CN109635868A - Determination method, apparatus, electronic equipment and the storage medium of barrier classification - Google Patents
Determination method, apparatus, electronic equipment and the storage medium of barrier classification Download PDFInfo
- Publication number
- CN109635868A CN109635868A CN201811506234.8A CN201811506234A CN109635868A CN 109635868 A CN109635868 A CN 109635868A CN 201811506234 A CN201811506234 A CN 201811506234A CN 109635868 A CN109635868 A CN 109635868A
- Authority
- CN
- China
- Prior art keywords
- classification
- current time
- reliability
- target obstacle
- corresponding current
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the invention discloses determination method, apparatus, electronic equipment and the storage mediums of a kind of barrier classification.The described method includes: receiving the classification output result at the target obstacle corresponding current time that each sensor is sent；The classification fusion results at the target obstacle corresponding current time are calculated according to the classification fusion results of the predetermined target obstacle corresponding last moment and the classification at the target obstacle corresponding current time output result；The final classification of the target obstacle is determined according to the classification fusion results at the target obstacle corresponding current time.It can more accurately determine the final classification of target obstacle.
Description
Technical field
The present embodiments relate to technical field of data processing more particularly to a kind of determination methods of barrier classification, dress
It sets, electronic equipment and storage medium.
Background technique
Automatic driving vehicle, alternatively referred to as automatic driving vehicle refer to through various sensors and perceive vehicle periphery ring
Border, and according to road, vehicle location and obstacle information obtained etc. is perceived, the steering and speed of vehicle are controlled, to make
Vehicle can be travelled reliably and securely on road.Therefore, automatic driving vehicle is when exercising, it is necessary to understand vehicle week in real time
The enforcement environment enclosed.And the acquisition of environmental information is driven automatically at present by the various sensors being installed on automatic driving vehicle
Sailing typical sensor on vehicle includes: laser radar, camera and millimetre-wave radar.Each sensor can all export target disorders
The classification of object, such as pedestrian, vehicle, and the output result of each sensor may have conflict, such as to some obstacle
Object, laser radar is identified as pedestrian and camera is identified as vehicle.In order to improve to the recognition capability of target obstacle it is necessary to utilizing
Multisensor Data Fusion technology makes full use of the complementarity of each sensor, forms the perception relatively uniform to system environments
Description.
The determination method of existing barrier classification uses the following two kinds scheme: the first, by the output of some sensor
Classification is determined as the final classification of target obstacle.It specifically chooses which sensor and is generally made with the classification performance of each sensor
For evaluation index, in general, camera is higher than laser sensor to the classification accuracy of barrier, so working as camera and laser
When radar all detects the same barrier, the output result of camera can be all determined as to the final classification of target obstacle.The
Two, fusion is weighted using output result of the priori knowledge to each sensor.It illustrates, it is assumed that some barrier may have
Following four classification: pedestrian, bicycle, vehicle, unknown barrier, output result of the laser radar to the barrier are as follows: Plidar
=[p1,p2,p3,p4], which indicates the probability for belonging to four classifications；Accordingly, output result of the camera to the barrier
Are as follows: Pcamera=[a1,a2,a3,a4].Weighted Fusion model are as follows:Wherein i is indicated i-th
Classification, MkIndicate weighting coefficient, PfusionTarget obstacle belongs to the probability of i-th of classification after [i] expression Weighted Fusion.
In the implementation of the present invention, at least there are the following problems in the prior art for inventor's discovery:
In the determination method of the first existing barrier classification, directly the output result of some sensor is determined
For the final result of target obstacle, this method does not comprehensively consider the output of each sensor as a result, determining in this way
Target obstacle final classification may inaccuracy；In the determination method of existing second of barrier classification, weighting
Coefficient also influences whether the accuracy of the final classification of target obstacle.
Summary of the invention
In view of this, the embodiment of the present invention provides determination method, apparatus, electronic equipment and the storage of a kind of barrier classification
Medium can more accurately determine the final classification of target obstacle.
In a first aspect, the embodiment of the invention provides a kind of determination methods of barrier classification, which comprises
Receive the classification output result at the target obstacle corresponding current time that each sensor is sent；
According to the classification fusion results of the predetermined target obstacle corresponding last moment and target barrier
The classification at object corresponding current time is hindered to export the classification fusion knot that result calculates the target obstacle corresponding current time
Fruit；
The target obstacle is determined most according to the classification fusion results at the target obstacle corresponding current time
Whole classification.
In the above-described embodiments, the classification according to the predetermined target obstacle corresponding last moment is melted
It closes result and the classification at the target obstacle corresponding current time output result calculates that the target obstacle is corresponding to be worked as
The classification fusion results at preceding moment, comprising:
It is corresponding that each candidate categories are obtained in the classification fusion results of the target obstacle corresponding last moment
The reliability fusion value of last moment；
It is corresponding that each candidate categories are obtained in the classification output result at the target obstacle corresponding current time
The reliability output valve at current time；
When according to the reliability fusion value and corresponding current each candidate categories of each candidate categories corresponding last moment
The reliability output valve at quarter calculates the classification fusion results at the target obstacle corresponding current time.
In the above-described embodiments, the reliability fusion value and each time according to each candidate categories corresponding last moment
The reliability output valve at classification corresponding current time is selected to calculate the classification fusion knot at the target obstacle corresponding current time
Fruit, comprising:
When according to the reliability fusion value and corresponding current each candidate categories of each candidate categories corresponding last moment
The reliability output valve at quarter calculates the reliability fusion value at each candidate categories corresponding current time；
It determines that the target obstacle is corresponding according to the reliability fusion value at each candidate categories corresponding current time to work as
The classification fusion results at preceding moment.
In the above-described embodiments, the reliability fusion value and each time according to each candidate categories corresponding last moment
It selects the reliability output valve at classification corresponding current time to calculate the reliability fusion value at each candidate categories corresponding current time, wraps
It includes:
Determine corresponding candidate categories and the mutually exclusive candidate categories of being mutually related of each candidate categories；
Be mutually related candidate described in obtaining in the classification fusion results of the target obstacle corresponding last moment
The reliability fusion value of classification corresponding last moment and the reliability of the mutually exclusive candidate categories corresponding last moment are melted
Conjunction value；
Be mutually related candidate described in obtaining in the classification output result at the target obstacle corresponding current time
The reliability output valve at classification corresponding current time and the reliability at the mutually exclusive candidate categories corresponding current time are defeated
It is worth out；
According to the reliability fusion value of the candidate categories that are mutually related corresponding last moment and described mutually exclusive
The reliability fusion value of candidate categories corresponding last moment and the candidate categories that are mutually related corresponding current time
Reliability output valve and the reliability output valve at the mutually exclusive candidate categories corresponding current time calculate each candidate categories
The reliability fusion value at corresponding current time.
In the above-described embodiments, described to be determined according to the classification fusion results at the target obstacle corresponding current time
The final classification of the target obstacle, comprising:
According to the classification fusion results at the target obstacle corresponding current time by whole candidate categories according to its
The reliability fusion value at corresponding current time is ranked up；
Reliability fusion is worth the final classification that maximum candidate categories are determined as the target obstacle.
Second aspect, the embodiment of the invention provides a kind of determining device of barrier classification, described device includes: to receive
Module, computing module and determining module；Wherein,
The receiving module, the classification for receiving the target obstacle corresponding current time that each sensor is sent are defeated
Result out；
The computing module, for being merged according to the classification of the predetermined target obstacle corresponding last moment
As a result it is corresponding current to calculate the target obstacle for the classification output result at current time corresponding with the target obstacle
The classification fusion results at moment；
The determining module, for determining institute according to the classification fusion results at the target obstacle corresponding current time
State the final classification of target obstacle.
In the above-described embodiments, the computing module includes: acquisition submodule and computational submodule；Wherein,
The acquisition submodule, for being obtained in the classification fusion results of the target obstacle corresponding last moment
The reliability fusion value of each candidate categories corresponding last moment；It is defeated in the classification at the target obstacle corresponding current time
The reliability output valve at each candidate categories corresponding current time is obtained in result out；
The computational submodule, for the reliability fusion value and each time according to each candidate categories corresponding last moment
The reliability output valve at classification corresponding current time is selected to calculate the classification fusion knot at the target obstacle corresponding current time
Fruit.
In the above-described embodiments, the computational submodule, for the letter according to each candidate categories corresponding last moment
When spending fusion value and the corresponding current each candidate categories of the reliability output valve at each candidate categories corresponding current time calculating
The reliability fusion value at quarter；The target obstacle pair is determined according to the reliability fusion value at each candidate categories corresponding current time
The classification fusion results at the current time answered.
In the above-described embodiments, the computational submodule is specifically used for determining that each candidate categories are corresponding interrelated
Candidate categories and mutually exclusive candidate categories；In the classification fusion results of the target obstacle corresponding last moment
Be mutually related described in acquisition candidate categories corresponding last moment reliability fusion value and the mutually exclusive candidate categories
The reliability fusion value of corresponding last moment；It is obtained in the classification output result at the target obstacle corresponding current time
The reliability output valve at the candidate categories that are mutually related corresponding current time and the mutually exclusive candidate categories are corresponding
Current time reliability output valve；According to the reliability fusion value of the candidate categories that are mutually related corresponding last moment and
The reliability fusion value of the mutually exclusive candidate categories corresponding last moment and the candidate categories pair that are mutually related
The reliability output valve meter of the reliability output valve at the current time answered and the mutually exclusive candidate categories corresponding current time
Calculate the reliability fusion value at each candidate categories corresponding current time.
In the above-described embodiments, the determining module was specifically used for according to the target obstacle corresponding current time
Classification fusion results whole candidate categories are ranked up according to the reliability fusion value at corresponding current time；By reliability
Fusion is worth the final classification that maximum candidate categories are determined as the target obstacle.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, comprising:
One or more processors；
Memory, 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 processing
Device realizes the determination method of barrier classification described in any embodiment of that present invention.
Fourth aspect, the embodiment of the invention provides a kind of storage mediums, are stored thereon with computer program, the program quilt
The determination method of barrier classification described in any embodiment of that present invention is realized when processor executes.
The embodiment of the present invention proposes determination method, apparatus, electronic equipment and the storage medium of a kind of barrier classification, first
Receive the classification output result at the target obstacle corresponding current time that each sensor is sent；Then according to predetermined
The classification fusion results and the classification at target obstacle corresponding current time of target obstacle corresponding last moment export knot
Fruit calculates the classification fusion results at target obstacle corresponding current time；Further according to target obstacle corresponding current time
Classification fusion results determine the final classification of target obstacle.That is, in the inventive solutions, it can be according to mesh
The classification fusion results and the classification at target obstacle corresponding current time for marking barrier corresponding last moment export result
Calculate the classification fusion results at target obstacle corresponding current time；Further according to the class at target obstacle corresponding current time
Other fusion results determine the final classification of target obstacle.And in the determination method of existing barrier classification, by some
The output classification of sensor is determined as the final classification of target obstacle；Alternatively, the output using priori knowledge to each sensor
As a result it is weighted fusion.The determination method for the barrier classification that therefore, compared to the prior art, the embodiment of the present invention proposes,
Device, electronic equipment and storage medium can more accurately determine the final classification of target obstacle；Also, the present invention
The technical solution realization of embodiment is simple and convenient, it is universal to be convenient for, and the scope of application is wider.
Detailed description of the invention
Fig. 1 is the flow diagram of the determination method for the barrier classification that the embodiment of the present invention one provides；
Fig. 2 is the flow diagram of the determination method of barrier classification provided by Embodiment 2 of the present invention；
Fig. 3 is the flow diagram of the determination method for the barrier classification that the embodiment of the present invention three provides；
Fig. 4 is the first structure diagram of the determining device for the barrier classification that the embodiment of the present invention four provides；
Fig. 5 is the second structural schematic diagram of the determining device for the barrier classification that the embodiment of the present invention four provides；
Fig. 6 is the structural schematic diagram for the electronic equipment that the embodiment of the present invention five provides.
Specific embodiment
The present invention 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 the present invention rather than limiting the invention.It also should be noted that in order to just
In description, only some but not all contents related to the present invention are shown in the drawings.
Embodiment one
Fig. 1 is the flow diagram for the determination method of barrier classification that the embodiment of the present invention one provides, and this method can be with
By barrier classification determining device perhaps electronic equipment come execute the device or electronic equipment can be by software and/or hard
The mode of part realizes that the device or electronic equipment can integrate in any smart machine with network communicating function.Such as
Shown in Fig. 1, the determination method of barrier classification be may comprise steps of:
S101, the classification for receiving the target obstacle corresponding current time that each sensor is sent export result.
In a specific embodiment of the present invention, it is corresponding to can receive the target obstacle that each sensor is sent for electronic equipment
Current time classification export result.For example, it is assumed that M sensor can be arranged on unmanned vehicle, be respectively as follows: sensor 1,
Sensor 2 ..., sensor M；It is defeated that sensor 1 can send the classification at target obstacle corresponding current time to electronic equipment
Result 1 out；Sensor 2 can send the classification at target obstacle corresponding current time to electronic equipment and export result 2；…；
Sensor M can send the classification at target obstacle corresponding current time to electronic equipment and export result M.Therefore, electronics is set
The classification output result 1 at the standby target obstacle corresponding current time that can receive the transmission of sensor 1；Sensing can also be received
The classification at the target obstacle corresponding current time that device 2 is sent exports result 1；…；The mesh that can be sent with receiving sensor M
The classification for marking barrier corresponding current time exports result M；Wherein, M is the natural number greater than 1.
S102, classification fusion results and target obstacle according to predetermined target obstacle corresponding last moment
The classification output result at corresponding current time calculates the classification fusion results at target obstacle corresponding current time.
In a specific embodiment of the present invention, electronic equipment can be according to predetermined target obstacle corresponding upper one
It is corresponding that the classification output result at classification fusion results and the target obstacle corresponding current time at moment calculates target obstacle
Current time classification fusion results.Specifically, electronic equipment can be first in the class of target obstacle corresponding last moment
The reliability fusion value of each candidate categories corresponding last moment is obtained in other fusion results；Then corresponding in target obstacle
The reliability output valve at each candidate categories corresponding current time is obtained in the classification output result at current time；Further according to each
The reliability fusion value of candidate categories corresponding last moment and the reliability output valve meter at each candidate categories corresponding current time
Calculate the classification fusion results at target obstacle corresponding current time.
S103, the final class that target obstacle is determined according to the classification fusion results at target obstacle corresponding current time
Not.
In a specific embodiment of the present invention, electronic equipment can be according to the classification at target obstacle corresponding current time
Fusion results determine the final classification of target obstacle.Specifically, electronic equipment can first work as according to target obstacle is corresponding
Whole candidate categories are ranked up by the classification fusion results at preceding moment according to the reliability fusion value at corresponding current time；
Then reliability fusion is worth the final classification that maximum candidate categories are determined as target obstacle.
The determination method for the barrier classification that the embodiment of the present invention proposes first receives the target disorders that each sensor is sent
The classification at object corresponding current time exports result；Then according to the class of predetermined target obstacle corresponding last moment
When other fusion results and the corresponding current classification at target obstacle corresponding current time output result calculating target obstacle
The classification fusion results at quarter；Target obstacle is determined further according to the classification fusion results at target obstacle corresponding current time
Final classification.That is, in the inventive solutions, it can be according to the classification of target obstacle corresponding last moment
Fusion results and the classification at target obstacle corresponding current time output result calculate target obstacle corresponding current time
Classification fusion results；Determine target obstacle most further according to the classification fusion results at target obstacle corresponding current time
Whole classification.And in the determination method of existing barrier classification, the output classification of some sensor is determined as target barrier
Hinder the final classification of object；Alternatively, being weighted fusion using output result of the priori knowledge to each sensor.Therefore with it is existing
Technology is compared, and the determination method for the barrier classification that the embodiment of the present invention proposes can more accurately determine target disorders
The final classification of object；Also, the technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and the scope of application is wider.
Embodiment two
Fig. 2 is the flow diagram of the determination method of barrier classification provided by Embodiment 2 of the present invention.As shown in Fig. 2,
The determination method of barrier classification may comprise steps of:
S201, the classification for receiving the target obstacle corresponding current time that each sensor is sent export result.
In a specific embodiment of the present invention, it is corresponding to can receive the target obstacle that each sensor is sent for electronic equipment
Current time classification export result.For example, it is assumed that M sensor can be arranged on unmanned vehicle, be respectively as follows: sensor 1,
Sensor 2 ..., sensor M；It is defeated that sensor 1 can send the classification at target obstacle corresponding current time to electronic equipment
Result 1 out；Sensor 2 can send the classification at target obstacle corresponding current time to electronic equipment and export result 2；…；
Sensor M can send the classification at target obstacle corresponding current time to electronic equipment and export result M.Therefore, electronics is set
The classification output result 1 at the standby target obstacle corresponding current time that can receive the transmission of sensor 1；Sensing can also be received
The classification at the target obstacle corresponding current time that device 2 is sent exports result 1；…；The mesh that can be sent with receiving sensor M
The classification for marking barrier corresponding current time exports result M；Wherein, M is the natural number greater than 1.
S202, to obtain each candidate categories in the classification fusion results of target obstacle corresponding last moment corresponding
The reliability fusion value of last moment.
In a specific embodiment of the present invention, electronic equipment can melt in the classification of target obstacle corresponding last moment
Close the reliability fusion value that each candidate categories corresponding last moment is obtained in result.Specifically, target obstacle it is corresponding on
The classification fusion results at one moment may include the reliability fusion value of N number of candidate categories corresponding last moment, be respectively as follows: candidate class
Reliability fusion value 1, the reliability fusion value 2 of the corresponding last moment of candidate categories 2 of other 1 corresponding last moment；…；Candidate categories
The reliability fusion value N of N corresponding last moment.For example, it is assumed that the classification fusion results of target obstacle corresponding last moment can
To include the reliability fusion value of four candidate categories corresponding last moment, Ped expression pedestrian；Bic indicates bicycle；Car is indicated
Motor vehicle；Unk indicates unknown classification；That is:
Wherein,Indicate the classification fusion results of target obstacle corresponding last moment；mK-1(Ped) on indicating that pedestrian is corresponding
The reliability fusion value at one moment；mK-1(Bic) the reliability fusion value of bicycle corresponding last moment is indicated；mK-1(Car) it indicates
The reliability fusion value of motor vehicle corresponding last moment；mK-1(Unk) the reliability fusion of unknown classification corresponding last moment is indicated
Value.Therefore, in this step, electronic equipment can obtain in the classification fusion results of target obstacle corresponding last moment
The reliability fusion value of each candidate categories corresponding last moment.
S203, to obtain each candidate categories corresponding in the classification output result at target obstacle corresponding current time
The reliability output valve at current time.
In a specific embodiment of the present invention, electronic equipment can target obstacle corresponding current time classification it is defeated
The reliability output valve at each candidate categories corresponding current time is obtained in result out.Specifically, the mesh of each sensor output
The classification output result at mark barrier corresponding current time may include that the reliability at N number of candidate categories corresponding current time is defeated
It is worth out, is respectively as follows: reliability output valve 1, the letter at the corresponding current time of candidate categories 2 at the corresponding current time of candidate categories 1
Spend output valve 2；…；The reliability output valve N at candidate categories N corresponding current time.For example, it is assumed that the mesh of first sensor output
The classification output result at mark barrier corresponding current time may include the reliability at four candidate categories corresponding current time
Output valve, Ped indicate pedestrian；Bic indicates bicycle；Car indicates motor vehicle；Unk indicates unknown classification；That is: m1=[a1
(Ped), a1(Bic), a1(Car), a1(Unk)]；Wherein, m1Indicate that the target obstacle of first sensor output is corresponding current
The classification at moment exports result；a1(Ped) the reliability output valve at pedestrian's corresponding current time of first sensor output is indicated；
a1(Bic) the reliability output valve at the bicycle corresponding current time of first sensor output is indicated；a1(Car) indicate that first passes
The reliability output valve at the motor vehicle corresponding current time of sensor output；a1(Unk) the unknown class of first sensor output is indicated
The reliability output valve at not corresponding current time.For another example assuming that the target obstacle of second sensor output is corresponding current
The classification output result at moment may include the reliability output valve at four candidate categories corresponding current time, and Ped indicates pedestrian；
Bic indicates bicycle；Car indicates motor vehicle；Unk indicates unknown classification；That is: m2=[a2(Ped), a2(Bic), a2(Car), a2
(Unk)]；Wherein, m2Indicate that the classification at the target obstacle corresponding current time of second sensor output exports result；a2
(Ped) the reliability output valve at pedestrian's corresponding current time of second sensor output is indicated；a2(Bic) second sensor is indicated
The reliability output valve at the bicycle of output corresponding current time；a2(Car) indicate that the motor vehicle of second sensor output is corresponding
Current time reliability output valve；a2(Unk) letter at the unknown classification corresponding current time of second sensor output is indicated
Spend output valve.And so on.For another example assuming that the classification at the target obstacle corresponding current time of M sensor output is defeated
Result may include the reliability output valve at four candidate categories corresponding current time out, and Ped indicates pedestrian；Bic is indicated voluntarily
Vehicle；Car indicates motor vehicle；Unk indicates unknown classification；That is: mM=[aM(Ped), aM(Bic), aM(Car), aM(Unk)]；Wherein,
mMIndicate the classification output result at the target obstacle corresponding current time of M sensor output；aM(Ped) M sensing is indicated
The reliability output valve at pedestrian's corresponding current time of device output；aM(Bic) indicate that the bicycle of M sensor output is corresponding
The reliability output valve at current time；aM(Car) the reliability output at the motor vehicle corresponding current time of M sensor output is indicated
Value；aM(Unk) the reliability output valve at the unknown classification corresponding current time of M sensor output is indicated.Therefore, in this step
In, it is corresponding that electronic equipment can obtain each candidate categories in the classification at target obstacle corresponding current time output result
Current time reliability output valve.
S204, according to the reliability fusion value of each candidate categories corresponding last moment and each candidate categories are corresponding works as
The reliability output valve at preceding moment calculates the classification fusion results at target obstacle corresponding current time.
In a specific embodiment of the present invention, electronic equipment can be according to the letter of each candidate categories corresponding last moment
It spends fusion value and the reliability output valve at each candidate categories corresponding current time calculates target obstacle corresponding current time
Classification fusion results.Specifically, electronic equipment can be according to the reliability fusion value of each candidate categories corresponding last moment
The reliability output valve at current time corresponding with each candidate categories calculates the reliability at each candidate categories corresponding current time
Fusion value；Target obstacle corresponding current time is determined according to the reliability fusion value at each candidate categories corresponding current time
Classification fusion results.
S205, the final class that target obstacle is determined according to the classification fusion results at target obstacle corresponding current time
Not.
In a specific embodiment of the present invention, electronic equipment can be according to the classification at target obstacle corresponding current time
Fusion results determine the final classification of target obstacle.Specifically, electronic equipment can first work as according to target obstacle is corresponding
Whole candidate categories are ranked up by the classification fusion results at preceding moment according to the reliability fusion value at corresponding current time；
Then reliability fusion is worth the final classification that maximum candidate categories are determined as target obstacle.
The determination method for the barrier classification that the embodiment of the present invention proposes first receives the target disorders that each sensor is sent
The classification at object corresponding current time exports result；Then according to the class of predetermined target obstacle corresponding last moment
When other fusion results and the corresponding current classification at target obstacle corresponding current time output result calculating target obstacle
The classification fusion results at quarter；Target obstacle is determined further according to the classification fusion results at target obstacle corresponding current time
Final classification.That is, in the inventive solutions, it can be according to the classification of target obstacle corresponding last moment
Fusion results and the classification at target obstacle corresponding current time output result calculate target obstacle corresponding current time
Classification fusion results；Determine target obstacle most further according to the classification fusion results at target obstacle corresponding current time
Whole classification.And in the determination method of existing barrier classification, the output classification of some sensor is determined as target barrier
Hinder the final classification of object；Alternatively, being weighted fusion using output result of the priori knowledge to each sensor.Therefore with it is existing
Technology is compared, and the determination method for the barrier classification that the embodiment of the present invention proposes can more accurately determine target disorders
The final classification of object；Also, the technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and the scope of application is wider.
Embodiment three
Fig. 3 is the flow diagram of the determination method for the barrier classification that the embodiment of the present invention three provides.As shown in figure 3,
The determination method of barrier classification may comprise steps of:
S301, the classification for receiving the target obstacle corresponding current time that each sensor is sent export result.
In a specific embodiment of the present invention, it is corresponding to can receive the target obstacle that each sensor is sent for electronic equipment
Current time classification export result.For example, it is assumed that M sensor can be arranged on unmanned vehicle, be respectively as follows: sensor 1,
Sensor 2 ..., sensor M；It is defeated that sensor 1 can send the classification at target obstacle corresponding current time to electronic equipment
Result 1 out；Sensor 2 can send the classification at target obstacle corresponding current time to electronic equipment and export result 2；…；
Sensor M can send the classification at target obstacle corresponding current time to electronic equipment and export result M.Therefore, electronics is set
The classification output result 1 at the standby target obstacle corresponding current time that can receive the transmission of sensor 1；Sensing can also be received
The classification at the target obstacle corresponding current time that device 2 is sent exports result 1；…；The mesh that can be sent with receiving sensor M
The classification for marking barrier corresponding current time exports result M；Wherein, M is the natural number greater than 1.
S302, to obtain each candidate categories in the classification fusion results of target obstacle corresponding last moment corresponding
The reliability fusion value of last moment.
In a specific embodiment of the present invention, electronic equipment can melt in the classification of target obstacle corresponding last moment
Close the reliability fusion value that each candidate categories corresponding last moment is obtained in result.Specifically, target obstacle it is corresponding on
The classification fusion results at one moment may include the reliability fusion value of N number of candidate categories corresponding last moment, be respectively as follows: candidate class
Reliability fusion value 1, the reliability fusion value 2 of the corresponding last moment of candidate categories 2 of other 1 corresponding last moment；…；Candidate categories
The reliability fusion value N of N corresponding last moment.For example, it is assumed that the classification fusion results of target obstacle corresponding last moment can
To include the reliability fusion value of four candidate categories corresponding last moment, Ped expression pedestrian；Bic indicates bicycle；Car is indicated
Motor vehicle；Unk indicates unknown classification；That is:
Wherein,Indicate the classification fusion results of target obstacle corresponding last moment；mK-1(Ped) on indicating that pedestrian is corresponding
The reliability fusion value at one moment；mK-1(Bic) the reliability fusion value of bicycle corresponding last moment is indicated；mK-1(Car) it indicates
The reliability fusion value of motor vehicle corresponding last moment；mK-1(Unk) the reliability fusion of unknown classification corresponding last moment is indicated
Value.Therefore, in this step, electronic equipment can obtain in the classification fusion results of target obstacle corresponding last moment
The reliability fusion value of each candidate categories corresponding last moment.
S303, to obtain each candidate categories corresponding in the classification output result at target obstacle corresponding current time
The reliability output valve at current time.
In a specific embodiment of the present invention, electronic equipment can target obstacle corresponding current time classification it is defeated
The reliability output valve at each candidate categories corresponding current time is obtained in result out.Specifically, the mesh of each sensor output
The classification output result at mark barrier corresponding current time may include that the reliability at N number of candidate categories corresponding current time is defeated
It is worth out, is respectively as follows: reliability output valve 1, the letter at the corresponding current time of candidate categories 2 at the corresponding current time of candidate categories 1
Spend output valve 2；…；The reliability output valve N at candidate categories N corresponding current time.For example, it is assumed that the mesh of first sensor output
The classification output result at mark barrier corresponding current time may include the reliability at four candidate categories corresponding current time
Output valve, Ped indicate pedestrian；Bic indicates bicycle；Car indicates motor vehicle；Unk indicates unknown classification；That is: m1=[a1
(Ped), a1(Bic), a1(Car), a1(Unk)]；Wherein, m1Indicate that the target obstacle of first sensor output is corresponding current
The classification at moment exports result；a1(Ped) the reliability output valve at pedestrian's corresponding current time of first sensor output is indicated；
a1(Bic) the reliability output valve at the bicycle corresponding current time of first sensor output is indicated；a1(Car) indicate that first passes
The reliability output valve at the motor vehicle corresponding current time of sensor output；a1(Unk) the unknown class of first sensor output is indicated
The reliability output valve at not corresponding current time.For another example assuming that the target obstacle of second sensor output is corresponding current
The classification output result at moment may include the reliability output valve at four candidate categories corresponding current time, and Ped indicates pedestrian；
Bic indicates bicycle；Car indicates motor vehicle；Unk indicates unknown classification；That is: m2=[a2(Ped), a2(Bic), a2(Car), a2
(Unk)]；Wherein, m2Indicate that the classification at the target obstacle corresponding current time of second sensor output exports result；a2
(Ped) the reliability output valve at pedestrian's corresponding current time of second sensor output is indicated；a2(Bic) second sensor is indicated
The reliability output valve at the bicycle of output corresponding current time；a2(Car) indicate that the motor vehicle of second sensor output is corresponding
Current time reliability output valve；a2(Unk) letter at the unknown classification corresponding current time of second sensor output is indicated
Spend output valve.And so on.For another example assuming that the classification at the target obstacle corresponding current time of M sensor output is defeated
Result may include the reliability output valve at four candidate categories corresponding current time out, and Ped indicates pedestrian；Bic is indicated voluntarily
Vehicle；Car indicates motor vehicle；Unk indicates unknown classification；That is: mM=[aM(Ped), aM(Bic), aM(Car), aM(Unk)]；Wherein,
mMIndicate the classification output result at the target obstacle corresponding current time of M sensor output；aM(Ped) M sensing is indicated
The reliability output valve at pedestrian's corresponding current time of device output；aM(Bic) indicate that the bicycle of M sensor output is corresponding
The reliability output valve at current time；aM(Car) the reliability output at the motor vehicle corresponding current time of M sensor output is indicated
Value；aM(Unk) the reliability output valve at the unknown classification corresponding current time of M sensor output is indicated.Therefore, in this step
In, it is corresponding that electronic equipment can obtain each candidate categories in the classification at target obstacle corresponding current time output result
Current time reliability output valve.
S304, according to the reliability fusion value of each candidate categories corresponding last moment and each candidate categories are corresponding works as
The reliability output valve at preceding moment calculates the reliability fusion value at each candidate categories corresponding current time.
In a specific embodiment of the present invention, electronic equipment can be according to the letter of each candidate categories corresponding last moment
When spending fusion value and the corresponding current each candidate categories of the reliability output valve at each candidate categories corresponding current time calculating
The reliability fusion value at quarter.Specifically, electronic equipment can first determine the corresponding candidate categories that are mutually related of each candidate categories
With mutually exclusive candidate categories；Then it obtains in the classification fusion results of target obstacle corresponding last moment and mutually closes
The letter of the reliability fusion value of the candidate categories of connection corresponding last moment and mutually exclusive candidate categories corresponding last moment
Spend fusion value；It is corresponding that the candidate categories that are mutually related are obtained in the classification output result at target obstacle corresponding current time
Current time reliability output valve and the reliability output valve at mutually exclusive candidate categories corresponding current time；Further according to phase
The reliability fusion value of the candidate categories of mutual correlation corresponding last moment and mutually exclusive candidate categories corresponding last moment
Reliability fusion value and the reliability output valve at the candidate categories that are mutually related corresponding current time and mutually exclusive candidate
The reliability output valve at classification corresponding current time calculates the reliability fusion value at each candidate categories corresponding current time.Specifically
Ground, electronic equipment can calculate the reliability fusion value at each candidate categories corresponding current time according to following formula:Wherein, A ∈ { Ped, Bic, Car, Unk }；Normaliztion constant
S305, it determines that target obstacle is corresponding according to the reliability fusion value at each candidate categories corresponding current time and works as
The classification fusion results at preceding moment.
In a specific embodiment of the present invention, electronic equipment can be according to the letter at each candidate categories corresponding current time
Degree fusion value determines the classification fusion results at target obstacle corresponding current time.Specifically, it is assumed that target obstacle is corresponding
Current time classification fusion results may include four candidate categories corresponding current time reliability fusion value, Ped table
Show pedestrian；Bic indicates bicycle；Car indicates motor vehicle；Unk indicates unknown classification；That is:Wherein,Indicate that target obstacle is corresponding
Current time classification fusion results；mK(Ped) the reliability fusion value at pedestrian's corresponding current time is indicated；mK(Bic) it indicates
The reliability fusion value at bicycle corresponding current time；mK(Car) the reliability fusion value at motor vehicle corresponding current time is indicated；
mK(Unk) the reliability fusion value at unknown classification corresponding current time is indicated.Therefore, in this step, electronic equipment can root
Determine that the classification at target obstacle corresponding current time is melted according to the reliability fusion value at each candidate categories corresponding current time
Close result.
S306, the final class that target obstacle is determined according to the classification fusion results at target obstacle corresponding current time
Not.
In a specific embodiment of the present invention, electronic equipment can be according to the classification at target obstacle corresponding current time
Fusion results determine the final classification of target obstacle.Specifically, electronic equipment can first work as according to target obstacle is corresponding
Whole candidate categories are ranked up by the classification fusion results at preceding moment according to the reliability fusion value at corresponding current time；
Then reliability fusion is worth the final classification that maximum candidate categories are determined as target obstacle.
The determination method for the barrier classification that the embodiment of the present invention proposes first receives the target disorders that each sensor is sent
The classification at object corresponding current time exports result；Then according to the class of predetermined target obstacle corresponding last moment
When other fusion results and the corresponding current classification at target obstacle corresponding current time output result calculating target obstacle
The classification fusion results at quarter；Target obstacle is determined further according to the classification fusion results at target obstacle corresponding current time
Final classification.That is, in the inventive solutions, it can be according to the classification of target obstacle corresponding last moment
Fusion results and the classification at target obstacle corresponding current time output result calculate target obstacle corresponding current time
Classification fusion results；Determine target obstacle most further according to the classification fusion results at target obstacle corresponding current time
Whole classification.And in the determination method of existing barrier classification, the output classification of some sensor is determined as target barrier
Hinder the final classification of object；Alternatively, being weighted fusion using output result of the priori knowledge to each sensor.Therefore with it is existing
Technology is compared, and the determination method for the barrier classification that the embodiment of the present invention proposes can more accurately determine target disorders
The final classification of object；Also, the technical solution realization of the embodiment of the present invention is simple and convenient, it is universal to be convenient for, and the scope of application is wider.
Example IV
Fig. 4 is the first structure diagram of the determining device for the barrier classification that the embodiment of the present invention four provides.Such as Fig. 4 institute
Show, the determining device of barrier classification described in the embodiment of the present invention may include: receiving module 401, computing module 402 and really
Cover half block 403；Wherein,
The receiving module 401, for receiving the class at the target obstacle corresponding current time that each sensor is sent
It Shu Chu not result；
The computing module 402, for the classification according to the predetermined target obstacle corresponding last moment
It is corresponding that fusion results and the classification at the target obstacle corresponding current time output result calculate the target obstacle
The classification fusion results at current time；
The determining module 403, it is true for the classification fusion results according to the target obstacle corresponding current time
The final classification of the fixed target obstacle.
Fig. 5 is the second structural schematic diagram of the determining device for the barrier classification that the embodiment of the present invention four provides.Such as Fig. 5 institute
Show, the computing module 402 includes: acquisition submodule 4021 and computational submodule 4022；Wherein,
The acquisition submodule 4021, in the classification fusion results of the target obstacle corresponding last moment
Obtain the reliability fusion value of each candidate categories corresponding last moment；In the class at the target obstacle corresponding current time
The reliability output valve at each candidate categories corresponding current time Shu Chu not be obtained in result；
The computational submodule 4022, for according to the reliability fusion value of each candidate categories corresponding last moment and each
The reliability output valve at a candidate categories corresponding current time calculates the classification at the target obstacle corresponding current time and melts
Close result.
Further, the computational submodule 4022, for the reliability according to each candidate categories corresponding last moment
Fusion value and the reliability output valve at each candidate categories corresponding current time calculate each candidate categories corresponding current time
Reliability fusion value；Determine that the target obstacle is corresponding according to the reliability fusion value at each candidate categories corresponding current time
Current time classification fusion results.
Further, the computational submodule 4022 is mutually related specifically for each candidate categories of determination are corresponding
Candidate categories and mutually exclusive candidate categories；It is obtained in the classification fusion results of the target obstacle corresponding last moment
Take the candidate categories corresponding last moment that is mutually related reliability fusion value and the mutually exclusive candidate categories pair
The reliability fusion value for the last moment answered；Institute is obtained in the classification output result at the target obstacle corresponding current time
Reliability output valve and the mutually exclusive candidate categories for stating the candidate categories that are mutually related corresponding current time are corresponding
The reliability output valve at current time；According to the reliability fusion value of the candidate categories that are mutually related corresponding last moment and institute
Reliability fusion value and the candidate categories that are mutually related for stating mutually exclusive candidate categories corresponding last moment are corresponding
Current time reliability output valve and the reliability output valve at the mutually exclusive candidate categories corresponding current time calculate
The reliability fusion value at each candidate categories corresponding current time.
Further, the determining module 403, specifically for the class according to the target obstacle corresponding current time
Whole candidate categories are ranked up by other fusion results according to the reliability fusion value at corresponding current time；Reliability is merged
It is worth the final classification that maximum candidate categories are determined as the target obstacle.
Method provided by any embodiment of the invention can be performed in the determining device of above-mentioned barrier classification, has the side of execution
The corresponding functional module of method and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is any
The determination method for the barrier classification that embodiment provides.
Embodiment five
Fig. 6 is the structural schematic diagram for the electronic equipment that the embodiment of the present invention five provides.Fig. 6, which is shown, to be suitable for being used to realizing this
The block diagram of the example electronic device of invention embodiment.The electronic equipment 12 that Fig. 6 is shown is only an example, should not be to this
The function and use scope of inventive embodiments bring any restrictions.
As shown in fig. 6, electronic equipment 12 is showed in the form of universal computing device.The component of electronic equipment 12 may include
But be not limited to: one or more processor or processing unit 16, system storage 28, connect different system components (including
System storage 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Electronic equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be electric
The usable medium that sub- equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Electronic equipment 12 may further include other removable/not removable
Dynamic, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for read and write can not
Mobile, non-volatile magnetic media (Fig. 6 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 6, Ke Yiti
For the disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to moving non-volatile light
The CD drive of disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver
It can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform of the invention each
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiment described in the invention.
Electronic equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Communication, can also be enabled a user to one or more equipment interact with the electronic equipment 12 communicate, and/or with make the electricity
Any equipment (such as network interface card, modem etc.) that sub- equipment 12 can be communicated with one or more of the other calculating equipment
Communication.This communication can be carried out by input/output (I/O) interface 22.Also, electronic equipment 12 can also be suitable by network
Orchestration 20 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet)
Communication.As shown, network adapter 20 is communicated by bus 18 with other modules of electronic equipment 12.Although should be understood that
It is not shown in the figure, other hardware and/or software module can be used in conjunction with electronic equipment 12, including but not limited to: microcode is set
Standby driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system
System etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the determination method of barrier classification provided by the embodiment of the present invention.
Embodiment six
The embodiment of the present invention six provides a kind of computer storage medium.
The computer readable storage medium of the embodiment of the present invention, can be using one or more computer-readable media
Any combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer
Readable storage medium storing program for executing for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, dress
It sets or device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium wraps
It includes: there is the electrical connection of one or more conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable
Storage medium can be it is any include or storage program tangible medium, the program can be commanded execution system, device or
Device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (12)
1. a kind of determination method of barrier classification, which is characterized in that the described method includes:
Receive the classification output result at the target obstacle corresponding current time that each sensor is sent；
According to the classification fusion results and the target obstacle of the predetermined target obstacle corresponding last moment
The classification output result at corresponding current time calculates the classification fusion results at the target obstacle corresponding current time；
The final class of the target obstacle is determined according to the classification fusion results at the target obstacle corresponding current time
Not.
2. the method according to claim 1, wherein described corresponding according to the predetermined target obstacle
Last moment classification fusion results and the classification at the target obstacle corresponding current time output result calculate described in
The classification fusion results at target obstacle corresponding current time, comprising:
Each candidate categories corresponding upper one are obtained in the classification fusion results of the target obstacle corresponding last moment
The reliability fusion value at moment；
It is corresponding current that each candidate categories are obtained in the classification output result at the target obstacle corresponding current time
The reliability output valve at moment；
According to the reliability fusion value of each candidate categories corresponding last moment and each candidate categories corresponding current time
Reliability output valve calculates the classification fusion results at the target obstacle corresponding current time.
3. according to the method described in claim 2, it is characterized in that, described according to each candidate categories corresponding last moment
Reliability fusion value and the reliability output valve at each candidate categories corresponding current time calculate that the target obstacle is corresponding to be worked as
The classification fusion results at preceding moment, comprising:
According to the reliability fusion value of each candidate categories corresponding last moment and each candidate categories corresponding current time
Reliability output valve calculates the reliability fusion value at each candidate categories corresponding current time；
When determining that the target obstacle is corresponding current according to the reliability fusion value at each candidate categories corresponding current time
The classification fusion results at quarter.
4. according to the method described in claim 3, it is characterized in that, described according to each candidate categories corresponding last moment
It is corresponding current that reliability fusion value and the reliability output valve at each candidate categories corresponding current time calculate each candidate categories
The reliability fusion value at moment, comprising:
Determine corresponding candidate categories and the mutually exclusive candidate categories of being mutually related of each candidate categories；
Be mutually related candidate categories described in obtaining in the classification fusion results of the target obstacle corresponding last moment
The reliability fusion value of the reliability fusion value of corresponding last moment and the mutually exclusive candidate categories corresponding last moment；
Be mutually related candidate categories described in obtaining in the classification output result at the target obstacle corresponding current time
The reliability output valve of the reliability output valve at corresponding current time and the mutually exclusive candidate categories corresponding current time；
According to the reliability fusion value of the candidate categories that are mutually related corresponding last moment and the mutually exclusive candidate
The reliability fusion value of classification corresponding last moment and the reliability at the candidate categories that are mutually related corresponding current time
It is corresponding that output valve and the reliability output valve at the mutually exclusive candidate categories corresponding current time calculate each candidate categories
Current time reliability fusion value.
5. the method according to claim 1, wherein described according to the target obstacle corresponding current time
Classification fusion results determine the final classification of the target obstacle, comprising:
According to the classification fusion results at the target obstacle corresponding current time by whole candidate categories according to corresponding
The reliability fusion value at current time be ranked up；
Reliability fusion is worth the final classification that maximum candidate categories are determined as the target obstacle.
6. a kind of determining device of barrier classification, which is characterized in that described device include: receiving module, computing module and really
Cover half block；Wherein,
The receiving module, for receiving the classification output knot at the target obstacle corresponding current time that each sensor is sent
Fruit；
The computing module, for the classification fusion results according to the predetermined target obstacle corresponding last moment
The classification output result at current time corresponding with the target obstacle calculates the target obstacle corresponding current time
Classification fusion results；
The determining module, for determining the mesh according to the classification fusion results at the target obstacle corresponding current time
Mark the final classification of barrier.
7. device according to claim 6, which is characterized in that the computing module includes: acquisition submodule and calculates sub
Module；Wherein,
The acquisition submodule, it is each for being obtained in the classification fusion results of the target obstacle corresponding last moment
The reliability fusion value of candidate categories corresponding last moment；Knot is exported in the classification at the target obstacle corresponding current time
The reliability output valve at each candidate categories corresponding current time is obtained in fruit；
The computational submodule, for the reliability fusion value and each candidate class according to each candidate categories corresponding last moment
The reliability output valve at not corresponding current time calculates the classification fusion results at the target obstacle corresponding current time.
8. device according to claim 7, which is characterized in that the computational submodule, for according to each candidate categories
The reliability fusion value and the reliability output valve at each candidate categories corresponding current time of corresponding last moment calculates each time
Select the reliability fusion value at classification corresponding current time；It is true according to the reliability fusion value at each candidate categories corresponding current time
Determine the classification fusion results at the target obstacle corresponding current time.
9. device according to claim 8, it is characterised in that:
The computational submodule, specifically for the corresponding candidate categories and mutually exclusive of being mutually related of each candidate categories of determination
Candidate categories；Be mutually related time described in obtaining in the classification fusion results of the target obstacle corresponding last moment
Select the reliability fusion value and the reliability of the mutually exclusive candidate categories corresponding last moment of classification corresponding last moment
Fusion value；Be mutually related candidate class described in obtaining in the classification output result at the target obstacle corresponding current time
The reliability output valve at not corresponding current time and the output of the reliability at the mutually exclusive candidate categories corresponding current time
Value；According to the reliability fusion value of the candidate categories that are mutually related corresponding last moment and the mutually exclusive candidate class
The reliability fusion value of not corresponding last moment and the reliability at the candidate categories that are mutually related corresponding current time are defeated
The each candidate categories of reliability output valve calculating for being worth current time corresponding with the mutually exclusive candidate categories out are corresponding
The reliability fusion value at current time.
10. device according to claim 6, it is characterised in that:
The determining module, specifically for will be whole according to the classification fusion results at the target obstacle corresponding current time
Candidate categories are ranked up according to the reliability fusion value at corresponding current time；Reliability fusion is worth maximum candidate categories
It is determined as the final classification of the target obstacle.
11. a kind of electronic equipment characterized by comprising
One or more processors；
Memory, 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 determination method of the barrier classification as described in any one of claims 1 to 5.
12. a kind of storage medium, is stored thereon with computer program, which is characterized in that the realization when program is executed by processor
The determination method of barrier classification as described in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811506234.8A CN109635868B (en) | 2018-12-10 | 2018-12-10 | Method and device for determining obstacle type, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811506234.8A CN109635868B (en) | 2018-12-10 | 2018-12-10 | Method and device for determining obstacle type, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109635868A true CN109635868A (en) | 2019-04-16 |
| CN109635868B CN109635868B (en) | 2021-07-20 |
Family
ID=66072547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811506234.8A Active CN109635868B (en) | 2018-12-10 | 2018-12-10 | Method and device for determining obstacle type, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635868B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110843792A (en) * | 2019-11-29 | 2020-02-28 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN111582173A (en) * | 2020-05-08 | 2020-08-25 | 东软睿驰汽车技术（沈阳）有限公司 | Automatic driving method and system |
| CN114858200A (en) * | 2022-04-19 | 2022-08-05 | 合众新能源汽车有限公司 | Method and device for evaluating quality of object detected by vehicle sensor |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120300975A1 (en) * | 2011-05-24 | 2012-11-29 | Tata Consultancy Services Limited | System and method for detecting the watermark using decision fusion |
| CN104718507A (en) * | 2012-11-05 | 2015-06-17 | 松下知识产权经营株式会社 | Autonomous traveling device traveling-information generation device, method, and program, and autonomous traveling device |
| CN106707293A (en) * | 2016-12-01 | 2017-05-24 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device for vehicles |
| US20170318360A1 (en) * | 2016-05-02 | 2017-11-02 | Bao Tran | Smart device |
| CN107966700A (en) * | 2017-11-20 | 2018-04-27 | 天津大学 | A kind of front obstacle detecting system and method for pilotless automobile |
| CN108573271A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | Optimization method and device, computer equipment and the recording medium of Multisensor Target Information fusion |
| CN108664989A (en) * | 2018-03-27 | 2018-10-16 | 北京达佳互联信息技术有限公司 | Image tag determines method, apparatus and terminal |
-
2018
- 2018-12-10 CN CN201811506234.8A patent/CN109635868B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120300975A1 (en) * | 2011-05-24 | 2012-11-29 | Tata Consultancy Services Limited | System and method for detecting the watermark using decision fusion |
| CN104718507A (en) * | 2012-11-05 | 2015-06-17 | 松下知识产权经营株式会社 | Autonomous traveling device traveling-information generation device, method, and program, and autonomous traveling device |
| US20170318360A1 (en) * | 2016-05-02 | 2017-11-02 | Bao Tran | Smart device |
| CN106707293A (en) * | 2016-12-01 | 2017-05-24 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device for vehicles |
| CN107966700A (en) * | 2017-11-20 | 2018-04-27 | 天津大学 | A kind of front obstacle detecting system and method for pilotless automobile |
| CN108573271A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | Optimization method and device, computer equipment and the recording medium of Multisensor Target Information fusion |
| CN108664989A (en) * | 2018-03-27 | 2018-10-16 | 北京达佳互联信息技术有限公司 | Image tag determines method, apparatus and terminal |
Non-Patent Citations (2)
| Title |
|---|
| DONG WON YANG 等: "An improved classification method of concealed obstacles using UWB radar and stereo cameras", 《IEEE》 * |
| 朱玉鹏 等: "决策层时空信息融合的神经网络模型研究", 《***工程与电子技术》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110843792A (en) * | 2019-11-29 | 2020-02-28 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN110843792B (en) * | 2019-11-29 | 2021-05-25 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN111582173A (en) * | 2020-05-08 | 2020-08-25 | 东软睿驰汽车技术（沈阳）有限公司 | Automatic driving method and system |
| CN114858200A (en) * | 2022-04-19 | 2022-08-05 | 合众新能源汽车有限公司 | Method and device for evaluating quality of object detected by vehicle sensor |
| CN114858200B (en) * | 2022-04-19 | 2023-06-27 | 合众新能源汽车股份有限公司 | Method and device for evaluating quality of object detected by vehicle sensor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109635868B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6017678B2 (en) | Landmark-based place-thinking tracking for voice-controlled navigation systems | |
| CN109188457A (en) | Generation method, device, equipment, storage medium and the vehicle of object detection frame | |
| CN110095752A (en) | Localization method, device, equipment and medium | |
| CN109635868A (en) | Determination method, apparatus, electronic equipment and the storage medium of barrier classification | |
| JP6756079B2 (en) | Artificial intelligence-based ternary check method, equipment and computer program | |
| CN110390054A (en) | Point of interest recalls method, apparatus, server and storage medium | |
| CN107194412A (en) | A kind of method of processing data, device, equipment and computer-readable storage medium | |
| CN109635861A (en) | A kind of data fusion method, device, electronic equipment and storage medium | |
| CN109543923A (en) | Vehicle queue time forecasting methods, system, equipment and storage medium | |
| CN109795505A (en) | Automatic Pilot method of discrimination, device, computer equipment and storage medium | |
| CN109344899A (en) | Multi-target detection method, device and electronic equipment | |
| CN109974733A (en) | POI display methods, device, terminal and medium for AR navigation | |
| CN110097121A (en) | A kind of classification method of driving trace, device, electronic equipment and storage medium | |
| CN109353345A (en) | Control method for vehicle, device, equipment, medium and vehicle | |
| US20220019616A1 (en) | Content display device and content display method | |
| CN110427444A (en) | Navigation guide point method for digging, device, equipment and storage medium | |
| CN112233428B (en) | Traffic flow prediction method, device, storage medium and equipment | |
| CN109784630A (en) | Automatic Pilot level evaluation method, device, computer equipment and storage medium | |
| CN109960554A (en) | Show method, equipment and the computer storage medium of reading content | |
| CN110017840B (en) | Navigation data processing method and device, electronic equipment and computer readable medium | |
| JP2023038164A (en) | Obstacle detection method, device, automatic driving vehicle, apparatus, and storage medium | |
| CN110008921A (en) | A kind of generation method of road boundary, device, electronic equipment and storage medium | |
| CN110186472A (en) | Vehicle yaw detection method, computer equipment, storage medium and Vehicular system | |
| CN110363193A (en) | Vehicle recognition methods, device, equipment and computer storage medium again | |
| CN112400147A (en) | Algorithm configuration method, equipment and system and movable platform |
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 |