-newton, column-horse algorithm and other straight line fitting methods.
3) Classifying scanning points outside the test line segment according to the test line segment to obtain a long-distance noise point and a short-distance noise point;
the obtained test line segment can not pass through all the scanning points, and the scanning points outside the test line segment are divided into long-distance noise points and short-distance noise points according to the distance between the scanning points which are not on the test line segment and the test line segment, wherein the long-distance noise points are the scanning points of which the distance between the long-distance noise points and the test line segment is greater than a second preset threshold value, and the short-distance noise points are the scanning points of which the distance between the short-distance noise points and the test line segment is not greater than the second preset threshold value.
4) And removing the long-distance noise points to obtain effective scanning points.
The effective scanning points include scanning points on the test line segment and close-range noise points.
S203, respectively determining the material type recognition rate, the close-range noise point occupation ratio, the effective point occupation ratio and the mean square error of straight line fitting of the radar to be detected.
The material type recognition rate, the near-range noise ratio, the effective point ratio, and the mean square error of the straight line fitting are the test indexes described in fig. 1. The four test indexes are selected according to the following: the material type identification rate is crucial to the universality of application scenes of intelligent equipment (such as a robot) applying laser radar, and the number of the identified material types directly determines whether the intelligent equipment can work in a complex environment; the close-range noise point can cause the false recognition of the obstacle for the intelligent equipment in the unknown environment; the effective point ratio directly reflects the data accuracy of the laser radar; the mean square error of the straight line fitting reflects the accuracy of the radar for describing the characteristics of the obstacle, and the intelligent equipment applying the laser radar establishes a map, so that the relation is great.
First, a close range noise floor ratio and a significant point floor ratio are calculated.
Calculating according to the number of the close-distance noise points and the theoretical scanning point number of the test board to obtain the close-distance noise point ratio: firstly, calculating the number of the close-range noise points obtained in the step; secondly, calculating the theoretical scanning point number of the test board according to the resolution of the radar; and calculating the ratio of the number of the close-range noise points to the theoretical scanning point number of the test board to obtain the close-range noise point ratio.
Secondly, calculating according to the number of the effective scanning points and the theoretical scanning points of the test board to obtain the effective point ratio: and calculating the ratio of the number of the effective scanning points determined in the step S202 to the theoretical scanning point number of the test board to obtain the effective point ratio.
Fourth, the mean square error of the straight line fit is calculated.
And (3) performing straight line fitting again according to the effective scanning points determined in the step (S202) to obtain a new test line segment, calculating the distance between each effective scanning point and the new test line segment, and calculating the straight line fitting mean square error according to the distances between all the effective scanning points and the new test line segment.
Fifth, the material kind identification rate is calculated.
Dividing the new test line segment according to different test materials, and calculating an effective scanning point corresponding to each test material: in this embodiment, the lengths and widths of different test materials are the same, so that the new test line segment is divided equally according to the number of the test materials, so that the test line segments corresponding to different test materials can be distinguished, and then the number of effective scanning points corresponding to each test material is counted according to the material division points of the new test line segment.
Calculating the material type recognition rate according to the effective scanning point corresponding to each test material and the theoretical scanning point corresponding to each test material: calculating the ratio of the number of the effective scanning points corresponding to each test material to the number of the theoretical scanning points corresponding to each test material; comparing the ratio with a preset ratio; if the ratio is larger than the preset ratio, the test material is considered to be identifiable; if the ratio is less than or equal to the preset ratio, the test material is considered to be unidentifiable; and calculating the ratio of the number of the identifiable test materials to the number of all the test materials to obtain the material type identification rate. The number of the theoretical scanning points of each test material can be calculated according to the coordinates of the segmentation points and the number of the theoretical scanning points of the test board.
And S204, performing combined calculation on the material type identification rate, the short-distance noise point ratio, the effective point ratio and the mean square error of straight line fitting according to preset weights to obtain the test score of the radar to be tested.
The calculation formula is as follows:
test score λ1Ratio of effective points + λ2Material species recognition rate + λ3Near distance noise ratio + lambda4Mean square error of straight line fitting
Wherein λ1、λ2、λ3、λ4Respectively obtaining weight values corresponding to the mean square error of the effective point ratio, the material type identification rate, the close-range noise point ratio and the straight line fitting, wherein lambda is1、λ2Is a value greater than zero, λ3、λ4A value less than zero.
And S205, evaluating the performance of the radar to be tested according to the test score.
The implementation of this step is the same as that in step S104 in fig. 1, and is not described here again.
In addition, in the process of evaluating the performance of the radar to be measured, in order to avoid the influence of the distance and the angle on the evaluation result, evaluation items with different distances (such as 0.8 m to 1.6 m) and different angles (such as vertical and positive and negative 45-degree angles) are added, and the specific evaluation process is the same as the method for evaluating the performance of the radar in the above-mentioned fig. 1 and fig. 2, and is not repeated here. Finally, test scores and corresponding performance grades under different distances and different angles are obtained and are used as reference standards for radar performance evaluation.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present application, there is also provided an apparatus for performing radar performance evaluation according to the method described in fig. 1 and fig. 2, as shown in fig. 3, the apparatus includes:
the acquiring unit 31 is configured to acquire image data corresponding to a radar to be tested, where the image data is obtained by scanning a test material by the radar to be tested;
a determining unit 32, configured to perform feature analysis on the image data, and determine an index value corresponding to a test index;
a calculating unit 33, configured to calculate a test score of the radar to be tested according to the index value;
and the evaluation unit 34 is used for evaluating the performance of the radar to be tested according to the test score.
The radar performance evaluation device can determine the index value corresponding to the test index by analyzing the image data scanned by the radar to be tested, and then calculate the test score of the radar to be tested according to the index value.
Further, as shown in fig. 4, the determining unit 32 includes:
an extracting module 321, configured to extract a preset number of image frames in the image data and perform feature analysis on the preset number of image frames;
and the determining module 322 is configured to determine a material type identification rate, a short-distance noise ratio, an effective point ratio, and a mean square error of straight line fitting of the radar to be detected according to an analysis result of the image frame.
Further, as shown in fig. 4, the extracting module 321 is configured to:
extracting all scanning points of a test board from a preset number of image frames, wherein all the scanning points comprise line segment characteristics and noise points between a radar to be tested and the test board, and the test board is formed by multiple test materials;
and filtering the noise points to obtain effective scanning points of the test board.
Further, as shown in fig. 4, the extracting module 321 is further configured to:
removing isolated noise points in the noise points;
performing linear fitting on other scanning points except the isolated noise points to obtain a testing line segment corresponding to the testing board;
classifying scanning points outside the test line segment according to the test line segment to obtain a long-distance noise point and a short-distance noise point;
and removing the long-distance noise points to obtain effective scanning points.
Further, as shown in fig. 4, the determining module 322 is configured to:
calculating to obtain the short-distance noise ratio according to the number of the short-distance noise points and the theoretical scanning point number of the test board;
calculating to obtain the effective point ratio according to the number of the effective scanning points and the theoretical scanning point number of the test board;
calculating the mean square error of straight line fitting according to the effective scanning points and the new testing line section determined by re-fitting the effective scanning points;
and determining the material type recognition rate according to the effective scanning point corresponding to each test material on the test board and the corresponding theoretical scanning point.
Further, as shown in fig. 4, the determining module 322 is further configured to:
dividing the new test line segment according to different test materials, and calculating an effective scanning point corresponding to each test material;
and calculating the material type recognition rate according to the effective scanning point corresponding to each test material and the theoretical scanning point corresponding to each test material.
Further, the calculating unit 33 is configured to:
and performing combined calculation on the material type identification rate, the close-range noise point ratio, the effective point ratio and the mean square error of straight line fitting according to preset weights to obtain the test score of the radar to be tested.
Specifically, the specific process of implementing the functions of each module in the apparatus in the embodiment of the present application may refer to the related description in the method embodiment, and is not described herein again.
A computer readable storage medium having stored thereon computer code which, when executed, performs a method of radar performance profiling as described in fig. 1 or fig. 2.
A computer device, the computer device comprising: one or more processors;
a memory for storing one or more computer programs;
the one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method of radar performance profiling as described in fig. 1 or fig. 2.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (9)
1. A method for radar performance evaluation, the method comprising:
acquiring image data corresponding to a radar to be tested, wherein the image data is obtained by scanning a test material by the radar to be tested;
performing characteristic analysis on the image data to determine an index value corresponding to a test index;
calculating the test score of the radar to be tested according to the index value;
evaluating the performance of the radar to be tested according to the test score;
the performing feature analysis on the image data and determining an index value corresponding to a test index includes:
extracting a preset number of image frames in the image data and performing feature analysis on the preset number of image frames;
and respectively determining the material type recognition rate, the close range noise point occupation ratio, the effective point occupation ratio and the mean square error of straight line fitting of the radar to be detected according to the analysis result of the image frame.
2. The method for radar performance evaluation according to claim 1, wherein the performing feature analysis on a preset number of image frames comprises:
extracting all scanning points of a test board from a preset number of image frames, wherein all the scanning points comprise line segment characteristics and noise points between a radar to be tested and the test board, and the test board is formed by multiple test materials;
and filtering the noise points to obtain effective scanning points of the test board.
3. The method for radar performance evaluation according to claim 2, wherein the filtering the noise points to obtain the valid scan points of the test board comprises:
removing isolated noise points in the noise points;
performing linear fitting on other scanning points except the isolated noise points to obtain a testing line segment corresponding to the testing board;
classifying scanning points outside the test line segment according to the test line segment to obtain a long-distance noise point and a short-distance noise point;
and removing the long-distance noise points to obtain effective scanning points.
4. The method for evaluating the performance of the radar according to claim 3, wherein the determining the index value corresponding to the test index comprises:
calculating to obtain the short-distance noise ratio according to the number of the short-distance noise points and the theoretical scanning point number of the test board;
calculating to obtain the effective point ratio according to the number of the effective scanning points and the theoretical scanning point number of the test board;
calculating the mean square error of straight line fitting according to the effective scanning points and the new testing line section determined by re-fitting the effective scanning points;
and determining the material type recognition rate according to the effective scanning point corresponding to each test material on the test board and the corresponding theoretical scanning point.
5. The method for evaluating radar performance of claim 4, wherein the determining the material type recognition rate according to the effective scanning point and the theoretical scanning point corresponding to each test material on the test board comprises:
dividing the new test line segment according to different test materials, and calculating an effective scanning point corresponding to each test material;
and calculating the material type recognition rate according to the effective scanning point corresponding to each test material and the theoretical scanning point corresponding to each test material.
6. The method for radar performance evaluation according to claim 5, wherein the calculating a test score of the radar to be tested according to the index value comprises:
and performing combined calculation on the material type identification rate, the close-range noise point ratio, the effective point ratio and the mean square error of straight line fitting according to preset weights to obtain the test score of the radar to be tested.
7. An apparatus for radar performance evaluation, the apparatus comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring image data corresponding to a radar to be tested, and the image data is obtained by scanning a test material by the radar to be tested;
the determining unit is used for carrying out feature analysis on the image data and determining an index value corresponding to the test index;
the calculation unit is used for calculating the test score of the radar to be tested according to the index value;
the evaluation unit is used for evaluating the performance of the radar to be tested according to the test score;
the performing feature analysis on the image data and determining an index value corresponding to a test index includes:
extracting a preset number of image frames in the image data and performing feature analysis on the preset number of image frames;
and respectively determining the material type recognition rate, the close range noise point occupation ratio, the effective point occupation ratio and the mean square error of straight line fitting of the radar to be detected according to the analysis result of the image frame.
8. A computer-readable storage medium storing computer code that, when executed, performs a method of radar performance evaluation as recited in any one of claims 1-6.
9. A computer device, the computer device comprising:
one or more processors;
a memory for storing one or more computer programs;
the one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method for radar performance profiling of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910319623.8A CN110045354B (en) | 2019-04-19 | 2019-04-19 | Method and device for evaluating radar performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910319623.8A CN110045354B (en) | 2019-04-19 | 2019-04-19 | Method and device for evaluating radar performance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110045354A CN110045354A (en) | 2019-07-23 |
| CN110045354B true CN110045354B (en) | 2021-05-11 |
Family
ID=67278116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910319623.8A Active CN110045354B (en) | 2019-04-19 | 2019-04-19 | Method and device for evaluating radar performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110045354B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240048A (en) * | 2021-11-15 | 2022-03-25 | 北京云迹科技股份有限公司 | Method, device, medium and equipment for evaluating performance of laser radar |
| CN114509744B (en) * | 2022-04-19 | 2022-07-26 | 苏州一径科技有限公司 | Method, device and equipment for evaluating range finding detection rate of laser radar |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5233415A (en) * | 1991-04-19 | 1993-08-03 | Kaman Aerospace Corporation | Imaging lidar employing transmitter referencing |
| CN108399643A (en) * | 2018-03-15 | 2018-08-14 | 南京大学 | A kind of outer ginseng calibration system between laser radar and camera and method |
| CN109031250A (en) * | 2018-06-12 | 2018-12-18 | 南京理工大学 | It is a kind of to emit quantitative detection system in servo-actuated laser radar performance room |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8483478B1 (en) * | 2010-01-11 | 2013-07-09 | Hrl Laboratories, Llc | Grammar-based, cueing method of object recognition, and a system for performing same |
| CN109597093A (en) * | 2018-11-14 | 2019-04-09 | 深圳市速腾聚创科技有限公司 | The parameter regulation means and device of laser radar |
-
2019
- 2019-04-19 CN CN201910319623.8A patent/CN110045354B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5233415A (en) * | 1991-04-19 | 1993-08-03 | Kaman Aerospace Corporation | Imaging lidar employing transmitter referencing |
| CN108399643A (en) * | 2018-03-15 | 2018-08-14 | 南京大学 | A kind of outer ginseng calibration system between laser radar and camera and method |
| CN109031250A (en) * | 2018-06-12 | 2018-12-18 | 南京理工大学 | It is a kind of to emit quantitative detection system in servo-actuated laser radar performance room |
Non-Patent Citations (2)
| Title |
|---|
| Evaluating the Lidar/HSI direct method for physics-based scene modeling;Ryan N. Givens et al.;《2014 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)》;20141016 * |
| 基于激光雷达的环境特征提取方法研究;于金霞 等;《计算机测量与控制》;20071125;第15卷(第11期);第1550-1552页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110045354A (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9147014B2 (en) | System and method for image selection of bundled objects | |
| Fernandes et al. | Pavement pathologies classification using graph-based features | |
| CN110045354B (en) | Method and device for evaluating radar performance | |
| CN107077735A (en) | Three dimensional object is recognized | |
| CN111598827A (en) | Appearance flaw detection method, electronic device and storage medium | |
| CN103674968A (en) | Method and device for evaluating machine vision original-value detection of exterior corrosion appearance characteristics of material | |
| CN111160451A (en) | Flexible material detection method and storage medium thereof | |
| CN109300119A (en) | Detection method, detection device and the terminal device in steel structure surface corrosion region | |
| CN107578021A (en) | Pedestrian detection method, apparatus and system based on deep learning network | |
| CN108280429A (en) | The nuclide identification method, apparatus and computer-readable medium of feature based peak match | |
| CN104198998B (en) | Clustering treatment based CFAR (Constant False Alarm Rate) detection method under non-uniform background | |
| CN108875184B (en) | Shale organic carbon content prediction method and device based on digital outcrop model | |
| CN102906851B (en) | Analyze mass spectrographic method and system | |
| CN112422650B (en) | Building positioning method, building positioning device, building positioning equipment and computer readable storage medium | |
| CN112037213B (en) | Method and device for acquiring contour data stable feature points based on statistical histogram | |
| CN107065007B (en) | Seismic data amplitude adjusting method and device | |
| CN109272491A (en) | The recognition methods of crack tip, device and equipment under experimental enviroment | |
| CN103246887A (en) | Airport object multithreading detection method based on optical remote sensing images with geometrical characteristics | |
| CN112132111A (en) | Parking typical scene extraction method, device, storage medium and device | |
| CN116071335A (en) | Wall surface acceptance method, device, equipment and storage medium | |
| CN109375187B (en) | Method and device for determining radar target | |
| CN114004744B (en) | Fingerprint splicing method and device, electronic equipment and medium | |
| US11748876B2 (en) | Joint surface safety evaluation apparatus | |
| CN114037993A (en) | Substation pointer instrument reading method and device, storage medium and electronic equipment | |
| CN112954310A (en) | Image quality detection method, device, computer equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 702, 7th floor, NO.67, Beisihuan West Road, Haidian District, Beijing 100089 Patentee after: Beijing Yunji Technology Co.,Ltd. Address before: Room 702, 7th floor, NO.67, Beisihuan West Road, Haidian District, Beijing 100089 Patentee before: BEIJING YUNJI TECHNOLOGY Co.,Ltd. |