CN106228602A - Determination method, device and the mobile unit of three-dimensional vehicle alternative area - Google Patents
Determination method, device and the mobile unit of three-dimensional vehicle alternative area Download PDFInfo
- Publication number
- CN106228602A CN106228602A CN201610581697.5A CN201610581697A CN106228602A CN 106228602 A CN106228602 A CN 106228602A CN 201610581697 A CN201610581697 A CN 201610581697A CN 106228602 A CN106228602 A CN 106228602A
- Authority
- CN
- China
- Prior art keywords
- region
- cloud
- vehicle
- solid
- dimensional
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides determination method, device and the mobile unit of a kind of three-dimensional vehicle alternative area.The method includes: obtains multiple somes clouds in road scene, utilizes the plurality of some cloud to determine the ground level in described road scene；According to preset vehicle dimension, described ground level generates multiple 3D region；The first solid comprising the plurality of some cloud is divided into the set of the second solid of specified quantity, determines one or more described second solid that each 3D region comprises；One or more described second solid comprised according to each 3D region described, determines whether this 3D region is three-dimensional vehicle alternative area.The embodiment of the present invention utilizes vehicle to be positioned at the priori near ground level, utilizes the template of known vehicle size simultaneously, the number of to be searched 3D region is greatly reduced, improves search efficiency, meets the requirement of real-time in reality application.
Description
Technical field
The present invention relates to intelligent vehicle technical field of environmental perception, the determination side of a kind of three-dimensional vehicle alternative area
Method, device and mobile unit.
Background technology
Point cloud is the massive point set of target surface characteristic, is sensed by vehicle-mounted laser radar or binocular camera etc.
Device, it is possible to get the point off density cloud information of road scene.Point cloud can be considered as the set of a series of three-dimensional coordinate.By a cloud
The three-dimensional alternative area of data genaration vehicle, it is simple to the vehicle that subsequent algorithm identifies quickly and accurately and positions in scene.This skill
Art is one of nucleus modules of application such as front truck anti-collision warning, adaptive cruise.
In correlation technique, generated the three-dimensional alternative area of vehicle by cloud data, need in three dimensional point cloud time
Going through all possible vehicle alternative area, search complexity is exponential, it is impossible to meet the real-time to algorithm in reality application
Requirement, it would be highly desirable to solve this technical problem.
Summary of the invention
In view of the above problems, it is proposed that the present invention in case provide one overcome the problems referred to above or at least in part solve on
State the determination method of the three-dimensional vehicle alternative area of problem, device and corresponding mobile unit.
According to an aspect of of the present present invention, it is provided that a kind of determination method of three-dimensional vehicle alternative area, including:
Obtain multiple somes clouds in road scene, utilize the plurality of some cloud to determine the ground level in described road scene；
According to preset vehicle dimension, described ground level generates multiple 3D region；
The first solid comprising the plurality of some cloud is divided into the set of the second solid of specified quantity, determines each
One or more described second solid that individual 3D region comprises；
Whether one or more described second solid comprised according to each 3D region described, determine this 3D region
For three-dimensional vehicle alternative area.
Alternatively, multiple somes clouds in described acquisition road scene, including:
Multiple somes clouds in road scene are gathered according to laser measurement principle；And/or
Multiple somes clouds in road scene are obtained according to photogrammetry principles.
Alternatively, the plurality of some cloud is utilized to determine the ground level in described road scene, including:
By stochastic sampling concordance RANSAC algorithm, determine in the plurality of some cloud and belong to the ground in described road scene
The point cloud of plane.
Alternatively, according to preset vehicle dimension, described ground level generates multiple 3D region, including:
According to preset vehicle dimension, at the described multiple 3D region of ground level stochastic generation, wherein, described 3D region
By specifying parameter determination.
Alternatively, described appointment parameter includes at least one following:
The three-dimensional coordinate of vehicle center, vehicle dimension, vehicle on described ground level towards angle.
Alternatively, the first solid comprising the plurality of some cloud is divided into the collection of the second solid of specified quantity
Close, including:
By comprising the cuboid of the plurality of some cloud according to fixed interval discretization, it is divided into the cubical of specified quantity
Set.
Alternatively, one or more described second solid comprised according to each 3D region described, determine this three-dimensional
Whether region is three-dimensional vehicle alternative area, including:
One or more described second solid comprised according to each 3D region described, utilizes three-dimensional integral figure to calculate
Point cloud quantity that each 3D region described comprises and/or some cloud average height；
The point cloud quantity comprised according to each 3D region described and/or some cloud average height, determine that this 3D region is
No for three-dimensional vehicle alternative area.
Alternatively, the some cloud quantity comprised according to each 3D region described and/or some cloud average height, determine this three-dimensional
Whether region is three-dimensional vehicle alternative area, including:
The point cloud quantity each 3D region described comprised according to the weight specified and some cloud average height summation weighting,
Obtain the comprehensive grading value of each 3D region described；
Comprehensive grading value according to each 3D region described, determines whether this 3D region is three-dimensional vehicle candidate area
Territory.
Alternatively, according to the comprehensive grading value of each 3D region described, determine whether this 3D region is three-dimensional vehicle
Alternative area, including:
The comprehensive grading value of each 3D region described is ranked up from big to small；
Choose the 3D region of the forward specified quantity of sequence as three-dimensional vehicle alternative area.
Alternatively, described method also includes:
During driving, according to the described three-dimensional vehicle alternative area determined, identify driving relevant information；
The driving relevant information identified is analyzed generating corresponding traffic navigation information, and is supplied to use
Family.
Alternatively, described driving relevant information includes at least one following:
Front truck and/or rear car and the distance of this car, driving road-condition identification information, road environment information.
Alternatively, described method is applied in vehicle-mounted intelligent control unit.
According to another aspect of the present invention, additionally provide the determination device of a kind of three-dimensional vehicle alternative area, including:
Point cloud acquisition module, is suitable to obtain multiple somes clouds in road scene；
Ground level determines module, is suitable to utilize the plurality of some cloud to determine the ground level in described road scene；
3D region generation module, is suitable to, according to preset vehicle dimension, generate multiple space on described ground level
Territory；
Solid determines module, is suitable to the first solid comprising the plurality of some cloud is divided into the second of specified quantity
The set of solid, determines one or more described second solid that each 3D region comprises；
Alternative area determines module, is suitable to one or more described second geometry comprised according to each 3D region described
Body, determines whether this 3D region is three-dimensional vehicle alternative area.
Alternatively, described some cloud acquisition module is further adapted for:
Multiple somes clouds in road scene are gathered according to laser measurement principle；And/or
Multiple somes clouds in road scene are obtained according to photogrammetry principles.
Alternatively, described ground level determines that module is further adapted for:
By stochastic sampling concordance RANSAC algorithm, determine in the plurality of some cloud and belong to the ground in described road scene
The point cloud of plane.
Alternatively, described 3D region generation module is further adapted for:
According to preset vehicle dimension, at the described multiple 3D region of ground level stochastic generation, wherein, described 3D region
By specifying parameter determination.
Alternatively, described appointment parameter includes at least one following:
The three-dimensional coordinate of vehicle center, vehicle dimension, vehicle on described ground level towards angle.
Alternatively, described solid determines that module is further adapted for:
By comprising the cuboid of the plurality of some cloud according to fixed interval discretization, it is divided into the cubical of specified quantity
Set.
Alternatively, described alternative area determines that module includes:
Computing unit, is suitable to one or more described second solid comprised according to each 3D region described, utilizes
Three-dimensional integral figure calculates some cloud quantity and/or the some cloud average height that each 3D region described comprises；
Determine unit, be suitable to some cloud quantity and/or the some cloud average height comprised according to each 3D region described, determine
Whether this 3D region is three-dimensional vehicle alternative area.
Alternatively, described determine that unit is further adapted for:
The point cloud quantity each 3D region described comprised according to the weight specified and some cloud average height summation weighting,
Obtain the comprehensive grading value of each 3D region described；
Comprehensive grading value according to each 3D region described, determines whether this 3D region is three-dimensional vehicle candidate area
Territory.
Alternatively, described determine that unit is further adapted for:
The comprehensive grading value of each 3D region described is ranked up from big to small；
Choose the 3D region of the forward specified quantity of sequence as three-dimensional vehicle alternative area.
Alternatively, described device also includes:
Traffic navigation information generation module, is suitable to during driving, according to the described three-dimensional vehicle determined
Alternative area, identifies driving relevant information；It is analyzed generating corresponding traffic navigation to the driving relevant information identified
Information, and it is supplied to user.
Alternatively, described driving relevant information includes at least one following:
Front truck and/or rear car and the distance of this car, driving road-condition identification information, road environment information.
Alternatively, described device is applied in vehicle-mounted intelligent control unit.
According to another aspect of the present invention, additionally provide a kind of mobile unit, including any of the above-described described three-dimensional car
The determination device of alternative area.
The technical scheme that the embodiment of the present invention provides, first obtains multiple somes clouds in road scene, utilizes multiple somes clouds
Determine the ground level in road scene.Subsequently, according to preset vehicle dimension, ground level generates multiple 3D region, enters
And the first solid comprising multiple somes clouds is divided into the set of the second solid of specified quantity, determine each 3D region
One or more second solids comprised.Afterwards, one or more second solids comprised according to each 3D region, really
Whether this 3D region fixed is three-dimensional vehicle alternative area.As can be seen here, to utilize vehicle to be positioned at ground level attached for the embodiment of the present invention
Near priori, utilizes the template of known vehicle size simultaneously, and the number of to be searched 3D region is greatly reduced, and improves
Search efficiency, meets the requirement of real-time in reality application.Further, comprise in road scene due to each second solid
At least one some cloud, one or more second solids that the embodiment of the present invention comprises based on each 3D region, determine this three
Whether dimension region is three-dimensional vehicle alternative area, it is ensured that the recall rate of 3D region.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of description, and in order to allow above and other objects of the present invention, the feature and advantage can
Become apparent, below especially exemplified by the detailed description of the invention of the present invention.
According to below in conjunction with the accompanying drawing detailed description to the specific embodiment of the invention, those skilled in the art will be brighter
Above-mentioned and other purposes, advantage and the feature of the present invention.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical parts.In the accompanying drawings:
Fig. 1 shows the flow chart of the determination method of three-dimensional vehicle alternative area according to an embodiment of the invention；
Fig. 2 shows the flow chart of the determination method of three-dimensional vehicle alternative area according to another embodiment of the present invention；
Fig. 3 shows the structural representation of the determination device of three-dimensional vehicle alternative area according to an embodiment of the invention
Figure；And
Fig. 4 shows the structural representation of the determination device of three-dimensional vehicle alternative area in accordance with another embodiment of the present invention
Figure.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows the disclosure
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should be by embodiments set forth here
Limited.On the contrary, it is provided that these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
For solving above-mentioned technical problem, embodiments provide a kind of determination method of three-dimensional vehicle alternative area.
Fig. 1 shows the flow chart of the determination method of three-dimensional vehicle alternative area according to an embodiment of the invention.As it is shown in figure 1, should
Method at least may comprise steps of S102 to step S108.
Step S102, obtains multiple somes clouds in road scene, utilizes the ground level that multiple somes clouds determine in road scene.
Step S104, according to preset vehicle dimension, generates multiple 3D region on ground level.
Step S106, is divided into the set of the second solid of specified quantity by the first solid comprising multiple somes clouds,
Determine one or more second solids that each 3D region comprises.
Step S108, one or more second solids comprised according to each 3D region, determine that this 3D region is
No for three-dimensional vehicle alternative area.
The embodiment of the present invention achieves the method for the three-dimensional alternative area determining vehicle based on a cloud, first obtains road field
Multiple somes clouds in scape, utilize the ground level that multiple somes clouds determine in road scene.Subsequently, according to preset vehicle dimension,
Generate multiple 3D region on ground level, and then the first solid comprising multiple somes clouds is divided into more than the second of specified quantity
The set of what body, determines one or more second solids that each 3D region comprises.Afterwards, according to each 3D region bag
One or more second solids contained, determine whether this 3D region is three-dimensional vehicle alternative area.As can be seen here, the present invention
Embodiment utilizes vehicle to be positioned at the priori near ground level, utilizes the template of known vehicle size simultaneously, is greatly reduced
The number of 3D region to be searched, improves search efficiency, meets the requirement of real-time in reality application.Further, due to respectively
Individual second solid comprise in road scene at least one some cloud, the embodiment of the present invention comprise based on each 3D region one
Individual or multiple second solids, determine whether this 3D region is three-dimensional vehicle alternative area, it is ensured that recalling of 3D region
Rate.
Above step S102 obtains multiple somes clouds in road scene, embodiments provides the side of plurality of optional
Case, such as, gathers multiple somes clouds in road scene according to laser measurement principle, can collect the three-dimensional coordinate of a cloud
And laser-bounce intensity (Intensity) (XYZ)；Or obtain multiple somes clouds in road scene according to photogrammetry principles,
Three-dimensional coordinate (XYZ) and the colouring information (RGB) of a cloud can be collected；Or, it is also possible to combine laser measurement and photography is surveyed
Amount principle obtains a cloud, it is possible to obtain the some three-dimensional coordinate (XYZ) of cloud, laser-bounce intensity (Intensity) and colouring information
(RGB)。
First, as a example by laser measurement principle, three-dimensional laser radar collection point cloud can be used.Three-dimensional laser radar is intelligence
One of important sensor of external information can be obtained by vehicle, there is reliability and real-time, accuracy advantages of higher, therefore by
It is widely used in intelligent vehicle environment sensing research.Radar has multiple laser sensor, each sensor measurement dispersion number
Strong point is represented by Pi, and (x, y, z, s), x, y, z represent three dimensional physical distance respectively, and unit is rice, and s represents reflex strength, for nothing
Dimension value.Cloud data be then large-scale discrete measurement point data set P1, P2, P3 ..., PN}, they for reduction
The basic configuration feature of type measurement object and CONSTRUCTED SPECIFICATION provide the information of abundance.
Secondly, as a example by photogrammetry principles, binocular camera collection point cloud can be used.Two cameras are positioned over same
Target object is shot by plane, obtains the subject image pair that many groups are corresponding, owing to camera and object are to meet triangle to survey
Amount principle, uses the parallax of corresponding point to calculate the steric information of object simultaneously, thus obtains the three dimensional point cloud of object.
In the alternative embodiment of the present invention, above step S102 utilizes the Horizon that multiple somes clouds determine in road scene
Face, can pass through RANSAC (RANdom Sample Consensus, stochastic sampling concordance) algorithm, determine in multiple somes clouds
Belong to the some cloud of ground level in road scene.
RANSAC can estimate mathematical model by iterative manner from one group of observation data set comprising " point not in the know "
Parameter.It is a kind of uncertain algorithm, and it has certain probability to draw a rational result.The basic assumption of RANSAC
It is:
(1) data are made up of, such as " intra-office point ": the distribution of data can be explained by some model parameters；
(2) " point not in the know " is the data not adapting to this model；
(3) data in addition belong to noise.
Not in the know some Producing reason has: the extreme value of noise, the measuring method of mistake, the false supposition to data.RANSAC
Have also been made it is assumed hereinafter that: given one group of (the least) intra-office point, there is a process that can estimate model parameter, and be somebody's turn to do
Model can explain or be applicable to intra-office point.
The input of RANSAC algorithm is one group of observation data, a parametrization that can explain or be adapted to observe data
Model, some believable parameters.RANSAC reaches target by the one group of random subset being chosen in data.It is selected
Subset is assumed to be intra-office point, and verifies by following method:
1) having a model to be adapted to the intra-office point assumed, the most all of unknown parameter can calculate from the intra-office point assumed
Draw；
2) with 1) in the model that obtains go to test other data all of, if certain point is applicable to the model estimated, recognize
It also it is intra-office point for it；
3) if there being abundant point to be classified as the intra-office point assumed, then the model of estimation is sufficient for rationally；
4) then, go to reappraise model with the intra-office point of all hypothesis, because it is only by initial hypothesis intra-office point
Estimated；
5) last, by estimating that intra-office point carrys out assessment models with the error rate of model.
This process is repeatedly executed fixing number of times, the model that every time produces or because intra-office point is given up very little
Abandon, otherwise because more preferable and selected than existing model.
In embodiments of the present invention, the cloud data of input has the substantial amounts of some cloud genera in ground level, calculated by RANSAC
Method can the most robustly estimate ground level.Ground level π=(a, b, c, d)TRepresented by the parametrization of four dimensional vectors, its ginseng
Examining coordinate system is the observation coordinate system centered by sensor.
According to preset vehicle dimension in above step S104, generating multiple 3D region on ground level, the present invention is real
Execute example and provide a kind of optional scheme, in this scenario, can be many at ground level stochastic generation according to preset vehicle dimension
Individual 3D region, wherein, 3D region is by specifying parameter determination.Here appointment parameter can be the three-dimensional seat of vehicle center
Mark, vehicle dimension, vehicle on ground level towards angle, etc., the invention is not restricted to this.
Specifically, under the scene of natural track, it is assumed that vehicle is respectively positioned near road surface (that is, ground level) and (does not consider to hang
The extreme cases such as vehicle), then according to the size template (length) of known vehicle input vehicle, do slight near road surface
Disturbance, simultaneously traversal car modal possible towards angle, i.e. can obtain M possible 3D region, these 3D regions
Can be determined by 7 parameters (x, y, z, l, w, h, θ), wherein (x, y z) represent the three-dimensional coordinate of vehicle center；(l,w,
H) it is the length template of vehicle；θ represent vehicle in the horizontal plane towards angle.
In the alternative embodiment of the present invention, the first solid comprising multiple somes clouds is divided into by above step S106
The set of the second solid of specified quantity, the invention provides a kind of optional scheme, i.e. will comprise the rectangular of multiple somes clouds
Body, according to fixed interval discretization, is divided into the cubical set of specified quantity.Specifically, all input three-dimensional point will be comprised
The cuboid of cloud, according to fixed interval discretization, is divided into the set of several small cubes, then for the M individual three obtained above
Dimension region, each 3D region will correspond to the set of several small cubes in this region.Here, it is intended that quantity can basis
Actual demand is configured, and such as, if desired divides less cube and then arranges bigger specified quantity.
After determining one or more second solids that each 3D region comprises in step s 106, due to each second
Solid comprise in road scene at least one some cloud, thus, step S108 can comprise according to each 3D region one
Individual or multiple second solids determine the feature of each 3D region, and then can come really according to the feature of each 3D region
Whether this 3D region fixed is three-dimensional vehicle alternative area.The feature of 3D region here can be that 3D region is interior to be comprised
Some cloud quantity, some cloud average height, some cloud number ratio up and down etc., the invention is not restricted to this.The present invention's
In alternative embodiment, it is possible to use three-dimensional integral figure calculates the feature of each 3D region, computation complexity is O (1), saves
Amount of calculation, can quickly calculate the feature of a large amount of 3D region.
Further, according to the some cloud quantity comprised in 3D region, step S108 can determine that this 3D region is
No for three-dimensional vehicle alternative area；Or determine that this 3D region is according to the some cloud average height comprised in 3D region
No for three-dimensional vehicle alternative area；Or determine this in conjunction with the some cloud quantity comprised in 3D region and some cloud average height
Whether 3D region is three-dimensional vehicle alternative area.Here it is possible to the point each 3D region comprised according to the weight specified
Cloud quantity and some cloud average height summation weighting, obtain the comprehensive grading value of each 3D region, subsequently according to each space
The comprehensive grading value in territory, determines whether this 3D region is three-dimensional vehicle alternative area.
In the alternative embodiment of the present invention, the comprehensive grading value of each 3D region can be arranged from big to small
Sequence, chooses the 3D region of the forward specified quantity of sequence as three-dimensional vehicle alternative area.
The reality of the determination method of the three-dimensional vehicle alternative area of the present invention is discussed in detail below by a specific embodiment
Existing process.In this embodiment, the sensors such as vehicle-mounted laser radar or binocular camera are first passed through, it is possible to get road
The point off density cloud information of scene.Point cloud can be considered as the set of a series of three-dimensional coordinate.As in figure 2 it is shown, the method is the most permissible
Comprise the following steps S202 to step S208.
Step S202, RANSAC algorithm finds ground level.
In this step, the cloud data of input there is substantial amounts of point belong to ground level, can be relatively by RANSAC algorithm
For robustly estimating ground level.Ground level π=(a, b, c, d)TRepresented by the parametrization of four dimensional vectors, its reference frame
For the observation coordinate system centered by sensor.
Step S204, according to car modal stochastic generation 3D region near ground level.
Under the scene of natural track, it is assumed that vehicle is respectively positioned near road surface (that is, ground level) and (does not consider to hang the poles such as vehicle
End situation), then according to the size template (length) of known vehicle input vehicle, near road surface, do slight perturbations, with
Time traversal car modal possible towards angle, i.e. can obtain M possible 3D region, these 3D regions can pass through
7 parameters (x, y, z, l, w, h, θ) determine, wherein (x, y z) represent the three-dimensional coordinate of vehicle center；(l, w h) are vehicle
Length template；θ represent vehicle in the horizontal plane towards angle.
Step S206, three dimensions discretization also asks for the feature of each 3D region.
In this step, by comprising the cuboid of all input three-dimensional point clouds according to fixed interval discretization, if being divided into
The set of dry small cubes, then M the 3D region obtained for step S204, each 3D region will correspond to this region
The set of several small cubes interior.Utilize three-dimensional integral figure, the some cloud comprised in can quickly trying to achieve each 3D region
Number and some cloud average height, some cloud number and some cloud average height are as the feature of this 3D region.At other of the present invention
In embodiment, it is also possible to utilize three-dimensional integral figure to calculate other features of 3D region, such as a cloud number ratio up and down
Etc., the invention is not restricted to this.
Step S208, obtains 3D region scoring by characteristic line combination, and sequence obtains three-dimensional vehicle alternative area.
In this step, according to certain weight, the some cloud number of each 3D region and some cloud average height are asked weighting
With, M 3D region, as the scoring of this 3D region, is sorted from big to small by the result obtained according to scoring, takes top n and makees
Three-dimensional vehicle alternative area for last algorithm output.
The embodiment of the present invention utilizes vehicle to be positioned at the priori near ground level, utilizes the mould of known vehicle size simultaneously
Plate, is greatly reduced the number of 3D region to be searched, improves search efficiency, and in satisfied reality application, real-time wants
Ask.Further, due to each second solid comprise in road scene at least one some cloud, the embodiment of the present invention based on each three
One or more second solids that dimension region comprises, determine whether this 3D region is three-dimensional vehicle alternative area, it is ensured that
The recall rate of 3D region.Additionally, the embodiment of the present invention is when calculating the feature of each 3D region, utilize three-dimensional integral figure,
Computation complexity is O (1), has saved amount of calculation, can quickly calculate the feature of a large amount of 3D region.
In the alternative embodiment of the present invention, during driving, can be according to the three-dimensional vehicle candidate area determined
Territory, identifies driving relevant information, and then the driving relevant information identified is analyzed generate corresponding traffic navigation carries
Show information, and be supplied to user.Here, driving relevant information can include front truck and/or rear car and the distance of this car, roadway
Condition identification information, road environment information, etc., the invention is not restricted to this.Specifically, driving road-condition identification information, such as, driving
The driving speed limit identification information of road conditions, limit for height identification information, way-finding sign information, sign information, road construction safety post
Knowledge information, Prohibition Sign information and Warning Sign information etc..Road environment information, such as, road neighboring buildings information and road
The construction information etc. of periphery.
In the alternative embodiment of the present invention, if the distance of the front truck identified and this car less than predetermined safety traffic away from
When threshold value, generate corresponding traffic navigation information, such as warning information etc., to inform user.If the rear car identified with
When the distance of this car is less than predetermined safety traffic distance threshold, generate corresponding traffic navigation information, such as warning information
Deng, to inform user.In actual applications, can be within display screen by driving relevant information and traffic navigation information phase
Associatedly it is highlighted, and by the way of speech play, exports traffic navigation information.
Additionally, after identifying front truck and/or the rear car distance with this car, except generate traffic navigation information it
Outward, it is also possible to adjust the speed of this car in real time.Such as, if the front truck identified and the distance of this car are less than predetermined safety traffic
During distance threshold, reduce speed the most as early as possible, in order to avoid colliding with front truck.
In the alternative embodiment of the present invention, it is also possible to before carrying out statistical analysis according to the three-dimensional vehicle alternative area determined
The information such as the travel speed of car or rear car, in order to this car carries out adaptive cruise.
In the alternative embodiment of the present invention, methods mentioned above can be applied in vehicle-mounted intelligent control unit.
It should be noted that in actual applications, above-mentioned all optional embodiments can be any in the way of using combination
Combination, forms the alternative embodiment of the present invention, and this is no longer going to repeat them.
Determination method based on the three-dimensional vehicle alternative area that each embodiment above provides, based on same inventive concept,
The embodiment of the present invention additionally provides the determination device of a kind of three-dimensional vehicle alternative area.
Fig. 3 shows the structural representation of the determination device of three-dimensional vehicle alternative area according to an embodiment of the invention
Figure.As it is shown on figure 3, this device at least can include that a cloud acquisition module 310, ground level determine that module 320,3D region generate
Module 330, solid determine that module 340 and alternative area determine module 350.
Now introduce each composition of the determination device of the three-dimensional vehicle alternative area of the embodiment of the present invention or the function of device with
And the annexation between each several part:
Point cloud acquisition module 310, is suitable to obtain multiple somes clouds in road scene；
Ground level determines module 320, is coupled with a cloud acquisition module 310, is suitable to utilize the plurality of some cloud to determine institute
State the ground level in road scene；
With ground level, 3D region generation module 330, determines that module 320 is coupled, be suitable to according to preset vehicle dimension,
Described ground level generates multiple 3D region；
Solid determines module 340, is coupled with 3D region generation module 330, is suitable to comprise the plurality of some cloud
The first solid be divided into the set of the second solid of specified quantity, determine that each 3D region comprises one or more
Described second solid；
Alternative area determines module 350, determines that module 340 is coupled with solid, is suitable to according to each space described
One or more described second solid that territory comprises, determines whether this 3D region is three-dimensional vehicle alternative area.
In an embodiment of the present invention, some cloud acquisition module 310 obtains multiple somes clouds in road scene, and the present invention implements
Example provides the scheme of plurality of optional, such as, gathers multiple somes clouds in road scene according to laser measurement principle, can gather
Three-dimensional coordinate (XYZ) and laser-bounce intensity (Intensity) to a cloud；Or obtain road field according to photogrammetry principles
Multiple somes clouds in scape, can collect three-dimensional coordinate (XYZ) and the colouring information (RGB) of a cloud；Or, it is also possible to combine and swash
Photo measure and photogrammetry principles obtain a cloud, it is possible to obtain the some three-dimensional coordinate (XYZ) of cloud, laser-bounce intensity
And colouring information (RGB) (Intensity).
First, as a example by laser measurement principle, some cloud acquisition module 310 can use three-dimensional laser radar collection point cloud.
Three-dimensional laser radar is one of important sensor that intelligent vehicle obtains external information, has reliability and real-time, accurately
Property advantages of higher, is therefore widely used in intelligent vehicle environment sensing research.Radar has multiple laser sensor, each
Sensor measurement discrete data point is represented by Pi, and (x, y, z, s), x, y, z represent three dimensional physical distance respectively, and unit is rice, s
Represent reflex strength, for dimensionless number.Cloud data be then large-scale discrete measurement point data set P1, P2,
P3 ..., PN}, they are that reduced form measures the basic configuration feature of object and CONSTRUCTED SPECIFICATION provides the information of abundance.
Secondly, as a example by photogrammetry principles, some cloud acquisition module 310 can use binocular camera collection point cloud.By two
Individual camera is positioned over same plane and shoots target object, obtains the subject image pair that many groups are corresponding, due to camera with
Object meets principle of triangulation, uses the parallax of corresponding point to calculate the steric information of object simultaneously, thus obtains thing
The three dimensional point cloud of body.
In an embodiment of the present invention, ground level determines that module 320 utilizes the Horizon that multiple somes clouds determine in road scene
During face, RANSAC algorithm can be passed through, determine the some cloud of the ground level belonged in multiple somes clouds in road scene.About RANSAC
Being discussed in detail of algorithm may refer to above, and here is omitted.
In embodiments of the present invention, the cloud data of input there is the substantial amounts of some cloud genera determine mould in ground level, ground level
Block 320 can the most robustly estimate ground level by RANSAC algorithm.Ground level π=(a, b, c, d)TBy four dimensional vectors
Parametrization represent, its reference frame is the observation coordinate system centered by sensor.
In an embodiment of the present invention, 3D region generation module 330 is according to preset vehicle dimension, raw on ground level
Become multiple 3D region, embodiments provide a kind of optional scheme, in this scenario, can be according to preset vehicle
Size, at the multiple 3D region of ground level stochastic generation, wherein, 3D region is by specifying parameter determination.Here appointment ginseng
Number can be the three-dimensional coordinate of vehicle center, vehicle dimension, vehicle on ground level towards angle, etc., the present invention does not limits
In this.
Specifically, under the scene of natural track, it is assumed that vehicle is respectively positioned near road surface (that is, ground level) and (does not consider to hang
The extreme cases such as vehicle), then 3D region generation module 330 according to known vehicle input vehicle size template (length and width,
High), near road surface, do slight perturbations, simultaneously traversal car modal possible towards angle, i.e. can obtain M possible three
Dimension region, these 3D regions can be determined by 7 parameters (x, y, z, l, w, h, θ), and wherein (x, y z) represent in vehicle
The three-dimensional coordinate of the heart；(l, w h) are the length template of vehicle；θ represent vehicle in the horizontal plane towards angle.
In an embodiment of the present invention, solid determines that the first solid comprising multiple somes clouds is divided into by module 340
The set of the second solid of specified quantity, the invention provides a kind of optional scheme, i.e. will comprise the rectangular of multiple somes clouds
Body, according to fixed interval discretization, is divided into the cubical set of specified quantity.Specifically, all input three-dimensional point will be comprised
The cuboid of cloud, according to fixed interval discretization, is divided into the set of several small cubes, then for the M individual three obtained above
Dimension region, each 3D region will correspond to the set of several small cubes in this region.Here, it is intended that quantity can basis
Actual demand is configured, and such as, if desired divides less cube and then arranges bigger specified quantity.
In an embodiment of the present invention, alternative area determine that module 350 can comprise according to each 3D region one
Or multiple second solid determines the feature of each 3D region, and then can determine according to the feature of each 3D region
Whether this 3D region is three-dimensional vehicle alternative area.The feature of 3D region here can be that 3D region is interior to be comprised
Point cloud quantity, some cloud average height, some cloud number ratio up and down etc., the invention is not restricted to this.In the present invention can
Selecting in embodiment, it is possible to use three-dimensional integral figure calculates the feature of each 3D region, computation complexity is O (1), saves
Amount of calculation, can quickly calculate the feature of a large amount of 3D region.
In an embodiment of the present invention, as shown in Figure 4, above-mentioned alternative area determines that module 350 may include that
Computing unit 410, is suitable to one or more described second solid comprised according to each 3D region described, profit
Point cloud quantity and/or the some cloud average height that each 3D region described comprises is calculated with three-dimensional integral figure；
Determine unit 420, be coupled with computing unit 410, be suitable to the some cloud number comprised according to each 3D region described
Amount and/or some cloud average height, determine whether this 3D region is three-dimensional vehicle alternative area.
In an embodiment of the present invention, determine that unit 420 is further adapted for:
The point cloud quantity each 3D region described comprised according to the weight specified and some cloud average height summation weighting,
Obtain the comprehensive grading value of each 3D region described；
Comprehensive grading value according to each 3D region described, determines whether this 3D region is three-dimensional vehicle candidate area
Territory.
In an embodiment of the present invention, determine that unit 420 is further adapted for:
The comprehensive grading value of each 3D region described is ranked up from big to small；
Choose the 3D region of the forward specified quantity of sequence as three-dimensional vehicle alternative area.
In an embodiment of the present invention, as shown in Figure 4, the device that figure 3 above is shown can also include:
With alternative area, traffic navigation information generation module 360, determines that module 350 is coupled, be suitable in driving
During, according to the described three-dimensional vehicle alternative area determined, identify driving relevant information；Letter relevant to the driving identified
Breath is analyzed generating corresponding traffic navigation information, and is supplied to user.
In an embodiment of the present invention, driving relevant information can include front truck and/or rear car and the distance of this car, driving
Road conditions identification information, road environment information, etc., the invention is not restricted to this.Specifically, driving road-condition identification information, such as, OK
The driving speed limit identification information of bus or train route condition, limit for height identification information, way-finding sign information, sign information, road construction safety
Identification information, Prohibition Sign information and Warning Sign information etc..Road environment information, such as, road neighboring buildings information and road
The construction information etc. of road periphery.
In an embodiment of the present invention, if the front truck identified and the distance of this car are less than predetermined safety traffic distance threshold
During value, traffic navigation information generation module 360 generates corresponding traffic navigation information, such as warning information etc., to accuse
Know user.If the rear car identified is less than predetermined safety traffic distance threshold with the distance of this car, generate corresponding driving
Navigation hint information, such as warning information etc., to inform user.In actual applications, can be relevant by driving within display screen
Information and traffic navigation information are highlighted explicitly, and export traffic navigation prompting letter by the way of speech play
Breath.
In an embodiment of the present invention, after identifying front truck and/or the rear car distance with this car, lead except generating driving
Outside boat information, it is also possible to adjust the speed of this car in real time.Such as, if the front truck identified and the distance of this car are less than pre-
During fixed safety traffic distance threshold, reduce speed the most as early as possible, in order to avoid colliding with front truck.
In the alternative embodiment of the present invention, it is also possible to before carrying out statistical analysis according to the three-dimensional vehicle alternative area determined
The information such as the travel speed of car or rear car, in order to this car carries out adaptive cruise.
In the alternative embodiment of the present invention, device mentioned above can be applied in vehicle-mounted intelligent control unit.
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of mobile unit, described including any of the above-described
The determination device of three-dimensional vehicle alternative area.
According to any one preferred embodiment above-mentioned or the combination of multiple preferred embodiment, the embodiment of the present invention can reach
Following beneficial effect:
The technical scheme that the embodiment of the present invention provides, first obtains multiple somes clouds in road scene, utilizes multiple somes clouds
Determine the ground level in road scene.Subsequently, according to preset vehicle dimension, ground level generates multiple 3D region, enters
And the first solid comprising multiple somes clouds is divided into the set of the second solid of specified quantity, determine each 3D region
One or more second solids comprised.Afterwards, one or more second solids comprised according to each 3D region, really
Whether this 3D region fixed is three-dimensional vehicle alternative area.As can be seen here, to utilize vehicle to be positioned at ground level attached for the embodiment of the present invention
Near priori, utilizes the template of known vehicle size simultaneously, and the number of to be searched 3D region is greatly reduced, and improves
Search efficiency, meets the requirement of real-time in reality application.Further, comprise in road scene due to each second solid
At least one some cloud, one or more second solids that the embodiment of the present invention comprises based on each 3D region, determine this three
Whether dimension region is three-dimensional vehicle alternative area, it is ensured that the recall rate of 3D region.
In description mentioned herein, illustrate a large amount of detail.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of not having these details.In some instances, it is not shown specifically known method, structure
And technology, in order to do not obscure the understanding of this description.
Similarly, it will be appreciated that one or more in order to simplify that the disclosure helping understands in each inventive aspect, exist
Above in the description of the exemplary embodiment of the present invention, each feature of the present invention is grouped together into single enforcement sometimes
In example, figure or descriptions thereof.But, the method for the disclosure should not be construed to reflect an intention that i.e. required guarantor
The application claims feature more more than the feature being expressly recited in each claim protected.More precisely, as following
Claims reflected as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
The claims following detailed description of the invention are thus expressly incorporated in this detailed description of the invention, the most each claim itself
All as the independent embodiment of the present invention.
Those skilled in the art are appreciated that and can carry out the module in the equipment in embodiment adaptively
Change and they are arranged in one or more equipment different from this embodiment.Can be the module in embodiment or list
Unit or assembly are combined into a module or unit or assembly, and can put them in addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit excludes each other, can use any
Combine all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed appoint
Where method or all processes of equipment or unit are combined.Unless expressly stated otherwise, this specification (includes adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be carried out generation by providing identical, equivalent or the alternative features of similar purpose
Replace.
Although additionally, it will be appreciated by those of skill in the art that embodiments more described herein include other embodiments
Some feature included by rather than further feature, but the combination of the feature of different embodiment means to be in the present invention's
Within the scope of and form different embodiments.Such as, in detail in the claims, embodiment required for protection one of arbitrarily
Can mode use in any combination.
The all parts embodiment of the present invention can realize with hardware, or to run on one or more processor
Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that and can use in practice
Microprocessor or digital signal processor (DSP) realize the determination of three-dimensional vehicle alternative area according to embodiments of the present invention
The some or all functions of the some or all parts in device and mobile unit.The present invention is also implemented as holding
Part or all equipment of row method as described herein or device program (such as, computer program and computer
Program product).The program of such present invention of realization can store on a computer-readable medium, or can have one or
The form of the multiple signal of person.Such signal can be downloaded from internet website and obtain, or provides on carrier signal, or
Person provides with any other form.
The present invention will be described rather than limits the invention to it should be noted above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference marks that should not will be located between bracket is configured to limitations on claims.Word " comprises " and does not excludes the presence of not
Arrange element in the claims or step.Word "a" or "an" before being positioned at element does not excludes the presence of multiple such
Element.The present invention and can come real by means of including the hardware of some different elements by means of properly programmed computer
Existing.If in the unit claim listing equipment for drying, several in these devices can be by same hardware branch
Specifically embody.Word first, second and third use do not indicate that any order.These word explanations can be run after fame
Claim.
So far, although those skilled in the art will appreciate that the multiple of the most detailed present invention of illustrate and describing show
Example embodiment, but, without departing from the spirit and scope of the present invention, still can be direct according to present disclosure
Determine or derive other variations or modifications of many meeting the principle of the invention.Therefore, the scope of the present invention is it is understood that and recognize
It is set to and covers other variations or modifications all these.
The one side of the embodiment of the present invention, it is provided that A1, a kind of determination method of three-dimensional vehicle alternative area, including:
Obtain multiple somes clouds in road scene, utilize the plurality of some cloud to determine the ground level in described road scene；
According to preset vehicle dimension, described ground level generates multiple 3D region；
The first solid comprising the plurality of some cloud is divided into the set of the second solid of specified quantity, determines each
One or more described second solid that individual 3D region comprises；
Whether one or more described second solid comprised according to each 3D region described, determine this 3D region
For three-dimensional vehicle alternative area.
A2, according to the method described in A1, wherein, multiple somes clouds in described acquisition road scene, including:
Multiple somes clouds in road scene are gathered according to laser measurement principle；And/or
Multiple somes clouds in road scene are obtained according to photogrammetry principles.
A3, according to the method described in A1 or A2, wherein, utilize the plurality of some cloud to determine the Horizon in described road scene
Face, including:
By stochastic sampling concordance RANSAC algorithm, determine in the plurality of some cloud and belong to the ground in described road scene
The point cloud of plane.
A4, according to the method according to any one of A1-A3, wherein, according to preset vehicle dimension, on described ground level
Generate multiple 3D region, including:
According to preset vehicle dimension, at the described multiple 3D region of ground level stochastic generation, wherein, described 3D region
By specifying parameter determination.
A5, according to the method described in A4, wherein, described appointment parameter includes at least one following:
The three-dimensional coordinate of vehicle center, vehicle dimension, vehicle on described ground level towards angle.
A6, according to the method according to any one of A1-A5, wherein, the first solid comprising the plurality of some cloud is drawn
It is divided into the set of the second solid of specified quantity, including:
By comprising the cuboid of the plurality of some cloud according to fixed interval discretization, it is divided into the cubical of specified quantity
Set.
A7, according to the method described in A6, wherein, one or more described second comprised according to each 3D region described
Solid, determines whether this 3D region is three-dimensional vehicle alternative area, including:
One or more described second solid comprised according to each 3D region described, utilizes three-dimensional integral figure to calculate
Point cloud quantity that each 3D region described comprises and/or some cloud average height；
The point cloud quantity comprised according to each 3D region described and/or some cloud average height, determine that this 3D region is
No for three-dimensional vehicle alternative area.
A8, according to the method described in A7, wherein, the some cloud quantity that comprises according to each 3D region described and/or some cloud
Average height, determines whether this 3D region is three-dimensional vehicle alternative area, including:
The point cloud quantity each 3D region described comprised according to the weight specified and some cloud average height summation weighting,
Obtain the comprehensive grading value of each 3D region described；
Comprehensive grading value according to each 3D region described, determines whether this 3D region is three-dimensional vehicle candidate area
Territory.
A9, according to the method described in A8, wherein, according to the comprehensive grading value of each 3D region described, determine this three-dimensional
Whether region is three-dimensional vehicle alternative area, including:
The comprehensive grading value of each 3D region described is ranked up from big to small；
Choose the 3D region of the forward specified quantity of sequence as three-dimensional vehicle alternative area.
A10, according to the method according to any one of A1-A9, wherein, also include:
During driving, according to the described three-dimensional vehicle alternative area determined, identify driving relevant information；
The driving relevant information identified is analyzed generating corresponding traffic navigation information, and is supplied to use
Family.
A11, according to the method described in A10, wherein, described driving relevant information includes at least one following:
Front truck and/or rear car and the distance of this car, driving road-condition identification information, road environment information.
A12, according to the method according to any one of A1-A11, wherein, described method is applied at vehicle-mounted intelligent control single
In unit.
The another aspect of the embodiment of the present invention, additionally provides B13, the determination device of a kind of three-dimensional vehicle alternative area, bag
Include:
Point cloud acquisition module, is suitable to obtain multiple somes clouds in road scene；
Ground level determines module, is suitable to utilize the plurality of some cloud to determine the ground level in described road scene；
3D region generation module, is suitable to, according to preset vehicle dimension, generate multiple space on described ground level
Territory；
Solid determines module, is suitable to the first solid comprising the plurality of some cloud is divided into the second of specified quantity
The set of solid, determines one or more described second solid that each 3D region comprises；
Alternative area determines module, is suitable to one or more described second geometry comprised according to each 3D region described
Body, determines whether this 3D region is three-dimensional vehicle alternative area.
B14, according to the device described in B13, wherein, described some cloud acquisition module is further adapted for:
Multiple somes clouds in road scene are gathered according to laser measurement principle；And/or
Multiple somes clouds in road scene are obtained according to photogrammetry principles.
B15, according to the device described in B13 or B14, wherein, described ground level determines that module is further adapted for:
By stochastic sampling concordance RANSAC algorithm, determine in the plurality of some cloud and belong to the ground in described road scene
The point cloud of plane.
B16, according to the device according to any one of B13-B15, wherein, described 3D region generation module is further adapted for:
According to preset vehicle dimension, at the described multiple 3D region of ground level stochastic generation, wherein, described 3D region
By specifying parameter determination.
B17, according to the device described in B16, wherein, described appointment parameter includes at least one following:
The three-dimensional coordinate of vehicle center, vehicle dimension, vehicle on described ground level towards angle.
B18, according to the device according to any one of B13-B17, wherein, described solid determines that module is further adapted for:
By comprising the cuboid of the plurality of some cloud according to fixed interval discretization, it is divided into the cubical of specified quantity
Set.
B19, according to the device described in B18, wherein, described alternative area determines that module includes:
Computing unit, is suitable to one or more described second solid comprised according to each 3D region described, utilizes
Three-dimensional integral figure calculates some cloud quantity and/or the some cloud average height that each 3D region described comprises；
Determine unit, be suitable to some cloud quantity and/or the some cloud average height comprised according to each 3D region described, determine
Whether this 3D region is three-dimensional vehicle alternative area.
B20, according to the device described in B19, wherein, described determine that unit is further adapted for:
The point cloud quantity each 3D region described comprised according to the weight specified and some cloud average height summation weighting,
Obtain the comprehensive grading value of each 3D region described；
Comprehensive grading value according to each 3D region described, determines whether this 3D region is three-dimensional vehicle candidate area
Territory.
B21, according to the device described in B20, wherein, described determine that unit is further adapted for:
The comprehensive grading value of each 3D region described is ranked up from big to small；
Choose the 3D region of the forward specified quantity of sequence as three-dimensional vehicle alternative area.
B22, according to the device according to any one of B13-B21, wherein, also include:
Traffic navigation information generation module, is suitable to during driving, according to the described three-dimensional vehicle determined
Alternative area, identifies driving relevant information；It is analyzed generating corresponding traffic navigation to the driving relevant information identified
Information, and it is supplied to user.
B23, according to the device described in B22, wherein, described driving relevant information includes at least one following:
Front truck and/or rear car and the distance of this car, driving road-condition identification information, road environment information.
B24, according to the device according to any one of B13-B23, wherein, described device is applied at vehicle-mounted intelligent control single
In unit.
The another aspect of the embodiment of the present invention, additionally provides C25, a kind of mobile unit, including institute any one of B13-B24
The determination device of the three-dimensional vehicle alternative area stated.
Claims (10)
1. a determination method for three-dimensional vehicle alternative area, including:
Obtain multiple somes clouds in road scene, utilize the plurality of some cloud to determine the ground level in described road scene；
According to preset vehicle dimension, described ground level generates multiple 3D region；
The first solid comprising the plurality of some cloud is divided into the set of the second solid of specified quantity, determine each three
One or more described second solid that dimension region comprises；
One or more described second solid comprised according to each 3D region described, determines whether this 3D region is three
Dimension vehicle alternative area.
Method the most according to claim 1, wherein, multiple somes clouds in described acquisition road scene, including:
Multiple somes clouds in road scene are gathered according to laser measurement principle；And/or
Multiple somes clouds in road scene are obtained according to photogrammetry principles.
Method the most according to claim 1 and 2, wherein, utilizes the plurality of some cloud to determine the ground in described road scene
Plane, including:
By stochastic sampling concordance RANSAC algorithm, determine in the plurality of some cloud and belong to the ground level in described road scene
Some cloud.
4. according to the method according to any one of claim 1-3, wherein, according to preset vehicle dimension, at described ground level
The multiple 3D region of upper generation, including:
According to preset vehicle dimension, at the described multiple 3D region of ground level stochastic generation, wherein, described 3D region passes through
Specify parameter determination.
Method the most according to claim 4, wherein, described appointment parameter includes at least one following:
The three-dimensional coordinate of vehicle center, vehicle dimension, vehicle on described ground level towards angle.
6. according to the method according to any one of claim 1-5, wherein, the first solid comprising the plurality of some cloud is drawn
It is divided into the set of the second solid of specified quantity, including:
By comprising the cuboid of the plurality of some cloud according to fixed interval discretization, it is divided into the cubical collection of specified quantity
Close.
Method the most according to claim 6, wherein, one or more described comprised according to each 3D region described
Two solids, determine whether this 3D region is three-dimensional vehicle alternative area, including:
One or more described second solid comprised according to each 3D region described, utilizes three-dimensional integral figure to calculate described
Point cloud quantity that each 3D region comprises and/or some cloud average height；
The point cloud quantity that comprises according to each 3D region described and/or some cloud average height, determine that whether this 3D region is
Three-dimensional vehicle alternative area.
Method the most according to claim 7, wherein, the some cloud quantity comprised according to each 3D region described and/or point
Cloud average height, determines whether this 3D region is three-dimensional vehicle alternative area, including:
The point cloud quantity comprised each 3D region described according to the weight specified and some cloud average height summation weighting, obtain
The comprehensive grading value of each 3D region described；
Comprehensive grading value according to each 3D region described, determines whether this 3D region is three-dimensional vehicle alternative area.
9. a determination device for three-dimensional vehicle alternative area, including:
Point cloud acquisition module, is suitable to obtain multiple somes clouds in road scene；
Ground level determines module, is suitable to utilize the plurality of some cloud to determine the ground level in described road scene；
3D region generation module, is suitable to, according to preset vehicle dimension, generate multiple 3D region on described ground level；
Solid determines module, is suitable to be divided into the first solid comprising the plurality of some cloud the second geometry of specified quantity
The set of body, determines one or more described second solid that each 3D region comprises；
Alternative area determines module, is suitable to one or more described second solid comprised according to each 3D region described,
Determine whether this 3D region is three-dimensional vehicle alternative area.
10. a mobile unit, including the determination device of the three-dimensional vehicle alternative area described in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610581697.5A CN106228602A (en) | 2016-07-21 | 2016-07-21 | Determination method, device and the mobile unit of three-dimensional vehicle alternative area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610581697.5A CN106228602A (en) | 2016-07-21 | 2016-07-21 | Determination method, device and the mobile unit of three-dimensional vehicle alternative area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106228602A true CN106228602A (en) | 2016-12-14 |
Family
ID=57532456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610581697.5A Pending CN106228602A (en) | 2016-07-21 | 2016-07-21 | Determination method, device and the mobile unit of three-dimensional vehicle alternative area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106228602A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019015496A1 (en) * | 2017-07-18 | 2019-01-24 | 武汉智象机器人有限公司 | Fixed radar and movable radar-based vehicle recognition system and parking method |
| CN110595492A (en) * | 2019-09-25 | 2019-12-20 | 上海交通大学 | Vehicle self-positioning system and method in park environment |
| CN111220786A (en) * | 2020-03-09 | 2020-06-02 | 生态环境部华南环境科学研究所 | Method for rapidly monitoring organic pollution of deep water sediments |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226833A (en) * | 2013-05-08 | 2013-07-31 | 清华大学 | Point cloud data partitioning method based on three-dimensional laser radar |
| US20150098076A1 (en) * | 2013-10-08 | 2015-04-09 | Hyundai Motor Company | Apparatus and method for recognizing vehicle |
| CN105015419A (en) * | 2015-07-17 | 2015-11-04 | 中山大学 | Automatic parking system and method based on stereoscopic vision localization and mapping |
| CN105292085A (en) * | 2015-11-02 | 2016-02-03 | 清华大学苏州汽车研究院（吴江） | Vehicle forward collision avoidance system based on infrared laser aid |
| CN105574552A (en) * | 2014-10-09 | 2016-05-11 | 东北大学 | Vehicle ranging and collision early warning method based on monocular vision |
-
2016
- 2016-07-21 CN CN201610581697.5A patent/CN106228602A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226833A (en) * | 2013-05-08 | 2013-07-31 | 清华大学 | Point cloud data partitioning method based on three-dimensional laser radar |
| US20150098076A1 (en) * | 2013-10-08 | 2015-04-09 | Hyundai Motor Company | Apparatus and method for recognizing vehicle |
| CN105574552A (en) * | 2014-10-09 | 2016-05-11 | 东北大学 | Vehicle ranging and collision early warning method based on monocular vision |
| CN105015419A (en) * | 2015-07-17 | 2015-11-04 | 中山大学 | Automatic parking system and method based on stereoscopic vision localization and mapping |
| CN105292085A (en) * | 2015-11-02 | 2016-02-03 | 清华大学苏州汽车研究院（吴江） | Vehicle forward collision avoidance system based on infrared laser aid |
Non-Patent Citations (3)
| Title |
|---|
| XIAOZHI CHEN 等: "3D Object Proposals for Accurate Object Class Detection", 《NIPS’15 PROCEEDINGS OF THE 28TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING SYSTEM》 * |
| 代新雷: "《车身控制***检修 汽车类》", 31 December 2011, 北京理工大学出版社 * |
| 肖强: "地面无人车辆越野环境多要素合成可通行区域检测", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019015496A1 (en) * | 2017-07-18 | 2019-01-24 | 武汉智象机器人有限公司 | Fixed radar and movable radar-based vehicle recognition system and parking method |
| CN110595492A (en) * | 2019-09-25 | 2019-12-20 | 上海交通大学 | Vehicle self-positioning system and method in park environment |
| CN111220786A (en) * | 2020-03-09 | 2020-06-02 | 生态环境部华南环境科学研究所 | Method for rapidly monitoring organic pollution of deep water sediments |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110988912B (en) | Road target and distance detection method, system and device for automatic driving vehicle | |
| CN109521756B (en) | Obstacle motion information generation method and apparatus for unmanned vehicle | |
| CN102248947B (en) | Object and vehicle detecting and tracking using a 3-D laser rangefinder | |
| Ashraf et al. | An investigation of interpolation techniques to generate 2D intensity image from LIDAR data | |
| CN110059608A (en) | A kind of object detecting method, device, electronic equipment and storage medium | |
| CN109902702A (en) | The method and apparatus of target detection | |
| CA2870677A1 (en) | Point cloud visualization of acceptable helicopter landing zones based on 4d lidar | |
| CN109472393A (en) | Space NO emissions reduction precipitation data detection method, device and electronic equipment | |
| CN108629231A (en) | Obstacle detection method, device, equipment and storage medium | |
| WO2017176112A1 (en) | Spatial data analysis | |
| CN110674705A (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
| CN104134216B (en) | The laser point cloud autoegistration method described based on 16 dimensional features and system | |
| JP7156515B2 (en) | Point cloud annotation device, method and program | |
| CN106080397B (en) | Self-adaption cruise system and mobile unit | |
| CN112798811B (en) | Speed measurement method, device and equipment | |
| CN108305277A (en) | A kind of heterologous image matching method based on straightway | |
| CN106228602A (en) | Determination method, device and the mobile unit of three-dimensional vehicle alternative area | |
| CN110110678A (en) | Determination method and apparatus, storage medium and the electronic device of road boundary | |
| CN106240454A (en) | System and the mobile unit of vehicle collision prewarning are provided | |
| KR20180092591A (en) | Detect algorithm for structure shape change using UAV image matching technology | |
| CN113111513A (en) | Sensor configuration scheme determination method and device, computer equipment and storage medium | |
| JP6322564B2 (en) | Point cloud analysis processing apparatus, method, and program | |
| CN116563466A (en) | Deep learning-based three-dimensional Shan Mudian cloud completion method | |
| CN114170188A (en) | Target counting method and system for overlook image and storage medium | |
| Subedi et al. | Development of a multiple‐camera 3D vehicle tracking system for traffic data collection at intersections |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161214 |