CN110068814A - A kind of method and device measuring obstacle distance - Google Patents
A kind of method and device measuring obstacle distance Download PDFInfo
- Publication number
- CN110068814A CN110068814A CN201910238525.1A CN201910238525A CN110068814A CN 110068814 A CN110068814 A CN 110068814A CN 201910238525 A CN201910238525 A CN 201910238525A CN 110068814 A CN110068814 A CN 110068814A
- Authority
- CN
- China
- Prior art keywords
- radar
- barrier
- distance
- vehicle
- coordinate system
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000004888 barrier function Effects 0.000 claims abstract description 146
- 238000005259 measurement Methods 0.000 claims description 24
- 238000006243 chemical reaction Methods 0.000 claims description 17
- 230000009466 transformation Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- 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
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar Systems Or Details Thereof (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
This application provides a kind of methods for measuring obstacle distance, obtain the position frame of barrier in shooting image；The shooting image is that the camera on vehicle takes the realtime graphic on vehicle current driving direction；The coordinate system of radar is converted to the coordinate system of the shooting image；Obtain the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system；The data point is clustered according to the distance between data point and the origin of coordinate system of the radar in the domain of the radar points cloud sector to obtain at a distance from the vehicle and the barrier.Using method provided by the present application, the distance between vehicle and barrier can be accurately obtained, improves the safety during automatic Pilot.Present invention also provides a kind of devices for measuring obstacle distance.
Description
Technical field
This application involves technical field of vehicle control more particularly to a kind of method and devices for measuring obstacle distance.
Background technique
Automatic Pilot technology is a kind of important technology of current automotive field, and the popular research of all big enterprises at present
Direction.Automatic Pilot technology relies primarily on the association of artificial intelligence, vision calculating, radar, monitoring device and global positioning system etc.
With cooperation, vehicle-mounted computer is allowed can to operate motor vehicles to automatic safe under the operation of nobody class active.And obstacle
Object is identified as the important link in automatic Pilot, has directly influenced the safety during automatic Pilot.
Current automatic Pilot technology obtains present road front obstacle at a distance from this vehicle by radar, but when at certain
There are, there are when partial occlusion, radar can only obtain the region and this spacing between multiple barriers and multiple barriers in a region
Position from nearest barrier, and other barriers being at least partially obscured can be ignored, this meeting so that vehicle in automatic Pilot mistake
There is security risk in driving strategy in journey.Such as (it is also possible to greenbelt, building wall, direction board when pedestrian is isolated column
Equal facilities) partial occlusion when, the isolated column on right side only may be determined as barrier in this direction and ignored by the radar of vehicle
Fall pedestrian, lead to not obtain the vehicle at a distance from pedestrian, this will lead to the driving strategy such as Path selection, row of vehicle
Sailing speed and brake moment etc., there are security risks.
Summary of the invention
In order to solve above-mentioned technical problem of the existing technology, this application provides a kind of methods of amount obstacle distance
And device, the distance between vehicle and barrier can be accurately obtained, the safety during automatic Pilot is promoted.
The embodiment of the present application provides a kind of method for measuring obstacle distance, which comprises
Obtain the position frame of barrier in shooting image；The shooting image is that the camera on vehicle takes the vehicle
Realtime graphic on current driving direction；
The coordinate system of radar is converted to the coordinate system of the shooting image；
Obtain the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system；
According to the distance between the origin of coordinate system of data point and the radar in the domain of the radar points cloud sector to institute
Data point is stated to be clustered to obtain the vehicle at a distance from the barrier.
Optionally, the coordinate system that the coordinate system of radar is converted to shooting image includes:
According to the relative position of the camera and the radar, the coordinate system of the radar is converted into the camera
Coordinate system；
The coordinate system of the camera is converted to the coordinate system of the shooting image.
Optionally, the position frame for obtaining the barrier corresponding radar points cloud in the radar fix system
Region, specifically:
Determine the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system；
Retain the corresponding radar points cloud sector domain of the position frame of the barrier and reduces the other radar points of removal
Cloud sector domain.
Optionally, between the origin of the coordinate system of the data point according in the domain of the radar points cloud sector and the radar
Distance the data point is clustered to obtain the vehicle at a distance from the barrier, specifically:
According to the distance between the origin of coordinate system of data point and the radar in the domain of the radar points cloud sector to institute
Data point is stated to be clustered to obtain the number of the barrier；
The vehicle is obtained at a distance from each barrier.
Optionally, the method also includes:
According to the vehicle at a distance from the barrier and the position frame deviates the current driving side of the vehicle
To angle obtain projector distance of the barrier on the current driving direction of the vehicle.
The embodiment of the present application also provides a kind of devices for measuring obstacle distance, and described device includes: the first acquisition list
Member, coordinate transformation unit, second acquisition unit and third acquiring unit；
The first acquisition unit, for obtaining the position frame of barrier in shooting image；The shooting image is vehicle
On camera take the realtime graphic on vehicle current driving direction；
The coordinate transformation unit, for the coordinate system of radar to be converted to the coordinate system of the shooting image；
The second acquisition unit, the position frame for obtaining the barrier are corresponding in the radar fix system
Radar points cloud sector domain；
The third acquiring unit, for the coordinate system according to data point and the radar in the domain of the radar points cloud sector
The distance between origin the data point is clustered to obtain the vehicle at a distance from the barrier.
Optionally, the converting unit specifically includes: the first conversion subunit and the second conversion subunit；
First conversion subunit, according to the relative position of the camera and the radar, by the seat of the radar
Mark system is converted to the coordinate system of the camera；
Second conversion subunit, for the coordinate system of the camera to be converted to the coordinate of the shooting image
System.
Optionally, the second acquisition unit specifically includes: position determines subelement and cuts subelement；
The position determines subelement, and the position frame for determining the barrier is right in the radar fix system
The radar points cloud sector domain answered；
The cutting subelement, for retaining the corresponding radar points cloud sector domain of the position frame of the barrier simultaneously
Reduce removal other radar points cloud sectors domain.
Optionally, the third acquiring unit specifically includes: number determines subelement and apart from acquisition subelement；
The number determines subelement, for the coordinate according to data point and the radar in the domain of the radar points cloud sector
The distance between origin of system clusters the data point to obtain the number of the barrier；
The distance obtains subelement, for obtaining the vehicle at a distance from each barrier.
Optionally, described device further include: the 4th acquiring unit；
4th acquiring unit, for according to the vehicle at a distance from the barrier and the position frame deviate
The angle in the current driving direction of the vehicle obtains throwing of the barrier on the current driving direction of the vehicle
Shadow distance.
Herein described method has the advantage that
This application provides a kind of methods for measuring obstacle distance, which comprises obtains obstacle in shooting image
The position frame of object determines the direction of the relatively described vehicle of barrier in shooting image；The shooting image is on vehicle
Camera take the realtime graphic on vehicle current driving direction；The coordinate system of radar is converted into shooting image
Coordinate system, to obtain position of the point cloud in the coordinate system of shooting image in the radar fix system；Obtain the barrier
The position frame in the radar fix system corresponding radar points cloud sector domain；According to the data in the domain of the radar points cloud sector
The distance between point and the origin of coordinate system of the radar cluster to obtain the data point in the domain of the radar points cloud sector
Take the vehicle at a distance from the barrier, there are the barriers in the domain of described cloud sector, and radar is with several group of data points
At point cloud characterize the barrier, the data point of the same barrier will be characterized as same class, then in radar points cloud sector
Distance of such data point on the coordinate system of radar apart from coordinate origin in domain is identical, and such distance is institute
State the distance between vehicle and barrier.Using method provided by the present application, can accurately obtain between vehicle and barrier
Distance, improve the safety during automatic Pilot and fluency.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of flow chart of the method for measurement obstacle distance that the embodiment of the present application one provides；
Fig. 2 is the schematic diagram of a scenario of the method for the measurement obstacle distance that the embodiment of the present application one provides；
Fig. 3 is another schematic diagram of a scenario of the method for the measurement obstacle distance that the embodiment of the present application one provides；
Fig. 4 is the flow chart of the method for another measurement obstacle distance that the embodiment of the present application two provides；
Fig. 5 is the schematic diagram of a scenario of the method for the measurement obstacle distance that the embodiment of the present application two provides；
Fig. 6 is a kind of schematic diagram of the device for measurement obstacle distance that the embodiment of the present application two provides；
Fig. 7 is the schematic diagram of the device for another measurement obstacle distance that the embodiment of the present application two provides.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
Embodiment one:
The embodiment of the present application one provides a kind of method for measuring obstacle distance, illustrates with reference to the accompanying drawing.
Referring to Fig. 1, which is a kind of flow chart of the method for measurement obstacle distance that the embodiment of the present application one provides.
Referring also to Fig. 2, which is that the scene of the method for the measurement obstacle distance that the embodiment of the present application one provides is shown
It is intended to.
The embodiment of the present application the described method comprises the following steps:
S101: the position frame of barrier in shooting image is obtained.
The shooting image is that the camera on vehicle takes the realtime graphic on vehicle current driving direction.Before
The shooting image is inputted in default neural network and carries out deep learning to judge whether there is obstacle in the shooting image
Object, if so, including the barrier with rectangle frame, for details, reference can be made to scene shown in Fig. 2, the position frame is just complete
Rectangle frame comprising the barrier.The application is not especially limited the quantity of barrier, it is thus possible to can be from the shooting
Multiple position frames are obtained in image.
In addition, under a kind of possible scene, before having partial occlusion, such as the vehicle between multiple barriers
There are two barriers, the first barriers therein to block to the formation of the second barrier for side, specifically may refer to field shown in Fig. 3
Scape only includes location information of the barrier on the coordinate system of the shooting image, not since shooting figure seems two dimensional image
Range information comprising barrier Yu the vehicle, it is thus possible to will appear include in a position frame multiple barriers feelings
Condition, the application are not especially limited the number of the barrier in the position frame.
It should be noted that the camera can be set in the top of the vehicle, also can be set in the vehicle
Point rear seat windscreen at be respectively used to shooting advance and reversing when realtime graphic, other suitable positions can also be set to,
The application is not especially limited this.
S102: the coordinate system of radar is converted to the coordinate system of the shooting image.
The coordinate system of the shooting image is the two-dimensional coordinate system established based on the shooting image, in a kind of possible reality
In existing mode, the coordinate system of the shooting image is using the midpoint of the shooting image as coordinate origin, with horizontal direction and vertically
Direction is respectively that plane right-angle coordinate is established in the direction of two reference axis.
The coordinate system of the radar is the two-dimensional coordinate system established based on the radar, in a kind of possible implementation
In, the coordinate system of the radar is using radar as coordinate origin, with horizontal direction, vertical direction and vehicle current direction of advance point
Not Wei the directions of three reference axis establish rectangular coordinate system in space.
Since shooting figure seems two dimensional image, only believe comprising position of the barrier on the coordinate system of the shooting image
Breath, can not determine the barrier at a distance from the vehicle according to the shooting image.And the resulting radar of radar scanning
Point cloud is distributed in three-dimensional space, contains the range information of the barrier Yu the vehicle, therefore can be according to the bat
The position frame for taking the photograph the barrier in image obtains the corresponding point of the barrier in resulting cloud of the radar scanning
Cloud, but since the shooting figure seems two dimensional image, the coordinate system of the shooting image is two-dimensional coordinate system, and the thunder
The coordinate system reached is three-dimensional system of coordinate, it is therefore desirable to convert the coordinate system of the radar to the coordinate system of shooting image.
The process of coordinate transform is specifically described below:
A: according to the relative position of the camera and the radar, the coordinate system of the radar is converted into the camera shooting
The coordinate system of head.
B: the coordinate system of the camera is converted to the coordinate system of the shooting image.
Illustrate a kind of method for realizing coordinate transform below:
The coordinate system of the camera be using the camera as the coordinate system of the actual physical situation of origin, one kind can
In the implementation of energy, the coordinate system of the camera is using the camera as coordinate origin, with horizontal direction and vertical direction
Plane right-angle coordinate is established in the direction of respectively two reference axis.
The coordinate system of the shooting image and the coordinate system of the camera are two-dimensional coordinate system, and the conversion process relates to
And the transformation of scale of coordinate, it may be implemented the point on the coordinate system of the shooting image being mapped to institute by the conversion of coordinate system
It states on the coordinate system of camera, the point P (x, y) on coordinate system for shooting image is mapped in the coordinate of the camera
It fastens as P1(x1, y1), then have:
Formula (1) k therein is proportionality coefficient, and the value of k can be determined that k value can quilt by the performance parameter of the camera
It measures in advance, and when the working condition of the camera is fixed, the value of k is fixed.
First using the camera as coordinate origin, distinguished with the direction of advance of horizontal direction, vertical direction and the vehicle
Assist three-dimensional rectangular coordinate system is established for reference axis, the point P that the former two-dimensional coordinate of the camera is fastened1(x1, y1) be mapped in
It is P in the assist three-dimensional rectangular coordinate system2(x1, y1, z1), wherein z1For the camera and point P1Distance in the vehicle
Direction of advance on projector distance.
After the position of the camera and the radar on the vehicle determines, the relative position of the two is also determined, is used
Position (x of the radar in the assist three-dimensional rectangular coordinate system0, y0, z0) indicate the radar and the camera
Relative position, wherein x0, y0And z0It is known that by the P in assist three-dimensional rectangular coordinate system2(x1, y1, z1) it is mapped to the seat of radar
It is P in mark system3(x2, y2, z2), wherein z2For the radar and point P3Projection of the distance in the direction of advance of the vehicle away from
From then having:
x2=x1-x0 (2)
y2=y1-y0 (3)
z2=z1-z0 (4)
The application is not especially limited the position that the radar is installed on the vehicle, in a kind of possible implementation
In, the radar may be mounted at vehicle forefront and rearmost, be respectively used to vehicle driving road when detection advances and moves backward
Barrier on diameter.In addition, the coordinate transform process can be completed on the vehicle-mounted computer of the vehicle, it can also be by long-range
It is completed in terminal, the application is not especially limited this.
Coordinate transform can also be realized by other methods, the application is not specifically limited in this embodiment.
S103: the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system is obtained.
Complete to obtain after coordinate conversion the point in the position frame be mapped to it is corresponding described after the coordinate system of the radar
Radar points cloud sector domain has determined position of the radar points cloud sector domain in the radar fix system in horizontal direction and vertical
Position on direction.
Since resulting cloud of the radar scanning is distributed in three-dimensional space, it is understood that there may be many non-barriers are also by thunder
It is arrived up to scanning, therefore in order to improve the subsequent efficiency clustered to data point, it can also point resulting to the radar scanning
Cloud is cut.
In one possible implementation, only retain the barrier after cutting to resulting cloud of the radar scanning
The position frame corresponding radar points cloud sector domain for hindering object can remove the other non-barrier resulting radar points cloud sector domains of scanning
Influence, reference can be made to shown in Fig. 2, the region that the dotted line that four vertex of Obstacle Position frame are connect with radar in Fig. 2 is constituted is i.e.
For the position frame corresponding radar points cloud sector domain of the barrier.
In alternatively possible implementation, according to the shooting angle range of the camera to the radar scanning institute
The point cloud obtained is cut, and the radar points cloud sector domain after cutting is the shooting area of the camera, in the shooting angle of camera
After degree confirmation, the cutting can be previously-completed, if the camera has taken the barrier, cut resulting cloud sector
Position frame corresponding radar points cloud sector domain described in the barrier is certainly existed in domain, can either remove the other non-barriers of scanning
The influence in resulting radar points cloud sector domain, while saving the used time for cutting radar points cloud.
S104: according to the distance between the origin of coordinate system of data point and the radar in the domain of the radar points cloud sector
The data point is clustered to obtain the vehicle at a distance from the barrier.
In the domain of described cloud sector there are the barrier, radar with several group of data points at point cloud characterize the obstacle
The data point for characterizing the same barrier can be become same class by object, therefore such data point in the domain of radar points cloud sector is in thunder
Distance on the coordinate system reached apart from coordinate origin is identical, and such distance is between the vehicle and barrier
Distance carries out the data point according to the distance between the origin of coordinate system of data point and radar in the domain of radar points cloud sector
Cluster, the distance between the corresponding barrier of available each classification and vehicle.
In one possible implementation, if causing practical in the position frame because multiple barriers block mutually
Contain multiple barriers, reference can be made to scene shown in Fig. 3, according at a distance from the vehicle to the corresponding radar of the position frame
Multiple classes can be obtained by putting after the data point in the domain of cloud sector is clustered, every a kind of all corresponding barrier, corresponding to every class
Distance is then the barrier corresponding to such at a distance from the vehicle.
It should be noted that the process of above-mentioned steps herein described method merely for convenience of description, do not constitute pair
The restriction of herein described method.
The embodiment of the present application provides a kind of method for measuring obstacle distance, and the method is by obtaining in shooting image
The position frame of barrier determines the direction of the relatively described vehicle of barrier in shooting image；The shooting image is vehicle
Camera on takes the realtime graphic on vehicle current driving direction；By the coordinate system conversion of the shooting image
The direction of the relatively described vehicle of the barrier, nothing can only be determined since shooting image is two dimensional image for the coordinate system of radar
Method determines the actual distance between the vehicle and the barrier, therefore can be by way of coordinate transform, by the bat
The positional relationship for taking the photograph image is mapped in radar fix system；The position frame of the barrier is obtained in the radar fix system
In corresponding radar points cloud sector domain；According in the domain of the radar points cloud sector data point and the radar coordinate system origin it
Between distance the data point in the domain of the radar points cloud sector is clustered to obtain the vehicle at a distance from the barrier,
For the existing barrier in the domain of described cloud sector, radar be scanned after with several group of data points at point cloud characterize
The data point for characterizing the same barrier is divided into same class, the coordinate of such data point and the radar by the barrier
The distance between origin of system characterizes the distance between the vehicle and barrier.Utilize side provided by the embodiments of the present application
Method can accurately obtain the distance between vehicle and barrier, improve the safety during automatic Pilot and fluency.
Embodiment two:
The embodiment of the present application two additionally provides the method for another measurement obstacle distance, with reference to the accompanying drawing specifically
It is bright.
Referring to fig. 4, which is the flow chart of the method for another measurement obstacle distance that the embodiment of the present application two provides.
Referring also to Fig. 5, which is that the scene of the method for the measurement obstacle distance that the embodiment of the present application two provides is shown
It is intended to.
The embodiment of the present application the described method comprises the following steps:
S101: the position frame of barrier in shooting image is obtained.
S102a: according to the relative position of the camera and the radar, the coordinate system of the radar is converted to described
The coordinate system of camera.
S102b: the coordinate system of the camera is converted to the coordinate system of the shooting image.
S103a: the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system is determined.
S103b: retain the corresponding radar points cloud sector domain of the position frame of the barrier and reduce removal it is other
Radar points cloud sector domain.
S104a: according between the origin of the coordinate system of data point and the radar in the domain of the radar points cloud sector away from
From being clustered to the data point to obtain the number of the barrier.
Cause actually to contain multiple barriers in the position frame due to multiple barriers block mutually, according to it is described
The distance of vehicle can obtain multiple classes after clustering to the data point in the domain of the position frame corresponding radar points cloud sector, each
Class all corresponds to a barrier, determines that the number of the class has determined the number of the barrier, distance corresponding to every class
It is then the barrier corresponding to such at a distance from the vehicle.
S104b: the vehicle is obtained at a distance from each barrier.
S105: according to the vehicle at a distance from the barrier and the position frame deviates the current line of the vehicle
The angle for sailing direction obtains projector distance of the barrier on the current driving direction of the vehicle.
For details, reference can be made to shown in Fig. 5, L is the vehicle at a distance from the barrier in Fig. 5, and β is that position frame deviates vehicle
Current driving direction angle, D be projector distance of the barrier on the current driving direction of the vehicle.
Since the barrier tends not to the front in the vehicle, so usually L > D, if the vehicle and the obstacle
When object has potential risk of collision, since the current driving direction of the vehicle is different from the line of the vehicle and the barrier
Direction, the driving strategy made according to L may have security risk, for example, may result in brake moment of vehicle compared with
Evening.Therefore the available projector distance D is so that the vehicle can make more correct safety according to the projector distance
Driving strategy.
The projector distance can be found out by following equation:
D=L × COS β (5)
It should be noted that the process of above-mentioned steps herein described method merely for convenience of description, do not constitute pair
The restriction of herein described method appropriate to above-mentioned steps progress can also be adjusted to obtain other possible implementations,
Such as in one possible implementation, former S102a can be revised as " according to the opposite position of the camera and the radar
Set, the coordinate system of the radar be converted to the coordinate system of the camera " former S102b is adjusted to " by the camera shooting simultaneously
The coordinate system of head is converted to the coordinate system of the shooting image ", coordinate transform process adjusted is converted with the coordinate before adjustment
Process on the contrary, also may be implemented determines the position frame of the barrier corresponding radar points cloud in the radar fix system
Region.
Using method provided by the embodiments of the present application, the distance between vehicle and barrier can be accurately obtained, simultaneously
The barrier can be obtained in the vehicle according to the angle that the position frame deviates the current driving direction of the vehicle
Projector distance on the current driving direction, so that the vehicle can make more correct safety according to the projector distance
Driving strategy, further improve the safety during automatic Pilot and fluency.
Embodiment three:
The method of the measurement obstacle distance provided based on the above embodiment, the embodiment of the present application three additionally provide a kind of survey
The device for measuring obstacle distance, illustrates with reference to the accompanying drawing.
Referring to Fig. 6, which is a kind of structure chart of the device for measurement obstacle distance that the embodiment of the present application three provides.
The embodiment of the present application described device includes: first acquisition unit 601, coordinate transformation unit 602, second acquisition unit
603 and third acquiring unit 604.
The first acquisition unit 601, for obtaining the position frame of barrier in shooting image；The shooting image is vehicle
Camera on takes the realtime graphic on vehicle current driving direction.
The coordinate transformation unit 602, for the coordinate system of radar to be converted to the coordinate system of shooting image.
The second acquisition unit 603, for obtaining the position frame of the barrier in the radar fix system
Corresponding radar points cloud sector domain.
The third acquiring unit 604, for the seat according to data point and the radar in the domain of the radar points cloud sector
The distance between the origin for marking system clusters the data point to obtain the number distance of the barrier to the data
Point is clustered to obtain the vehicle at a distance from the barrier.
It should be noted that words such as " first ", " second " and " third " described in the embodiment of the present application are intended merely to convenient pair
Described device is illustrated, and does not constitute the restriction to described device.
The embodiment of the present application provides a kind of device for measuring obstacle distance, and described device is obtained by first acquisition unit
The position frame for taking barrier in shooting image determines the direction of the relatively described vehicle of barrier in shooting image；It is described
Shooting image is that the camera on vehicle takes the realtime graphic on vehicle current driving direction；It is converted by coordinate single
The coordinate system of radar is converted to the coordinate system of shooting image by member；Institute's rheme of the barrier is obtained by second acquisition unit
Set frame corresponding radar points cloud sector domain in the radar fix system；By third acquiring unit according to the coordinate with the radar
The distance between origin of system clusters to obtain the vehicle and the barrier data point in the domain of the radar points cloud sector
The distance for hindering object, due in the domain of described cloud sector there are the barrier, radar with several group of data points at point cloud characterize
The barrier, therefore the data point that the same barrier is characterized after clustering can become same class, and such distance is
The distance between the vehicle and barrier.Using device provided by the embodiments of the present application, vehicle and barrier can be accurately obtained
Hinder the distance between object, safety and fluency during promotion automatic Pilot.
Example IV:
The embodiment of the present application four additionally provides the device of another measurement obstacle distance, with reference to the accompanying drawing specifically
It is bright.
Referring to Fig. 7, which is the flow chart of the device for another measurement obstacle distance that the embodiment of the present application four provides.
The embodiment of the present application described device on the basis of three described device of embodiment further include: the 4th acquiring unit 705.
4th acquiring unit 705, for according to the vehicle at a distance from the barrier and the position frame
The angle for deviateing the current driving direction of the vehicle obtains the barrier on the current driving direction of the vehicle
Projector distance.
The converting unit of the present embodiment described device specifically includes: the first conversion subunit 602a and the second conversion subunit
602b。
The first conversion subunit 602a will be described for the relative position according to the camera and the radar
The coordinate system of radar is converted to the coordinate system of the camera.
The second conversion subunit 602b, for the coordinate system of the camera to be converted to the seat of the shooting image
Mark system.
The second acquisition unit of the present embodiment described device specifically includes: position determines subelement 603a and cuts subelement
604b。
The position determines subelement 603a, for determining the position frame of the barrier in the radar fix system
In corresponding radar points cloud sector domain.
The cutting subelement 604b, the corresponding radar points cloud sector of the position frame for retaining the barrier
Simultaneously reduce removal other radar points cloud sectors domain in domain.
The third acquiring unit of the present embodiment described device specifically includes: number determines subelement 604a and apart from acquisition
Unit 604b.
The number determines subelement 604a, for according in the domain of the radar points cloud sector data point and the radar
The distance between origin of coordinate system clusters the data point to obtain the number distance of the barrier to the number
Strong point is clustered to obtain the number of the barrier.
The distance obtains subelement 604b, for obtaining the vehicle at a distance from each barrier.
It should be noted that the words side of being intended merely to such as " first ", " second ", " third " and " the 4th " in the embodiment of the present application
Just described device is illustrated, does not constitute the restriction to described device.
Device provided by the embodiments of the present application can not only accurately obtain the distance between vehicle and barrier, simultaneously
4th acquiring unit is using the vehicle is at a distance from the barrier and the position frame deviates working as the vehicle
The angle of preceding driving direction obtains projector distance of the barrier on the current driving direction of the vehicle, so that institute
More correct safe driving strategy can be made according to the projector distance by stating vehicle, further improve automatic Pilot process
In safety and fluency.
It should be appreciated that in this application, " at least one (item) " refers to one or more, and " multiple " refer to two or two
More than a."and/or" indicates may exist three kinds of relationships, for example, " A and/or B " for describing the incidence relation of affiliated partner
It can indicate: only exist A, only exist B and exist simultaneously tri- kinds of situations of A and B, wherein A, B can be odd number or plural number.Word
Symbol "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or"." at least one of following (a) " or its similar expression, refers to
Any combination in these, any combination including individual event (a) or complex item (a).At least one of for example, in a, b or c
(a) can indicate: a, b, c, " a and b ", " a and c ", " b and c ", or " a and b and c ", and wherein a, b, c can be individually, can also
To be multiple.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.The apparatus embodiments described above are merely exemplary, wherein described be used as separate part description
Unit and module may or may not be physically separated.Furthermore it is also possible to select it according to the actual needs
In some or all of unit and module achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying
In the case where creative work, it can understand and implement.
The above is only the specific embodiment of the application, it is noted that for the ordinary skill people of the art
For member, under the premise of not departing from the application principle, several improvements and modifications can also be made, these improvements and modifications are also answered
It is considered as the protection scope of the application.
Claims (10)
1. a kind of method for measuring obstacle distance, which is characterized in that the described method includes:
Obtain the position frame of barrier in shooting image；The shooting image takes the vehicle for the camera on vehicle and works as
Realtime graphic in preceding driving direction；
The coordinate system of radar is converted to the coordinate system of the shooting image；
Obtain the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system；
According to the distance between the origin of coordinate system of data point and the radar in the domain of the radar points cloud sector to the number
Strong point is clustered to obtain the vehicle at a distance from the barrier.
2. the method for measurement obstacle distance according to claim 1, which is characterized in that the coordinate system by radar turns
Being changed to the coordinate system for shooting image includes:
According to the relative position of the camera and the radar, the coordinate system of the radar is converted to the seat of the camera
Mark system；
The coordinate system of the camera is converted to the coordinate system of the shooting image.
3. the method for measurement obstacle distance according to claim 2, which is characterized in that the acquisition barrier
The position frame corresponding radar points cloud sector domain in the radar fix system, specifically:
Determine the position frame of the barrier corresponding radar points cloud sector domain in the radar fix system；
Retain the corresponding radar points cloud sector domain of the position frame of the barrier and reduces the other radar points cloud sectors of removal
Domain.
4. the method for measurement obstacle distance according to claim 3, which is characterized in that described according to the radar points cloud
The distance between the origin of coordinate system of data point and the radar in region clusters to obtain the data point
Vehicle is stated at a distance from the barrier, specifically:
According to the distance between the origin of coordinate system of data point and the radar in the domain of the radar points cloud sector to the thunder
It is clustered up to the data point in cloud sector domain to obtain the number of the barrier；
The vehicle is obtained at a distance from each barrier.
5. the method for measurement obstacle distance according to claim 1, which is characterized in that the method also includes:
According to the vehicle at a distance from the barrier and the position frame deviates the current driving direction of the vehicle
Angle obtains projector distance of the barrier on the current driving direction of the vehicle.
6. a kind of device for measuring obstacle distance, which is characterized in that described device includes: first acquisition unit, coordinate conversion
Unit, second acquisition unit and third acquiring unit；
The first acquisition unit, for obtaining the position frame of barrier in shooting image；The shooting image is on vehicle
Camera takes the realtime graphic on vehicle current driving direction；
The coordinate transformation unit, for the coordinate system of radar to be converted to the coordinate system of the shooting image；
The second acquisition unit, for obtaining the position frame of the barrier corresponding thunder in the radar fix system
Up to a cloud sector domain；
The third acquiring unit, for according to the data point and the original of the coordinate system of the radar in the domain of the radar points cloud sector
The distance between point clusters the data point to obtain the vehicle at a distance from the barrier.
7. the device of measurement obstacle distance according to claim 6, which is characterized in that the converting unit is specifically wrapped
It includes: the first conversion subunit and the second conversion subunit；
First conversion subunit, for the relative position according to the camera and the radar, by the seat of the radar
Mark system is converted to the coordinate system of the camera；
Second conversion subunit, for the coordinate system of the camera to be converted to the coordinate system of the shooting image.
8. the device of measurement obstacle distance according to claim 7, which is characterized in that the second acquisition unit is specific
It include: that position determines subelement and cuts subelement；
The position determines subelement, and the position frame for determining the barrier is corresponding in the radar fix system
Radar points cloud sector domain；
The cutting subelement, for retaining the corresponding radar points cloud sector domain of the position frame of the barrier and reducing
Remove other radar points cloud sectors domain.
9. the device of measurement obstacle distance according to claim 8, which is characterized in that the third acquiring unit is specific
It include: that number determines subelement and apart from acquisition subelement；
The number determines subelement, for according to the data point and the coordinate system of the radar in the domain of the radar points cloud sector
The distance between origin clusters the data point to obtain the number of the barrier；
The distance obtains subelement, for obtaining the vehicle at a distance from each barrier.
10. the device of measurement obstacle distance according to claim 6, which is characterized in that described device further include: the 4th
Acquiring unit；
4th acquiring unit, for according to the vehicle at a distance from the barrier and the position frame deviate described in
The angle in the current driving direction of vehicle obtain projection of the barrier on the current driving direction of the vehicle away from
From.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910238525.1A CN110068814B (en) | 2019-03-27 | 2019-03-27 | Method and device for measuring distance of obstacle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910238525.1A CN110068814B (en) | 2019-03-27 | 2019-03-27 | Method and device for measuring distance of obstacle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110068814A true CN110068814A (en) | 2019-07-30 |
| CN110068814B CN110068814B (en) | 2021-08-24 |
Family
ID=67366627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910238525.1A Active CN110068814B (en) | 2019-03-27 | 2019-03-27 | Method and device for measuring distance of obstacle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110068814B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112364888A (en) * | 2020-10-16 | 2021-02-12 | 爱驰汽车（上海）有限公司 | Point cloud data processing method and device, computing equipment and computer storage medium |
| CN112379674A (en) * | 2020-11-26 | 2021-02-19 | 中国第一汽车股份有限公司 | Automatic driving equipment and system |
| CN112445215A (en) * | 2019-08-29 | 2021-03-05 | 阿里巴巴集团控股有限公司 | Automatic guided vehicle driving control method, device and computer system |
| CN112668371A (en) * | 2019-10-16 | 2021-04-16 | 北京京东乾石科技有限公司 | Method and apparatus for outputting information |
| CN112802092A (en) * | 2021-01-29 | 2021-05-14 | 深圳一清创新科技有限公司 | Obstacle sensing method and device and electronic equipment |
| CN113223076A (en) * | 2021-04-07 | 2021-08-06 | 东软睿驰汽车技术（沈阳）有限公司 | Coordinate system calibration method, device and storage medium for vehicle and vehicle-mounted camera |
| CN113376643A (en) * | 2021-05-10 | 2021-09-10 | 广州文远知行科技有限公司 | Distance detection method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5617085A (en) * | 1995-11-17 | 1997-04-01 | Mitsubishi Denki Kabushiki Kaisha | Method and apparatus for monitoring the surroundings of a vehicle and for detecting failure of the monitoring apparatus |
| CN106774296A (en) * | 2016-10-24 | 2017-05-31 | 中国兵器装备集团自动化研究所 | A kind of disorder detection method based on laser radar and ccd video camera information fusion |
| CN109270534A (en) * | 2018-05-07 | 2019-01-25 | 西安交通大学 | A kind of intelligent vehicle laser sensor and camera online calibration method |
-
2019
- 2019-03-27 CN CN201910238525.1A patent/CN110068814B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5617085A (en) * | 1995-11-17 | 1997-04-01 | Mitsubishi Denki Kabushiki Kaisha | Method and apparatus for monitoring the surroundings of a vehicle and for detecting failure of the monitoring apparatus |
| CN106774296A (en) * | 2016-10-24 | 2017-05-31 | 中国兵器装备集团自动化研究所 | A kind of disorder detection method based on laser radar and ccd video camera information fusion |
| CN109270534A (en) * | 2018-05-07 | 2019-01-25 | 西安交通大学 | A kind of intelligent vehicle laser sensor and camera online calibration method |
Non-Patent Citations (2)
| Title |
|---|
| 薛金林等: "基于信息融合的农业自主车辆障碍物检测方法", 《农业机械学报》 * |
| 邹斌等: "基于三维激光雷达的动态障碍物检测和追踪方法", 《汽车技术》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112445215A (en) * | 2019-08-29 | 2021-03-05 | 阿里巴巴集团控股有限公司 | Automatic guided vehicle driving control method, device and computer system |
| CN112668371A (en) * | 2019-10-16 | 2021-04-16 | 北京京东乾石科技有限公司 | Method and apparatus for outputting information |
| CN112668371B (en) * | 2019-10-16 | 2024-04-09 | 北京京东乾石科技有限公司 | Method and device for outputting information |
| CN112364888A (en) * | 2020-10-16 | 2021-02-12 | 爱驰汽车（上海）有限公司 | Point cloud data processing method and device, computing equipment and computer storage medium |
| CN112379674A (en) * | 2020-11-26 | 2021-02-19 | 中国第一汽车股份有限公司 | Automatic driving equipment and system |
| CN112379674B (en) * | 2020-11-26 | 2022-06-21 | 中国第一汽车股份有限公司 | Automatic driving equipment and system |
| CN112802092A (en) * | 2021-01-29 | 2021-05-14 | 深圳一清创新科技有限公司 | Obstacle sensing method and device and electronic equipment |
| CN112802092B (en) * | 2021-01-29 | 2024-04-09 | 深圳一清创新科技有限公司 | Obstacle sensing method and device and electronic equipment |
| CN113223076A (en) * | 2021-04-07 | 2021-08-06 | 东软睿驰汽车技术（沈阳）有限公司 | Coordinate system calibration method, device and storage medium for vehicle and vehicle-mounted camera |
| CN113223076B (en) * | 2021-04-07 | 2024-02-27 | 东软睿驰汽车技术（沈阳）有限公司 | Coordinate system calibration method, device and storage medium for vehicle and vehicle-mounted camera |
| CN113376643A (en) * | 2021-05-10 | 2021-09-10 | 广州文远知行科技有限公司 | Distance detection method and device and electronic equipment |
| CN113376643B (en) * | 2021-05-10 | 2024-07-16 | 广州文远知行科技有限公司 | Distance detection method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110068814B (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110068814A (en) | A kind of method and device measuring obstacle distance | |
| US11146783B2 (en) | Partial calibration target detection for improved vehicle sensor calibration | |
| JP7160040B2 (en) | Signal processing device, signal processing method, program, moving object, and signal processing system | |
| US11520349B2 (en) | Autonomous driving device | |
| CN110443225B (en) | Virtual and real lane line identification method and device based on feature pixel statistics | |
| CN110758477B (en) | Train positioning method and system based on two-dimensional code recognition | |
| JP2019096314A (en) | Vehicle position estimation device, parking lot, and vehicle control device | |
| CN106560835B (en) | A kind of guideboard recognition methods and device | |
| JP2018060512A (en) | Image generating system, program and method, and simulation system, program and method | |
| CN107703951B (en) | A kind of unmanned plane barrier-avoiding method and system based on binocular vision | |
| DE112016007429T5 (en) | Remote operating system, transport system and remote operating procedure | |
| US11326888B2 (en) | Generation of polar occlusion maps for autonomous vehicles | |
| US11403947B2 (en) | Systems and methods for identifying available parking spaces using connected vehicles | |
| WO2018066352A1 (en) | Image generation system, program and method, and simulation system, program and method | |
| CN109166353A (en) | Complex crossing guided vehicle road detection method and system in front of a kind of vehicle driving | |
| KR102373492B1 (en) | Method for correcting misalignment of camera by selectively using information generated by itself and information generated by other entities and device using the same | |
| CN109781129A (en) | A kind of road surface safety detection system and method based on inter-vehicular communication | |
| CN111348043A (en) | Method and device for determining an idealised overtaking process | |
| CN109117690A (en) | Drivable region detection method, device, equipment and storage medium | |
| CN113469045A (en) | Unmanned card-collecting visual positioning method and system, electronic equipment and storage medium | |
| JP7232604B2 (en) | NAVIGATION SYSTEM, NAVIGATION DISPLAY METHOD AND NAVIGATION DISPLAY PROGRAM | |
| CN111833443A (en) | Landmark position reconstruction in autonomous machine applications | |
| CN109297502A (en) | Laser projection pointing method and device based on image procossing Yu GPS navigation technology | |
| JP7327083B2 (en) | Region clipping method and region clipping program | |
| CN110727269B (en) | Vehicle control method and related product |
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 |