CN112729341A - Visual ranging precision testing method and system - Google Patents

Visual ranging precision testing method and system Download PDF

Info

Publication number
CN112729341A
CN112729341A CN202011573046.4A CN202011573046A CN112729341A CN 112729341 A CN112729341 A CN 112729341A CN 202011573046 A CN202011573046 A CN 202011573046A CN 112729341 A CN112729341 A CN 112729341A
Authority
CN
China
Prior art keywords
real
time dynamic
differential device
dynamic differential
distance
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011573046.4A
Other languages
Chinese (zh)
Inventor
王伟平
张钊
刘备备
彭剑
俞剑峰
叶枫
王斌
范少娟
邹羽婷
王曦
程士庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Tiantong Weishi Electronic Technology Co ltd
SAIC Motor Corp Ltd
Original Assignee
Tianjin Tiantong Weishi Electronic Technology Co ltd
SAIC Motor Corp Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Tiantong Weishi Electronic Technology Co ltd, SAIC Motor Corp Ltd filed Critical Tianjin Tiantong Weishi Electronic Technology Co ltd
Publication of CN112729341A publication Critical patent/CN112729341A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C25/00Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S19/00Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/01Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/13Receivers
    • G01S19/24Acquisition or tracking or demodulation of signals transmitted by the system
    • G01S19/25Acquisition or tracking or demodulation of signals transmitted by the system involving aiding data received from a cooperating element, e.g. assisted GPS
    • G01S19/256Acquisition or tracking or demodulation of signals transmitted by the system involving aiding data received from a cooperating element, e.g. assisted GPS relating to timing, e.g. time of week, code phase, timing offset
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S19/00Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/40Correcting position, velocity or attitude
    • G01S19/41Differential correction, e.g. DGPS [differential GPS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Manufacturing & Machinery (AREA)
  • Traffic Control Systems (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention discloses a method and a system for testing visual ranging precision, wherein the method comprises the following steps: synchronizing clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the vision system; synchronously acquiring coordinate data of a first real-time dynamic differential device, a second real-time dynamic differential device and a visual sensor in a visual system; determining a first transverse distance and a first longitudinal distance of a target under a vehicle coordinate system based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device; determining a second lateral distance and a second longitudinal distance of the target in the vehicle coordinate system based on the coordinate data of the vision sensor; and comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result. The invention does not need combined calibration and target matching, can ensure the precision of data, and simply and effectively realizes the test of the visual ranging precision.

Description

Visual ranging precision testing method and system
The present application claims priority from a domestic application filed on 20/11/2020 of the national patent office under the name "a method and system for measuring accuracy of visual ranging" with the application number 202011313925.3, the entire contents of which are incorporated herein by reference.
Technical Field
The invention relates to the technical field of visual ranging, in particular to a visual ranging precision testing method and system.
Background
Computer vision is a foundation among others in the field of smart cars, which serves as the eye part in traditional driving behavior. In order to accurately and safely realize unmanned driving, computer vision replaces human eyes to carry out semantic analysis at a higher level, but with the deepening of the unmanned driving technology, the computer vision not only keeps the functions in the semantic analysis, but also provides certain precision of visual distance measurement. Such as how far the front truck is from the vehicle, the relative speed, whether there is a possibility of collision, etc. Therefore, the quantitative visual ranging accuracy is a relatively important index for evaluating the quality of the computer vision algorithm.
At present, the general method for quantifying the precision of visual ranging is to measure by a sensor with higher precision, and compare the result given by a visual algorithm, and the conventionally used sensor is a laser radar, a millimeter wave radar and the like. The sensor of the type has a common characteristic, has respective visual field ranges, needs to complete accurate visual measurement value comparison, needs to jointly calibrate the camera and the sensor, needs to keep the position unchanged after calibration, and is difficult to cover the visual field range of the camera, such as a laser radar, the sensor has low line number and cannot cover a distant target, and the blind area of the installation position is large.
In addition, if target-level matching is performed on different sensors with a camera, data processing and algorithm development in the early stage are needed, and if target matching is wrong, the matching influence on the precision test result is large. Such as laser radar, the point cloud needs to be subject to target-level clustering. The sensor can give target distance information based on a world coordinate system, but different suppliers of distance measurement points provide different algorithms for selection, and universality is difficult to achieve. For example, millimeter wave radar can provide clustered targets, but the accuracy of information of the targets that can be provided is limited, and information such as target classification and orientation is not accurate enough, so that the millimeter wave radar cannot provide a basis for matching the targets between images and sensors, and a ranging result with high accuracy is different according to different selection points of each selection algorithm. Therefore, the traditional sensor is accessed as a visual ranging precision analysis tool, and a large amount of early-stage data processing algorithm development is required.
Therefore, how to simply and effectively test the precision of the visual ranging is an urgent problem to be solved.
Disclosure of Invention
In view of the above, the invention provides a method for testing the precision of visual ranging, which does not need joint calibration and target matching when testing the precision of visual ranging, can ensure the precision of data, and simply and effectively realizes the test of the precision of visual ranging.
The invention provides a visual ranging precision testing method, which comprises the following steps:
synchronizing a first real-time dynamic differential device, a second real-time dynamic differential device and a clock of a vision system, wherein the first real-time dynamic differential device and a vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the vision system;
synchronously acquiring coordinate data of the first real-time dynamic differential device, the second real-time dynamic differential device and a visual sensor in the visual system;
determining a first transverse distance and a first longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
determining a second lateral distance and a second longitudinal distance of the target in a vehicle coordinate system based on the coordinate data of the vision sensor;
and comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
Preferably, the determining a first lateral distance and a first longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the first real-time dynamic difference device and the second real-time dynamic difference device comprises:
calculating the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on an earth coordinate system according to the acquired coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
the first transverse distance and the first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation distance.
Preferably, the synchronizing the clocks of the first real-time dynamic differencing device, the second real-time dynamic differencing device and the vision system comprises:
and synchronizing clocks of the vision system based on the GPS time of the first real-time dynamic differential device and the second real-time dynamic differential device.
Preferably, the first real-time dynamic differential device is installed at the origin of a vehicle coordinate system, and the installation point of the second real-time dynamic differential device is a visual ranging selection point.
A visual ranging accuracy testing system, comprising:
the clock synchronization module is used for synchronizing clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system, wherein the first real-time dynamic differential device and the vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the visual system;
the acquisition module is used for synchronously acquiring the first real-time dynamic difference device, the second real-time dynamic difference device and coordinate data of a visual sensor in the visual system;
the first determining module is used for determining a first transverse distance and a first longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the first real-time dynamic difference device and the second real-time dynamic difference device;
a second determination module to determine a second lateral distance and a second longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the vision sensor;
and the comparison module is used for comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
Preferably, the first determining module is specifically configured to:
calculating the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on an earth coordinate system according to the acquired coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
the first transverse distance and the first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation distance.
Preferably, the clock synchronization module is specifically configured to:
and synchronizing clocks of the vision system based on the GPS time of the first real-time dynamic differential device and the second real-time dynamic differential device.
Preferably, the first real-time dynamic differential device is installed at the origin of a vehicle coordinate system, and the installation point of the second real-time dynamic differential device is a visual ranging selection point.
In summary, the present invention discloses a method for testing precision of visual ranging, when the precision of visual ranging needs to be tested, first synchronizing a first real-time dynamic differential device, a second real-time dynamic differential device and a clock of a visual system, wherein the first real-time dynamic differential device and a vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the visual system; then synchronously acquiring coordinate data of the first real-time dynamic differential device, the second real-time dynamic differential device and a visual sensor in a visual system; determining a first transverse distance and a first longitudinal distance of a target under a vehicle coordinate system based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device; determining a second lateral distance and a second longitudinal distance of the target in the vehicle coordinate system based on the coordinate data of the vision sensor; and comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result. When the method is used for testing the visual ranging precision, joint calibration and target matching are not needed, the data precision can be ensured, and the test on the visual ranging precision is simply and effectively realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of an embodiment 1 of a method for testing precision of visual ranging according to the present disclosure;
FIG. 2 is a flowchart of a method for testing precision of visual ranging according to embodiment 2 of the present disclosure;
FIG. 3 is a schematic structural diagram of a system for testing precision of visual ranging according to an embodiment 1 of the present disclosure;
FIG. 4 is a schematic structural diagram of a system for testing precision of visual ranging according to an embodiment 2 of the present disclosure;
fig. 5 is a schematic diagram of an installation position of an RTK device disclosed in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
As shown in fig. 1, which is a flowchart of embodiment 1 of a method for testing precision of visual ranging disclosed in the present invention, the method may include the following steps:
s101, synchronizing a first real-time dynamic differential device, a second real-time dynamic differential device and a clock of a visual system, wherein the first real-time dynamic differential device and a vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the visual system;
when the vision distance measurement precision needs to be tested, two sets of RTK devices (real-time kinematic differential devices) need to be accessed simultaneously, wherein the first real-time kinematic differential device is used for vehicle positioning, the second real-time kinematic differential device is used for target positioning, and data can be stored between the first real-time kinematic differential device and the second real-time kinematic differential device through a 4G network. The first real-time dynamic differential equipment used for positioning the vehicle is selected to be installed in the same vertical position as the vehicle camera, and the second real-time dynamic differential equipment used for positioning the target is selected to be an installation point according to a visual ranging point selection principle. For example, if the target ranging point is selected at the center of the rear axle, the second real-time dynamic differential device may be selected to be installed at the center of the rear axle, so as to achieve precise ranging matching.
After the first real-time dynamic differential device and the second real-time dynamic differential device are installed at corresponding positions, clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are synchronized in real time, so that the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are guaranteed to use the same group of clock sources, and accuracy of data is guaranteed.
S102, synchronously acquiring coordinate data of a first real-time dynamic differential device, a second real-time dynamic differential device and a visual sensor in a visual system;
and then, synchronously acquiring coordinate data of the first real-time dynamic difference device, the second real-time dynamic difference device and the visual sensor in the visual system.
S103, determining a first transverse distance and a first longitudinal distance of a target in a vehicle coordinate system based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
then, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, a first transverse distance and a first longitudinal distance of the target in a vehicle coordinate system are determined, wherein the first transverse distance and the first longitudinal distance are distance truth values of the target.
S104, determining a second transverse distance and a second longitudinal distance of the target under the vehicle coordinate system based on the coordinate data of the vision sensor;
and meanwhile, determining a second transverse distance and a second longitudinal distance of the target in the vehicle coordinate system according to the collected coordinate data of the visual sensor, wherein the second transverse distance and the second longitudinal distance are visual ranging values.
S105, comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
And finally, comparing the obtained first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
In summary, in the above embodiments, when the visual ranging accuracy needs to be tested, the clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the visual system are synchronized, where the first real-time dynamic differential device and the vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on the visual ranging point selection principle of the visual system; then synchronously acquiring coordinate data of the first real-time dynamic differential device, the second real-time dynamic differential device and a visual sensor in a visual system; determining a first transverse distance and a first longitudinal distance of a target under a vehicle coordinate system based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device; determining a second lateral distance and a second longitudinal distance of the target in the vehicle coordinate system based on the coordinate data of the vision sensor; and comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result. When the method is used for testing the visual ranging precision, joint calibration and target matching are not needed, the data precision can be ensured, and the test on the visual ranging precision is simply and effectively realized.
Fig. 2 is a flowchart of an embodiment 2 of a method for testing precision of visual ranging disclosed in the present invention, where the method may include the following steps:
s201, synchronizing clocks of a vision system based on GPS time of a first real-time dynamic differential device and GPS time of a second real-time dynamic differential device, wherein the first real-time dynamic differential device and a vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a vision distance measurement point selection principle of the vision system;
when the vision distance measurement precision needs to be tested, two sets of RTK devices (real-time kinematic differential devices) need to be accessed simultaneously, wherein the first real-time kinematic differential device is used for vehicle positioning, the second real-time kinematic differential device is used for target positioning, and data can be stored between the first real-time kinematic differential device and the second real-time kinematic differential device through a 4G network. The first real-time dynamic differential equipment used for positioning the vehicle is selected to be installed in the same vertical position as the vehicle camera, and the second real-time dynamic differential equipment used for positioning the target is selected to be an installation point according to a visual ranging point selection principle. For example, if the target ranging point is selected at the center of the rear axle, the second real-time dynamic differential device may be selected to be installed at the center of the rear axle, so as to achieve precise ranging matching.
After the first real-time dynamic differential device and the second real-time dynamic differential device are installed at corresponding positions, clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are synchronized in real time, so that the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are guaranteed to use the same group of clock sources, and accuracy of data is guaranteed.
Specifically, when synchronizing the clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the vision system, the clocks of the vision system may be synchronized by the GPS time of the first real-time dynamic differential device and the second real-time dynamic differential device.
S202, synchronously acquiring coordinate data of a first real-time dynamic differential device, a second real-time dynamic differential device and a visual sensor in a visual system;
and then, synchronously acquiring coordinate data of the first real-time dynamic difference device, the second real-time dynamic difference device and the visual sensor in the visual system.
S203, calculating the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on the earth coordinate system according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
then, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, a first transverse distance and a first longitudinal distance of the target in a vehicle coordinate system are determined, wherein the first transverse distance and the first longitudinal distance are distance truth values of the target.
Specifically, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on the earth coordinate system is calculated.
S204, splitting the orientation distance into a first transverse distance and a first longitudinal distance of the target under the vehicle coordinate system;
then, a first lateral distance and a first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation traversed distance.
S205, determining a second transverse distance and a second longitudinal distance of the target under the vehicle coordinate system based on the coordinate data of the vision sensor;
and meanwhile, determining a second transverse distance and a second longitudinal distance of the target in the vehicle coordinate system according to the collected coordinate data of the visual sensor, wherein the second transverse distance and the second longitudinal distance are visual ranging values.
S206, comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
And finally, comparing the obtained first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
To sum up, in this embodiment, on the basis of the above embodiments, when synchronizing the clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the vision system, the clocks of the vision system may be synchronized based on the GPS time of the first real-time dynamic differential device and the GPS time of the second real-time dynamic differential device; when a first transverse distance and a first longitudinal distance of a target under a vehicle coordinate system are determined based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, calculating a Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device under a terrestrial coordinate system according to collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device; the first transverse distance and the first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation distance.
In order to further understand the method for testing the precision of the visual ranging provided by the present invention, the following description is made by using specific examples:
as shown in fig. 5, a schematic diagram of the mounting positions of the RTK devices is shown, where the mounting point of the first real-time dynamic differential device is the origin of the coordinate system of the vehicle, and the mounting point of the second real-time dynamic differential device is the algorithm ranging selection point. In the example, joint calibration among multiple groups of sensors is omitted, and a true value of distance measurement can be accurately obtained. The first real-time dynamic differential device and the second real-time dynamic differential device need to perform time calibration with the vision system through the serial port, and the clock uniformity of the three systems is guaranteed. The unified coordinate system selects to unify the earth coordinate system into a vehicle coordinate system, the direction of the vehicle needs to be calculated through the two groups of RTK equipment, the Euclidean distance between the two groups of RTK equipment based on the earth coordinate system can be calculated according to the coordinate information, and the Euclidean distance is divided into the transverse distance and the longitudinal distance under the vehicle coordinate system according to the direction and the distance. The calculation process is as follows:
1) and returning the orientation alpha of the vehicle based on the earth coordinate system according to the GPS coordinates of the vehicle.
2) And calculating the Euclidean distance D between the vehicle and the target GPS based on the terrestrial coordinate system according to the coordinates of the vehicle and the target GPS.
3) And calculating an angle beta between the vehicle and the target GPS under the terrestrial coordinate system according to the coordinates of the vehicle and the target GPS.
4) And obtaining an included angle theta between the two vehicles by taking the difference between alpha and beta.
5) And carrying out transverse and longitudinal decomposition on the distance according to theta to obtain a first transverse distance and a first longitudinal distance.
And then comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
In conclusion, the invention can avoid the joint calibration among multiple sensors, and realize the distance calculation between direct points according to the algorithm implementation mode to obtain accurate distance information.
The invention can avoid automatic calibration, the installation position can be relatively free, the RTK equipment only needs to ensure the same axis with the origin of the vehicle coordinate system, and the target RTK equipment selects the installation position according to the point selection principle of the visual ranging method, so the invention can avoid a large amount of algorithms and program development.
The invention only provides a method for synchronizing multiple systems, and ensures the data accuracy. The multiple sets of RTK equipment are aligned by using a GPS (global positioning system) to realize natural synchronization, however, a visual system has a system clock, and the multiple sets of RTK equipment are directly synchronized in the vision after network delay brought by network transmission, so that a large error exists. By using the RTK equipment, RTK data is received in a serial port mode, delay can be ignored, system time synchronization is carried out after GPS time is analyzed, time is used for carrying out data synchronization after clock synchronization between a plurality of groups of RTK equipment and a visual system is ensured, and accurate RTK and visual synchronization results are obtained.
As shown in fig. 3, which is a schematic structural diagram of an embodiment 1 of a system for testing precision of visual ranging disclosed in the present invention, the system may include:
the clock synchronization module 301 is configured to synchronize clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the vision system, where the first real-time dynamic differential device and the vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the vision system;
when the vision distance measurement precision needs to be tested, two sets of RTK devices (real-time kinematic differential devices) need to be accessed simultaneously, wherein the first real-time kinematic differential device is used for vehicle positioning, the second real-time kinematic differential device is used for target positioning, and data can be stored between the first real-time kinematic differential device and the second real-time kinematic differential device through a 4G network. The first real-time dynamic differential equipment used for positioning the vehicle is selected to be installed in the same vertical position as the vehicle camera, and the second real-time dynamic differential equipment used for positioning the target is selected to be an installation point according to a visual ranging point selection principle. For example, if the target ranging point is selected at the center of the rear axle, the second real-time dynamic differential device may be selected to be installed at the center of the rear axle, so as to achieve precise ranging matching.
After the first real-time dynamic differential device and the second real-time dynamic differential device are installed at corresponding positions, clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are synchronized in real time, so that the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are guaranteed to use the same group of clock sources, and accuracy of data is guaranteed.
The acquisition module 302 is configured to acquire coordinate data of the first real-time dynamic differential device, the second real-time dynamic differential device, and the visual sensor in the visual system synchronously;
and then, synchronously acquiring coordinate data of the first real-time dynamic difference device, the second real-time dynamic difference device and the visual sensor in the visual system.
A first determining module 303, configured to determine a first lateral distance and a first longitudinal distance of a target in a vehicle coordinate system based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
then, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, a first transverse distance and a first longitudinal distance of the target in a vehicle coordinate system are determined, wherein the first transverse distance and the first longitudinal distance are distance truth values of the target.
A second determination module 304 for determining a second lateral distance and a second longitudinal distance of the target in the vehicle coordinate system based on the coordinate data of the vision sensor;
and meanwhile, determining a second transverse distance and a second longitudinal distance of the target in the vehicle coordinate system according to the collected coordinate data of the visual sensor, wherein the second transverse distance and the second longitudinal distance are visual ranging values.
The comparison module 305 is configured to compare the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance, respectively, to obtain a visual ranging accuracy test result.
And finally, comparing the obtained first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
In summary, in the above embodiments, when the visual ranging accuracy needs to be tested, the clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the visual system are synchronized, where the first real-time dynamic differential device and the vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on the visual ranging point selection principle of the visual system; then synchronously acquiring coordinate data of the first real-time dynamic differential device, the second real-time dynamic differential device and a visual sensor in a visual system; determining a first transverse distance and a first longitudinal distance of a target under a vehicle coordinate system based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device; determining a second lateral distance and a second longitudinal distance of the target in the vehicle coordinate system based on the coordinate data of the vision sensor; and comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result. When the method is used for testing the visual ranging precision, joint calibration and target matching are not needed, the data precision can be ensured, and the test on the visual ranging precision is simply and effectively realized.
Fig. 4 is a schematic structural diagram of a visual ranging accuracy testing system 2 according to an embodiment of the present invention, where the system may include:
the clock synchronization module 401 is configured to synchronize clocks of the vision system based on GPS time of a first real-time dynamic differential device and a second real-time dynamic differential device, where the first real-time dynamic differential device and a vehicle camera are installed at the same vertical position, and an installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the vision system;
when the vision distance measurement precision needs to be tested, two sets of RTK devices (real-time kinematic differential devices) need to be accessed simultaneously, wherein the first real-time kinematic differential device is used for vehicle positioning, the second real-time kinematic differential device is used for target positioning, and data can be stored between the first real-time kinematic differential device and the second real-time kinematic differential device through a 4G network. The first real-time dynamic differential equipment used for positioning the vehicle is selected to be installed in the same vertical position as the vehicle camera, and the second real-time dynamic differential equipment used for positioning the target is selected to be an installation point according to a visual ranging point selection principle. For example, if the target ranging point is selected at the center of the rear axle, the second real-time dynamic differential device may be selected to be installed at the center of the rear axle, so as to achieve precise ranging matching.
After the first real-time dynamic differential device and the second real-time dynamic differential device are installed at corresponding positions, clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are synchronized in real time, so that the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system are guaranteed to use the same group of clock sources, and accuracy of data is guaranteed.
Specifically, when synchronizing the clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the vision system, the clocks of the vision system may be synchronized by the GPS time of the first real-time dynamic differential device and the second real-time dynamic differential device.
An acquisition module 402, configured to acquire coordinate data of the first real-time dynamic difference device, the second real-time dynamic difference device, and the visual sensor in the visual system synchronously;
and then, synchronously acquiring coordinate data of the first real-time dynamic difference device, the second real-time dynamic difference device and the visual sensor in the visual system.
A first determining module 403, configured to calculate, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, a euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on a terrestrial coordinate system;
then, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, a first transverse distance and a first longitudinal distance of the target in a vehicle coordinate system are determined, wherein the first transverse distance and the first longitudinal distance are distance truth values of the target.
Specifically, according to the collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on the earth coordinate system is calculated.
A first determining module 403, further configured to split the first lateral distance and the first longitudinal distance of the target in the vehicle coordinate system according to the orientation traversed distance;
then, a first lateral distance and a first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation traversed distance.
A second determination module 404 for determining a second lateral distance and a second longitudinal distance of the target in the vehicle coordinate system based on the coordinate data of the vision sensor;
and meanwhile, determining a second transverse distance and a second longitudinal distance of the target in the vehicle coordinate system according to the collected coordinate data of the visual sensor, wherein the second transverse distance and the second longitudinal distance are visual ranging values.
And a comparison module 405, configured to compare the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance, respectively, to obtain a visual ranging accuracy test result.
And finally, comparing the obtained first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
To sum up, in this embodiment, on the basis of the above embodiments, when synchronizing the clocks of the first real-time dynamic differential device, the second real-time dynamic differential device, and the vision system, the clocks of the vision system may be synchronized based on the GPS time of the first real-time dynamic differential device and the GPS time of the second real-time dynamic differential device; when a first transverse distance and a first longitudinal distance of a target under a vehicle coordinate system are determined based on coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device, calculating a Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device under a terrestrial coordinate system according to collected coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device; the first transverse distance and the first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation distance.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. A visual ranging accuracy testing method is characterized by comprising the following steps:
synchronizing a first real-time dynamic differential device, a second real-time dynamic differential device and a clock of a vision system, wherein the first real-time dynamic differential device and a vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the vision system;
synchronously acquiring coordinate data of the first real-time dynamic differential device, the second real-time dynamic differential device and a visual sensor in the visual system;
determining a first transverse distance and a first longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
determining a second lateral distance and a second longitudinal distance of the target in a vehicle coordinate system based on the coordinate data of the vision sensor;
and comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
2. The method of claim 1, wherein determining a first lateral distance and a first longitudinal distance of a target in a vehicle coordinate system based on coordinate data of the first real-time dynamic differencing device and the second real-time dynamic differencing device comprises:
calculating the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on an earth coordinate system according to the acquired coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
the first transverse distance and the first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation distance.
3. The method of claim 1, wherein synchronizing the clocks of the first real-time dynamic differencing device, the second real-time dynamic differencing device, and the vision system comprises:
and synchronizing clocks of the vision system based on the GPS time of the first real-time dynamic differential device and the second real-time dynamic differential device.
4. The method of claim 1, wherein the first real-time dynamic differencing device is mounted at a vehicle coordinate system origin and the mounting point of the second real-time dynamic differencing device is a visual ranging selection point.
5. A visual ranging accuracy testing system, comprising:
the clock synchronization module is used for synchronizing clocks of the first real-time dynamic differential device, the second real-time dynamic differential device and the visual system, wherein the first real-time dynamic differential device and the vehicle camera are installed at the same vertical position, and the installation position of the second real-time dynamic differential device is determined based on a visual ranging point selection principle of the visual system;
the acquisition module is used for synchronously acquiring the first real-time dynamic difference device, the second real-time dynamic difference device and coordinate data of a visual sensor in the visual system;
the first determining module is used for determining a first transverse distance and a first longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the first real-time dynamic difference device and the second real-time dynamic difference device;
a second determination module to determine a second lateral distance and a second longitudinal distance of a target in a vehicle coordinate system based on the coordinate data of the vision sensor;
and the comparison module is used for comparing the first transverse distance and the first longitudinal distance with the second transverse distance and the second longitudinal distance respectively to obtain a visual ranging precision test result.
6. The system of claim 5, wherein the first determination module is specifically configured to:
calculating the Euclidean distance between the first real-time dynamic differential device and the second real-time dynamic differential device based on an earth coordinate system according to the acquired coordinate data of the first real-time dynamic differential device and the second real-time dynamic differential device;
the first transverse distance and the first longitudinal distance of the target under the vehicle coordinate system are split according to the orientation distance.
7. The system of claim 5, wherein the clock synchronization module is specifically configured to:
and synchronizing clocks of the vision system based on the GPS time of the first real-time dynamic differential device and the second real-time dynamic differential device.
8. The system of claim 5, wherein the first real-time dynamic differencing device is mounted at the origin of a vehicle coordinate system and the mounting point of the second real-time dynamic differencing device is a visual ranging selection point.
CN202011573046.4A 2020-11-20 2020-12-25 Visual ranging precision testing method and system Pending CN112729341A (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2020113139253 2020-11-20
CN202011313925 2020-11-20

Publications (1)

Publication Number Publication Date
CN112729341A true CN112729341A (en) 2021-04-30

Family

ID=75617130

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011573046.4A Pending CN112729341A (en) 2020-11-20 2020-12-25 Visual ranging precision testing method and system

Country Status (1)

Country Link
CN (1) CN112729341A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116026349A (en) * 2022-12-30 2023-04-28 吉咖智能机器人有限公司 Method, apparatus, electronic device and medium for vehicle distance measurement

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108845343A (en) * 2018-07-03 2018-11-20 河北工业大学 The vehicle positioning method that a kind of view-based access control model, GPS are merged with high-precision map
CN109166155A (en) * 2018-09-26 2019-01-08 北京图森未来科技有限公司 A kind of calculation method and device of vehicle-mounted binocular camera range error
CN109781120A (en) * 2019-01-25 2019-05-21 长安大学 A kind of vehicle combination localization method based on synchronous positioning composition
CN110221326A (en) * 2019-05-29 2019-09-10 中国第一汽车股份有限公司 Vehicle positioning method, device, equipment and storage medium
CN110843772A (en) * 2019-11-19 2020-02-28 腾讯科技(深圳)有限公司 Method, device, equipment and storage medium for judging relative direction of potential collision
CN111429527A (en) * 2020-03-24 2020-07-17 广东星舆科技有限公司 Method and system for automatically calibrating external parameters of vehicle-mounted camera
CN111928862A (en) * 2020-08-10 2020-11-13 廊坊和易生活网络科技股份有限公司 Method for constructing semantic map on line by fusing laser radar and visual sensor

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108845343A (en) * 2018-07-03 2018-11-20 河北工业大学 The vehicle positioning method that a kind of view-based access control model, GPS are merged with high-precision map
CN109166155A (en) * 2018-09-26 2019-01-08 北京图森未来科技有限公司 A kind of calculation method and device of vehicle-mounted binocular camera range error
CN109781120A (en) * 2019-01-25 2019-05-21 长安大学 A kind of vehicle combination localization method based on synchronous positioning composition
CN110221326A (en) * 2019-05-29 2019-09-10 中国第一汽车股份有限公司 Vehicle positioning method, device, equipment and storage medium
CN110843772A (en) * 2019-11-19 2020-02-28 腾讯科技(深圳)有限公司 Method, device, equipment and storage medium for judging relative direction of potential collision
CN111429527A (en) * 2020-03-24 2020-07-17 广东星舆科技有限公司 Method and system for automatically calibrating external parameters of vehicle-mounted camera
CN111928862A (en) * 2020-08-10 2020-11-13 廊坊和易生活网络科技股份有限公司 Method for constructing semantic map on line by fusing laser radar and visual sensor

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116026349A (en) * 2022-12-30 2023-04-28 吉咖智能机器人有限公司 Method, apparatus, electronic device and medium for vehicle distance measurement
CN116026349B (en) * 2022-12-30 2024-03-19 吉咖智能机器人有限公司 Method, apparatus, electronic device and medium for vehicle distance measurement

Similar Documents

Publication Publication Date Title
CN111559372B (en) Parking space detection performance evaluation method of parking system and electronic equipment
CN112285676B (en) Laser radar and IMU external parameter calibration method and device
CN112086010B (en) Map generation method, map generation device, map generation equipment and storage medium
CN110081881A (en) It is a kind of based on unmanned plane multi-sensor information fusion technology warship bootstrap technique
WO2022121672A1 (en) Positioning accuracy evaluation method and apparatus
CN110032201A (en) A method of the airborne visual gesture fusion of IMU based on Kalman filtering
CN111080682B (en) Registration method and device for point cloud data
CN113514821B (en) Positioning method, device and system based on time-varying time difference
CN113537287A (en) Multi-sensor information fusion method and device, storage medium and automatic driving system
CN111983655A (en) Method and device for determining urban canyon region, electronic device and storage medium
CN112313536B (en) Object state acquisition method, movable platform and storage medium
CN112729341A (en) Visual ranging precision testing method and system
CN117852319A (en) Space target visibility judging method for space foundation situation awareness system
CN112710343B (en) RT-based vehicle-mounted sensor performance test method
CN217981856U (en) Laser radar test system and vehicle
CN116182905A (en) Laser radar and combined inertial navigation space-time external parameter calibration method, device and system
CN114488039A (en) Radar precision detection method and equipment
US10670730B2 (en) Measuring system and measuring method for model based generation of global navigation satellite system signals
Bogatin et al. Evaluation of linear Kalman filter processing geodetic kinematic measurements
Margaria et al. Proof-of-concept of the local integrity approach: Prototype implementation and performance assessment in an urban context
CN110796707A (en) Calibration parameter calculation method, calibration parameter calculation device and storage medium
CN113625319B (en) Non-line-of-sight signal detection method and device based on ensemble learning
CN117763818A (en) Vehicle-mounted laser radar simulation model evaluation method and device and computer equipment
CN117207990A (en) Method, device, equipment and storage medium for determining course angle of target vehicle
CN115267838A (en) Method, device, equipment and medium for testing positioning performance

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