CN110059393A - A kind of emulation test method of vehicle, apparatus and system - Google Patents
A kind of emulation test method of vehicle, apparatus and system Download PDFInfo
- Publication number
- CN110059393A CN110059393A CN201910289957.5A CN201910289957A CN110059393A CN 110059393 A CN110059393 A CN 110059393A CN 201910289957 A CN201910289957 A CN 201910289957A CN 110059393 A CN110059393 A CN 110059393A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- target
- road
- pedestrian
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010998 test method Methods 0.000 title claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 84
- 238000001514 detection method Methods 0.000 claims abstract description 52
- 230000007613 environmental effect Effects 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000004088 simulation Methods 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 23
- 238000009434 installation Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000011056 performance test Methods 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003716 rejuvenation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
This application discloses a kind of emulation test methods of vehicle, apparatus and system, by according to the target detection environmental information and information of vehicles to be tested extracted from target video, it is emulated using emulator, virtual testing environment and virtual test vehicle are respectively obtained, is tested for the property so that virtual test vehicle to be put into virtual testing environment.Since vehicle testing process is to participate in by carrying out test realization in virtual testing environment using virtual test vehicle without true vehicle to be tested, thus reduce testing cost, the safety of vehicle testing process is improved.In addition, since target video is to be obtained by unmanned plane by shooting, thus, target video accurately can comprehensively reflect the real driving environment of vehicle to be tested, so that target detection environmental information and virtual testing environment accurately can comprehensively reflect the real driving environment of vehicle to be tested, to improve the accuracy and comprehensive, the credibility of raising vehicle testing process of virtual testing environment.
Description
Technical field
This application involves technical field of vehicle more particularly to a kind of emulation test methods of vehicle, apparatus and system.
Background technique
With the fast development of automatic driving vehicle, the test of vehicle performance is more and more important.In the prior art, usually
The vehicle to be tested produced can be directly placed into the driving test environment arranged and be tested.
However, since driving test environment is according to the function to be tested of vehicle to be tested by tester to driving ring
What border was arranged, and real driving environment be it is very various and complicated, thus, which tests environment can not be quasi-
Real driving environment really is restored, the test process for easily leading to vehicle to be tested is not comprehensive, to reduce vehicle testing process
Credibility.
In addition, since the production of vehicle to be tested needs certain production cost, thus will be after test vehicle produces
It is tested again, will increase vehicle testing cost；Moreover, because the performance of vehicle to be tested be it is unstable, thus, using to
Test vehicle carry out be easy to happen danger during testing.
Summary of the invention
In order to solve the above technical problem existing in the prior art, the application provides a kind of emulation testing side of vehicle
Method, apparatus and system can carry out emulation testing in the virtual testing environment for accurately having restored real driving environment, improve
The credibility and safety of vehicle testing process, also reduces vehicle testing cost.
To achieve the goals above, technical solution provided by the present application is as follows:
The application provides a kind of emulation test method of vehicle, comprising:
Target detection environmental information is extracted from target video；Wherein, the target video is to pass through shooting by unmanned plane
What vehicle running state and running environment in target road obtained；The target detection environmental information includes that road periphery is built
Build at least one of information, road information, vehicle traveling information and pedestrian's driving information；
According to the target detection environmental information and information of vehicles to be tested, is emulated, respectively obtained using emulator
Virtual testing environment and virtual test vehicle, so that the virtual test vehicle is put into progressive in the virtual testing environment
It can test.
Optionally, described that target detection environmental information is extracted from target video, it specifically includes:
Target entity is identified from target video using deep learning algorithm；Wherein, target entity include building, road,
At least one of vehicle and pedestrian；
According to the target entity, target detection environmental information is obtained using preset algorithm.
Optionally, when the target entity includes vehicle, and the vehicle traveling information include vehicle driving trace and
It is described according to the target entity when driving direction of vehicle, target detection environmental information is obtained using preset algorithm, it is specific to wrap
It includes:
According to the vehicle, the driving trace of the vehicle is obtained using the first track algorithm, and is calculated using towards identification
Method obtains the driving direction of the vehicle.
Optionally, when the target entity includes pedestrian, and pedestrian's driving information includes the driving trace of pedestrian,
It is described to be specifically included according to the target entity using preset algorithm acquisition target detection environmental information:
According to the pedestrian, the driving trace of the pedestrian is obtained using the second track algorithm.
Optionally, described according to the target entity when the target entity includes road, it is obtained using preset algorithm
Target detection environmental information, specifically includes:
According to the road, the road information is obtained using visual identification algorithm.
Present invention also provides a kind of simulation testing devices of vehicle, comprising:
Extraction unit, for extracting target detection environmental information from target video；Wherein, the target video is by nothing
It is man-machine to be obtained by photographic subjects road vehicle driving status and running environment；The target detection environmental information packet
Include at least one of road neighboring buildings information, road information, vehicle traveling information and pedestrian's driving information；
Simulation unit, for being carried out using emulator according to the target detection environmental information and information of vehicles to be tested
Emulation, respectively obtains virtual testing environment and virtual test vehicle, so that the virtual test vehicle is put into the virtual survey
Test ring is tested for the property in border.
Optionally, the extraction unit, specifically includes:
Subelement is identified, for identifying target entity from target video using deep learning algorithm；Wherein, target entity
Including at least one of building, road, vehicle and pedestrian；
Subelement is obtained, for obtaining target detection environmental information using preset algorithm according to the target entity.
Optionally, the acquisition subelement, specifically includes:
Information of vehicles obtains module, and for including vehicle when the target entity, and the vehicle traveling information includes vehicle
Driving trace and vehicle driving direction when, according to the vehicle, the row of the vehicle is obtained using the first track algorithm
Track is sailed, and utilizes the driving direction for obtaining the vehicle towards recognizer.
Optionally, the acquisition subelement, specifically includes:
Pedestrian information obtains module, and for including pedestrian when the target entity, and pedestrian's driving information includes row
When the driving trace of people, according to the pedestrian, the driving trace of the pedestrian is obtained using the second track algorithm.
Optionally, the acquisition subelement, specifically includes:
Road information obtains module, for according to the road, being known using vision when the target entity includes road
Other algorithm obtains the road information.
Present invention also provides a kind of emulation test systems of vehicle, comprising: the emulation of any vehicle of above-mentioned offer
Test device and unmanned plane.
Compared with prior art, the application has at least the following advantages:
The emulation test method of vehicle provided by the present application, by according to the target detection environment extracted from target video
Information and information of vehicles to be tested, are emulated using emulator, respectively obtain virtual testing environment and virtual test vehicle, with
Just the virtual test vehicle is put into the virtual testing environment and is tested for the property.Since vehicle testing process is to pass through
Test realization is carried out in virtual testing environment using virtual test vehicle, without the participation of true vehicle to be tested, thus
Testing cost is reduced, the safety of vehicle testing process is also improved.In addition, since target video is to pass through bat by unmanned plane
What the vehicle running state and running environment taken the photograph in target road obtained, thus, which can be accurately comprehensively anti-
The real driving environment of vehicle to be tested is reflected, so that the target detection environmental information extracted from target video also can be accurately complete
Reflect to face the real driving environment of vehicle to be tested, but also carrying out the virtual of emulation acquisition according to target detection environmental information
Test environment also accurately can comprehensively reflect the real driving environment of vehicle to be tested, to improve virtual testing environment
Accuracy and comprehensive, and then improve the credibility of vehicle testing process.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is the flow chart of the emulation test method for the vehicle that the application embodiment of the method provides；
Fig. 2 is the structural schematic diagram of the simulation testing device for the vehicle that the application Installation practice provides；
Fig. 3 is the structural schematic diagram of the emulation test system for the vehicle that the application system embodiment provides.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment of the method
Referring to Fig. 1, which is the flow chart of the emulation test method for the vehicle that the application embodiment of the method provides.
The emulation test method of vehicle provided by the embodiments of the present application, comprising:
S101: target detection environmental information is extracted from target video.
S102: it according to target detection environmental information, is emulated using emulator, obtains virtual testing environment.
S103: according to information of vehicles to be tested, being emulated using emulator, obtains virtual test vehicle.
S104: the virtual test vehicle is put into the virtual testing environment and is tested for the property.
It should be noted that do not have between S101-S102 and S103 it is fixed execute sequence, can be executed sequentially S101,
S102 and S103, also can be executed sequentially S103, S101 and S102, can also successively execute S101, S103 and S102, the application
It is not specifically limited in this embodiment.
The above are the specific execution steps of the emulation test method of vehicle provided by the embodiments of the present application, in order to facilitate understanding
Emulation test method with vehicle provided by the embodiments of the present application is explained, will successively introduce S101, S102, S103 and S104 below
Specific embodiment.
The specific embodiment of S101 is introduced first.
In S101, target video is to pass through photographic subjects road vehicle driving status and traveling ring by unmanned plane
What border obtained.In addition, since target video can be used for recording the road information of target road, the neighboring buildings letter of target road
At least one of breath, the vehicle traveling information in target road and pedestrian's driving information information, thus, target detection environment letter
Breath may include at least one of road neighboring buildings information, road information, vehicle traveling information and pedestrian's driving information.
As an implementation, in order to improve the accuracy of target detection environmental information and comprehensive, S101 is specific
May include:
S1011: target entity is identified from target video using deep learning algorithm；Wherein, target entity include building,
At least one of road, vehicle and pedestrian.
As an example, then S1011 is specifically as follows when target entity includes building, road, vehicle and pedestrian: utilizing
Deep learning algorithm respectively identifies building, road, vehicle and pedestrian from target video.
S1012: according to the target entity, target detection environmental information is obtained using preset algorithm.
Preset algorithm can be preset, moreover, preset algorithm can be any information extracting method.
In addition, in order to further increase the accuracy of target detection environmental information and comprehensive, it can also be for difference
Target entity information extraction is carried out using different algorithm, thus, present invention also provides the different embodiments of S1012,
For the ease of explanation and illustration, below by the embodiment of successively every kind of S1012.
Due in target video vehicle in moving condition, thus, for the vehicle, the driving trace of vehicle and
Driving direction is highly important vehicle traveling information, in this way, making in order to accurately comprehensively extract vehicle traveling information
The vehicle more true and accurate travelled in virtual testing environment is obtained, this application provides a kind of embodiments of S1012, in the implementation
In mode, S1012 is specifically as follows: according to the vehicle, the driving trace of the vehicle is obtained using the first track algorithm, and
Utilize the driving direction that the vehicle is obtained towards recognizer；Wherein, the vehicle traveling information includes the traveling rail of vehicle
The driving direction of mark and vehicle.
First track algorithm can be preset, moreover, the first track algorithm can be it is any be able to carry out vehicle with
The algorithm of track.
It can be preset towards recognizer, moreover, can be towards recognizer any can identify vehicle row
Sail the algorithm in direction.
As an example, then can use the first track algorithm to target video when in target entity including the first vehicle
In the first vehicle tracked, in order to obtain driving trace of first vehicle in target video, and using towards identification
Algorithm identifies the driving direction of the first vehicle in target video.
The above are a kind of embodiments of S1012, in this embodiment, when the target entity includes vehicle, and institute
When stating the driving direction of driving trace and vehicle that vehicle traveling information includes vehicle, it can use
First track algorithm obtains the driving trace of the vehicle, and utilizes the row that the vehicle is obtained towards recognizer
Sail direction.It so, it is possible to improve the accuracy of vehicle traveling information and comprehensive, to be conducive to improve in virtual test ring
The authenticity and accuracy of the virtual vehicle travelled in target road in border.
In addition, since the pedestrian in target video is also movement, thus, for pedestrian, the driving trace of pedestrian
And it is highly important, thus, in order to accurately comprehensively extract pedestrian's driving information, this application provides the another of S1012
A kind of embodiment, in this embodiment, S1012 is specifically as follows: according to the pedestrian, being obtained using the second track algorithm
The driving trace of the pedestrian.
Second track algorithm can be preset, moreover, the second track algorithm can be it is any be able to carry out pedestrian with
The algorithm of track.In addition, the second track algorithm can be identical as the first track algorithm, can also be different.
As an example, then can use the second track algorithm to target video when in target entity including the first pedestrian
In the first pedestrian track, to obtain driving trace of first pedestrian in target video.
The above are the another embodiments of S1012, in this embodiment, when the target entity includes pedestrian, and
When pedestrian's driving information includes the driving trace of pedestrian, institute can be obtained using the second track algorithm according to the pedestrian
State the driving trace of pedestrian.It so, it is possible to improve the accuracy of pedestrian's driving information and comprehensive, to be conducive to improve empty
The authenticity and accuracy of virtual pedestrian in quasi- test environment.
Further, since target road is static in target video, and vehicle to be tested needs in the target road
It is tested for the property, therefore, it is possible to improve the standard of vehicle testing process by the accuracy and authenticity that improve target road
True property and comprehensive.In this way, this application provides the another embodiments of S1012, and in this embodiment, S1012 tool
Body can be with are as follows: according to the road, visual identification algorithm is utilized to obtain the road information.
Visual identification algorithm can be preset, moreover, visual identification algorithm can be and any can recognize that road
Algorithm.
It should be noted that the road information of target road may include lane in target road, target road
Traffic lights and other information relevant to road.
The above are another embodiments of S1012, in this embodiment, when the target entity includes road,
The road information can be obtained using visual identification algorithm according to the road.It so, it is possible to improve the accurate of road information
Property and it is comprehensive, thus be conducive to improve virtual testing environment in virtual road authenticity and accuracy.
The above are the specific embodiments of S101, in these embodiments, can use deep learning algorithm from target
Building, road, the vehicle and pedestrian in target video are identified in video, and according to building, road, vehicle and the row identified
People obtains road neighboring buildings information, road information, vehicle traveling information and pedestrian's driving information using preset algorithm.In this way,
Can be improved road neighboring buildings information, road information, vehicle traveling information and pedestrian's driving information accuracy and comprehensively
Property, to be conducive to improve the authenticity and accuracy of virtual testing environment.
The specific embodiment of S102 is described below.
In S102, emulator can be it is any can be to the emulator that environment is emulated, for example, emulator can be with
It is carla emulator.
As an implementation, when target detection environmental information includes road neighboring buildings information, road information, vehicle
When driving information and pedestrian's driving information, then S102 is specifically as follows: according to road neighboring buildings information, road information, vehicle
Driving information and pedestrian's driving information, are emulated using Carla emulator, obtain virtual testing environment, so that virtual test
Environment can truely and accurately simulate target road in target video, the neighboring buildings of target road, target road uplink
The pedestrian travelled on the vehicle and target road sailed.
The above are the specific embodiments of S102, in this embodiment, can be utilized according to target detection environmental information
Emulator is emulated, and virtual testing environment is obtained.At this point, since target detection environmental information accurately can comprehensively record mesh
The test environmental information in video is marked, thus, it can be complete according to the virtual testing environment that target detection environmental information emulates
The face accurately test environment in rejuvenation target video, to ensure that virtual testing environment can be represented all-sidedly and accurately really
Test environment.
The specific embodiment of S103 is described below.
In S103, vehicle to be tested is the vehicle for being tested, moreover, vehicle to be tested have it is some need into
The performance of row test.
Information of vehicles to be tested accurately can comprehensively record all or part of relevant information of vehicle to be tested.
As an implementation, S103 is specifically as follows: information of vehicles to be tested is input in Carla emulator,
To obtain the virtual test vehicle with vehicle performance to be tested；Moreover, the virtual test vehicle can be in virtual test ring
It is tested for the property in border.
The above are the specific embodiments of S103, in this embodiment, can be according to information of vehicles to be tested, using imitative
True device is emulated, and virtual test vehicle is obtained.At this point, due to information of vehicles to be tested accurately can comprehensively record it is to be tested
The relevant information of vehicle, thus, the virtual test vehicle emulated according to information of vehicles to be tested can have test run to be measured
Performance, enable virtual test vehicle accurately to represent vehicle to be tested.In this way, when virtual test vehicle can be in void
When being travelled safely in quasi- test environment, and can be realized function to be tested, then it represents that vehicle to be tested also can be
It is travelled safely in true test environment, and can be realized function to be tested.
The specific embodiment of S104 is described below.
In S104, performance test refers to verify the survey whether vehicle has certain specific function and carry out
Examination；Moreover, performance test may include: avoidance test, the test of identification traffic sign or automatic stopping test etc..
As an example, then S104 is specifically as follows when needing to treat test vehicle progress avoidance test: will be described virtual
Test vehicle, which is put into the virtual testing environment, to be travelled, and determines whether the virtual test vehicle can successfully avoid
Barrier.
The above are the specific embodiments of S104, in this embodiment, the virtual test vehicle can be put into institute
It states in virtual testing environment and is tested for the property.
The above are the specific embodiments of the emulation test method of the vehicle of embodiment of the method offer, preferably
In, by being carried out using emulator according to the target detection environmental information and information of vehicles to be tested extracted from target video
Emulation, respectively obtains virtual testing environment and virtual test vehicle, so that the virtual test vehicle is put into the virtual survey
Test ring is tested for the property in border.Since vehicle testing process is by being carried out using virtual test vehicle in virtual testing environment
What test was realized, without the participation of true vehicle to be tested, thus testing cost is reduced, also improves vehicle testing process
Safety.In addition, since target video is to pass through photographic subjects road vehicle driving status and traveling by unmanned plane
What environment obtained, thus, which accurately can comprehensively reflect the real driving environment of vehicle to be tested, so that from mesh
The target detection environmental information extracted in mark video also accurately can comprehensively reflect the real driving environment of vehicle to be tested,
So that also accurately can comprehensively be reflected according to the virtual testing environment that target detection environmental information carries out emulation acquisition to be tested
The real driving environment of vehicle to improve the accuracy of virtual testing environment and comprehensive, and then improves vehicle survey
The credibility of examination process.
Emulation test method based on the vehicle that above method embodiment provides, present invention also provides a kind of the imitative of vehicle
True test device, is explained and illustrated below in conjunction with attached drawing.
Installation practice
Referring to fig. 2, which is the structural schematic diagram of the simulation testing device for the vehicle that the application Installation practice provides.
The simulation testing device of vehicle provided by the embodiments of the present application, comprising:
Extraction unit 201, for extracting target detection environmental information from target video；Wherein, the target video is
It is obtained by unmanned plane by photographic subjects road vehicle driving status and running environment；The target detection environment letter
Breath includes at least one of road neighboring buildings information, road information, vehicle traveling information and pedestrian's driving information；
Simulation unit 202, for according to the target detection environmental information and information of vehicles to be tested, using emulator into
Row emulation, respectively obtains virtual testing environment and virtual test vehicle, described virtual so that the virtual test vehicle to be put into
It is tested for the property in test environment.
As an implementation, described to mention in order to further increase the accuracy of vehicle testing process and comprehensive
Unit 201 is taken, is specifically included:
Subelement is identified, for identifying target entity from target video using deep learning algorithm；Wherein, target entity
Including at least one of building, road, vehicle and pedestrian；
Subelement is obtained, for obtaining target detection environmental information using preset algorithm according to the target entity.
As an implementation, described to obtain in order to further increase the accuracy of vehicle testing process and comprehensive
Subelement is taken, is specifically included:
Information of vehicles obtains module, and for including vehicle when the target entity, and the vehicle traveling information includes vehicle
Driving trace and vehicle driving direction when, according to the vehicle, the traveling rail of the vehicle is obtained using track algorithm
Mark, and utilize the driving direction that the vehicle is obtained towards recognizer.
As an implementation, described to obtain in order to further increase the accuracy of vehicle testing process and comprehensive
Subelement is taken, is specifically included:
Pedestrian information obtains module, and for including pedestrian when the target entity, and pedestrian's driving information includes row
When the driving trace of people, according to the pedestrian, the driving trace of the pedestrian is obtained using track algorithm.
As an implementation, described to obtain in order to further increase the accuracy of vehicle testing process and comprehensive
Subelement is taken, is specifically included:
Road information obtains module, for according to the road, being known using vision when the target entity includes road
Other algorithm obtains the road information.
The above are the specific embodiments of the simulation testing device of the vehicle of the application Installation practice offer, in the implementation
In mode, by utilizing emulator according to the target detection environmental information and information of vehicles to be tested extracted from target video
It is emulated, respectively obtains virtual testing environment and virtual test vehicle, so that the virtual test vehicle is put into the void
It is tested for the property in quasi- test environment.Since vehicle testing process is by utilizing virtual test vehicle in virtual testing environment
Test realization is carried out, without the participation of true vehicle to be tested, thus testing cost is reduced, also improves vehicle testing
The safety of process.In addition, due to target video be by unmanned plane by photographic subjects road vehicle driving status and
What running environment obtained, thus, which accurately can comprehensively reflect the real driving environment of vehicle to be tested, so that
The target detection environmental information extracted from target video also accurately can comprehensively reflect the real driving ring of vehicle to be tested
Border, but also according to target detection environmental information carry out emulation acquisition virtual testing environment also accurately can comprehensively reflect to
The real driving environment of vehicle is tested, to improve the accuracy of virtual testing environment and comprehensive, and then improves vehicle
The credibility of test process.
Any embodiment and device of the emulation test method of vehicle based on above method embodiment offer are real
Any embodiment of the simulation testing device of the vehicle of example offer is applied, the embodiment of the present application also provides a kind of the imitative of vehicle
True test macro, is explained and illustrated below in conjunction with attached drawing.
System embodiment
Referring to Fig. 3, which is the structural schematic diagram of the emulation test system for the vehicle that the application system embodiment provides.
The emulation test system of vehicle provided by the embodiments of the present application, comprising: the simulation testing device 301 of vehicle and nobody
Machine 302.
Wherein, unmanned plane 302 is used for the video of photographic subjects road vehicle driving status and running environment, and will
Its video shot is sent to the simulation testing device 301 of vehicle.
The simulation testing device 301 of vehicle can be used for executing any of the emulation test method provided in embodiment of the method
Kind embodiment, moreover, the simulation testing device 301 of vehicle can be using the emulation testing dress for the vehicle that Installation practice provides
Any embodiment set.
The above are the specific embodiments of the emulation test system of the vehicle of system embodiment offer, preferably
In, by being carried out using emulator according to the target detection environmental information and information of vehicles to be tested extracted from target video
Emulation, respectively obtains virtual testing environment and virtual test vehicle, so that the virtual test vehicle is put into the virtual survey
Test ring is tested for the property in border.Since vehicle testing process is by being carried out using virtual test vehicle in virtual testing environment
What test was realized, without the participation of true vehicle to be tested, thus testing cost is reduced, also improves vehicle testing process
Safety.In addition, since target video is to pass through photographic subjects road vehicle driving status and traveling by unmanned plane
What environment obtained, thus, which accurately can comprehensively reflect the real driving environment of vehicle to be tested, so that from mesh
The target detection environmental information extracted in mark video also accurately can comprehensively reflect the real driving environment of vehicle to be tested,
So that also accurately can comprehensively be reflected according to the virtual testing environment that target detection environmental information carries out emulation acquisition to be tested
The real driving environment of vehicle to improve the accuracy of virtual testing environment and comprehensive, and then improves vehicle survey
The credibility of examination process.
It should be appreciated that in this application, " at least one (item) " refers to one or more, and " multiple " refer to two or two
More than a."and/or" indicates may exist three kinds of relationships, for example, " A and/or B " for describing the incidence relation of affiliated partner
It can indicate: only exist A, only exist B and exist simultaneously tri- kinds of situations of A and B, wherein A, B can be odd number or plural number.Word
Symbol "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or"." at least one of following (a) " or its similar expression, refers to
Any combination in these, any combination including individual event (a) or complex item (a).At least one of for example, in a, b or c
(a) can indicate: a, b, c, " a and b ", " a and c ", " b and c ", or " a and b and c ", and wherein a, b, c can be individually, can also
To be multiple.
The above described is only a preferred embodiment of the present invention, being not intended to limit the present invention in any form.Though
So the present invention has been disclosed as a preferred embodiment, and however, it is not intended to limit the invention.It is any to be familiar with those skilled in the art
Member, without departing from the scope of the technical proposal of the invention, all using the methods and technical content of the disclosure above to the present invention
Technical solution makes many possible changes and modifications or equivalent example modified to equivalent change.Therefore, it is all without departing from
The content of technical solution of the present invention, according to the technical essence of the invention any simple modification made to the above embodiment, equivalent
Variation and modification, all of which are still within the scope of protection of the technical scheme of the invention.
Claims (11)
1. a kind of emulation test method of vehicle characterized by comprising
Target detection environmental information is extracted from target video；Wherein, the target video is to pass through photographic subjects by unmanned plane
What road vehicle driving status and running environment obtained；The target detection environmental information includes road neighboring buildings letter
At least one of breath, road information, vehicle traveling information and pedestrian's driving information；
It according to the target detection environmental information and information of vehicles to be tested, is emulated, is respectively obtained virtual using emulator
Environment and virtual test vehicle are tested, so that the virtual test vehicle is put into progress performance survey in the virtual testing environment
Examination.
2. the method according to claim 1, wherein described extract target detection environment letter from target video
Breath, specifically includes:
Target entity is identified from target video using deep learning algorithm；Wherein, target entity includes building, road, vehicle
At least one of with pedestrian；
According to the target entity, target detection environmental information is obtained using preset algorithm.
3. according to the method described in claim 2, it is characterized in that, when the target entity includes vehicle, and the vehicle row
It is described according to the target entity when sailing the driving direction of driving trace and vehicle that information includes vehicle, utilize preset algorithm
Target detection environmental information is obtained, is specifically included:
According to the vehicle, the driving trace of the vehicle is obtained using the first track algorithm, and is utilized and obtained towards recognizer
Take the driving direction of the vehicle.
4. according to the method described in claim 2, it is characterized in that, when the target entity includes pedestrian, and pedestrian's row
It is described according to the target entity when to sail information include the driving trace of pedestrian, utilize preset algorithm to obtain target detection environment
Information specifically includes:
According to the pedestrian, the driving trace of the pedestrian is obtained using the second track algorithm.
5. described according to institute according to the method described in claim 2, it is characterized in that, when the target entity includes road
Target entity is stated, target detection environmental information is obtained using preset algorithm, specifically includes:
According to the road, the road information is obtained using visual identification algorithm.
6. a kind of simulation testing device of vehicle characterized by comprising
Extraction unit, for extracting target detection environmental information from target video；Wherein, the target video is by unmanned plane
It is obtained by photographic subjects road vehicle driving status and running environment；The target detection environmental information includes
At least one of road neighboring buildings information, road information, vehicle traveling information and pedestrian's driving information；
Simulation unit, for being emulated using emulator according to the target detection environmental information and information of vehicles to be tested,
Virtual testing environment and virtual test vehicle are respectively obtained, so that the virtual test vehicle is put into the virtual testing environment
In be tested for the property.
7. device according to claim 6, which is characterized in that the extraction unit specifically includes:
Subelement is identified, for identifying target entity from target video using deep learning algorithm；Wherein, target entity includes
At least one of building, road, vehicle and pedestrian；
Subelement is obtained, for obtaining target detection environmental information using preset algorithm according to the target entity.
8. device according to claim 7, which is characterized in that the acquisition subelement specifically includes:
Information of vehicles obtains module, and for including vehicle when the target entity, and the vehicle traveling information includes vehicle
When the driving direction of driving trace and vehicle, according to the vehicle, the traveling rail of the vehicle is obtained using the first track algorithm
Mark, and utilize the driving direction that the vehicle is obtained towards recognizer.
9. device according to claim 7, which is characterized in that the acquisition subelement specifically includes:
Pedestrian information obtains module, and for including pedestrian when the target entity, and pedestrian's driving information includes pedestrian's
When driving trace, according to the pedestrian, the driving trace of the pedestrian is obtained using the second track algorithm.
10. device according to claim 7, which is characterized in that the acquisition subelement specifically includes:
Road information obtains module, for according to the road, being calculated using visual identity when the target entity includes road
Method obtains the road information.
11. a kind of emulation test system of vehicle characterized by comprising any one vehicle described in claim 6 to 10
Simulation testing device and unmanned plane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910289957.5A CN110059393A (en) | 2019-04-11 | 2019-04-11 | A kind of emulation test method of vehicle, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910289957.5A CN110059393A (en) | 2019-04-11 | 2019-04-11 | A kind of emulation test method of vehicle, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059393A true CN110059393A (en) | 2019-07-26 |
Family
ID=67317695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910289957.5A Pending CN110059393A (en) | 2019-04-11 | 2019-04-11 | A kind of emulation test method of vehicle, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059393A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112859810A (en) * | 2021-01-13 | 2021-05-28 | 自行科技(武汉)有限公司 | ADAS algorithm verification method and device based on Carla platform |
| CN114067062A (en) * | 2022-01-17 | 2022-02-18 | 深圳慧拓无限科技有限公司 | Method and system for simulating real driving scene, electronic equipment and storage medium |
| WO2022246852A1 (en) * | 2021-05-28 | 2022-12-01 | 吉林大学 | Automatic driving system testing method based on aerial survey data, testing system, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685516A (en) * | 2011-03-07 | 2012-09-19 | 李慧盈 | Active safety type assistant driving method based on stereoscopic vision |
| US20180211117A1 (en) * | 2016-12-20 | 2018-07-26 | Jayant Ratti | On-demand artificial intelligence and roadway stewardship system |
| CN108627350A (en) * | 2018-03-27 | 2018-10-09 | 北京新能源汽车股份有限公司 | Vehicle testing system and method |
| CN108647638A (en) * | 2018-05-09 | 2018-10-12 | 东软集团股份有限公司 | A kind of vehicle location detection method and device |
| CN109196076A (en) * | 2016-02-29 | 2019-01-11 | 智能材料解决方案公司 | A kind of collaborative navigation System and method for |
| CN109187048A (en) * | 2018-09-14 | 2019-01-11 | 盯盯拍（深圳）云技术有限公司 | Automatic Pilot performance test methods and automatic Pilot performance testing device |
| CN109271924A (en) * | 2018-09-14 | 2019-01-25 | 盯盯拍（深圳）云技术有限公司 | Image processing method and image processing apparatus |
| CN109326124A (en) * | 2018-10-17 | 2019-02-12 | 江西洪都航空工业集团有限责任公司 | A kind of urban environment based on machine vision parks cars Activity recognition system |
-
2019
- 2019-04-11 CN CN201910289957.5A patent/CN110059393A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102685516A (en) * | 2011-03-07 | 2012-09-19 | 李慧盈 | Active safety type assistant driving method based on stereoscopic vision |
| CN109196076A (en) * | 2016-02-29 | 2019-01-11 | 智能材料解决方案公司 | A kind of collaborative navigation System and method for |
| US20180211117A1 (en) * | 2016-12-20 | 2018-07-26 | Jayant Ratti | On-demand artificial intelligence and roadway stewardship system |
| CN108627350A (en) * | 2018-03-27 | 2018-10-09 | 北京新能源汽车股份有限公司 | Vehicle testing system and method |
| CN108647638A (en) * | 2018-05-09 | 2018-10-12 | 东软集团股份有限公司 | A kind of vehicle location detection method and device |
| CN109187048A (en) * | 2018-09-14 | 2019-01-11 | 盯盯拍（深圳）云技术有限公司 | Automatic Pilot performance test methods and automatic Pilot performance testing device |
| CN109271924A (en) * | 2018-09-14 | 2019-01-25 | 盯盯拍（深圳）云技术有限公司 | Image processing method and image processing apparatus |
| CN109326124A (en) * | 2018-10-17 | 2019-02-12 | 江西洪都航空工业集团有限责任公司 | A kind of urban environment based on machine vision parks cars Activity recognition system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112859810A (en) * | 2021-01-13 | 2021-05-28 | 自行科技(武汉)有限公司 | ADAS algorithm verification method and device based on Carla platform |
| WO2022246852A1 (en) * | 2021-05-28 | 2022-12-01 | 吉林大学 | Automatic driving system testing method based on aerial survey data, testing system, and storage medium |
| CN114067062A (en) * | 2022-01-17 | 2022-02-18 | 深圳慧拓无限科技有限公司 | Method and system for simulating real driving scene, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109194436B (en) | Sensor timestamp synchronous testing method, device, equipment, medium and vehicle | |
| CN107153363B (en) | Simulation test method, device, equipment and readable medium for unmanned vehicle | |
| CN112668153B (en) | Method, device and equipment for generating automatic driving simulation scene | |
| Hauer et al. | Did we test all scenarios for automated and autonomous driving systems? | |
| CN110059393A (en) | A kind of emulation test method of vehicle, apparatus and system | |
| CN104460349B (en) | Real automobile in-the-loop simulation testing method, real-time simulation machine and system | |
| CN106644503B (en) | A kind of intelligent vehicle planning aptitude tests platform | |
| CN106157688B (en) | Parking space detection method and system based on deep learning and big data | |
| CN104751110A (en) | Bio-assay detection method and device | |
| CN110764494A (en) | Human-computer hybrid driving automatic driving virtual test platform based on SCANeR | |
| CN109684803A (en) | Man-machine verification method based on gesture sliding | |
| CN109711285A (en) | Training, test method and the device of identification model | |
| CN103760774A (en) | Simulation assessment system for reasonability of traffic sign design and set position | |
| CN108268831A (en) | The robustness test method and system of a kind of unmanned vehicle vision-based detection | |
| CN110208001A (en) | A kind of road test method and apparatus of vehicle | |
| CN109029372A (en) | A kind of detection vehicle localization method and device | |
| CN109664921A (en) | The more vehicle tracking security verification methods of VBTC and system based on trackside emulator | |
| CN106355329A (en) | Method and system for testing sign aligning ability of driver | |
| CN114266805A (en) | Twin region suggestion network model for unmanned aerial vehicle target tracking | |
| CN109740598A (en) | Object localization method and device under structuring scene | |
| US11656328B2 (en) | Validating object detection hardware and algorithms | |
| CN114488851B (en) | Automatic driving test method, device and system based on digital twin technology | |
| CN110377982A (en) | The test method and system of automatic Pilot performance, electronic equipment, storage medium | |
| Hu et al. | Testing and evaluation of autonomous vehicles based on safety of the intended functionality | |
| CN116311433A (en) | Middle-distance running test method, device, equipment and medium based on vision technology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |