CN109270545B - Positioning true value verification method, device, equipment and storage medium - Google Patents
Positioning true value verification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109270545B CN109270545B CN201811236618.2A CN201811236618A CN109270545B CN 109270545 B CN109270545 B CN 109270545B CN 201811236618 A CN201811236618 A CN 201811236618A CN 109270545 B CN109270545 B CN 109270545B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- positioning
- value
- laser radar
- true value
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
Abstract
The invention discloses a method, a device, equipment and a storage medium for verifying a positioning truth value, wherein the method comprises the following steps: registering an original point cloud data frame acquired by a laser radar to position attitude data of a positioning true value, and generating a point cloud data frame with the position attitude data as a reference; extracting point cloud information in the generated point cloud data frames; and obtaining an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning. Through the technical scheme, the purpose of automatically checking the positioning truth value is achieved, the dependence on manual checking is eliminated, and the checking efficiency of the positioning truth value is improved.
Description
Technical Field
The embodiment of the invention relates to an automatic driving technology, in particular to a method, a device, equipment and a storage medium for verifying a positioning true value.
Background
The automatic driving automobile is also called as an unmanned automobile, and can automatically acquire environmental information around the automobile and make decisions and plan paths by means of technologies such as artificial intelligence, computer vision, radar, global positioning system, high-precision maps and the like, so that automatic driving completely independent of human operation is realized. Laser radar positioning is one of the mainstream positioning schemes of automatic driving at present, and has important significance in evaluating the positioning effect of the laser radar positioning in various environments and scenes.
Currently, the evaluation process of the laser radar positioning effect is generally as follows: firstly, collecting data required by positioning, then inputting the data into a positioning algorithm, obtaining a positioning result through calculation of the positioning algorithm, and finally obtaining an evaluation result of the positioning effect through comparison of the positioning result and a positioning true value of a vehicle.
The obtaining of the true positioning value of the vehicle depends on multiple links, and is determined by various algorithm qualities such as Global Navigation Satellite System (GNSS) signal quality and Iterative Closest Point (ICP) algorithm, so that the reliability of the true positioning value is uncertain. Therefore, the acquired positioning true value needs to be verified, and the process of verifying the positioning true value at present mostly depends on manual verification, so that the efficiency is low.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for verifying a positioning truth value, which are used for improving the verification efficiency of the positioning truth value.
In a first aspect, an embodiment of the present invention provides a positioning truth verification method, where the method includes:
registering an original point cloud data frame acquired by a laser radar to position attitude data of a positioning true value, and generating a point cloud data frame with the position attitude data as a reference;
extracting point cloud information in the generated point cloud data frames;
and obtaining an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning.
In a second aspect, an embodiment of the present invention further provides a positioning true value verification apparatus, where the apparatus includes:
the registration module is used for registering an original point cloud data frame acquired by a laser radar to position attitude data of a positioning true value and generating a point cloud data frame taking the position attitude data as a reference;
the extraction module is used for extracting point cloud information in the generated point cloud data frames;
and the verification result acquisition module is used for acquiring an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a positioning truth verification method as described above in the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the positioning truth verification method according to the first aspect.
The invention provides a calibration method of a positioning truth value, which is characterized in that an original point cloud data frame collected by a laser radar is registered to position attitude data of the positioning truth value to generate a point cloud data frame based on the position attitude data; extracting point cloud information in the generated point cloud data frames; according to the extracted point cloud information and a high-precision map used for laser radar positioning, the technical means for obtaining the accuracy verification result of the positioning true value achieves the purpose of automatically verifying the positioning true value, avoids the dependence on manual verification, and improves the verification efficiency of the positioning true value.
Drawings
Fig. 1 is a schematic flow chart illustrating a positioning truth value verification method according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a positioning truth value verification method according to a second embodiment of the present invention;
fig. 3 is a schematic flow chart of a positioning true value verification method in the third embodiment of the present invention;
fig. 4 is a schematic flow chart of a positioning true value verification method in the fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a true value positioning verification apparatus according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device in a sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a schematic flow chart of a positioning true value verification method according to an embodiment of the present invention; the positioning true value verification method provided in this embodiment may be applicable to the case of verifying the positioning true value obtained by the self-based positioning system of the unmanned vehicle, and the method may be executed by a positioning true value verification apparatus, which may be composed of software and/or hardware and is generally integrated in a terminal, such as a server. With particular reference to fig. 1, the method comprises the following steps:
and 110, registering an original point cloud data frame acquired by the laser radar to position attitude data of the positioning true value, and generating a point cloud data frame by taking the position attitude data as a reference.
In this embodiment, the unmanned vehicle is configured with a laser radar (or a radar sensor such as a millimeter wave radar or an ultrasonic radar) for scanning a target object around a driving environment during driving of the unmanned vehicle to obtain a point cloud data frame around a current driving environment of the unmanned vehicle, where the point cloud data frame is defined as an original point cloud data frame collected by the laser radar. In order to realize the normal running of the unmanned automobile, the positioning system is an important component of the unmanned system, and various positioning systems and positioning algorithms are applied to the unmanned automobile along with the pursuit of higher and higher positioning accuracy. In this embodiment, the obtaining manner of the positioning true value is not limited, for example, the positioning true value may be obtained by calculation based on GNSS (Global Navigation Satellite System) data, IMU (Inertial Measurement Unit) data, and laser point cloud data of the unmanned vehicle, where the GNSS data is exemplified by differential GPS data, specifically, the differential GPS data is obtained in real time by a vehicle-mounted GPS module during the driving process of the unmanned vehicle, the IMU data is obtained in real time by an Inertial Measurement Unit, and the laser point cloud data is obtained in real time by a laser radar, and then the differential GPS data and the laser point cloud data may be registered by using an ICP (Iterative closest point) algorithm to obtain the current positioning true value of the unmanned vehicle; the acquired differential GPS data, IMU data and laser point cloud data can also be compared with a predetermined high-precision map to obtain the current true positioning value of the unmanned automobile. Because the positioning precision of the differential GPS data can reach centimeter level, the accuracy of a positioning truth value determined by offline registration by combining the laser point cloud data and utilizing an ICP algorithm can be higher than centimeter level. The positioning true value can also be obtained according to sensing positioning data of the unmanned vehicle, where the sensing positioning data refers to data collected by a positioning sensor in the unmanned vehicle, and the positioning sensor may include a gyroscope, an acceleration sensor, and the like, and the sensing positioning data may include acceleration data, angular velocity data, and the like, and the INS calculates positioning coordinate information of a next point of the unmanned vehicle from an initial position of the unmanned vehicle according to a continuously measured heading angle and velocity of the unmanned vehicle, so that the positioning coordinate information of the unmanned vehicle at each time, that is, the positioning true value, can be continuously measured. Of course, the unmanned vehicle may also adopt other various Positioning systems to perform Positioning, such as a GPS (Global Positioning System) or a BDS (BeiDou Navigation Satellite System), and the like.
The principle of verifying the positioning truth value in this embodiment is as follows: and constructing a local map based on an original point cloud data frame acquired by a laser radar by taking the positioning truth value as a reference origin, matching the local map with a predetermined high-precision map, and determining the accuracy of the positioning truth value according to matching similarity so as to realize the aim of verifying the positioning truth value. Therefore, firstly, an original point cloud data frame acquired by the laser radar needs to be registered to position attitude data of a positioning true value to generate a point cloud data frame based on the position attitude data, and specifically, an ICP algorithm can be adopted to register the original point cloud data frame acquired by the laser radar to the position attitude data of the positioning true value, that is, the original point cloud data acquired by the laser radar and the position attitude data of the positioning true value are transformed to a uniform coordinate system to realize the construction of a local map.
And 120, extracting point cloud information in the generated point cloud data frames.
The point cloud data frame can accurately represent the topological structure and the geometric structure of a target object, namely the characteristics of the target object, the target object is usually a static object, such as a bus stop board, a traffic sign, a telegraph pole or a tree, and the like, the stability of the static object is high and cannot be changed frequently, so that once a high-precision map is generated, the high-precision map does not need to be updated for a long time. The accuracy of the positioning true value is determined by extracting point cloud information from a constructed local map with the positioning true value as a reference origin and then comparing the point cloud information with point cloud information of an area corresponding to the local map in a pre-made high-precision map.
Specifically, the point cloud information may include a three-dimensional coordinate value of the point cloud, a point cloud intensity value, and color information, where the point cloud intensity value refers to reflection intensity information of a laser, specifically, optical power of a backscatter echo of a laser beam emitted by the laser radar to the target object. The point cloud intensity values of the same target object are the same or close. The point cloud information is used for representing the characteristics of the target object.
And step 130, obtaining an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning.
When the high-precision map used for laser radar positioning is manufactured, the characteristics of an object are extracted, for example, the characteristics include points, lines and surfaces, and the characteristics are also quick, and after being extracted, the characteristics are stored in the high-precision map and serve as original data; the method comprises the steps that a vehicle equipped with a laser radar scans surrounding target objects in the driving process to obtain an original point cloud data frame, then a relation is established between the original point cloud data frame and a positioning true value, feature extraction is carried out, finally the extracted features are compared with point cloud information features of an area near the positioning true value in a high-precision map, and the accuracy of the positioning true value is determined according to a comparison result.
Specifically, the accuracy verification result for obtaining the positioning true value according to the extracted point cloud information and the high-precision map used for laser radar positioning is substantially as follows: and comparing the point cloud information of the target object near the real positioning value detected in real time with the point cloud information of the target object near the real positioning value on a high-precision map used for laser radar positioning, wherein if the similarity of the point cloud information is higher, the higher the accuracy of the real positioning value is.
In the method for verifying the positioning truth value provided by the embodiment, an original point cloud data frame acquired by a laser radar is registered to position attitude data of the positioning truth value, and a point cloud data frame based on the position attitude data is generated; extracting point cloud information in the generated point cloud data frames; according to the extracted point cloud information and a high-precision map used for laser radar positioning, the technical means for obtaining the accuracy verification result of the positioning true value achieves the purpose of automatically verifying the positioning true value, avoids the dependence on manual verification, and improves the verification efficiency of the positioning true value.
Example two
Fig. 2 is a schematic flow chart of a positioning true value verification method according to a second embodiment of the present invention, where on the basis of the above-mentioned embodiment, this embodiment provides an implementation manner of "registering an original point cloud data frame acquired by a laser radar to position attitude data of a positioning true value, and generating a point cloud data frame based on the position attitude data", where the position attitude data of the positioning true value in this embodiment includes: the system comprises a timestamp, 3D position coordinates and attitude information, wherein the attitude information can specifically refer to a course angle or an angular speed of the unmanned automobile at the current moment. Referring specifically to fig. 2, the method comprises the following steps:
and step 210, giving the 3D position coordinates in the position posture data of the positioning truth value as an origin to a point cloud coordinate system corresponding to the original point cloud data frame, and generating a new point cloud coordinate system.
Specifically, the ICP registration algorithm may be adopted to implement the above process of using the 3D position coordinates in the position and posture data of the localization true value as the origin in the point cloud coordinate system corresponding to the original point cloud data frame, updating the coordinate values of the original point cloud data frame, generating a new point cloud coordinate system, and implementing the construction of the local point cloud map using the localization true value as the origin.
And step 220, extracting point cloud information in the generated point cloud data frames.
And step 230, obtaining an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning.
And the high-precision map used for laser radar positioning refers to a local high-precision map corresponding to the positioning truth value, and does not refer to the whole high-precision map.
On the basis of the above embodiment, in the localization true value verification method provided in this embodiment, the 3D position coordinates in the position posture data of the localization true value are given to the point cloud coordinate system corresponding to the original point cloud data frame as the origin, so that the original point cloud data frame acquired by the laser radar is registered to the position posture data of the localization true value, and the point cloud data frame based on the position posture data is generated, thereby improving the verification efficiency of the localization true value.
EXAMPLE III
Fig. 3 is a schematic flow chart of a positioning true value verification method according to a third embodiment of the present invention, where on the basis of the third embodiment of the present invention, the present embodiment optimizes "step 120, extracting point cloud information in each generated point cloud data frame" and "step 130, and obtains an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning", where the optimization has the advantage of improving the accuracy of the positioning true value verification, and as shown in fig. 3 in particular, the method includes the following steps:
and 310, giving the 3D position coordinates in the position posture data of the positioning truth value as an origin to a point cloud coordinate system corresponding to the original point cloud data frame to generate a new point cloud coordinate system.
And step 320, extracting the mean value and the variance of the point cloud intensity and the mean value and the variance of the point cloud height in the generated point cloud data frames.
And 330, generating a point cloud intensity map according to the extracted mean value and variance of the point cloud intensity, and generating a point cloud height map according to the extracted mean value and variance of the point cloud height.
The point cloud intensity map is a two-dimensional map with time represented by a horizontal axis and point cloud intensity represented by a vertical axis, and similarly, the point cloud height map is a two-dimensional map with time represented by a horizontal axis and point cloud height represented by a vertical axis. The point cloud intensity map and the point cloud height map can highlight the characteristics of the target object represented by the point cloud.
And 340, comparing the point cloud intensity map and the point cloud height map with a high-precision map used for laser radar positioning respectively to obtain an accuracy verification result of the positioning true value.
Illustratively, the comparing the point cloud intensity map and the point cloud height map with a high-precision map used for laser radar positioning respectively to obtain an accuracy verification result of the positioning true value includes:
respectively calculating a point cloud intensity deviation value of the point cloud intensity map and a high-precision map used by laser radar positioning and a point cloud height deviation value of the point cloud height map and the high-precision map used by the laser radar positioning by using an error Square Sum (SSD) algorithm and/or an absolute error Sum (SAD) algorithm;
and taking the point cloud intensity deviation value and the point cloud height deviation value as the accuracy verification result of the positioning true value.
On the basis of the above embodiments, the method for verifying the true localization value provided by this embodiment specifically extracts the mean and variance of the point cloud intensities in the generated point cloud data frames and the mean and variance of the point cloud heights, generates the point cloud intensity map according to the extracted mean and variance of the point cloud intensities, generates the point cloud height map according to the extracted mean and variance of the point cloud heights, and finally compares the point cloud intensity map and the point cloud height map with the high-precision map used for laser radar localization to obtain the accuracy verification result of the true localization value.
Example four
Fig. 4 is a schematic flow chart of a verification method of a true localization value according to a fourth embodiment of the present invention, where on the basis of the above embodiments, the present embodiment adds a step of determining a region and a time period in which the accuracy of a true localization value is smaller than a set threshold according to the point cloud intensity deviation value, the point cloud height deviation value, the time of the corresponding point cloud data frame, and the position of the corresponding point cloud data frame. Referring specifically to fig. 4, the method includes the steps of:
and step 410, giving the 3D position coordinates in the position posture data of the positioning truth value as an origin to a point cloud coordinate system corresponding to the original point cloud data frame, and generating a new point cloud coordinate system.
And step 420, extracting the mean value and the variance of the point cloud intensity and the mean value and the variance of the point cloud height in the generated point cloud data frames.
And 430, generating a point cloud intensity map according to the extracted mean value and variance of the point cloud intensity, and generating a point cloud height map according to the extracted mean value and variance of the point cloud height.
And 440, comparing the point cloud intensity map and the point cloud height map with a high-precision map used for laser radar positioning respectively to obtain an accuracy verification result of the positioning true value.
And step 450, determining an area and a time period with the positioning truth value accuracy smaller than a set threshold according to the point cloud intensity deviation value, the point cloud height deviation value, the time of the corresponding point cloud data frame and the position of the corresponding point cloud data frame.
On the basis of the above embodiments, according to the positioning true value verification method provided in this embodiment, after the accuracy verification result of the positioning true value is obtained, a time period and a region where the accuracy of the positioning true value is smaller than a set threshold can be further determined according to the timestamp of each point cloud data frame, so that a region with poor accuracy can be given according to the accuracy verification result of the positioning true value, the region and the time period with poor accuracy of the positioning true value can be reversely deduced through the region, the positioning true value with higher reliability can be selectively used, and the accuracy of the whole positioning effect evaluation flow is further improved.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a positioning truth value verifying apparatus according to a fifth embodiment of the present invention, where the apparatus may be composed of software and/or hardware, and is generally integrated in a terminal, such as a server. With particular reference to fig. 5, the device comprises: a registration module 510, an extraction module 520 and a verification result acquisition module 530;
the registration module 510 is configured to register an original point cloud data frame acquired by a laser radar to position and attitude data of a positioning true value, and generate a point cloud data frame based on the position and attitude data;
an extracting module 520, configured to extract point cloud information in the generated point cloud data frames;
and a verification result obtaining module 530, configured to obtain an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning.
Illustratively, the position and orientation data includes a time stamp, 3D position coordinates, and orientation information.
Illustratively, the registration module 510 is specifically configured to: and giving the 3D position coordinates in the position posture data of the positioning truth value as an origin to a point cloud coordinate system corresponding to the original point cloud data frame to generate a new point cloud coordinate system.
Illustratively, the extracting module 520 is specifically configured to: and extracting the mean value and the variance of the point cloud intensity and the mean value and the variance of the point cloud height in the generated point cloud data frames.
Illustratively, the verification result obtaining module includes:
the generating unit is used for generating a point cloud intensity map according to the mean value and the variance of the extracted point cloud intensity; generating a point cloud height map according to the extracted mean value and variance of the point cloud heights;
and the comparison unit is used for comparing the point cloud intensity map and the point cloud height map with a high-precision map used for laser radar positioning respectively to obtain an accuracy verification result of the positioning true value.
Illustratively, the alignment unit is specifically configured to:
respectively calculating a point cloud intensity deviation value of the point cloud intensity map and a high-precision map used by laser radar positioning and a point cloud height deviation value of the point cloud height map and the high-precision map used by the laser radar positioning by using an error Square Sum (SSD) algorithm and/or an absolute error Sum (SAD) algorithm;
and taking the point cloud intensity deviation value and the point cloud height deviation value as the accuracy verification result of the positioning true value.
Further, the apparatus further comprises: and the determining module is used for determining the area and the time period of which the accuracy of the positioning true value is less than the set threshold according to the point cloud intensity deviation value, the point cloud height deviation value, the time of the corresponding point cloud data frame and the position of the corresponding point cloud data frame.
The positioning truth value verifying device provided by the embodiment generates a point cloud data frame based on position attitude data by registering an original point cloud data frame acquired by a laser radar to the position attitude data of a positioning truth value; extracting point cloud information in the generated point cloud data frames; according to the extracted point cloud information and a high-precision map used for laser radar positioning, the technical means for obtaining the accuracy verification result of the positioning true value achieves the purpose of automatically verifying the positioning true value, avoids the dependence on manual verification, and improves the verification efficiency of the positioning true value.
The positioning true value verification device provided by the embodiment of the invention can execute the positioning true value verification method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE six
Fig. 6 is a schematic structural diagram of an apparatus provided in embodiment 6 of the present invention. Fig. 6 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 6 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present invention.
As shown in FIG. 6, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, and commonly referred to as a "hard drive"). Although not shown in FIG. 6, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set of program modules (e.g., registration module 510, extraction module 520, and verification result acquisition module 530) configured to perform the functions of embodiments of the present invention.
A program/utility 40 having a set (registration module 510, extraction module 520, and verification result acquisition module 530) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may include an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes programs stored in the system memory 28 to execute various functional applications and data processing, such as implementing the positioning truth verification method provided by the embodiment of the present invention.
EXAMPLE seven
The seventh embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the positioning true value verification method described in the foregoing embodiments.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A method for verifying a positioning truth value, comprising:
registering an original point cloud data frame acquired by a laser radar to position attitude data of a positioning true value, and generating a point cloud data frame with the position attitude data as a reference;
extracting point cloud information in the generated point cloud data frames;
obtaining an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning;
the method for extracting the point cloud information in the generated point cloud data frames comprises the following steps:
and extracting the mean value and the variance of the point cloud intensity and the mean value and the variance of the point cloud height in the generated point cloud data frames.
2. The method of claim 1, wherein the position-pose data comprises a timestamp, 3D position coordinates, and pose information.
3. The method of claim 2, wherein registering the frame of raw point cloud data collected by the lidar to position and pose data of the localization truth value generates a frame of point cloud data based on the position and pose data, comprising:
and giving the 3D position coordinates in the position posture data of the positioning truth value as an origin to a point cloud coordinate system corresponding to the original point cloud data frame to generate a new point cloud coordinate system.
4. The method of claim 1, wherein obtaining an accuracy verification result of the positioning truth value according to the extracted point cloud information and a high-precision map used for laser radar positioning comprises:
generating a point cloud intensity map according to the extracted mean value and variance of the point cloud intensity; generating a point cloud height map according to the extracted mean value and variance of the point cloud heights;
and comparing the point cloud intensity map and the point cloud height map with a high-precision map used for laser radar positioning respectively to obtain an accuracy verification result of the positioning true value.
5. The method of claim 4, wherein the comparing the point cloud intensity map and the point cloud height map with a high-precision map used for laser radar positioning to obtain the accuracy verification result of the positioning truth value comprises:
respectively calculating a point cloud intensity deviation value of the point cloud intensity map and a high-precision map used by laser radar positioning and a point cloud height deviation value of the point cloud height map and the high-precision map used by the laser radar positioning by using an error Square Sum (SSD) algorithm and/or an absolute error Sum (SAD) algorithm;
and taking the point cloud intensity deviation value and the point cloud height deviation value as the accuracy verification result of the positioning true value.
6. The method of claim 5, further comprising:
and determining the area and the time period with the positioning truth value accuracy smaller than the set threshold according to the point cloud intensity deviation value, the point cloud height deviation value, the time of the corresponding point cloud data frame and the position of the corresponding point cloud data frame.
7. A positioning truth verification apparatus, comprising:
the registration module is used for registering an original point cloud data frame acquired by a laser radar to position attitude data of a positioning true value and generating a point cloud data frame taking the position attitude data as a reference;
the extraction module is used for extracting the mean value and the variance of the point cloud intensity and the mean value and the variance of the point cloud height in the generated point cloud data frames;
and the verification result acquisition module is used for acquiring an accuracy verification result of the positioning true value according to the extracted point cloud information and a high-precision map used for laser radar positioning.
8. An electronic device, characterized in that the device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a positioning truth verification method as recited in any one of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method for location truth verification as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811236618.2A CN109270545B (en) | 2018-10-23 | 2018-10-23 | Positioning true value verification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811236618.2A CN109270545B (en) | 2018-10-23 | 2018-10-23 | Positioning true value verification method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109270545A CN109270545A (en) | 2019-01-25 |
| CN109270545B true CN109270545B (en) | 2020-08-11 |
Family
ID=65193911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811236618.2A Active CN109270545B (en) | 2018-10-23 | 2018-10-23 | Positioning true value verification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109270545B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11364931B2 (en) * | 2019-01-30 | 2022-06-21 | Baidu Usa Llc | Lidar localization using RNN and LSTM for temporal smoothness in autonomous driving vehicles |
| CN111721283B (en) * | 2019-03-18 | 2023-08-15 | 深圳市速腾聚创科技有限公司 | Precision detection method and device for positioning algorithm, computer equipment and storage medium |
| CN110174686B (en) * | 2019-04-16 | 2021-09-24 | 百度在线网络技术（北京）有限公司 | Method, device and system for matching GNSS (global navigation satellite system) position and image in crowdsourcing map |
| CN110068824B (en) * | 2019-04-17 | 2021-07-23 | 北京地平线机器人技术研发有限公司 | Sensor pose determining method and device |
| WO2020223868A1 (en) * | 2019-05-06 | 2020-11-12 | 深圳市大疆创新科技有限公司 | Terrain information processing method and apparatus, and unmanned vehicle |
| WO2021016803A1 (en) * | 2019-07-29 | 2021-02-04 | 深圳市大疆创新科技有限公司 | High definition map positioning method and system, platform and computer-readable storage medium |
| CN111664869A (en) * | 2020-05-28 | 2020-09-15 | 武汉中海庭数据技术有限公司 | High-precision map surface feature data quality evaluation method and device |
| CN111680596B (en) * | 2020-05-29 | 2023-10-13 | 北京百度网讯科技有限公司 | Positioning true value verification method, device, equipment and medium based on deep learning |
| CN111998860B (en) * | 2020-08-21 | 2023-02-17 | 阿波罗智能技术(北京)有限公司 | Automatic driving positioning data verification method and device, electronic equipment and storage medium |
| CN113011517A (en) * | 2021-03-30 | 2021-06-22 | 上海商汤临港智能科技有限公司 | Positioning result detection method and device, electronic equipment and storage medium |
| CN113252053B (en) * | 2021-06-16 | 2021-09-28 | 中智行科技有限公司 | High-precision map generation method and device and electronic equipment |
| CN113673105A (en) * | 2021-08-20 | 2021-11-19 | 安徽江淮汽车集团股份有限公司 | Design method of true value comparison strategy |
| CN114077875B (en) * | 2022-01-19 | 2022-05-20 | 浙江吉利控股集团有限公司 | Information verification method, device, equipment and storage medium |
| US20230236022A1 (en) * | 2022-01-26 | 2023-07-27 | Motional Ad Llc | Localization functional safety |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107850445A (en) * | 2015-08-03 | 2018-03-27 | 通腾全球信息公司 | Method and system for generating and using locating reference datum |
| CN108007453A (en) * | 2017-12-11 | 2018-05-08 | 北京奇虎科技有限公司 | Map updating method, device and electronic equipment based on a cloud |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243378A1 (en) * | 2007-02-21 | 2008-10-02 | Tele Atlas North America, Inc. | System and method for vehicle navigation and piloting including absolute and relative coordinates |
| CN102518028B (en) * | 2011-10-25 | 2014-03-12 | 中交第二公路勘察设计研究院有限公司 | Precise plane coordinate correction method in laser radar scanning measurement |
| US9430822B2 (en) * | 2013-06-14 | 2016-08-30 | Microsoft Technology Licensing, Llc | Mobile imaging platform calibration |
| CN106842269A (en) * | 2017-01-25 | 2017-06-13 | 北京经纬恒润科技有限公司 | Localization method and system |
| CN106840179B (en) * | 2017-03-07 | 2019-12-10 | 中国科学院合肥物质科学研究院 | Intelligent vehicle positioning method based on multi-sensor information fusion |
| CN107328410B (en) * | 2017-06-30 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Method for locating an autonomous vehicle and vehicle computer |
| CN108152831B (en) * | 2017-12-06 | 2020-02-07 | 中国农业大学 | Laser radar obstacle identification method and system |
-
2018
- 2018-10-23 CN CN201811236618.2A patent/CN109270545B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107850445A (en) * | 2015-08-03 | 2018-03-27 | 通腾全球信息公司 | Method and system for generating and using locating reference datum |
| CN108007453A (en) * | 2017-12-11 | 2018-05-08 | 北京奇虎科技有限公司 | Map updating method, device and electronic equipment based on a cloud |
Non-Patent Citations (1)
| Title |
|---|
| LIDAR框架构建下的gps基站联合测量准确度探索;王晓磊;《自动化与仪器仪表》;20161231;第68-70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109270545A (en) | 2019-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109270545B (en) | Positioning true value verification method, device, equipment and storage medium | |
| US11480443B2 (en) | Method for calibrating relative pose, device and medium | |
| CN109459734B (en) | Laser radar positioning effect evaluation method, device, equipment and storage medium | |
| US11042762B2 (en) | Sensor calibration method and device, computer device, medium, and vehicle | |
| CN109285220B (en) | Three-dimensional scene map generation method, device, equipment and storage medium | |
| EP3620823B1 (en) | Method and device for detecting precision of internal parameter of laser radar | |
| CN111812658B (en) | Position determination method, device, system and computer readable storage medium | |
| KR102581263B1 (en) | Method, apparatus, computing device and computer-readable storage medium for positioning | |
| CN110095752B (en) | Positioning method, apparatus, device and medium | |
| CN109146938B (en) | Method, device and equipment for calibrating position of dynamic obstacle and storage medium | |
| CN109435955B (en) | Performance evaluation method, device and equipment for automatic driving system and storage medium | |
| JP2019215853A (en) | Method for positioning, device for positioning, device, and computer readable storage medium | |
| CN111220164A (en) | Positioning method, device, equipment and storage medium | |
| CN111680596B (en) | Positioning true value verification method, device, equipment and medium based on deep learning | |
| CN113933818A (en) | Method, device, storage medium and program product for calibrating laser radar external parameter | |
| CN111469781B (en) | For use in output of information processing system method and apparatus of (1) | |
| CN114187357A (en) | High-precision map production method and device, electronic equipment and storage medium | |
| CN110647600A (en) | Three-dimensional map construction method and device, server and storage medium | |
| CN115147561A (en) | Pose graph generation method, high-precision map generation method and device | |
| CN114281832A (en) | High-precision map data updating method and device based on positioning result and electronic equipment | |
| CN111932611A (en) | Object position acquisition method and device | |
| CN110647591A (en) | Method and device for testing vector map | |
| CN111398961B (en) | Method and apparatus for detecting obstacles | |
| CN112556701A (en) | Method, device, equipment and storage medium for positioning vehicle | |
| CN117606506A (en) | Vehicle positioning method, device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211014 Address after: 105 / F, building 1, No. 10, Shangdi 10th Street, Haidian District, Beijing 100085 Patentee after: Apollo Intelligent Technology (Beijing) Co.,Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| TR01 | Transfer of patent right |