CN109212532A - Method and apparatus for detecting barrier - Google Patents
Method and apparatus for detecting barrier Download PDFInfo
- Publication number
- CN109212532A CN109212532A CN201710541847.4A CN201710541847A CN109212532A CN 109212532 A CN109212532 A CN 109212532A CN 201710541847 A CN201710541847 A CN 201710541847A CN 109212532 A CN109212532 A CN 109212532A
- Authority
- CN
- China
- Prior art keywords
- information
- barrier
- obstacle information
- obstacle
- identifier
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
This application discloses the method and apparatus for detecting barrier.One specific embodiment of the above method includes: to obtain point cloud data and millimetre-wave radar data；Point cloud data and millimetre-wave radar data are handled respectively, obtain the first obstacle information of point cloud data instruction and the second obstacle information of millimetre-wave radar data instruction；According to the first obstacle information and the second obstacle information, the first obstacle information and the second obstacle information weight shared in fusion are determined；According to above-mentioned weight, the first obstacle information and the second obstacle information are merged；According to fused obstacle information, barrier is determined.The embodiment takes full advantage of the millimetre-wave radar data that the point cloud data that laser radar obtains and millimetre-wave radar obtain, and improves the accuracy and sensitivity of detection of obstacles.
Description
Technical field
This application involves vehicle driving fields, and in particular to detection of obstacles field, more particularly to it is a kind of for detecting barrier
Hinder the method and apparatus of object.
Background technique
Millimetre-wave radar and laser radar automatic Pilot, ADAS (Advanced Driver Assistant System,
Advanced driving assistance system) etc. fields have a wide range of applications.Laser radar may be implemented accurate shape to barrier and perceive；
Millimetre-wave radar can provide effective perception data to the position of barrier, speed, and can anti-sleet interference.Due to not
There is respective advantage with sensor, therefore the safety of automatic Pilot can be improved in the data for effectively merging each sensor.
Existing fusion method has that precision is low, error estimation is larger.
Summary of the invention
The purpose of the application is to propose a kind of method and apparatus for detecting barrier, to solve background above technology
The technical issues of part is mentioned.
In a first aspect, the embodiment of the present application provides a kind of method for detecting barrier, the above method includes: to obtain
Point cloud data and millimetre-wave radar data；Point cloud data and millimetre-wave radar data are handled respectively, obtain point cloud data
Second obstacle information of the first obstacle information and millimetre-wave radar the data instruction indicated；According to the first obstacle information
And second obstacle information, determine the first obstacle information and the second obstacle information weight shared in fusion；Root
According to above-mentioned weight, the first obstacle information and the second obstacle information are merged；According to fused obstacle information, barrier is determined
Hinder object.
In some embodiments, above-mentioned that above-mentioned point cloud data and above-mentioned millimetre-wave radar data are handled respectively, packet
It includes: point cloud data being clustered, tracking processing, obtain the first obstacle information；Place is filtered to millimetre-wave radar data
Reason, obtains the second obstacle information.
In some embodiments, the first obstacle information includes first position, First Speed, the first position of barrier
The error of error and First Speed, the second obstacle information include the second position, second speed, the second position of barrier
The error of error and second speed；And above-mentioned the first obstacle information of determination and the second obstacle information are in fusion when institute
The weight accounted for, comprising: according to the error of first position and the error of First Speed, determine the first composition error；According to second
The error of position and the error of second speed, determine the second composition error；It is missed according to the first composition error and second are comprehensive
Difference, when determining the first obstacle information of fusion and the second obstacle information, the first weight of the first obstacle information and second
Second weight of obstacle information.
It is in some embodiments, above-mentioned that first obstacle information and the second obstacle information are merged according to above-mentioned weight,
It include: to be believed the first obstacle information and the second barrier according to preset first transition matrix and/or the second transition matrix
Breath is converted to the same coordinate system；According to preset obstacle information merge list, matching conversion after the first obstacle information with
And the second obstacle information after conversion；The second barrier letter after the first obstacle information and matching after fusion matching
Breath.
In some embodiments, obstacle information fusion list include history barrier identifier and with history barrier
The corresponding historical movement information of identifier, the first obstacle information include the first barrier identifier and with the first barrier mark
Know and accord with corresponding motion information, the second obstacle information include the second barrier identifier and with the second barrier identifier pair
The motion information answered；And above-mentioned the first obstacle information that list is merged according to preset obstacle information, matches after converting
And the second obstacle information after conversion, comprising: according to history barrier identifier, the first barrier identifier and second
Barrier identifier determines in obstacle information fusion list whether include the first barrier identifier and the second barrier mark
Know symbol；In response to obstacle information fusion list in include the first barrier identifier, using with the first barrier identifier pair
The corresponding historical movement information of first barrier identifier in the motion information answered more new historical barrier motion information；In response to
It includes the second barrier identifier that obstacle information, which merges in list, using motion information corresponding with the second barrier identifier
The corresponding historical movement information of second barrier identifier in more new historical barrier motion information.
In some embodiments, above-mentioned that list is merged according to preset obstacle information, the first obstacle after matching conversion
The second obstacle information after object information and conversion, comprising: in response to not including the first barrier in obstacle information fusion list
Hinder object identifier or the second barrier identifier, determines the corresponding motion information of the first barrier identifier and the second barrier
Matching degree between the corresponding motion information of identifier；It is greater than or equal to preset threshold in response to above-mentioned matching degree, determines first
Barrier identifier and the second barrier identifier indicate same barrier, and according to the corresponding movement of the first barrier identifier
First barrier identifier in information or the corresponding motion information of the second barrier identifier more new historical barrier motion information
Corresponding historical movement information or the corresponding historical movement information of the second barrier identifier.
In some embodiments, above-mentioned that list is merged according to preset obstacle information, the first obstacle after matching conversion
The second obstacle information after object information and conversion, comprising: be less than preset threshold in response to above-mentioned matching degree, believe in barrier
Increase the first obstacle information or the second obstacle information in breath fusion list.
It is in some embodiments, above-mentioned that first obstacle information and the second obstacle information are merged according to above-mentioned weight,
Include: to be filtered to the second obstacle information, obtains filtered second obstacle information；According to the first weight and
Second weight merges the first obstacle information and filtered second obstacle information.
In some embodiments, obstacle information fusion list includes the corresponding motion information of each history barrier identifier
The generation moment；And the above method further include: for each history barrier identifier pair in obstacle information fusion list
The motion information answered, determines whether the time difference between above-mentioned generation moment and current time is greater than preset duration；In response to upper
The time difference is stated greater than preset duration, deletes the corresponding motion information of history barrier identifier.
Second aspect, the embodiment of the present application provide a kind of for detecting the device of barrier, and above-mentioned apparatus includes: data
Acquiring unit, for obtaining point cloud data and millimetre-wave radar data；Data processing unit, for respectively to point cloud data and milli
Metre wave radar data are handled, what the first obstacle information and millimetre-wave radar data for obtaining point cloud data instruction indicated
Second obstacle information；Weight determining unit, for determining first according to the first obstacle information and the second obstacle information
Obstacle information and the second obstacle information weight shared in fusion；Information fusion unit is used for according to above-mentioned weight,
Merge the first obstacle information and the second obstacle information；Obstacle determination unit, for being believed according to fused barrier
Breath, determines barrier.
In some embodiments, above-mentioned data processing unit is further used for: being clustered to point cloud data, at tracking
Reason, obtains the first obstacle information；Millimetre-wave radar data are filtered, the second obstacle information is obtained.
In some embodiments, the first obstacle information includes first position, First Speed, the first position of barrier
The error of error and First Speed, the second obstacle information include the second position, second speed, the second position of barrier
The error of error and second speed；And above-mentioned weight determining unit includes: first error determining module, for according to first
The error of position and the error of First Speed, determine the first composition error；Second error determination module, for according to second
The error of the error and second speed set determines the second composition error；Weight determination module, for according to the first composition error
And second composition error, when determining the first obstacle information of fusion and the second obstacle information, the of the first obstacle information
Second weight of one weight and the second obstacle information.
In some embodiments, above- mentioned information integrated unit includes: info conversion module, for according to preset first turn
Matrix and/or the second transition matrix are changed, the first obstacle information and the second obstacle information are converted to the same coordinate system；Letter
Matching module is ceased, for merging list according to preset obstacle information, matching the first obstacle information after converting and turning
The second obstacle information after changing；Information Fusion Module, after merging the first obstacle information after matching and matching
Second obstacle information.
In some embodiments, obstacle information fusion list include history barrier identifier and with history barrier
The corresponding historical movement information of identifier, the first obstacle information include the first barrier identifier and with the first barrier mark
Know and accord with corresponding motion information, the second obstacle information include the second barrier identifier and with the second barrier identifier pair
The motion information answered；And above- mentioned information matching module is further used for: according to history barrier identifier, the first barrier mark
Know symbol and the second barrier identifier, determine obstacle information fusion list in whether include the first barrier identifier and
Second barrier identifier；In response to including the first barrier identifier in obstacle information fusion list, hinder using with first
Hinder the corresponding history fortune of the first barrier identifier in the corresponding motion information of object identifier more new historical barrier motion information
Dynamic information；In response to obstacle information fusion list in include the second barrier identifier, using with the second barrier identifier
The corresponding historical movement information of second barrier identifier in corresponding motion information more new historical barrier motion information.
In some embodiments, above- mentioned information matching module is further used for: in response in obstacle information fusion list
Do not include the first barrier identifier or the second barrier identifier, determine the corresponding motion information of the first barrier identifier with
And the second matching degree between the corresponding motion information of barrier identifier；It is greater than or equal to default threshold in response to above-mentioned matching degree
Value determines that the first barrier identifier and the second barrier identifier indicate same barrier, and is identified according to the first barrier
It accords with first in corresponding motion information or the corresponding motion information of the second barrier identifier more new historical barrier motion information
The corresponding historical movement information of barrier identifier or the corresponding historical movement information of the second barrier identifier.
In some embodiments, above- mentioned information matching module is further used for: being less than default threshold in response to above-mentioned matching degree
Value increases the first obstacle information or the second obstacle information in obstacle information fusion list.
In some embodiments, above- mentioned information integrated unit is further used for: being filtered place to the second obstacle information
Reason, obtains filtered second obstacle information；According to the first weight and the second weight, merge the first obstacle information and
Filtered second obstacle information.
In some embodiments, obstacle information fusion list includes the corresponding motion information of each history barrier identifier
The generation moment；And above-mentioned apparatus further includes information deletion unit, above- mentioned information are deleted unit and are used for: for above-mentioned barrier
Information merges the corresponding motion information of each history barrier identifier in list, determines and generates between moment and current time
Whether the time difference is greater than preset duration；It is greater than preset duration in response to the above-mentioned time difference, deletes the history barrier identifier pair
The motion information answered.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, comprising: one or more processors；Storage dress
It sets, for storing one or more programs, when said one or multiple programs are executed by said one or multiple processors, so that
Said one or multiple processors realize method described in any of the above-described embodiment.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, the program realize method described in any of the above-described embodiment when being executed by processor.
The method and apparatus provided by the above embodiment for detecting barrier of the application, get point cloud data and
After millimetre-wave radar data, point cloud data and millimetre-wave radar data are handled respectively, obtained corresponding with point cloud data
First obstacle information and the second obstacle information corresponding with millimetre-wave radar data, then according to the first obstacle information
And second obstacle information, the weight both when determining both fusions, according to obtained weight, by the first obstacle information with
And second obstacle information merged, finally according to fused information, determine barrier.The above method of the present embodiment,
The point cloud data that laser radar obtains and the millimetre-wave radar data that millimetre-wave radar obtains are taken full advantage of, barrier is improved
The accuracy and sensitivity of detection.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow chart according to one embodiment of the method for detecting barrier of the application；
Fig. 2 is that this application can be applied to exemplary system architecture figures therein；
Fig. 3 is the schematic diagram according to an application scenarios of the method for detecting barrier of the application；
Fig. 4 is to merge the first obstacle information and the second obstacle in the method for detecting barrier according to the application
The flow chart of one embodiment of object information；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for detecting barrier of the application；
Fig. 6 is adapted for the structural representation of the computer system for the terminal device or server of realizing the embodiment of the present application
Figure.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the process 100 of one embodiment of the method for detecting barrier according to the application.This implementation
The method for detecting barrier of example, comprising the following steps:
Step 101, point cloud data and millimetre-wave radar data are obtained.
In the present embodiment, point cloud data can come from laser radar, and millimetre-wave radar data can come from millimetre-wave radar.
Above-mentioned point cloud data and millimetre-wave radar data can respectively include multiframe data, the generation time of every frame data not phases
Together, all comprising the information for the barrier for including in the environment where vehicle in every frame data.Above-mentioned laser radar and millimeter
Wave radar may be mounted on vehicle, such as be mounted on unmanned vehicle, automatic driving vehicle etc..Above-mentioned barrier can be other vehicles
, pedestrian or it is any hinder vehicle driving object.
The method for detecting barrier of the present embodiment is generally executed by terminal or server, above-mentioned terminal or service
Device can be connect with vehicle communication.Terminal or server are when obtaining above-mentioned point cloud data and millimetre-wave radar data, Ke Yizhi
It connects and is obtained from the storage device that each sensor (laser radar or millimetre-wave radar) with vehicle is connect, local can also be obtained
The data of storage.It is understood that above-mentioned terminal may be mounted at vehicle when the method for the present embodiment is executed by terminal
On.
When the method for the present embodiment is executed by server, server needs to obtain point cloud data and millimeter wave thunder from vehicle
Up to data, corresponding system architecture diagram is as shown in Figure 2.In Fig. 2, system architecture 200 may include vehicle 201,202 and of network
Server 203.Network 202 between vehicle 201 and server 203 to provide the medium of communication link.Network 202 can wrap
Include various connection types, such as wired, wireless communication link or fiber optic cables etc..
Laser radar and millimetre-wave radar can be installed on vehicle 201, the barrier in the running environment of vehicle can be acquired
Hinder the point cloud data and millimetre-wave radar data of object.
Server 203 can be to provide the server of various services, such as point cloud data and millimeter wave thunder to vehicle 201
The background server handled up to data.The point cloud data and millimetre-wave radar number of the available vehicle 201 of background server
According to, and analyzed to obtain the barrier in the environment at 201 place of vehicle.
It should be noted that for detecting the method for barrier generally by server 203 provided by the embodiment of the present application
It executes, correspondingly, the device for detecting barrier is generally positioned in server 203.
It should be understood that the number of vehicle, network and server in Fig. 2 is only schematical.It, can according to needs are realized
With any number of vehicle, network and server.
Fig. 1 is returned respectively to handle point cloud data and millimetre-wave radar data in step 102, obtain point cloud data
Second obstacle information of the first obstacle information and millimetre-wave radar the data instruction indicated.
In the present embodiment, after getting point cloud data and millimetre-wave radar data, above two data can be distinguished
It is handled, obtains the first obstacle information of point cloud data instruction and the second barrier letter of millimetre-wave radar data instruction
Breath.Point cloud data and the processing carried out to millimetre-wave radar data may be the same or different.For example, can be to a cloud
Data and millimetre-wave radar data are filtered, and can also carry out the processing such as clustering to point cloud data, and to millimeter wave thunder
It is filtered up to data.Above-mentioned first obstacle information can be identical with the content that the second obstacle information is included,
It can be different.In the present embodiment, the first obstacle information and the second obstacle information can positions all including barrier, speed
The information such as degree, the error of position, the error of speed, meanwhile, it can also include the classification letter of barrier in the first obstacle information
Breath, profile information etc..
In some optional implementations of the present embodiment, to point cloud data and millimetre-wave radar in above-mentioned steps 102
Data are handled, and can be realized by following steps unshowned in Fig. 1: point cloud data is clustered, tracking processing,
Obtain the first obstacle information；Millimetre-wave radar data are filtered, the second obstacle information is obtained.
In this implementation, point cloud data can be clustered and (to divide to point cloud data, classify, be determined in environment
Barrier), tracking (determine the position and speed of barrier detected) processing, obtain the first obstacle information；It can be with
Millimetre-wave radar data are filtered, to obtain the second obstacle information, above-mentioned filtering processing may include but unlimited
In: Kalman filtering, Extended Kalman filter, lossless Kalman filtering (Unscented Kalman Filter, UKF).
Step 103, according to the first obstacle information and the second obstacle information, the first obstacle information and are determined
The two obstacle informations weight shared in fusion.
It, can be using the error of the error of position and speed as the sensing noise of hardware device in the present embodiment.Such as
Can be using the error of the error and speed of position in the first obstacle information as the sensing noise of laser radar, it can be by
Sensing noise of the error of the error and speed of position as millimetre-wave radar in two obstacle informations.Terminal or server exist
When first obstacle information and the second obstacle information are merged, the power of the two can be determined according to above-mentioned sensing noise
Weight.
In some optional implementations of the present embodiment, the first obstacle information include barrier first position,
The error of First Speed, the error of first position and First Speed, the second obstacle information include barrier the second position,
The error of second speed, the error of the second position and second speed.Then above-mentioned steps 103 specifically can be by not showing in Fig. 1
Following steps out are realized: according to the error of first position and the error of First Speed, determining the first composition error；According to
The error of the second position and the error of second speed, determine the second composition error；It is comprehensive according to the first composition error and second
Close error, determine the first obstacle information of fusion and when the second obstacle information, the first weight of the first obstacle information and
Second weight of the second obstacle information.
In this implementation, in order to comprehensively consider position when merging the first obstacle information and the second obstacle information
Error and speed influence of the error to fusion results, can be first according to the error of first position and the mistake of First Speed
Difference determines the first composition error, and determines the second composition error according to the error of the second position and the error of second speed.
When determining composition error, can the error of error and speed to position be weighted superposition.Finally, comprehensive according to first
Error and the second composition error determine the first weight of the first obstacle information and the second weight of the second obstacle information.
It is understood that the error that the weight of obstacle information includes with itself is inversely proportional, i.e., error is got in this implementation
Greatly, the weight shared by is conducive to the accuracy for improving the obstacle information that fusion obtains with regard to smaller in this way.
Step 104, according to above-mentioned weight, the first obstacle information and the second obstacle information are merged.
Terminal or server, can be with after the weight of weight and the second obstacle information that the first obstacle information has been determined
According to above-mentioned weight, the first obstacle information and the second obstacle information are merged.
Step 105, according to fused obstacle information, barrier is determined.
After merging the first obstacle information and the second obstacle information, can according to fused obstacle information,
Determine barrier.It is understood that in fused obstacle information, may include the classification of barrier, profile, position,
The specifying informations such as speed, driving direction, terminal or server can specifically determine barrier after obtaining above- mentioned information, with
Driving strategy is provided.
It is that one of the application scenarios of the method according to the present embodiment for detecting barrier shows with continued reference to Fig. 3, Fig. 3
It is intended to.In the application scenarios of Fig. 3, laser radar 311 and millimetre-wave radar 312 are installed, wherein laser radar on vehicle 31
311 can obtain point cloud data, the available millimeter wave thunder of millimetre-wave radar 312 by the environment where scanning vehicle 31
Up to data.Above-mentioned point cloud data and millimetre-wave radar data are sent to server 33 by vehicle 31, and server 33 handles above-mentioned number
According to rear, the first obstacle information and the second obstacle information are obtained, the first weight of then getting back and the second weight finally merge
Determine obstacle information.Determining obstacle information is sent to vehicle 31, vehicle 31 passes through the letter that resolution server 33 is sent
Breath, determines that vehicle front has a group traveling together 32, to formulate driving strategy pedestrian 32 to avoid collision.
The method provided by the above embodiment for detecting barrier of the application, is getting point cloud data and millimeter wave
After radar data, point cloud data and millimetre-wave radar data are handled respectively, obtain the first barrier corresponding with point cloud data
Hinder object information and the second obstacle information corresponding with millimetre-wave radar data, then according to the first obstacle information and
Two obstacle informations, determine fusion both when both weight, according to obtained weight, by the first obstacle information and second
Obstacle information is merged, and finally according to fused information, determines barrier.The above method of the present embodiment, sufficiently benefit
The millimetre-wave radar data that the point cloud data and millimetre-wave radar obtained with laser radar obtains, improve detection of obstacles
Accuracy and sensitivity.
With continued reference to Fig. 4, it illustrates merge the first barrier in the method for detecting barrier according to the application
Information and the process of the second obstacle information 400.As shown in figure 4, can realize fusion by following steps in the present embodiment
First obstacle information and the second obstacle information:
Step 401, according to preset first transition matrix and/or the second transition matrix, by the first obstacle information and
Second obstacle information is converted to the same coordinate system.
In the present embodiment, the first obstacle information is obtained by Point Cloud Processing, and point cloud data is acquired by laser radar, then
First obstacle information is located in laser radar coordinate system.Similarly, the second obstacle information is located in millimetre-wave radar coordinate system.
When merging the first obstacle information and the second obstacle information, need first to convert the two into the same coordinate system, example
The first obstacle information can such as be converted into millimetre-wave radar coordinate system, the second obstacle information can also be converted to sharp
In optical radar coordinate system, the first obstacle information and the second obstacle information can also all be converted into world coordinate system.
Above-mentioned first transition matrix can be the transition matrix between laser radar coordinate system and world coordinate system, be also possible to laser thunder
Transition matrix up between coordinate system and millimetre-wave radar coordinate system.Likewise, above-mentioned second transition matrix can be millimeter wave
Transition matrix between radar fix system and laser radar coordinate system is also possible to millimetre-wave radar coordinate system and world coordinate system
Between transition matrix.
Step 402, list is merged according to preset obstacle information, match the first obstacle information after converting and turned
The second obstacle information after changing.
In the present embodiment, convert by the first obstacle information and the second obstacle information to the same coordinate system, it can
The second obstacle after the first obstacle information and conversion to combine preset obstacle information to merge list, after matching conversion
Object information.It may include the history barrier that laser radar and millimetre-wave radar detect in above-mentioned obstacle information fusion list
Information.The first obstacle information after conversion and the second obstacle information after conversion are merged with above-mentioned obstacle information
List, which carries out matching, to be on the one hand updated history barrier, the first barrier after on the other hand can determining conversion
Whether the second obstacle information after information and conversion indicates same barrier.
In some optional implementations of the present embodiment, above-mentioned obstacle information fusion list includes history barrier
Identifier and historical movement information corresponding with history barrier identifier.Above-mentioned first obstacle information includes the first obstacle
Object identifier and motion information corresponding with the first barrier identifier.Above-mentioned second obstacle information includes the second barrier
Identifier and motion information corresponding with the second barrier identifier.It include multiple history in list when obstacle information merges
When barrier identifier, the corresponding historical movement information of each history barrier identifier.Similarly, when there are multiple first barriers
When hindering object identifier, the corresponding motion information of each first barrier identifier.Above-mentioned steps 402 can specifically pass through Fig. 4
In unshowned following steps realize:
According to history barrier identifier, the first barrier identifier and the second barrier identifier, barrier is determined
Whether it includes the first barrier identifier and the second barrier identifier that information merges in list；Melt in response to obstacle information
Closing in list includes the first barrier identifier, using motion information more new historical obstacle corresponding with the first barrier identifier
The corresponding historical movement information of first barrier identifier in object motion information；In response to including in obstacle information fusion list
Second barrier identifier, using in motion information more new historical barrier motion information corresponding with the second barrier identifier
The corresponding historical movement information of second barrier identifier.
For distinguishing different barriers, i.e., same radar sensor assigns different barriers different barrier identifier
Barrier identifier, while different radar sensor assigns different barrier identifiers to same barrier.This realization side
In formula, according to history barrier identifier, the first barrier identifier and the second barrier identifier, barrier can be determined
Whether it includes the first barrier identifier and the second barrier identifier that information merges in list.It is arranged when obstacle information merges
When including the first barrier identifier in table, illustrate to be detected before the barrier of the first barrier identifier instruction by laser radar
It arrived, and utilized the first obstacle in motion information more new historical barrier motion information corresponding with the first barrier identifier at this time
The corresponding historical movement information of object identifier.When including the second barrier identifier in obstacle information fusion list, explanation
It was detected before the barrier of second barrier identifier instruction by millimetre-wave radar, and utilized identified with the second barrier at this time
Accord with the corresponding historical movement information of the second barrier identifier in corresponding motion information more new historical barrier motion information.On
Stating historical movement information may include the information such as the historical position of barrier, historical speed.
In some optional implementations of the present embodiment, above-mentioned steps 402 can also include Fig. 4 in it is unshowned with
Lower step:
In response to not including the first barrier identifier or the second barrier identifier in obstacle information fusion list, really
Matching between the fixed corresponding motion information of first barrier identifier and the corresponding motion information of the second barrier identifier
Degree；It is greater than or equal to preset threshold in response to above-mentioned matching degree, determines the first barrier identifier and the second barrier identifier
Indicate same barrier, and according to the corresponding motion information of the first barrier identifier or the corresponding fortune of the second barrier identifier
The corresponding historical movement information of first barrier identifier or the second barrier in dynamic information update history barrier motion information
The corresponding historical movement information of identifier.
When not including the first barrier identifier or the second barrier identifier in obstacle information fusion list, determine
It was not detected by laser radar before the barrier of first barrier identifier instruction or the second barrier identifier indicates
Barrier before do not detected by millimetre-wave radar.At this point it is possible to determine the corresponding movement letter of the first barrier identifier
Cease the matching degree between motion information corresponding with the second barrier identifier.Above-mentioned motion information may include the position of barrier
Confidence breath and velocity information, above-mentioned matching degree can be by Euclidean distance, manhatton distance or the mahalanobis distances between position come table
Show, can also be indicated by the distance between two velocity vectors.When indicating matching degree and two using the distance between two positions
Get over hour in the distance between position, it is believed that the matching degree of two positions is higher.When it is above-mentioned match degree is greater than the preset threshold when, recognize
Same barrier is indicated for the first barrier identifier and the second barrier identifier, can use the first barrier identifier pair
First obstacle in the corresponding motion information regeneration barrier object information fusion list of the motion information or the second barrier identifier answered
Object identifier or the corresponding historical movement information of the second barrier identifier.
In some optional implementations of the present embodiment, above-mentioned steps 402, which can further include in Fig. 4, not to be shown
Following steps out:
It is less than preset threshold in response to above-mentioned matching degree, increases by the first obstacle information in obstacle information fusion list
Or second obstacle information.
When between the corresponding motion information of the first barrier identifier motion information corresponding with the second barrier identifier
Matching degree when being less than preset threshold, illustrate the barrier of the first barrier identifier instruction for emerging barrier, or
The barrier of second barrier identifier instruction is emerging barrier, then needs to increase in obstacle information fusion list
The corresponding obstacle information of barrier identifier not to be covered.That is, if not including the first barrier in obstacle information fusion list
Hinder object identifier, then increases by the first obstacle information；If not including the second barrier mark in obstacle information fusion list
Symbol, then increase by the second obstacle information.
Step 403, the first obstacle information after fusion matching and the second obstacle information after matching.
After the first obstacle information after converting is matched with the second obstacle information after conversion, which can determine
Barrier was detected before being, which barrier is emerging, it can accurately determines the information of barrier.So
The barrier that laser radar detects is merged with the barrier that millimetre-wave radar detects afterwards, may be implemented more accurately
Detect barrier.
In some optional implementations of the present embodiment, above-mentioned steps 403 specifically can be by unshowned in Fig. 4
Following steps are realized:
Second obstacle information is filtered, filtered second obstacle information is obtained；According to the first weight
And second weight, merge the first obstacle information and filtered second obstacle information.
In this implementation, further the second obstacle information can be filtered, the second obstacle can be removed
Noise in object information.Then according to the first weight and the second weight, the first obstacle information and filtered the are merged
Two obstacle informations.
In some optional implementations of the present embodiment, above-mentioned obstacle information fusion list includes history barrier
The generation moment of the corresponding motion information of identifier.The above method can also include unshowned following steps in Fig. 4:
Motion information corresponding for history barrier identifier each in obstacle information fusion list, when determining generation
Whether the time difference carved between current time is greater than preset duration；It is greater than preset duration in response to the above-mentioned time difference, deleting should
The corresponding motion information of history barrier identifier.
In this implementation, the history barrier mark of " expired " in deletion obstacle information fusion list that can be in due course
Accord with corresponding motion information.It can be judged according to the time difference between generation moment and the current time of every motion information,
When the above-mentioned time difference being greater than preset duration, it is believed that this motion information " expired ", then can delete this motion information.
The method provided by the above embodiment for detecting barrier of the application, can accurately determine each barrier
It whether is history barrier, so as to realize more preferable, more quasi- by the testing result of fusion laser radar and millimetre-wave radar
Really detect barrier.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind for detecting barrier
Hinder one embodiment of the device of object, the Installation practice is corresponding with embodiment of the method shown in FIG. 1, which specifically can be with
Applied in various electronic equipments.
As shown in figure 5, the present embodiment includes: data capture unit 501, data for detecting the device 500 of barrier
Processing unit 502, weight determining unit 503, information fusion unit 504 and obstacle determination unit 505.
Wherein, data capture unit 501, for obtaining point cloud data and millimetre-wave radar data.
Data processing unit 502 obtains a cloud number for handling respectively point cloud data and millimetre-wave radar data
The second obstacle information indicated according to the first obstacle information and millimetre-wave radar data of instruction.
Weight determining unit 503, for determining the first obstacle according to the first obstacle information and the second obstacle information
Object information and the second obstacle information weight shared in fusion.
Information fusion unit 504, for merging the first obstacle information and the second barrier letter according to above-mentioned weight
Breath.
Obstacle determination unit 505, for determining barrier according to fused obstacle information.
In some optional implementations of the present embodiment, above-mentioned data processing unit 502 can be further used for: right
Point cloud data is clustered, tracking is handled, and obtains the first obstacle information；Millimetre-wave radar data are filtered, are obtained
To the second obstacle information.
In some optional implementations of the present embodiment, the first obstacle information include barrier first position,
The error of First Speed, the error of first position and First Speed, the second obstacle information include barrier the second position,
The error of second speed, the error of the second position and second speed.Above-mentioned weight determining unit 503 may further include figure
Unshowned first error determining module, the second error determination module and weight determination module in 5.
Wherein, first error determining module, for determining according to the error of first position and the error of First Speed
One composition error.
Second error determination module, for determining that second is comprehensive according to the error of the second position and the error of second speed
Close error.
Weight determination module, for determining the first barrier of fusion according to the first composition error and the second composition error
When information and the second obstacle information, the first weight of the first obstacle information and the second weight of the second obstacle information.
In some optional implementations of the present embodiment, above- mentioned information integrated unit 504 may further include Fig. 5
In unshowned info conversion module, information matches module and information Fusion Module.
Wherein, info conversion module is used for according to preset first transition matrix and/or the second transition matrix, by first
Obstacle information and the second obstacle information are converted to the same coordinate system.
Information matches module, for merging list according to preset obstacle information, the first barrier after matching conversion
The second obstacle information after information and conversion.
Information Fusion Module is believed for merging the first obstacle information after matching and the second barrier after matching
Breath.
In some optional implementations of the present embodiment, above-mentioned obstacle information fusion list includes history barrier
Identifier and historical movement information corresponding with each history barrier identifier, the first obstacle information include the first barrier
Identifier and motion information corresponding with each first barrier identifier, the second obstacle information are identified including the second barrier
Symbol and motion information corresponding with each second barrier identifier.Above- mentioned information matching module can be further used for: according to
History barrier identifier, the first barrier identifier and the second barrier identifier determine that obstacle information merges list
In whether include the first barrier identifier and the second barrier identifier；In response to including in obstacle information fusion list
First barrier identifier, using in motion information more new historical barrier motion information corresponding with the first barrier identifier
The corresponding historical movement information of the first barrier identifier；In response to including the second obstacle in obstacle information fusion list
Object identifier, using the second obstacle in motion information more new historical barrier motion information corresponding with the second barrier identifier
The corresponding historical movement information of object identifier.
In some optional implementations of the present embodiment, above- mentioned information matching module can be further used for: response
Do not include the first barrier identifier or the second barrier identifier in obstacle information fusion list, determines each first obstacle
Matching degree between the corresponding motion information of object identifier and the corresponding motion information of each second barrier identifier；In response to
Above-mentioned matching degree is greater than or equal to preset threshold, determines that the first barrier identifier and the second barrier identifier indicate same barrier
Hinder object, and is updated according to the corresponding motion information of the first barrier identifier or the corresponding motion information of the second barrier identifier
The corresponding historical movement information of the first barrier identifier or the second barrier identifier are corresponding in history barrier motion information
Historical movement information.
In some optional implementations of the present embodiment, above- mentioned information matching module can be further used for: response
It is less than preset threshold in above-mentioned matching degree, increases the first obstacle information or the second barrier in obstacle information fusion list
Information.
In some optional implementations of the present embodiment, above- mentioned information integrated unit 504 can be further used for: right
Second obstacle information is filtered, and obtains filtered second obstacle information；It is weighed according to the first weight and second
Weight merges the first obstacle information and filtered second obstacle information.
In some optional implementations of the present embodiment, above-mentioned obstacle information fusion list includes each history obstacle
The generation moment of the corresponding motion information of object identifier.Then above-mentioned apparatus 500 can also include unshowned information deletion in Fig. 5
Unit, above- mentioned information, which delete unit, can be used for: for each history barrier identifier pair in obstacle information fusion list
The motion information answered, determines whether the time difference generated between moment and current time is greater than preset duration；In response to it is above-mentioned when
Between difference be greater than preset duration, delete the corresponding motion information of history barrier identifier.
The application's is provided by the above embodiment for detecting the device of barrier, is getting point cloud data and millimeter wave
After radar data, point cloud data and millimetre-wave radar data are handled respectively, obtain the first barrier corresponding with point cloud data
Hinder object information and the second obstacle information corresponding with millimetre-wave radar data, then according to the first obstacle information and
Two obstacle informations, determine fusion both when both weight, according to obtained weight, by the first obstacle information and second
Obstacle information is merged, and finally according to fused information, determines barrier.The above-mentioned apparatus of the present embodiment, sufficiently benefit
The millimetre-wave radar data that the point cloud data and millimetre-wave radar obtained with laser radar obtains, improve detection of obstacles
Accuracy and sensitivity.
It should be appreciated that for detect the unit 501 recorded in the device 500 of barrier to unit 505 respectively with reference Fig. 1
Described in each step in method it is corresponding.As a result, above with respect to for detecting barrier method description operation and
Feature is equally applicable to device 500 and unit wherein included, and details are not described herein.The corresponding units of device 500 can be with end
Unit in end or server cooperates to realize the scheme of the embodiment of the present application.
Below with reference to Fig. 6, it illustrates the calculating of the terminal device or server that are suitable for being used to realize the embodiment of the present application
The structural schematic diagram of machine system 600.Terminal device/server shown in Fig. 6 is only an example, should not be implemented to the application
The function and use scope of example bring any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 605 as needed.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 610, in order to read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising carrying is on a machine-readable medium
Computer program, which includes the program code for method shown in execution flow chart.In such implementation
In example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media 611
It is mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes upper
State function.
It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two any combination.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires electrical connection,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And
In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include data capture unit, data processing unit, weight determining unit, information fusion unit and obstacle determination unit.Wherein, this
The title of a little units does not constitute the restriction to the unit itself under certain conditions, for example, data capture unit can also quilt
It is described as " obtaining the unit of point cloud data and millimetre-wave radar data ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in device described in above-described embodiment；It is also possible to individualism, and without in the supplying device.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should
Device: point cloud data and millimetre-wave radar data are obtained；Point cloud data and millimetre-wave radar data are handled respectively, obtained
First obstacle information of point cloud data instruction and the second obstacle information of millimetre-wave radar data instruction；According to the first barrier
Hinder object information and the second obstacle information, determines that the first obstacle information and the second obstacle information are shared in fusion
Weight；According to above-mentioned weight, the first obstacle information and the second obstacle information are merged；Believed according to fused barrier
Breath, determines barrier.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (20)
1. a kind of method for detecting barrier, which is characterized in that the described method includes:
Obtain point cloud data and millimetre-wave radar data；
The point cloud data and the millimetre-wave radar data are handled respectively, obtain the first of the point cloud data instruction
Obstacle information and the second obstacle information of millimetre-wave radar data instruction；
According to first obstacle information and second obstacle information, first obstacle information and institute are determined
State the second obstacle information weight shared in fusion；
According to the weight, first obstacle information and second obstacle information are merged；
According to fused obstacle information, barrier is determined.
2. the method according to claim 1, wherein described respectively to the point cloud data and the millimeter wave thunder
It is handled up to data, comprising:
The point cloud data is clustered, tracking processing, obtains first obstacle information；
The millimetre-wave radar data are filtered, second obstacle information is obtained.
3. the method according to claim 1, wherein first obstacle information includes first of barrier
It sets, the error of First Speed, the error of first position and First Speed, second obstacle information includes the of barrier
Two positions, second speed, the error of the error of the second position and second speed；And
Determination first obstacle information and second obstacle information weight shared in fusion, comprising:
According to the error of the first position and the error of the First Speed, the first composition error is determined；
According to the error of the second position and the error of the second speed, the second composition error is determined；
According to first composition error and second composition error, determine merge first obstacle information with it is described
When the second obstacle information, the second power of the first weight of first obstacle information and second obstacle information
Weight.
4. the method according to claim 1, wherein described according to the weight, fusion first barrier
Information and second obstacle information, comprising:
According to preset first transition matrix and/or the second transition matrix, by first obstacle information and described second
Obstacle information is converted to the same coordinate system；
List is merged according to preset obstacle information, the second barrier after the first obstacle information and conversion after matching conversion
Hinder object information；
The second obstacle information after the first obstacle information and matching after fusion matching.
5. according to the method described in claim 4, it is characterized in that, obstacle information fusion list includes history barrier
Identifier and historical movement information corresponding with history barrier identifier, first obstacle information include the first obstacle
Object identifier and motion information corresponding with the first barrier identifier, second obstacle information include the second barrier
Identifier and motion information corresponding with the second barrier identifier；And
It is described that list is merged according to preset obstacle information, the after the first obstacle information and conversion after matching conversion
Two obstacle informations, comprising:
According to the history barrier identifier, the first barrier identifier and the second barrier identifier, really
It whether include that the first barrier identifier and second barrier identify in the fixed obstacle information fusion list
Symbol；
In response to the obstacle information fusion list in include the first barrier identifier, using with first obstacle
It is corresponding that the corresponding motion information of object identifier updates the first barrier identifier described in the history barrier motion information
Historical movement information；
In response to the obstacle information fusion list in include the second barrier identifier, using with second obstacle
It is corresponding that the corresponding motion information of object identifier updates the second barrier identifier described in the history barrier motion information
Historical movement information.
6. according to the method described in claim 5, it is characterized in that, it is described according to preset obstacle information merge list,
With the first obstacle information after conversion and the second obstacle information after conversion, comprising:
In response to not including the first barrier identifier or second barrier in obstacle information fusion list
Identifier determines the corresponding motion information of the first barrier identifier and the corresponding fortune of the second barrier identifier
Matching degree between dynamic information；
It is greater than or equal to preset threshold in response to the matching degree, determines the first barrier identifier and second obstacle
Object identifier indicates same barrier, and according to the corresponding motion information of the first barrier identifier or the second barrier identifier
Corresponding motion information updates the corresponding historical movement of the first barrier identifier described in the history barrier motion information
Information or the corresponding historical movement information of the second barrier identifier.
7. according to the method described in claim 6, it is characterized in that, it is described according to preset obstacle information merge list,
With the first obstacle information after conversion and the second obstacle information after conversion, comprising:
It is less than preset threshold in response to the matching degree, increases by first barrier in obstacle information fusion list
Information or second obstacle information.
8. according to the method described in claim 3, it is characterized in that, described according to the weight, fusion first barrier
Information and second obstacle information, comprising:
Second obstacle information is filtered, filtered second obstacle information is obtained；
According to first weight and second weight, first obstacle information and filtered second barrier are merged
Hinder object information.
9. according to the method described in claim 4, it is characterized in that, obstacle information fusion list includes each history obstacle
The generation moment of the corresponding motion information of object identifier；And
The method also includes:
Motion information corresponding for history barrier identifier each in obstacle information fusion list, determines the life
Whether it is greater than preset duration at the time difference between moment and current time；
It is greater than preset duration in response to the time difference, deletes the corresponding motion information of history barrier identifier.
10. a kind of for detecting the device of barrier, which is characterized in that described device includes:
Data capture unit, for obtaining point cloud data and millimetre-wave radar data；
Data processing unit obtains described for handling respectively the point cloud data and the millimetre-wave radar data
First obstacle information of point cloud data instruction and the second obstacle information of millimetre-wave radar data instruction；
Weight determining unit, for according to first obstacle information and second obstacle information, determining described the
One obstacle information and second obstacle information weight shared in fusion；
Information fusion unit, for merging first obstacle information and second barrier letter according to the weight
Breath；
Obstacle determination unit, for determining barrier according to fused obstacle information.
11. device according to claim 10, which is characterized in that the data processing unit is further used for:
The point cloud data is clustered, tracking processing, obtains first obstacle information；
The millimetre-wave radar data are filtered, second obstacle information is obtained.
12. device according to claim 10, which is characterized in that first obstacle information includes the first of barrier
Position, First Speed, the error of first position and First Speed error, second obstacle information includes barrier
The second position, second speed, the error of the error of the second position and second speed；And
The weight determining unit includes:
First error determining module, for determining according to the error of the first position and the error of the First Speed
One composition error；
Second error determination module, for determining according to the error of the second position and the error of the second speed
Two composition errors；
Weight determination module, for according to first composition error and second composition error, determining fusion described the
When one obstacle information and second obstacle information, the first weight of first obstacle information and second barrier
Hinder the second weight of object information.
13. device according to claim 10, which is characterized in that the information fusion unit includes:
Info conversion module is used for according to preset first transition matrix and/or the second transition matrix, by first barrier
Information and second obstacle information are converted to the same coordinate system；
Information matches module, for merging list according to preset obstacle information, the first obstacle information after matching conversion
And the second obstacle information after conversion；
Information Fusion Module, for merging the first obstacle information after matching and the second obstacle information after matching.
14. device according to claim 13, which is characterized in that the obstacle information fusion list includes history obstacle
Object identifier and historical movement information corresponding with history barrier identifier, first obstacle information include the first barrier
Hinder object identifier and motion information corresponding with the first barrier identifier, second obstacle information includes the second obstacle
Object identifier and motion information corresponding with the second barrier identifier；And
The information matches module is further used for:
According to the history barrier identifier, the first barrier identifier and the second barrier identifier, really
It whether include that the first barrier identifier and second barrier identify in the fixed obstacle information fusion list
Symbol；
In response to the obstacle information fusion list in include the first barrier identifier, using with first obstacle
It is corresponding that the corresponding motion information of object identifier updates the first barrier identifier described in the history barrier motion information
Historical movement information；
In response to the obstacle information fusion list in include the second barrier identifier, using with second obstacle
It is corresponding that the corresponding motion information of object identifier updates the second barrier identifier described in the history barrier motion information
Historical movement information.
15. device according to claim 14, which is characterized in that the information matches module is further used for:
In response to not including the first barrier identifier or second barrier in obstacle information fusion list
Identifier determines the corresponding motion information of the first barrier identifier and the corresponding fortune of the second barrier identifier
Matching degree between dynamic information；
It is greater than or equal to preset threshold in response to the matching degree, determines the first barrier identifier and second obstacle
Object identifier indicates same barrier, and according to the corresponding motion information of the first barrier identifier or the second barrier identifier
Corresponding motion information updates the corresponding historical movement of the first barrier identifier described in the history barrier motion information
Information or the corresponding historical movement information of the second barrier identifier.
16. device according to claim 15, which is characterized in that the information matches module is further used for:
It is less than preset threshold in response to the matching degree, increases by first barrier in obstacle information fusion list
Information or second obstacle information.
17. device according to claim 12, which is characterized in that the information fusion unit is further used for:
Second obstacle information is filtered, filtered second obstacle information is obtained；
According to first weight and second weight, first obstacle information and filtered second barrier are merged
Hinder object information.
18. device according to claim 13, which is characterized in that the obstacle information fusion list includes each history barrier
Hinder the generation moment of the corresponding motion information of object identifier；And
Described device further includes information deletion unit, and the information deletion unit is used for:
Motion information corresponding for history barrier identifier each in obstacle information fusion list, determines the life
Whether it is greater than preset duration at the time difference between moment and current time；
It is greater than preset duration in response to the time difference, deletes the corresponding motion information of history barrier identifier.
19. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-9.
20. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in any in claim 1-9 is realized when execution.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710541847.4A CN109212532B (en) | 2017-07-04 | 2017-07-04 | Method and apparatus for detecting obstacles |
| CN202110882862.1A CN113466822B (en) | 2017-07-04 | Method and device for detecting obstacles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710541847.4A CN109212532B (en) | 2017-07-04 | 2017-07-04 | Method and apparatus for detecting obstacles |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110882862.1A Division CN113466822B (en) | 2017-07-04 | Method and device for detecting obstacles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109212532A true CN109212532A (en) | 2019-01-15 |
| CN109212532B CN109212532B (en) | 2021-08-20 |
Family
ID=64993117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710541847.4A Active CN109212532B (en) | 2017-07-04 | 2017-07-04 | Method and apparatus for detecting obstacles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109212532B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109738884A (en) * | 2018-12-29 | 2019-05-10 | 百度在线网络技术（北京）有限公司 | Method for checking object, device and computer equipment |
| CN109901183A (en) * | 2019-03-13 | 2019-06-18 | 电子科技大学中山学院 | Method for improving all-weather distance measurement precision and reliability of laser radar |
| CN110502019A (en) * | 2019-09-06 | 2019-11-26 | 北京云迹科技有限公司 | A kind of barrier-avoiding method and device of Indoor Robot |
| CN110517483A (en) * | 2019-08-06 | 2019-11-29 | 杭州博信智联科技有限公司 | A kind of traffic information processing method and digital rail roadside unit |
| CN110531376A (en) * | 2019-08-23 | 2019-12-03 | 畅加风行(苏州)智能科技有限公司 | Detection of obstacles and tracking for harbour automatic driving vehicle |
| CN110658531A (en) * | 2019-08-23 | 2020-01-07 | 畅加风行(苏州)智能科技有限公司 | Dynamic target tracking method for port automatic driving vehicle |
| CN110796705A (en) * | 2019-10-23 | 2020-02-14 | 北京百度网讯科技有限公司 | Error elimination method, device, equipment and computer readable storage medium |
| CN110794406A (en) * | 2019-11-12 | 2020-02-14 | 北京经纬恒润科技有限公司 | Multi-source sensor data fusion system and method |
| CN110866544A (en) * | 2019-10-28 | 2020-03-06 | 杭州飞步科技有限公司 | Sensor data fusion method and device and storage medium |
| CN111923898A (en) * | 2019-05-13 | 2020-11-13 | 广州汽车集团股份有限公司 | Obstacle detection method and device |
| CN112001287A (en) * | 2020-08-17 | 2020-11-27 | 禾多科技（北京）有限公司 | Method and device for generating point cloud information of obstacle, electronic device and medium |
| CN112180910A (en) * | 2019-06-18 | 2021-01-05 | 北京京东尚科信息技术有限公司 | Obstacle sensing method and device for mobile robot |
| CN112378050A (en) * | 2020-11-10 | 2021-02-19 | 珠海格力电器股份有限公司 | Control method and device for air conditioning equipment, electronic equipment and storage medium |
| CN113296120A (en) * | 2021-05-24 | 2021-08-24 | 福建盛海智能科技有限公司 | Obstacle detection method and terminal |
| CN113366341A (en) * | 2020-01-06 | 2021-09-07 | 深圳市速腾聚创科技有限公司 | Point cloud data processing method and device, storage medium and laser radar system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060250297A1 (en) * | 2005-05-06 | 2006-11-09 | Ford Global Technologies, Llc | System and method for preemptively sensing an object and selectively operating both a collision countermeasure system and a parking assistance system aboard an automotive vehicle |
| CN103176185A (en) * | 2011-12-26 | 2013-06-26 | 上海汽车集团股份有限公司 | Method and system for detecting road barrier |
| CN105109484A (en) * | 2015-08-21 | 2015-12-02 | 奇瑞汽车股份有限公司 | Target-barrier determining method and device |
| CN105629985A (en) * | 2016-03-20 | 2016-06-01 | 北京工业大学 | Indoor four-rotor unmanned aerial vehicle 360-degree three-dimensional obstacle avoidance system |
| GB2545540A (en) * | 2015-10-19 | 2017-06-21 | Ford Global Tech Llc | Probabilistic inference using weighted-integrals-and-sums-by-hashing for object tracking |
-
2017
- 2017-07-04 CN CN201710541847.4A patent/CN109212532B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060250297A1 (en) * | 2005-05-06 | 2006-11-09 | Ford Global Technologies, Llc | System and method for preemptively sensing an object and selectively operating both a collision countermeasure system and a parking assistance system aboard an automotive vehicle |
| CN103176185A (en) * | 2011-12-26 | 2013-06-26 | 上海汽车集团股份有限公司 | Method and system for detecting road barrier |
| CN105109484A (en) * | 2015-08-21 | 2015-12-02 | 奇瑞汽车股份有限公司 | Target-barrier determining method and device |
| GB2545540A (en) * | 2015-10-19 | 2017-06-21 | Ford Global Tech Llc | Probabilistic inference using weighted-integrals-and-sums-by-hashing for object tracking |
| CN105629985A (en) * | 2016-03-20 | 2016-06-01 | 北京工业大学 | Indoor four-rotor unmanned aerial vehicle 360-degree three-dimensional obstacle avoidance system |
Non-Patent Citations (2)
| Title |
|---|
| JIAN WANG ET.AL.: "A novel InSAR based off-road positive and negative obstacle detection technique for unmanned ground vehicle", 《2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS)》 * |
| 那田: "基于雷达和机器视觉融合的前方车辆障碍物检测", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109738884B (en) * | 2018-12-29 | 2022-03-11 | 百度在线网络技术（北京）有限公司 | Object detection method and device and computer equipment |
| CN109738884A (en) * | 2018-12-29 | 2019-05-10 | 百度在线网络技术（北京）有限公司 | Method for checking object, device and computer equipment |
| CN109901183A (en) * | 2019-03-13 | 2019-06-18 | 电子科技大学中山学院 | Method for improving all-weather distance measurement precision and reliability of laser radar |
| CN111923898A (en) * | 2019-05-13 | 2020-11-13 | 广州汽车集团股份有限公司 | Obstacle detection method and device |
| CN112180910A (en) * | 2019-06-18 | 2021-01-05 | 北京京东尚科信息技术有限公司 | Obstacle sensing method and device for mobile robot |
| CN110517483A (en) * | 2019-08-06 | 2019-11-29 | 杭州博信智联科技有限公司 | A kind of traffic information processing method and digital rail roadside unit |
| CN110531376A (en) * | 2019-08-23 | 2019-12-03 | 畅加风行(苏州)智能科技有限公司 | Detection of obstacles and tracking for harbour automatic driving vehicle |
| CN110658531A (en) * | 2019-08-23 | 2020-01-07 | 畅加风行(苏州)智能科技有限公司 | Dynamic target tracking method for port automatic driving vehicle |
| CN110658531B (en) * | 2019-08-23 | 2022-03-29 | 畅加风行(苏州)智能科技有限公司 | Dynamic target tracking method for port automatic driving vehicle |
| CN110502019A (en) * | 2019-09-06 | 2019-11-26 | 北京云迹科技有限公司 | A kind of barrier-avoiding method and device of Indoor Robot |
| CN110796705A (en) * | 2019-10-23 | 2020-02-14 | 北京百度网讯科技有限公司 | Error elimination method, device, equipment and computer readable storage medium |
| CN110866544A (en) * | 2019-10-28 | 2020-03-06 | 杭州飞步科技有限公司 | Sensor data fusion method and device and storage medium |
| CN110866544B (en) * | 2019-10-28 | 2022-04-15 | 杭州飞步科技有限公司 | Sensor data fusion method and device and storage medium |
| CN110794406B (en) * | 2019-11-12 | 2022-08-02 | 北京经纬恒润科技股份有限公司 | Multi-source sensor data fusion system and method |
| CN110794406A (en) * | 2019-11-12 | 2020-02-14 | 北京经纬恒润科技有限公司 | Multi-source sensor data fusion system and method |
| CN113366341B (en) * | 2020-01-06 | 2024-04-26 | 深圳市速腾聚创科技有限公司 | Point cloud data processing method and device, storage medium and laser radar system |
| CN113366341A (en) * | 2020-01-06 | 2021-09-07 | 深圳市速腾聚创科技有限公司 | Point cloud data processing method and device, storage medium and laser radar system |
| CN112001287A (en) * | 2020-08-17 | 2020-11-27 | 禾多科技（北京）有限公司 | Method and device for generating point cloud information of obstacle, electronic device and medium |
| CN112001287B (en) * | 2020-08-17 | 2023-09-12 | 禾多科技（北京）有限公司 | Point cloud information generation method and device for obstacle, electronic equipment and medium |
| CN112378050B (en) * | 2020-11-10 | 2021-09-14 | 珠海格力电器股份有限公司 | Control method and device for air conditioning equipment, electronic equipment and storage medium |
| CN112378050A (en) * | 2020-11-10 | 2021-02-19 | 珠海格力电器股份有限公司 | Control method and device for air conditioning equipment, electronic equipment and storage medium |
| CN113296120A (en) * | 2021-05-24 | 2021-08-24 | 福建盛海智能科技有限公司 | Obstacle detection method and terminal |
| CN113296120B (en) * | 2021-05-24 | 2023-05-12 | 福建盛海智能科技有限公司 | Obstacle detection method and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113466822A (en) | 2021-10-01 |
| CN109212532B (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109212532A (en) | Method and apparatus for detecting barrier | |
| CN109212530A (en) | Method and apparatus for determining barrier speed | |
| US11579307B2 (en) | Method and apparatus for detecting obstacle | |
| CN107945198A (en) | Method and apparatus for marking cloud data | |
| US11416005B2 (en) | Method and apparatus for controlling unmanned vehicle to perform route verification | |
| JP6205030B2 (en) | How to locate train events on the rail network | |
| CN110696826B (en) | Method and device for controlling a vehicle | |
| CN110533055A (en) | A kind for the treatment of method and apparatus of point cloud data | |
| CN109448373A (en) | Method and apparatus for generating information | |
| CN109883438A (en) | Automobile navigation method, device, medium and electronic equipment | |
| CN111563398A (en) | Method and device for determining information of target object | |
| CN104567909A (en) | Apparatus and method for guiding shadow area | |
| CN112651266A (en) | Pedestrian detection method and device | |
| CN109635870A (en) | Data processing method and device | |
| CN110309240A (en) | The method and apparatus for removing dynamic object | |
| CN109635868B (en) | Method and device for determining obstacle type, electronic device and storage medium | |
| CN112578781A (en) | Data processing method, device, chip system and medium | |
| CN109774716A (en) | Control method for vehicle and device | |
| CN109637148A (en) | Vehicle-mounted whistle monitoring system, method, storage medium and equipment | |
| CN108320184A (en) | For the method, apparatus of vehicle charging, equipment, system and storage medium | |
| CN109827610A (en) | Method and apparatus for check sensor fusion results | |
| CN114724116B (en) | Vehicle traffic information generation method, device, equipment and computer readable medium | |
| CN115061386B (en) | Intelligent driving automatic simulation test system and related equipment | |
| CN109427202A (en) | The device and method that running section for predicting to be determined by construction site changes | |
| CN109116357A (en) | Method, apparatus and server for synchronization time |
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 |