CN109961502A - Road conditions display methods, equipment, driving device and computer readable storage medium - Google Patents
Road conditions display methods, equipment, driving device and computer readable storage medium Download PDFInfo
- Publication number
- CN109961502A CN109961502A CN201810048865.3A CN201810048865A CN109961502A CN 109961502 A CN109961502 A CN 109961502A CN 201810048865 A CN201810048865 A CN 201810048865A CN 109961502 A CN109961502 A CN 109961502A
- Authority
- CN
- China
- Prior art keywords
- driving device
- image
- road conditions
- threedimensional model
- road
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000004888 barrier function Effects 0.000 claims description 57
- 238000004891 communication Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 7
- 230000009467 reduction Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 230000008447 perception Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 230000035484 reaction time Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/003—Navigation within 3D models or images
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of road conditions display methods, equipment, driving device and computer readable storage medium, which includes: the image for acquiring multiple and different angles of driving device surrounding road condition；The road conditions threedimensional model of driving device surrounding road condition is determined according to the image of multiple and different angles；Road conditions 3-D image is carried out to road conditions threedimensional model to show；Driving device threedimensional model is incorporated in road conditions 3-D image and is shown.Implementation through the invention optimizes structure, data processing and the decision-making technique of the equipment for realizing that road conditions are shown, improves environment sensing efficiency, brings bigger convenience for user, the user experience is improved.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of road conditions display methods, equipment, driving device and meters
Calculation machine readable storage medium storing program for executing.
Background technique
With the rapid development of society, unmanned air vehicle technique, intelligent driving technology, the application of robot technology are also increasingly wider
It is general, as the walking environment of the flight environment of vehicle of unmanned plane, the running environment of automobile and robot becomes increasingly complex, to ambient enviroment
Perception degree and avoiding barrier ability etc. requirement it is higher and higher, have great significance to safety and traffic dispersion.
Such as in car steering, it is frequently encountered such case, when having barrier on the road in front, causing can
Become very narrow with the road passed through, but only by the range estimation of driver, is usually unable to accurately judge the narrow of front
Can road have enough width that the vehicle driven can be made to pass through, and caused consequence is mainly reflected in two aspects, on the one hand,
Vehicle it is practical can mistake, but driver and the case where dare not cross, that detours the crowded or user that will lead to road from other roads
And it goes；On the other hand, vehicle can not actually pass through, if driver drives to pass through at this time by force, then vehicle will be with obstacle
Object is collided or is blocked on obstacle section, and the influence to traffic is also very big.In the prior art to the prison of traveling road conditions
In control, external environment mainly is perceived by a large amount of sensing equipments of such as radar, infrared sensor, GPS positioning module, is formed
Structure and decision-making technique are sufficiently complex, there is no a kind of effective, convenient and fast solution is proposed for perception ambient enviroment, make
It is bad to obtain user experience.
Summary of the invention
The present invention provides a kind of road conditions display methods, equipment, driving device and computer readable storage mediums, to solve
Used equipment composition and the more complicated technology of decision-making technique in awareness driven device ambient enviroment in the prior art
Problem.
In order to solve the above-mentioned technical problem, the invention adopts the following technical scheme:
The present invention provides a kind of road conditions display methods, which includes:
Acquire the image of multiple and different angles of driving device surrounding road condition；
The road conditions threedimensional model of driving device surrounding road condition is determined according to the image of multiple and different angles；
Road conditions 3-D image is carried out to road conditions threedimensional model to show；
Driving device threedimensional model is incorporated in road conditions 3-D image and is shown.
Further, the road conditions threedimensional model packet of driving device surrounding road condition is determined according to the image of multiple and different angles
It includes:
The same feature object in the image of multiple and different angles is identified respectively；Feature object includes road, barrier；
Identify at least one characteristic point on feature object；
Binding characteristic point and the image of multiple and different angles determine the road conditions threedimensional model of driving device surrounding road condition.
Further, identify that the same feature object in the image of multiple and different angles includes:
The image feature information of the image of multiple and different angles is extracted respectively；
Vectorized process is carried out to image feature information, obtains characteristics of image vector data；
Characteristics of image vector data is matched with preset sample characteristics vector library；
Feature object is identified according to matching result.
Further, binding characteristic point and the image of multiple and different angles determine that the road conditions of driving device surrounding road condition are three-dimensional
Model includes:
Characteristic point is subjected to matching treatment, obtains the corresponding relationship of characteristic point；
The range information of characteristic point is calculated based on corresponding relationship；
Obtain the two-dimensional image information of the image of multiple and different angles；
The three-dimensional coordinate of characteristic point is determined according to the range information of characteristic point and two-dimensional image information；
The road conditions threedimensional model of driving device surrounding road condition is generated according to the three-dimensional coordinate of characteristic point.
Further, driving device threedimensional model is incorporated in after being shown in road conditions 3-D image, further includes:
Judge current road conditions with the presence or absence of obstacle section；
If so, determining the driving device passability in obstacle section according to driving device threedimensional model and road conditions threedimensional model
Data；
Passability prompt is carried out by obstacle section to driving device according to driving device passability data.
Further, passability prompt is carried out by obstacle section to driving device according to driving device passability data
Later, further includes:
Prompt result determines whether driving device can be by obstacle section according to passability；
If so, determining the avoidance decision data of driving device according to driving device threedimensional model and road conditions threedimensional model；
The prompt of avoidance decision is carried out by obstacle section to driving device according to avoidance decision data.
The present invention provides a kind of road conditions to show equipment, comprising:
Image capture module, the image of multiple and different angles for acquiring driving device surrounding road condition；
Threedimensional model determining module, for determining the road conditions of driving device surrounding road condition according to the image of multiple and different angles
Threedimensional model；
Display module is shown for carrying out road conditions 3-D image to road conditions threedimensional model；By driving device threedimensional model knot
Conjunction is shown in road conditions 3-D image.
Further, threedimensional model determining module includes:
Visual identity submodule, the same feature object in image for identifying multiple and different angles respectively；Feature pair
As including road, barrier；
Labeling submodule, for identifying at least one characteristic point on feature object；
Three-dimensional modeling submodule, the image for binding characteristic point and multiple and different angles determine driving device surrounding road condition
Road conditions threedimensional model.
Further, the present invention also provides a kind of driving device, which includes processor, memory, communication
Bus and at least one camera group；Camera group is at least provided in the front surface of driving device；
Camera group is used to acquire the image of multiple and different angles of driving device surrounding road condition；
Communication bus is for realizing the connection communication between processor, memory, camera group；
Processor is above-mentioned according to multiple and different to realize for executing one or more program stored in memory
The image of angle determines the road conditions threedimensional model of driving device surrounding road condition；It is aobvious that road conditions 3-D image is carried out to road conditions threedimensional model
Show；Driving device threedimensional model is incorporated in the step of showing in road conditions 3-D image.
Further, the quantity of camera group is six, and six camera groups are respectively arranged at six of driving device
On surface.
Further, the present invention also provides a kind of computer readable storage medium, which is deposited
One or more program is contained, one or more program can be executed by one or more processor, above-mentioned to realize
The step of road conditions display methods.
The invention has the benefit that
The present invention provides a kind of road conditions display methods, equipment, driving device and computer readable storage mediums, for existing
By in awareness driven device ambient enviroment, used equipment is formed in the prior art in technology and decision-making technique is more multiple
Miscellaneous defect, the road conditions display methods include: the image for acquiring multiple and different angles of driving device surrounding road condition；According to multiple
The image of different angle determines the road conditions threedimensional model of driving device surrounding road condition；Road conditions three-dimensional figure is carried out to road conditions threedimensional model
As display；Driving device threedimensional model is incorporated in road conditions 3-D image and is shown.Implementation through the invention, optimizes
Structure, data processing and the decision-making technique for realizing the equipment that road conditions are shown, improve environment sensing efficiency, bring more for user
Big convenience, the user experience is improved.
Detailed description of the invention
Fig. 1 is the basic flow chart for the road conditions display methods that the embodiment of the present invention one provides；
Fig. 2 is road conditions display methods refined flow chart provided by Embodiment 2 of the present invention；
Fig. 3 is that vehicle provided by Embodiment 2 of the present invention prejudges aid prompting schematic diagram；
Fig. 4 is Vehicle Decision Method aid prompting schematic diagram provided by Embodiment 2 of the present invention；
Fig. 5 is the structural block diagram that the road conditions that the embodiment of the present invention three provides show equipment；
Fig. 6 is the structural schematic diagram for the driving device that the embodiment of the present invention four provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is a part of the embodiment in the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Further annotation explanation now is made to the present invention by way of specific embodiment combination attached drawing.
Embodiment one:
Fig. 1 is the basic flow chart for the road conditions display methods that embodiment one provides, which is applied to
Generated the driving device of displacement by itself or external drive power drive, the driving device may is that automobile, steamer, nobody
Machine, ground robot etc..The road conditions display methods specifically includes the following steps:
S101, acquire driving device surrounding road condition multiple and different angles image.
Specifically, the driving device in the present embodiment is preferably the vehicles such as automobile, bus, surrounding road condition is adopted
Collection is not limited only to the application scenarios for such as advancing in driving device driving process, moving backward, and can also include driving device in static shape
Such as parking, the application scenarios of engine idling under state.In addition, the surrounding road condition according to specific application scenarios, in the present embodiment
It can be and only refer to road conditions in front of driving device, realize multi-faceted or comprehensive avoidance if necessary, then need multiple to driving device
The road conditions in orientation are perceived, and surrounding road condition here refers to surrounding running environment.
In practical applications, the acquisition of the image of particular orientation passes through the Image Acquisition being arranged in driving device respective side
Device is realized.The image of multiple and different angles can pass through binocular camera shooting device, more mesh photographic devices or stereo photographic device
Shooting obtains, and in further embodiments, binocular camera shooting device and more mesh photographic devices can also be directly by two or more only
Vertical camera is combined and substitutes, and binocular camera shooting device is preferably used in the present embodiment, it should be noted that can also be with
Obtain the multiple image of surrounding road condition from different perspectives by single camera.In addition, in order to when ambient brightness is lower such as night
Also it can be carried out Image Acquisition, low-light level auxiliary shooting function, such as infrared function, flash function can also be integrated on photographic device
Deng.It carries out shooting the image for obtaining two different angles by surrounding road condition of the binocular camera shooting device to same orientation, because
The difference of angle and make corresponding object between two images that can generate certain position deviation.
S102, the road conditions threedimensional model that driving device surrounding road condition is determined according to the image of multiple and different angles.
Specifically, the left image or right image of surrounding road condition are collected according to binocular camera shooting device, by calculating left image
Position deviation between right image corresponding points, to obtain the threedimensional model of surrounding road condition, which includes: travel
Model, barrier model etc..
Optionally, the road conditions threedimensional model for determining driving device surrounding road condition according to the image of multiple and different angles includes:
The same feature object in the image of multiple and different angles is identified respectively；Feature object includes road, barrier；Identify feature
At least one characteristic point on object；Binding characteristic point and the image of multiple and different angles determine the road of driving device surrounding road condition
Condition threedimensional model.
Specifically, the feature object in the present embodiment includes: one of travel, barrier etc. or a variety of, wherein
Barrier includes: obstructing objects, pedestrian, vehicle etc. on narrow road section or road again, and spy is included in usual acquired image
All objects in orientation, and the object unrelated with the traveling behavior of driving device at this time may not necessarily further be located
Reason only needs to identify feature object relevant to driving device traveling behavior and be further processed and carry out three-dimensional and build
Mould.Modeling method in the present embodiment is then divided based on the feature object identified in the image of different angle respectively
Corresponding contour feature point is not selected in different feature objects and is identified, the selection of characteristic point, which should ensure that, to be based on
Selected characteristic point can the space profiles to object carry out simulation reduction, for guarantee reduction object self construction and position it is accurate
The characteristic point more than the optional amount of exhausting is spent, in addition, the characteristic point chosen on the basis of can guarantee reduction accuracy is fewer, processing effect
Rate then can be higher, and then three-dimensional scenic surface reconstruction is realized based on the two dimensional image of the characteristic point and acquisition that identify.
Optionally, identify that the same feature object in the image of multiple and different angles includes: to extract multiple and different angles respectively
The image feature information of the image of degree；Vectorized process is carried out to image feature information, obtains characteristics of image vector data；It will figure
As feature vector data is matched with preset sample characteristics vector library；Feature object is identified according to matching result.
Image feature information in the present embodiment includes: color character, contour feature, edge feature, textural characteristics, pixel
Gray feature etc., corresponding image feature information is different in the picture for different objects, thus according to specific image spy
Reference breath or combinations thereof can distinguish feature object.The extraction for carrying out image feature information previously according to different objects is gone forward side by side
Row vectorized process and obtain vector quantization data, and then sample characteristics vector library is established, to facilitate preservation and later period to carry out
With identification.It when needing to carry out feature object identification to acquired image, first has to cut sample, i.e. extraction characteristics of image letter
Breath, then the feature vector data of extracted image feature information is obtained, and then it is matched with sample characteristics vector library
Qualified feature object can be identified.
Optionally, binding characteristic point and the image of multiple and different angles determine the road conditions three-dimensional mould of driving device surrounding road condition
Type includes: that characteristic point is carried out matching treatment, obtains the corresponding relationship of characteristic point；The distance of characteristic point is calculated based on corresponding relationship
Information；Obtain the two-dimensional image information of the image of multiple and different angles；According to the range information and two-dimensional image information of characteristic point
Determine the three-dimensional coordinate of characteristic point；The road conditions threedimensional model of driving device surrounding road condition is generated according to the three-dimensional coordinate of characteristic point.
Specifically, being separated by one between multiple camera units when acquiring the image of the same multiple and different angles in target bearing
Fixed distance, similar to the principle of eye-observation, each corresponding objects between variant angular image form certain parallax, this
In parallax can be understood as the position deviation of each object.Modeling method provided in the present embodiment, with binocular camera shooting device
For the left image and right image of acquisition, any image be can be used as into reference picture, then another image is then contrast images, is known
Feature object in other reference picture and after indicating the characteristic point of feature object, chooses from all pixels point in contrast images
The pixel to match with characteristic point in reference picture has determined the characteristic point of contrast images, to obtain different angles
Spend the corresponding relationship between the characteristic point of image.Matching relationship based on characteristic point can calculate the view between each pair of characteristic point
The depth information of characteristic point can be obtained in conjunction with the parameter matrix of photographic device in difference, and characteristic point can be calculated and fill to camera shooting
The distance for setting lens centre can reconstruct feature in conjunction with the two-dimensional image information of any image in left image and right image
Three-dimensional coordinate of the point in solid space, can reconstruct the three of object based on three-dimensional reconstruction by multiple target feature points
Dimension module.
S103, road conditions threedimensional model progress road conditions 3-D image is shown.
In practical applications, road conditions threedimensional model is shown, it can situation of change to such as road width, barrier
Orientation, the distance of barrier, the quantity of barrier etc. be shown so that user to travel have one it is more straight
The understanding of sight.
S104, it driving device threedimensional model is incorporated in road conditions 3-D image shows.
It, can be with specifically, the driving device threedimensional model in the present embodiment is obtained based on the three-dimensional information of driving device
That i.e. storage is good after initialization for drive unit system itself, be also possible to user from the official's data downloaded to from the background and into
Row storage, naturally it is also possible to be user by the length data at position each outside manual measurement driving device, and by its hand
It is dynamic be input to it is in system and storage.Three-dimensional information based on driving device can carry out three-dimensional modeling to it and obtain driving dress
The threedimensional model set, then the threedimensional model of driving device is mapped to progress 3-D image in road conditions threedimensional model and is shown
Relativeness between driving device and travel, barrier etc. is organically combined, is obtained to be conducive to raising user
The accuracy for taking driving information facilitates user to carry out Driving Decision-making.
Optionally, driving device threedimensional model is incorporated in after being shown in road conditions 3-D image, further includes: judgement
Current road conditions whether there is obstacle section；If so, determining obstacle road according to driving device threedimensional model and road conditions threedimensional model
The driving device passability data of section；Passability is carried out by obstacle section to driving device according to driving device passability data
Prompt.
Specifically, the obstacle section in the present embodiment includes the section for being placed with barrier or the narrow road section of mutation.?
In practical application, bigger driving facility and safety guarantor can be provided for user by carrying out auxiliary driving prompt to driving device
Card.For example, determining that passability data then include driving device there are when obstacle section in front of driving device in the present embodiment
The width data in obstacle section corresponding to the width data and road conditions threedimensional model of the corresponding driving device of threedimensional model,
Can determine whether vehicle can be by the obstacle section according to the two；In addition, passability data can also be in obstacle section
Barrier with respect to driving device with current driving route normally travel when respective side lateral distance, it is possible thereby to know driving
Spatial correlation between device and barrier can also judge the passability of driving device.Driving device is based on
The passability data including driving device passability judging result of above-mentioned determination carry out passability prompt to user, are such as incorporated in
It is shown in 3-D image above-mentioned, or carries out voice broadcasting, prejudge aid prompting to carry out road to user.
Optionally, passability is carried out by obstacle section to driving device according to driving device passability data and prompts it
Afterwards, further includes: prompt result determines whether driving device can be by obstacle section according to passability；If so, according to driving
Device threedimensional model and road conditions threedimensional model determine the avoidance decision data of driving device；Driving is filled according to avoidance decision data
It sets and the prompt of avoidance decision is carried out by obstacle section.
Specifically, in further embodiments, there are obstacle section and determine that driving device can be in front of driving device
In the case where by the obstacle section, the real-time lateral distance data based on driving device and obstacle section respective side can to
Family carries out the prompt of avoidance decision, i.e., how prompt user should manipulate driving device and safer by obstacle section, such as
Lateral distance on the left of the opposite driving device in obstacle section left side is 0.1 meter, and the opposite driving device right side on the right side of obstacle section
When the lateral distance of side is 0.3 meter, it may be said that the amount of redundancy opposing left on the right side of bright driving device wants larger, and user slightly leans on
Traveling can be more conducive to keep safe distance between barrier after right hand steering, to be not easy to collide with barrier.Keeping away here
Hindering decision data includes driving device avoidance direction, driving device avoidance steering angle etc..It should be noted that in the present embodiment
Avoidance decision application scenarios be not limited only to the real-time prompting to driving device when through obstacle section, can also be and passing through
Pre-tip is carried out before obstacle section.
It should also be noted that real-time vertical with respect to obstacle section based on driving device front in yet other embodiments,
The prompt of avoidance decision can also be carried out to user to range data, corresponding avoidance decision data may include: that driving device is kept away
Hinder speed, such as when driving device is towards traveling at obstacle section, driving device is constantly close with respect to obstacle section, user's manipulation
Driving device is also accordingly reduced by the reaction time in obstacle section, is based on this, according to driving device front with respect to barrier road
The fore-and-aft distance data of section are determined the driving device avoidance speed of driving device, with the reduction pair of fore-and-aft distance data
To preset safe speed, allowed a user to the enough reaction time goes to manipulate the speed that user should be prompted to reduce driving device
Driving device passes through obstacle section.
In addition, avoidance decision data can also include driving device start and stop data, according to driving device with respect to obstacle section
On barrier or the real-time linear distance data of pedestrian etc. avoidance start and stop prompt is carried out to user, such as it is opposite in driving device
Barrier or pedestrian are constantly during, when the linear distance data between driving device and barrier or pedestrian are less than in advance
If when threshold value, driving device may strike barrier or pedestrian, parking prompt is carried out to protect to user in this case
It demonstrate,proves user security or public safety, and is moved away in barrier or pedestrian is mobile and form certain safety between driving device
Apart from when, then starting prompt is carried out to user so that user is known can continue normally travel.
The present invention provides a kind of road conditions display methods, which includes: acquisition driving device surrounding road condition
Multiple and different angles image；The road conditions three-dimensional mould of driving device surrounding road condition is determined according to the image of multiple and different angles
Type；Road conditions 3-D image is carried out to road conditions threedimensional model to show；Driving device threedimensional model is incorporated in road conditions 3-D image
It shows.The present invention carries out traveling prompt to user by machine vision technique and dimensional Modeling Technology, optimizes and realizes road
Structure, data processing and the decision-making technique for the equipment that condition is shown improve the perception efficiency of running environment, bring more for user
Big convenience, the user experience is improved.
Embodiment two:
Fig. 2 is road conditions display methods refined flow chart provided by Embodiment 2 of the present invention, which is applied to
On vehicle.Specifically includes the following steps:
S201, the binocular image for acquiring vehicle's surroundings road conditions.
Preferably, the surrounding of vehicle is provided with binocular camera shooting device in the present embodiment, i.e., the front of vehicle, rear portion,
Left part, right part are provided with binocular camera shooting device, it is contemplated that the limited problem of the shooting angle of single photographic device, the present embodiment
At least provided with a photographic device, the space environment to guarantee vehicle periphery is as complete as possible for the middle every side of vehicle.All binoculars
Device is shot simultaneously, and the binocular camera shooting device of every side collects the left image and right image of the space environment of vehicle side.
S202, the image feature information in binocular image is extracted respectively and carries out vectorized process and obtains characteristics of image arrow
Data are measured, characteristics of image vector data is matched with preset sample characteristics vector library then and is identified in binocular image
Road and barrier.
Preferably, vehicle driving road and barrier are only determined as feature object, characteristics of image in the present embodiment
Information includes: color character, contour feature, edge feature, textural characteristics, pixel grey scale feature etc., for distinguishing variety classes
Object.Also, machine learning method is used in the present embodiment, the characteristic information of object is extracted and is matched with sample database
And identify corresponding feature object.
S203, it is identified respectively to characteristic point required for road and barrier progress three-dimensional modeling and is carried out at matching
Reason, corresponding relationship based on the characteristic point after matching treatment calculate characteristic point to the lens centre of correspondence binocular camera shooting device away from
From.
Preferably, the matching relationship based on characteristic point can calculate the parallax between each pair of characteristic point, in conjunction with binocular
The depth information of characteristic point can be obtained in the parameter matrix of photographic device, and characteristic point can be calculated into photographic device lens
The distance of the heart.
S204, the distance based on characteristic point to the lens centre of corresponding binocular camera shooting device and corresponding two dimensional image letter
Breath, determines the three-dimensional coordinate of characteristic point, and generates vehicle periphery road and barrier according to the three-dimensional coordinate of all characteristic points
Threedimensional model.
Preferably, distance of the characteristic point to any lens centre of photographic device, and corresponding lens acquired image
Two-dimensional image information can reconstruct three-dimensional coordinate of the characteristic point in solid space, be based on three by multiple target feature points
Dimension reconstruction technique can reconstruct the threedimensional model of object.
S205, three-dimensional vehicle model is obtained, and by three-dimensional vehicle models coupling in the threedimensional model of road and barrier
It performs image display.
Preferably, vehicle, road and barrier are subjected to Three-dimensional Display, user can be made to current road conditions and vehicle
It is understood more intuitively with the relative position of barrier.
S206, judge that whether there are obstacles on present road, if so, S207 is gone to, if it is not, then going to S201.
S207, determine vehicle with respect to obstacle section in the threedimensional model of road and barrier according to three-dimensional vehicle models coupling
Passability data, and based on passability data carry out passability prompt.
In the present embodiment, passability data can only include width data between vehicle width data, barrier with
And trafficability judging result, such as in the present embodiment, obstacle section can be 2.1 meters by width, vehicle width 2.2
Rice, vehicle can not pass through, to show in conjunction with 3-D image above-mentioned to these data, to pass through obstacle section to vehicle
Before carry out anticipation aid prompting.The vehicle anticipation aid prompting schematic diagram being illustrated in figure 3 in the present embodiment.
The obstacle section at place if S208, vehicle can break the barriers, according to three-dimensional vehicle models coupling in road and barrier
Hinder the threedimensional model of object to determine avoidance decision data when vehicle passes through, and avoidance decision assistant is carried out based on avoidance decision data
Prompt.
In the present embodiment, vehicle obstacle-avoidance decision data includes the real-time lateral distance of vehicle Yu barrier section respective side
Data and vehicle obstacle-avoidance direction, such as in the present embodiment, the lateral distance on the left of the barrier relative vehicle of left side is 0.3 meter,
And the lateral distance on the right side of the barrier relative vehicle of right side is 0.5 meter, can determine that vehicle suitably leans on right traveling that can more pacify at this time
Entirely, auxiliary to carry out decision when passing through obstacle section to vehicle to be shown in conjunction with 3-D image above-mentioned to these data
Help prompt.The Vehicle Decision Method aid prompting schematic diagram being illustrated in figure 4 in the present embodiment.
The present invention provides the binocular figures that a kind of road conditions display methods, the road conditions display methods pass through acquisition vehicle's surroundings
Picture based on the road and barrier in machine learning algorithm identification image and identifies required characteristic point, then according to binocular figure
As the corresponding relationship between information and characteristic point carries out three-dimensional modeling, and three-dimensional vehicle models coupling road and barrier is three-dimensional
Model shows, can also further be carried out respectively during the entire process of vehicle passes through obstacle section anticipation aid prompting and
Decision assistant prompt.Structure, data processing and the decision-making technique for optimizing the equipment for realizing that road conditions are shown, improve running environment
Perception efficiency, bring bigger convenience for user, the user experience is improved.
Embodiment three:
A kind of road conditions display equipment is present embodiments provided, Fig. 5 is specifically referred to, which shows that equipment can be used for energy
It is enough to be generated in the driving device of displacement by itself or external drive power drive, the driving device may is that automobile, steamer,
Unmanned plane, ground robot etc..It include: image capture module 51, for acquiring multiple and different angles of driving device surrounding road condition
The image of degree；Threedimensional model determining module 52, for determining driving device surrounding road condition according to the image of multiple and different angles
Road conditions threedimensional model；Display module 53 is shown for carrying out road conditions 3-D image to road conditions threedimensional model；By driving device three-dimensional
Models coupling is shown in road conditions 3-D image.
Specifically, image capture module 51 is not limited only in driving device driving process as before the acquisition of surrounding road condition
Into, reversing application scenarios, can also include driving device under static state as parking, engine idling application scenarios.
In addition, the surrounding road condition in the present embodiment, which can be, only refers to road conditions in front of driving device, if needing according to specific application scenarios
It realizes multi-faceted or comprehensive avoidance, then the road conditions to the multiple orientation of driving device is needed to perceive, surrounding road here
Condition refers to surrounding running environment.In practical applications, the image capture module 51 in the present embodiment can be binocular camera shooting device,
More mesh photographic devices or stereo photographic device, in further embodiments, binocular camera shooting device and more mesh photographic devices can be with
It is directly combined and is substituted by two or more independent cameras, it should be noted that image capture module 51 can also be with
It is the single camera that can obtain the multiple image of surrounding road condition from different perspectives.In addition, in order to make image capture module 51 exist
When ambient brightness is lower such as night also can be carried out Image Acquisition, and low-light level auxiliary can also be integrated on image capture module 51 and is clapped
Camera shooting function, such as infrared function, flash function.
In addition, collecting the left image or right image of surrounding road condition, threedimensional model determining module according to binocular camera shooting device
52 by calculating the position deviation between left image and right image corresponding points, to obtain the threedimensional model of surrounding road condition, the three-dimensional
Model includes: travel model, barrier model etc..
In practical applications, display module 53 shows road conditions threedimensional model, can be to the variation of such as road width
Situation, the orientation of barrier, the distance of barrier, quantity of barrier etc. are shown, so that user is to travel
There is one more to get information about.It should also be noted that the threedimensional model of driving device is mapped to road conditions by display module 53
In threedimensional model carry out 3-D image show, can to the relativeness between driving device and travel, barrier etc. into
Row organically combines, to be conducive to improve the accuracy that user obtains driving information, user is facilitated to carry out Driving Decision-making.
Further, threedimensional model determining module includes: visual identity submodule, for identifying multiple and different angles respectively
Image in same feature object；Feature object includes road, barrier；Labeling submodule, for identifying feature object
On at least one characteristic point；Three-dimensional modeling submodule is determined for binding characteristic point and the image of multiple and different angles and is driven
The road conditions threedimensional model of device surrounding road condition.
Specifically, the feature object in the present embodiment includes: one of travel, barrier etc. or a variety of, wherein
Barrier includes: obstructing objects, pedestrian, vehicle etc. on narrow road section or road again, and usual image capture module is collected
Comprising all objects in particular orientation in image, and the object unrelated with the traveling behavior of driving device at this time may not necessarily be into
Row is further processed, i.e., only need will to identify and be further processed to the relevant feature object of driving device traveling behavior and into
Row three-dimensional modeling.Modeling method in the present embodiment is that view-based access control model identification submodule identifies in the image of different angle respectively
Feature object out, then labeling submodule selects corresponding contour feature point in different feature objects respectively and goes forward side by side
Line identifier, the selection of characteristic point should ensure that three-dimensional modeling submodule can carry out the space profiles of object based on selected characteristic point
Simulation reduction, for guarantee reduction object self construction and position the optional amount of exhausting of accuracy more than characteristic point, in addition, in energy
Guarantee that the characteristic point chosen on the basis of reduction accuracy is fewer, treatment effeciency then can be higher, and then three-dimensional modeling submodule base
Three-dimensional scenic surface reconstruction is realized in the two dimensional image of the characteristic point and acquisition that identify.
Further, further includes: aid prompting module, when aid prompting module carries out anticipation aid prompting, auxiliary is mentioned
Show that module is specifically used for: judging current road conditions with the presence or absence of obstacle section；If so, according to driving device threedimensional model and road conditions
Threedimensional model determines the driving device passability data in obstacle section；Driving device is passed through according to driving device passability data
Obstacle section carries out passability prompt.
Specifically, the aid prompting module in the present embodiment is determining in front of driving device there are when obstacle section, pass through
Property data then include corresponding to the width data and road conditions threedimensional model of the corresponding driving device of threedimensional model of driving device
Obstacle section width data, according to the two i.e. can determine whether vehicle can be by the obstacle section；In addition, passability data
The transverse direction of respective side when can also be the barrier in obstacle section with respect to driving device with current driving route normally travel
Distance, it is possible thereby to know the spatial correlation between driving device and barrier, it can also be to the passability of driving device
Judged.Aid prompting module based on the passability data including driving device passability judging result of above-mentioned determination to
Family carry out passability prompt, be such as incorporated in 3-D image above-mentioned and shown, or carry out voice broadcasting, with to user into
Trade road prejudges aid prompting.
Further, when aid prompting module carries out the prompt of avoidance decision assistant, aid prompting module is specifically used for: root
Determine whether driving device can be by obstacle section according to passability prompt result；If so, according to driving device threedimensional model
The avoidance decision data of driving device is determined with road conditions threedimensional model；Obstacle road is passed through to driving device according to avoidance decision data
The prompt of Duan Jinhang avoidance decision.
Specifically, in further embodiments, there are obstacle section and determine that driving device can be in front of driving device
In the case where the obstacle section, aid prompting module based on the real-time transverse direction of driving device and barrier section respective side away from
The prompt of avoidance decision can be carried out to user from data, i.e., how prompt user should manipulate driving device and safer pass through
Obstacle section.Here avoidance decision data includes driving device avoidance direction, driving device avoidance steering angle etc..This implementation
Avoidance decision application scenarios in example are not limited only to the real-time prompting to driving device when through obstacle section, can also be
By carrying out pre-tip before obstacle section.
It should also be noted that aid prompting module is based on driving device front with respect to obstacle in yet other embodiments,
The real-time fore-and-aft distance data in section can also carry out the prompt of avoidance decision to user, and corresponding avoidance decision data can wrap
It includes: driving device avoidance speed, such as when driving device is towards traveling at obstacle section, driving device is continuous with respect to obstacle section
Close, user manipulates driving device and is also accordingly reduced by the reaction time in obstacle section, is based on this, aid prompting module according to
Driving device front is determined the driving device avoidance speed of driving device with respect to the fore-and-aft distance data in barrier section,
And as the speed of the corresponding prompt user reduction driving device of the reduction of fore-and-aft distance data is to preset safe speed, to use
Family can have the enough reaction time that manipulation driving device is gone to pass through obstacle section.
In addition, avoidance decision data can also include driving device start and stop data, aid prompting module is according to driving device
The real-time linear distance data of barrier or pedestrian etc. on opposite obstacle section carry out avoidance start and stop prompt to user, such as
Driving device with respect to barrier or pedestrian constantly during, when the straight line between driving device and barrier or pedestrian away from
When being less than preset threshold from data, driving device may strike barrier or pedestrian, in this case, aid prompting mould
Block carries out parking prompt to user to guarantee user security or public safety, and barrier moved away or pedestrian it is mobile and with drive
When forming certain safe distance between dynamic device, then it starting prompt is carried out to user can continue normal row so that user is known
It sails.
A kind of road conditions display equipment is present embodiments provided, which shows that equipment includes: image capture module, for adopting
Collect the image of multiple and different angles of driving device surrounding road condition；Threedimensional model determining module, for according to multiple and different angles
Image determine the road conditions threedimensional model of driving device surrounding road condition；Display module, for carrying out road conditions to road conditions threedimensional model
3-D image is shown；Driving device threedimensional model is incorporated in road conditions 3-D image and is shown.The present invention is regarded by machine
Feel technology and dimensional Modeling Technology carry out traveling prompt to user, optimize the structure for realizing the equipment that shows of road conditions, at data
Reason and decision-making technique, improve the perception efficiency of running environment, bring bigger convenience for user, improve user's body
It tests.
Example IV:
A kind of driving device is present embodiments provided, it is shown in Figure 6, including processor 61, memory 62, communication bus
63 and at least one camera group 64；Camera group 64 is at least provided in the front surface of driving device；
Camera group 64 is used to acquire the image of multiple and different angles of driving device surrounding road condition；
Communication bus 63 is for realizing the connection communication between processor 61, memory 62, camera group 64；
Memory 62 for storing one or more programs, processor 61 for execute one stored in memory 62 or
The multiple programs of person are determined around driving device shown in the various embodiments described above according to the image of multiple and different angles with realizing
The road conditions threedimensional model of road conditions；Road conditions 3-D image is carried out to road conditions threedimensional model to show；Driving device threedimensional model is combined
The step of being shown in road conditions 3-D image.
Specifically, in practical applications, at least at least one camera group is provided in driving device front surface, to realize
Road conditions of the driving device when moving forward are shown；And in order to realize that carrying out multi-faceted road conditions to driving device shows, then it answers
Multiple camera groups are separately positioned on the different surfaces of driving device, so as to make user to the perception of running environment more
Comprehensively.Since the image-capture field of single camera group is limited, in order to guarantee the corresponding space environment in each surface of driving device
Sensing range it is as big as possible, the deployment of multiple camera groups can be carried out on each surface of driving device.
Further, the quantity of camera group 64 is six, and six camera groups 64 are respectively arranged at the six of driving device
On a surface.
Specifically, in the present embodiment preferably on six surfaces of driving device, i.e., front, rear portion, left part, right part,
Top, lower part are respectively arranged with camera group, to realize that user carries out panorama perception to the running environment of driving device.
Embodiment five:
The present invention also provides a kind of computer readable storage medium, one is stored in the computer readable storage medium
Or multiple programs, which can be executed by one or more processor, to realize the various embodiments described above
Shown in road conditions display methods the step of, details are not described herein.
In summary, implementation through the embodiment of the present invention, at least exist it is following the utility model has the advantages that
The present invention provides a kind of road conditions display methods, equipment, driving device and computer readable storage mediums, for existing
By in awareness driven device ambient enviroment, used equipment is formed in the prior art in technology and decision-making technique is more multiple
Miscellaneous defect, the road conditions display methods include: the image for acquiring multiple and different angles of driving device surrounding road condition；According to multiple
The image of different angle determines the road conditions threedimensional model of driving device surrounding road condition；Road conditions three-dimensional figure is carried out to road conditions threedimensional model
As display；Driving device threedimensional model is incorporated in road conditions 3-D image and is shown.Implementation through the invention, optimizes
Structure, data processing and the decision-making technique for realizing the equipment that road conditions are shown, improve environment sensing efficiency, bring more for user
Big convenience, the user experience is improved.
The above content is specific embodiment is combined, further detailed description of the invention, and it cannot be said that this hair
Bright specific implementation is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, it is not taking off
Under the premise of from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to protection of the invention
Range.
Claims (11)
1. a kind of road conditions display methods, which is characterized in that the road conditions display methods includes:
Acquire the image of multiple and different angles of driving device surrounding road condition；
The road conditions threedimensional model of the driving device surrounding road condition is determined according to the image of the multiple different angle；
Road conditions 3-D image is carried out to the road conditions threedimensional model to show；
Driving device threedimensional model is incorporated in the road conditions 3-D image and is shown.
2. road conditions display methods as described in claim 1, which is characterized in that the image according to the multiple different angle
The road conditions threedimensional model for determining the driving device surrounding road condition includes:
The same feature object in the image of the multiple different angle is identified respectively；The feature object includes road, obstacle
Object；
Identify at least one characteristic point on the feature object；
Determine that the road conditions of the driving device surrounding road condition are three-dimensional in conjunction with the image of the characteristic point and the multiple different angle
Model.
3. road conditions display methods as claimed in claim 2, which is characterized in that the image of the multiple different angle of identification
In same feature object include:
The image feature information of the image of the multiple different angle is extracted respectively；
Vectorized process is carried out to described image characteristic information, obtains characteristics of image vector data；
Described image feature vector data is matched with preset sample characteristics vector library；
The feature object is identified according to matching result.
4. road conditions display methods as claimed in claim 2, which is characterized in that characteristic point described in the combination and it is the multiple not
Image with angle determines that the road conditions threedimensional model of the driving device surrounding road condition includes:
The characteristic point is subjected to matching treatment, obtains the corresponding relationship of the characteristic point；
The range information of the characteristic point is calculated based on the corresponding relationship；
Obtain the two-dimensional image information of the image of the multiple different angle；
The three-dimensional coordinate of the characteristic point is determined according to the range information of the characteristic point and the two-dimensional image information；
The road conditions threedimensional model of the driving device surrounding road condition is generated according to the three-dimensional coordinate of the characteristic point.
5. road conditions display methods according to any one of claims 1 to 4, which is characterized in that described by driving device three-dimensional
After models coupling is shown in the road conditions 3-D image, further includes:
Judge current road conditions with the presence or absence of obstacle section；
If so, determining that the driving in the obstacle section fills according to the driving device threedimensional model and the road conditions threedimensional model
Set passability data；
Passability prompt is carried out by the obstacle section to the driving device according to the driving device passability data.
6. road conditions display methods as claimed in claim 5, which is characterized in that described according to the driving device passability data
To the driving device by the obstacle section carry out passability prompt after, further includes:
Prompt result determines whether the driving device can be by the obstacle section according to the passability；
If so, determining that the avoidance of the driving device is determined according to the driving device threedimensional model and the road conditions threedimensional model
Plan data；
The prompt of avoidance decision is carried out by the obstacle section to the driving device according to the avoidance decision data.
7. a kind of road conditions show equipment characterized by comprising
Image capture module, the image of multiple and different angles for acquiring driving device surrounding road condition；
Threedimensional model determining module, for determining the driving device surrounding road condition according to the image of the multiple different angle
Road conditions threedimensional model；
Display module is shown for carrying out road conditions 3-D image to the road conditions threedimensional model；By driving device threedimensional model knot
Conjunction is shown in the road conditions 3-D image.
8. road conditions as claimed in claim 7 show equipment, which is characterized in that the threedimensional model determining module includes:
Visual identity submodule, the same feature object in image for identifying the multiple different angle respectively；The spy
Levying object includes road, barrier；
Labeling submodule, for identifying at least one characteristic point on the feature object；
Three-dimensional modeling submodule determines the driving device for the image in conjunction with the characteristic point and the multiple different angle
The road conditions threedimensional model of surrounding road condition.
9. a kind of driving device, which is characterized in that the driving device includes processor, memory, communication bus and at least
One camera group；The camera group is at least provided in the front surface of the driving device；
The camera group is used to acquire the image of multiple and different angles of driving device surrounding road condition；
The communication bus is for realizing the connection communication between processor, memory, camera group；
The processor is for executing one or more program stored in memory, to realize as appointed in claim 1 to 6
The road conditions threedimensional model of the driving device surrounding road condition is determined described in one according to the image of the multiple different angle；It is right
The road conditions threedimensional model carries out road conditions 3-D image and shows；Driving device threedimensional model is incorporated in the road conditions 3-D image
In show.
10. driving device as claimed in claim 9, which is characterized in that the quantity of the camera group is six, described six
Camera group is respectively arranged on six surfaces of the driving device.
11. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, to realize such as claim 1 to 6
Any one of described in road conditions display methods the step of.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711423683 | 2017-12-25 | ||
| CN2017114236831 | 2017-12-25 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109961502A true CN109961502A (en) | 2019-07-02 |
Family
ID=67023066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810048865.3A Pending CN109961502A (en) | 2017-12-25 | 2018-01-18 | Road conditions display methods, equipment, driving device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961502A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759922A (en) * | 2022-10-18 | 2023-03-07 | 甘肃倚莱克特电力科技有限公司 | Smart storage goods storage method, electronic equipment and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005044224A (en) * | 2003-07-24 | 2005-02-17 | Denso Corp | Three-dimensional digital map creation device, three-dimensional digital map display system, and safe driving support system |
| JP2005062924A (en) * | 2003-08-08 | 2005-03-10 | Omron Corp | Three-dimensional object recognition device and setting method therefor |
| JP2011070580A (en) * | 2009-09-28 | 2011-04-07 | Mitsubishi Motors Corp | Driving support device |
| JP2013114610A (en) * | 2011-11-30 | 2013-06-10 | Sharp Corp | Image processing device, driving support device, image processing method, and image processing program |
| CN107464290A (en) * | 2017-08-07 | 2017-12-12 | 上海白泽网络科技有限公司 | Three-dimensional information methods of exhibiting, device and mobile terminal |
-
2018
- 2018-01-18 CN CN201810048865.3A patent/CN109961502A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005044224A (en) * | 2003-07-24 | 2005-02-17 | Denso Corp | Three-dimensional digital map creation device, three-dimensional digital map display system, and safe driving support system |
| JP2005062924A (en) * | 2003-08-08 | 2005-03-10 | Omron Corp | Three-dimensional object recognition device and setting method therefor |
| JP2011070580A (en) * | 2009-09-28 | 2011-04-07 | Mitsubishi Motors Corp | Driving support device |
| JP2013114610A (en) * | 2011-11-30 | 2013-06-10 | Sharp Corp | Image processing device, driving support device, image processing method, and image processing program |
| CN107464290A (en) * | 2017-08-07 | 2017-12-12 | 上海白泽网络科技有限公司 | Three-dimensional information methods of exhibiting, device and mobile terminal |
Non-Patent Citations (2)
| Title |
|---|
| 李向阳;: "图像检索中多个特征量的提取与比较", 广东农工商职业技术学院学报, no. 03, pages 55 - 59 * |
| 李宏才;闫清东;王涛;: "三维视景仿真技术在实践教学中的应用研究", 实验技术与管理, no. 10 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759922A (en) * | 2022-10-18 | 2023-03-07 | 甘肃倚莱克特电力科技有限公司 | Smart storage goods storage method, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112912920B (en) | Point cloud data conversion method and system for 2D convolutional neural network | |
| US20210201507A1 (en) | System and Method for Movement Detection | |
| KR102275310B1 (en) | Mtehod of detecting obstacle around vehicle | |
| CN108520536B (en) | Disparity map generation method and device and terminal | |
| CN114723955B (en) | Image processing method, apparatus, device and computer readable storage medium | |
| Pfeiffer et al. | Efficient representation of traffic scenes by means of dynamic stixels | |
| US20200209858A1 (en) | Generating environmental parameters based on sensor data using machine learning | |
| CN101941438B (en) | Intelligent detection control device and method of safe interval | |
| CN109101957B (en) | Binocular solid data processing method, device, intelligent driving equipment and storage medium | |
| CN108243623A (en) | Vehicle anticollision method for early warning and system based on binocular stereo vision | |
| CN110969064B (en) | Image detection method and device based on monocular vision and storage equipment | |
| JP6574611B2 (en) | Sensor system for obtaining distance information based on stereoscopic images | |
| CN111539484B (en) | Method and device for training neural network | |
| CN111462249B (en) | Traffic camera calibration method and device | |
| CN111856963A (en) | Parking simulation method and device based on vehicle-mounted looking-around system | |
| JP2019124538A (en) | Information processing device, system, and information processing method | |
| KR20200071293A (en) | Localization method and apparatus based on 3d colored map | |
| US11380110B1 (en) | Three dimensional traffic sign detection | |
| WO2022062480A1 (en) | Positioning method and positioning apparatus of mobile device | |
| CN113177429A (en) | Vehicle neural network training | |
| CN113537047A (en) | Obstacle detection method, obstacle detection device, vehicle and storage medium | |
| Badino et al. | Stereo-based free space computation in complex traffic scenarios | |
| CN109961502A (en) | Road conditions display methods, equipment, driving device and computer readable storage medium | |
| Ikeda et al. | Diminished reality system based on open-source software for self-driving mobility | |
| CN115953446A (en) | Depth estimation method and device based on error correction and electronic equipment |
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 |