CN107229690B - Dynamic High-accuracy map datum processing system and method based on trackside sensor - Google Patents
Dynamic High-accuracy map datum processing system and method based on trackside sensor Download PDFInfo
- Publication number
- CN107229690B CN107229690B CN201710359395.8A CN201710359395A CN107229690B CN 107229690 B CN107229690 B CN 107229690B CN 201710359395 A CN201710359395 A CN 201710359395A CN 107229690 B CN107229690 B CN 107229690B
- Authority
- CN
- China
- Prior art keywords
- road
- map
- data
- image
- behavioral characteristics
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title abstract description 8
- 238000013461 design Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 14
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000012800 visualization Methods 0.000 claims abstract description 7
- 230000003542 behavioural effect Effects 0.000 claims description 57
- 230000003068 static effect Effects 0.000 claims description 26
- 238000013135 deep learning Methods 0.000 claims description 21
- 239000000284 extract Substances 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000012546 transfer Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000010354 integration Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009440 infrastructure construction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000003716 rejuvenation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
- G08G1/096783—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a roadside individual element
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of Dynamic High-accuracy map datum processing system and method based on trackside sensor, which includes: map data collecting end, generates server-side for high-precision map and provides magnanimity, the map road initial data of diversification;It includes: map datum processing module that high-precision map, which generates server-side, map road initial data is subjected to road feature extraction, hierarchical design is used to all roadway characteristics, same road information is spliced, first roadway characteristic data fusion is completed in roadway characteristic level, image mosaic finally is completed in image level, the result of splicing generates the downward projection figure of road;Map generates visualization model, marks road information on downward projection figure, and the road information and downward projection figure that have marked collectively constitute the map datum of high-precision map, and map datum is carried out visual edit, generates Dynamic High-accuracy map.The present invention can reduce accurately map generalization cost;Realize the quick update of Dynamic High-accuracy map.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of Dynamic High-accuracy map number based on trackside sensor
According to processing system and method.
Background technique
Currently, with the fast development of automatic Pilot technology, high-precision map importance is increasingly prominent, it has also become realizes nothing
People drives and the indispensable important ring of intelligent transportation.Existing navigation map precision is not generally high, and is made with entire road
Road information data are provided for object or carry out navigation instruction publication, and it is pair that this navigation map, which is referred to as road grade map,
Actual traffic environment significantly simplifies, and the information content that can be provided is few, and accuracy is low, lower to the supporting capacity of driver.
Map required for automatic Pilot will not only have high-precision, also possess a large amount of road peripheries abundant details,
General map navigation accuracy can only achieve a meter magnitude, and high-precision map can be accurate to 10cm rank, not only increase lane attribute
Related data also adds the multiple types of data such as overhead object, protective fence, barrier, road edge type, roadside terrestrial reference.
The massive map data of polynary isomery needs to occupy a large amount of memory spaces, and the high-precision map of free hand drawing layer is unable to satisfy real-time update
Demand.
The technologies such as deep learning, image recognition can significantly promote map datum in the application in high-precision map field
Acquisition and treatment effeciency.The continuous promotion of automatic Pilot technology and user demand, data capacity, accurate journey to high-precision map
More stringent requirements are proposed for degree, renewal frequency etc., and traditional map data collecting draws mode, and there are many technical bottlenecks, utilizes
The artificial intelligence technologys such as image recognition, big data processing, deep learning, being capable of automatic identification traffic sign, surface mark, lane
Line, signal lamp etc. realize that road and POI information are extracted in panoramic picture automation, improve data mart modeling efficiency and update the frequency, protect
Demonstrate,prove the accuracy of data.
The production of high-precision map resurveys all road informations by the staff of profession mostly at present, and plans
Periodically most of region is updated again after the completion of acquisition.The acquisition equipment of this method is often mounted with laser radar
The collecting vehicle of equal special equipments.Joint Japan of the Japanese cars manufacturer such as Mitsubishi and Toyota figure quotient Zenrin is making three-dimensional move
State map.It plans to be to carry out side to road using the special purpose vehicle equipped with high end sensor to draw, and the first step is covering Japan 300
The major highways of kilometer.Here, TomTom and Google also use similar fashion to make three-dimensional map.Domestic tradition figure quotient
10cm dimension accuracy required for high moral is met by way of assembling 2 laser radars and 4 cameras.Tencent, Baidu,
The companies such as NavInfo are also making high-precision map with similar mode.
The above-mentioned original map information accuracy acquired with special onboard sensor is very high, however has the following problems:
1), mobile unit cost is high, high using laser radar acquisition precision of information, of overall importance good but at high cost
High, data volume is big, and generating image is albedo image, is had differences with real-world scene;
2), data-handling efficiency is lower, map data collecting to realize map rejuvenation period it is long, it may appear that map more
The phenomenon that actual road conditions characteristic attribute state early has changed when new, the behavioral characteristics letter that timely and effective can not react real road
Breath, hinders the fast development of location-based service, reduces unpiloted safety and reliability;
3), collected data are dense point clouds, and packing density is very big, consume a large amount of computing resource, and the later period
The figure traffic is high;
4) the link characteristic information content, acquired is limited, needs specific sensor for some specific roadway characteristics
(such as relevant behavioral characteristics data of temperature and humidity, road ponding weather) data acquisition, therefore vehicle-mounted acquisition mode can not
The needs of in terms of meeting automatic Pilot to high-precision map content.
Therefore, how low cost, efficiently and accurately production or update high-precision map are a problem to be solved.
Summary of the invention
In view of this, in order to solve, map acquisition mode data volume in the prior art is big, handles difficult, at high cost, map
The problem of update cycle length, the present invention proposes a kind of based on the Dynamic High-accuracy map datum processing system of trackside sensor and side
Method realizes that high-precision map generates by trackside sensor and AI technology, and at low cost, generation result can real-time effective Feedback road
The current state of feature provides accurate driving assistance information for automatic Pilot.
The present invention is solved the above problems by following technological means:
A kind of Dynamic High-accuracy map datum processing system based on trackside sensor, comprising:
Map data collecting end provides magnanimity, the map road original of diversification for generating server-side for high-precision map
Beginning data;
High-precision map generates server-side, the map road of the magnanimity, diversification that provide for data collection terminal according to the map
Road Raw Data Generation Dynamic High-accuracy map;
The high-precision map generates server-side
Map datum processing module, for map road initial data to be carried out road feature extraction, to all roads
Feature uses hierarchical design, and same road information is spliced, and first completes roadway characteristic data fusion in roadway characteristic level,
Image mosaic finally is completed in image level, the result of splicing generates the downward projection figure of road;
Map generate visualization model, for marking road information on downward projection figure, the road information marked and
Downward projection figure collectively constitutes the map datum of high-precision map, and map datum is carried out visual edit, it is dynamic to generate high-precision
State map.
Further, the map data collecting end includes:
Image data acquiring module, the original road image data of map for acquiring magnanimity;
Road condition data acquisition module, the original road conditions data of map for acquiring magnanimity.
Further, the map datum processing module includes:
Pre-processing image data unit, for the original road image data of map to be carried out image rectification, image coordinate becomes
It changes, the pretreatment of image projection transformation, the image overlay region energy of the image data acquiring module acquisition of adjacent position after pretreatment
Enough alignment;
Road feature extraction unit, for identifying road behavioral characteristics from the original road image data of map;According to existing
There is navigation map to carry out fining feature modeling, obtains road static nature;Number is done by the original road conditions data of to map
According to screening verification, half behavioral characteristics of corresponding road semi-static nature and road are extracted;
Roadway characteristic design cell, for carrying out hierarchical design to all roadway characteristics from content, first layer is road
Static nature, the second layer are road semi-static nature, and third layer is half behavioral characteristics of road, and the 4th layer is road behavioral characteristics;
Multidimensional road information anastomosing and splicing unit, for splicing same road information, first in roadway characteristic level
Roadway characteristic data fusion is completed, pretreated image is finally completed into image mosaic in image level, the result of splicing is raw
At the downward projection figure of road.
Further, the road feature extraction unit includes:
Behavioral characteristics extract subelement, for establishing a depth using the related AI technology of deep learning, image recognition
Learn road behavioral characteristics identification model, using deep learning road behavioral characteristics identification model from the original road image number of map
According to middle identification road behavioral characteristics;
Static nature extracts subelement and it is quiet to obtain road for carrying out fining feature modeling according to existing navigation map
State feature;
Semi-static nature extracts subelement, for doing data screening verifying by the original road conditions data of to map, takes out
Take corresponding road semi-static nature;
Half behavioral characteristics extract subelement, for doing data screening verifying by the original road conditions data of to map, take out
Take corresponding half behavioral characteristics of road.
Further, the multidimensional road information anastomosing and splicing unit includes:
Roadway characteristic anastomosing and splicing subelement, for all roadway characteristics extracted to be spliced according to Dividing Characteristics,
First splice static nature, finally merges behavioral characteristics;
Image mosaic subelement, for pretreated image to be carried out anastomosing and splicing into a basic downward projection
Figure.
Further, the map generation visualization model includes:
Geography information marks unit, for marking road information on downward projection figure, the road information marked and bows
The map datum of high-precision map is collectively constituted depending on perspective view;
Geography information calibration verification unit, for carrying out calibration verification to the road information marked;
Map generation unit generates Dynamic High-accuracy map for map datum to be carried out visual edit.
Further, described image data acquisition module is camera, and the road condition data acquisition module includes GPS, temperature
Humidity sensor, ponding sensor.
Further, the camera is on security monitoring camera and Internet of Things wisdom light pole used in urban transportation
The camera of carry;GPS is the GPS Base Station in current smart city, and Temperature Humidity Sensor, ponding sensor are Internet of Things wisdom
Temperature Humidity Sensor, the ponding sensor integrated on light pole;The original road image data of map and the original road conditions of map
Data generate server-side to high-precision map by the Common Gateway module transfer configured on Internet of Things wisdom light pole.
A kind of Dynamic High-accuracy map data processing method based on trackside sensor, comprising:
S1, the original road image data of map and the original road conditions data of map for acquiring magnanimity;
S2, the pre- place that the original road image data of map are carried out to image rectification, image coordinate transformation, image projection transformation
Reason, the image overlay region of the image data acquiring module acquisition of adjacent position can be aligned after pretreatment;
S3, a deep learning road behavioral characteristics identification is established using deep learning, the related AI technology of image recognition
Model identifies that road dynamic is special using deep learning road behavioral characteristics identification model from the original road image data of map
Sign;
Fining feature modeling is carried out according to existing navigation map, obtains road static nature;
Data screening verifying is done by the original road conditions data of to map, extracts corresponding road semi-static nature and road
Half behavioral characteristics of road;
S4, hierarchical design is carried out to all roadway characteristics from content, first layer is road static nature, and the second layer is
Road semi-static nature, third layer are half behavioral characteristics of road, and the 4th layer is road behavioral characteristics;
S5, same road information is spliced, first completes roadway characteristic data fusion in roadway characteristic level, finally will
Pretreated image completes image mosaic in image level, and the result of splicing generates the downward projection figure of road;
S6, road information is marked on downward projection figure, the road information and downward projection figure marked collectively constitutes height
The map datum of precision map;
S7, calibration verification is carried out to the road information marked;
S8, map datum is carried out to visual edit, generates Dynamic High-accuracy map.
Further, in step S1, using the original road image data of map of camera acquisition magnanimity, using GPS, temperature
Humidity sensor, ponding sensor locality primitive beginning road conditions data;
The camera is that carry is taken the photograph on security monitoring camera and Internet of Things wisdom light pole used in urban transportation
As head;GPS is the GPS Base Station in current smart city, and Temperature Humidity Sensor, ponding sensor are on Internet of Things wisdom light pole
Integrated Temperature Humidity Sensor, ponding sensor;The original road image data of map and the original road conditions data of map pass through
The Common Gateway module transfer configured on Internet of Things wisdom light pole generates server-side to high-precision map.
Compared with prior art, beneficial effects of the present invention are as follows:
1), the camera of present invention acquisition trackside image is deployed in trackside infrastructure (light pole, high hack lever), compares vehicle
The map datum for carrying camera acquisition has more real-time effectiveness;
2), the present invention passes through the multiple sensors terminal device of Internet of Things integration lamp stand carry, can acquire in real time high-precision
The Dynamic and Multi dimensional information (surface gathered water, humidity, weather, street sign indicator etc.) of map is spent, these information only need backstage to carry out letter
Single ground verification processing, so that it may be published to the application platform of high-precision map, real time service is in intelligent transportation field;
3), the map data collecting in the present invention takes full advantage of infrastructure (the wisdom street lamp, road of current smart city
Side camera, GPS Base Station), it is uploaded by the automatic collection of the trackside approach sensor and map datum of sharing smart city
Mode can reduce accurately map generalization cost from many aspects;
4), the present invention passes through to roadway characteristic hierarchical design, Dividing Characteristics anastomosing and splicing and the number for supporting incremental update
According to format storage, it can be achieved that the quick update of Dynamic High-accuracy map.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the structural schematic diagram of the Dynamic High-accuracy map datum processing system the present invention is based on trackside sensor;
Fig. 2 is the topological diagram of the Dynamic High-accuracy map datum processing system the present invention is based on trackside sensor;
Fig. 3 is the work flow diagram of the Dynamic High-accuracy map datum processing system the present invention is based on trackside sensor;
Fig. 4 is the camera deployment diagram of present invention acquisition map;
Fig. 5 is the flow chart of the Dynamic High-accuracy map data processing method the present invention is based on trackside sensor.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with attached drawing and specifically
Embodiment technical solution of the present invention is described in detail.It should be pointed out that described embodiment is only this hair
Bright a part of the embodiment, instead of all the embodiments, based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Embodiment 1
As shown in Figure 1, the present invention provides a kind of Dynamic High-accuracy map datum processing system based on trackside sensor, packet
It includes:
Map data collecting end provides magnanimity, the map road original of diversification for generating server-side for high-precision map
Beginning data;
High-precision map generates server-side, the map road of the magnanimity, diversification that provide for data collection terminal according to the map
Road Raw Data Generation Dynamic High-accuracy map;
The high-precision map generates server-side
Map datum processing module, for map road initial data to be carried out road feature extraction, to all roads
Feature uses hierarchical design, and same road information is spliced, and first completes roadway characteristic data fusion in roadway characteristic level,
Image mosaic finally is completed in image level, the result of splicing generates the downward projection figure of road;
Map generate visualization model, for marking road information on downward projection figure, the road information marked and
Downward projection figure collectively constitutes the map datum of high-precision map, and map datum is carried out visual edit, it is dynamic to generate high-precision
State map.
The map data collecting end includes:
Image data acquiring module, the original road image data of map for acquiring magnanimity;
Road condition data acquisition module, the original road conditions data of map for acquiring magnanimity.
Described image data acquisition module is camera, and the road condition data acquisition module includes GPS, temperature and humidity sensing
Device, ponding sensor etc..
The camera is that carry is taken the photograph on security monitoring camera and Internet of Things wisdom light pole used in urban transportation
As head;GPS is the GPS Base Station in current smart city, and Temperature Humidity Sensor, ponding sensor are on Internet of Things wisdom light pole
Integrated Temperature Humidity Sensor, ponding sensor.
The map datum processing module includes:
Pre-processing image data unit, for the original road image data of map to be carried out image rectification, image coordinate becomes
It changes, the pretreatment of image projection transformation, the image overlay region energy of the image data acquiring module acquisition of adjacent position after pretreatment
Enough alignment;
Road feature extraction unit, for identifying road behavioral characteristics from the original road image data of map;According to existing
There is navigation map to carry out fining feature modeling, obtains road static nature;Number is done by the original road conditions data of to map
According to screening verification, half behavioral characteristics of corresponding road semi-static nature and road are extracted;
Roadway characteristic design cell, for carrying out hierarchical design to all roadway characteristics from content, first layer is road
Static nature, the second layer are road semi-static nature, and third layer is half behavioral characteristics of road, and the 4th layer is road behavioral characteristics;
Multidimensional road information anastomosing and splicing unit, for splicing same road information, first in roadway characteristic level
Roadway characteristic data fusion is completed, pretreated image is finally completed into image mosaic in image level, the result of splicing is raw
At the downward projection figure of road.
The road feature extraction unit includes:
Behavioral characteristics extract subelement, for establishing a depth using the related AI technology of deep learning, image recognition
Learn road behavioral characteristics identification model, using deep learning road behavioral characteristics identification model from the original road image number of map
According to middle identification road behavioral characteristics;
Static nature extracts subelement and it is quiet to obtain road for carrying out fining feature modeling according to existing navigation map
State feature;
Semi-static nature extracts subelement, for doing data screening verifying by the original road conditions data of to map, takes out
Take corresponding road semi-static nature;
Half behavioral characteristics extract subelement, for doing data screening verifying by the original road conditions data of to map, take out
Take corresponding half behavioral characteristics of road.
The multidimensional road information anastomosing and splicing unit includes:
Roadway characteristic anastomosing and splicing subelement, for all roadway characteristics extracted to be spliced according to Dividing Characteristics,
First splice static nature, finally merges behavioral characteristics;
Image mosaic subelement, for pretreated image to be carried out anastomosing and splicing into a basic downward projection
Figure.
The map generates visualization model
Geography information marks unit, for marking road information on downward projection figure, the road information marked and bows
The map datum of high-precision map is collectively constituted depending on perspective view;
Geography information calibration verification unit, for carrying out calibration verification to the road information marked;
Map generation unit generates Dynamic High-accuracy map for map datum to be carried out visual edit.
As shown in Fig. 2, the Image Acquisition in map data collecting end, camera used is security protection used in urban transportation
The camera of carry on monitoring camera and wisdom light pole.As smart city construction reaches its maturity, the covering of camera is got over
Come more intensive, each camera acquisition region corresponds to the road attribute image in monitoring range, uploads to high-precision map
Generate server-side.As shown in figure 4, the camera carry of acquisition road image is on the tracksides facilities such as light pole, high hack lever.For
Other road conditions attributes that camera cannot obtain such as (temperature and humidity, surface gathered water data), pass through Internet of Things integrated lamp
Temperature Humidity Sensor, the ponding sensor integrated on bar is obtained, and the sensing equipment terminal on Internet of Things integration lamp stand can
According to circumstances flexibly apolegamy, data generate server-side to high-precision map by the Common Gateway module transfer configured on lamp stand.
Roadway characteristic design cell, the demand according to automatic Pilot to high-precision map, from content to roadway characteristic into
Row Modeling and Design, the feature of hierarchical design road network.First layer is the static nature of road, and static nature information includes: road
The position of route lane line, traffic signals and traffic sign position;The basic informations such as road ID number, shape, the gradient, width.
The second layer is the semi-static nature of road: traffic rule information (such as tide section etc.), road construction information, extensively regional day
Gas information (rain and snow weather) etc.;Third layer is half multidate information of roadway characteristic: traffic accident position, is handed at traffic congestion position
Logical ponding position, road hollow position, road barricade object location etc.;4th layer of roadway characteristic is multidate information: pedestrian, automobile,
The targets such as bicycle, motorcycle changing coordinates, motion profile.Roadway characteristic design cell the result is that by all roads of design
Characteristic information is abstracted as data entity and object in high-precision map.The principle that roadway characteristic design uses is that difference is driven automatically
Demand of the rank to high-precision map content and precision is sailed, as automatic Pilot rank is constantly promoted, roadway characteristic needs continuous
It refines and abundant.
Pre-processing image data unit is to the original road image data of the map of upload firstly the need of progress image rectification, figure
As a series of pretreatment such as coordinate transform, image projection transformation;For the image data under the same coordinate system after having handled,
Road behavioral characteristics, such as the depth good using precondition are extracted using the relevant AI technology such as deep learning, image recognition
Learning model identifies the dynamic road feature (signal lamp, pedestrian, automobile, bicycle, motorcycle) in high-precision map.
Multidimensional road information anastomosing and splicing is spliced for same road information in high-precision map, first in road spy
Sign level completes the analysis of roadway characteristic data fusion, finally completes image mosaic in image level, the result of splicing generates road
Top view, eventually by the mark of road attribute, roadway characteristic database visual edit generate Dynamic High-accuracy map.
Dynamic High-accuracy map datum processing system proposed by the present invention based on trackside sensor, incorporates wisdom road
Lamp, trackside camera, the infrastructure such as communication base station, can be effectively reduced accurately map generalization cost.Road in the present invention
The processing of side sensing data, the road feature extraction analysis based on AI, multidimensional roadway characteristic analysis fusion pass in server-side or cloud
Sense device end only needs to be responsible for the acquisition of data and uploads data to service background, therefore not excessive to sensing equipment terminal
The requirement of storage computing resource, realize the feasibility that entire map generates scheme.
As shown in figure 3, the present invention is based on the Dynamic High-accuracy map datum processing system workflows of trackside sensor such as
Under:
1), the covering of trackside camera.The present invention is used to acquire the camera installation and deployment of trackside image data in road
On the light pole of two sides, as the wisdomization in city develops, the related infrastructure construction of the street lamp of town road two sides is more
Perfect, distance is generally at 30 meters or so between town road street lamp.As shown in Figure 4, it is assumed that for acquiring the camera of trackside image
Visual angle is θ degree, and light pole is m meters a height of, and camera can acquire the range of imageRice.By calculating, as long as acquisition
The camera view angle theta of trackside image is greater thanCamera pickup area range l is then greater than 30 meters, is imaged based on trackside
The road data of head acquisition would not be omitted.
2) it, can be uploaded at server-side by some cycles for the camera data that roadway characteristic stablizes section
Reason, for the section (such as crossroad) that roadway characteristic is complicated and changeable or traffic active safety demand levels are high, need to shorten upload
Period of the image to server-side, it is ensured that the characteristic accurate and effective in the dynamic road section of acquisition.
3), city Internet of Things integration lamp stand covers.Internet of Things integration lamp stand can integrate Internet of Things charging pile, intelligence is shone
Functions, each sections such as bright, monitoring camera, micro weather station, electronic bulletin screen, alarm button integrate in modular fashion, can
According to circumstances flexibly apolegamy.The present invention utilizes the sensing equipment acquisition condition of road surface data on integrated lamp stand, integrated lamp stand
Upper each sensing equipment data handle server-side, map datum to map datum by the Common Gateway module transfer configured on lamp stand
Processing server-side can carry out that each section remotely control, long-range management, data acquisition, data are divided by unified management platform
Analysis, news release, malfunction monitoring etc..
4), image data space conversion process.Since the deployment of city street lamp is to be arranged with different positions, therefore carry exists
Camera deployment and arrangement mode on light pole are also not quite similar, and cannot guarantee the camera of all acquisition road image data
In the same plane, therefore needs are coordinately transformed to all original images and projective transformation processing.Adjacent bit that treated
The image overlay region for setting camera acquisition can be aligned, and the image after alignment splices convenient for subsequent road feature extraction and map
Image co-registration splicing.
5), roadway characteristic entity design.It is right according to automatic Pilot to the two aspect demand of content and precision of high-precision map
All roadway characteristics use hierarchical design.First layer is the static nature of road, and static nature information includes: Road lane
The basic informations such as position, traffic signals and the traffic sign position of line, road ID number, shape, the gradient, width.The second layer is
The semi-static nature on road: traffic rule information (such as tide section etc.), road construction information, extensively regional Weather information (rain
Snowy day gas) etc.;Third layer is half multidate information of roadway characteristic: traffic accident position, traffic congestion position, traffic ponding position
It sets, road hollow position, road barricade object location etc.;4th layer of roadway characteristic is multidate information: pedestrian, bicycle, rubs at automobile
The targets such as motorcycle changing coordinates, motion profile.Roadway characteristic design module the result is that by all link characteristic informations of design
The data entity and object being abstracted as in high-precision map, as shown in Figure 4, Figure 5.
6), road feature extraction.First layer static state roadway characteristic can carry out fining feature according to existing navigation map
Modeling, obtains each feature entity, is finally stored in the table of database using suitable data structure.The road of second and third layer
Road feature can do simple pretreatment (data screening verifying) by the road condition data that diagram data collection terminal reports over the ground, final to take out
Take corresponding semi-static and half behavioral characteristics.
7), the 4th layer of road behavioral characteristics are using deep learning, the related AI technology of image recognition from map image number
According to the pedestrian in middle identification road, automobile, bicycle, motorcycle.It is extensive first against one that map datum handles server-side
The image library comprising the object type such as pedestrian, automobile, bicycle, motorcycle carry out deep learning training, trained and established one
A model that can accurately identify road behavioral characteristics.It, can be fast and effective when map data collecting end uploads present road image
The traffic object feature that ground identification present road is included, the dynamic road feature that these are identified are updated to accurately
The 4th layer of corresponding database of feature of figure, then quickly can really feed back current condition of road surface.
8), road feature extraction is complete, and all features are stored in the database in the form of a complete data entity, the number
Roadway characteristic incremental update is supported according to library.
9), multidimensional roadway characteristic anastomosing and splicing.Sequence of operations is carried out based on accurate roadway characteristic database, completes road
The anastomosing and splicing of road feature, the anastomosing and splicing of roadway characteristic by it is above-mentioned 6), 7) in all roadway characteristics for extracting according to feature point
Layer is spliced, and is first spliced static nature, is finally merged behavioral characteristics.
10), 5) the trackside figure anastomosing and splicing after Image space transformation in is finally existed at a basic downward projection figure
Road information is marked on this image, comprising: road edge, lane line, crossing point etc., the information marked collectively constitutes high-precision
Spend the map datum of map;
11), by map data base data carry out visual edit, can be observed lane grade high-precision road-map and
Road behavioral characteristics, wherein data precision is up to Centimeter Level.Map data base once has the update of dynamic road feature, can quick body
Now on visual map.
Embodiment 2
As shown in figure 5, also a kind of Dynamic High-accuracy map data processing method based on trackside sensor of the present invention, packet
It includes:
S1, the original road image data of map and the original road conditions data of map for acquiring magnanimity;
S2, the pre- place that the original road image data of map are carried out to image rectification, image coordinate transformation, image projection transformation
Reason, the image overlay region of the image data acquiring module acquisition of adjacent position can be aligned after pretreatment;
S3, a deep learning road behavioral characteristics identification is established using deep learning, the related AI technology of image recognition
Model identifies that road dynamic is special using deep learning road behavioral characteristics identification model from the original road image data of map
Sign;
Fining feature modeling is carried out according to existing navigation map, obtains road static nature;
Data screening verifying is done by the original road conditions data of to map, extracts corresponding road semi-static nature and road
Half behavioral characteristics of road;
S4, hierarchical design is carried out to all roadway characteristics from content, first layer is road static nature, and the second layer is
Road semi-static nature, third layer are half behavioral characteristics of road, and the 4th layer is road behavioral characteristics;
S5, same road information is spliced, first completes roadway characteristic data fusion in roadway characteristic level, finally will
Pretreated image completes image mosaic in image level, and the result of splicing generates the downward projection figure of road;
S6, road information is marked on downward projection figure, the road information and downward projection figure marked collectively constitutes height
The map datum of precision map;
S7, calibration verification is carried out to the road information marked;
S8, map datum is carried out to visual edit, generates Dynamic High-accuracy map.
In step S1, using the original road image data of map of camera acquisition magnanimity, using GPS, temperature and humidity sensing
Device, ponding sensor locality primitive beginning road conditions data;
The camera is that carry is taken the photograph on security monitoring camera and Internet of Things wisdom light pole used in urban transportation
As head;GPS is the GPS Base Station in current smart city, and Temperature Humidity Sensor, ponding sensor are on Internet of Things wisdom light pole
Integrated Temperature Humidity Sensor, ponding sensor.
Compared with prior art, beneficial effects of the present invention are as follows:
1), the camera of present invention acquisition trackside image is deployed in trackside infrastructure (light pole, high hack lever), compares vehicle
The map datum for carrying camera acquisition has more real-time effectiveness;
2), the present invention passes through the multiple sensors terminal device of Internet of Things integration lamp stand carry, can acquire in real time high-precision
The Dynamic and Multi dimensional information (surface gathered water, humidity, weather, street sign indicator etc.) of map is spent, these information only need backstage to carry out letter
Single ground verification processing, so that it may be published to the application platform of high-precision map, real time service is in intelligent transportation field;
3), the map data collecting in the present invention takes full advantage of infrastructure (the wisdom street lamp, road of current smart city
Side camera, GPS Base Station), it is uploaded by the automatic collection of the trackside approach sensor and map datum of sharing smart city
Mode can reduce accurately map generalization cost from many aspects;
4), the present invention passes through to roadway characteristic hierarchical design, Dividing Characteristics anastomosing and splicing and the number for supporting incremental update
According to format storage, it can be achieved that the quick update of Dynamic High-accuracy map.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (8)
1. a kind of Dynamic High-accuracy map datum processing system based on trackside sensor characterized by comprising
Map data collecting end provides magnanimity, the map road original number of diversification for generating server-side for high-precision map
According to;
High-precision map generates server-side, and the map road of the magnanimity, diversification that provide for data collection terminal according to the map is former
Beginning data generate Dynamic High-accuracy map;
The high-precision map generates server-side
Map datum processing module, for map road initial data to be carried out road feature extraction, to all roadway characteristics
Using hierarchical design, same road information is spliced, first completes roadway characteristic data fusion in roadway characteristic level, finally
Image mosaic is completed in image level, the result of splicing generates the downward projection figure of road;
Map generates visualization model, for marking road information on downward projection figure, the road information and vertical view marked
Perspective view collectively constitutes the map datum of high-precision map, and map datum is carried out visual edit, with generating Dynamic High-accuracy
Figure;
The map datum processing module includes:
Pre-processing image data unit, for the original road image data of map to be carried out image rectification, image coordinate transformation, figure
As the pretreatment of projective transformation, the image overlay region of the image data acquiring module acquisition of adjacent position can be right after pretreatment
Together;
Road feature extraction unit, for identifying road behavioral characteristics from the original road image data of map;It is led according to existing
Boat map carries out fining feature modeling, obtains road static nature;Data sieve is done by the original road conditions data of to map
Choosing verifying, extracts half behavioral characteristics of corresponding road semi-static nature and road;
Roadway characteristic design cell, for carrying out hierarchical design to all roadway characteristics from content, first layer is that road is static
Feature, the second layer are road semi-static nature, and third layer is half behavioral characteristics of road, and the 4th layer is road behavioral characteristics;
Multidimensional road information anastomosing and splicing unit is first completed in roadway characteristic level for splicing same road information
Pretreated image is finally completed image mosaic in image level by roadway characteristic data fusion, and the result of splicing generates road
The downward projection figure on road;
The road feature extraction unit includes:
Behavioral characteristics extract subelement, for establishing a deep learning using the related AI technology of deep learning, image recognition
Road behavioral characteristics identification model, using deep learning road behavioral characteristics identification model from the original road image data of map
Identify road behavioral characteristics;
Static nature extracts subelement, and for carrying out fining feature modeling according to existing navigation map, it is static special to obtain road
Sign;
Semi-static nature extracts subelement, for doing data screening verifying, extraction pair by the original road conditions data of to map
The road semi-static nature answered;
Half behavioral characteristics extract subelement, for doing data screening verifying, extraction pair by the original road conditions data of to map
Half behavioral characteristics of road answered.
2. the Dynamic High-accuracy map datum processing system according to claim 1 based on trackside sensor, feature exist
In the map data collecting end includes:
Image data acquiring module, the original road image data of map for acquiring magnanimity;
Road condition data acquisition module, the original road conditions data of map for acquiring magnanimity.
3. the Dynamic High-accuracy map datum processing system according to claim 1 based on trackside sensor, feature exist
In the multidimensional road information anastomosing and splicing unit includes:
Roadway characteristic anastomosing and splicing subelement is first spelled for splicing all roadway characteristics extracted according to Dividing Characteristics
Static nature is connect, behavioral characteristics are finally merged;
Image mosaic subelement, for pretreated image to be carried out anastomosing and splicing into a basic downward projection figure.
4. the Dynamic High-accuracy map datum processing system according to claim 1 based on trackside sensor, feature exist
In the map generates visualization model and includes:
Geography information marks unit, and for marking road information on downward projection figure, the road information marked and vertical view are thrown
Shadow figure collectively constitutes the map datum of high-precision map;
Geography information calibration verification unit, for carrying out calibration verification to the road information marked;
Map generation unit generates Dynamic High-accuracy map for map datum to be carried out visual edit.
5. the Dynamic High-accuracy map datum processing system according to claim 2 based on trackside sensor, feature exist
In described image data acquisition module is camera, and the road condition data acquisition module includes GPS, Temperature Humidity Sensor, ponding
Sensor.
6. the Dynamic High-accuracy map datum processing system according to claim 5 based on trackside sensor, feature exist
In the camera is the camera of carry on security monitoring camera used in urban transportation and Internet of Things wisdom light pole;
GPS is the GPS Base Station in current smart city, and Temperature Humidity Sensor, ponding sensor are to integrate on Internet of Things wisdom light pole
Temperature Humidity Sensor, ponding sensor;The original road image data of map and the original road conditions data of map pass through Internet of Things
The Common Gateway module transfer configured on net wisdom light pole generates server-side to high-precision map.
7. a kind of Dynamic High-accuracy map data processing method based on trackside sensor characterized by comprising
S1, the original road image data of map and the original road conditions data of map for acquiring magnanimity;
S2, the original road image data of map are carried out to image rectification, image coordinate transformation, the pretreatment of image projection transformation,
The image overlay region of the image data acquiring module acquisition of adjacent position can be aligned after pretreatment;
S3, a deep learning road behavioral characteristics identification model is established using deep learning, the related AI technology of image recognition,
Road behavioral characteristics are identified from the original road image data of map using deep learning road behavioral characteristics identification model;
Fining feature modeling is carried out according to existing navigation map, obtains road static nature;
Data screening verifying is done by the original road conditions data of to map, extracts corresponding road semi-static nature and road half
Behavioral characteristics;
S4, hierarchical design is carried out to all roadway characteristics from content, first layer is road static nature, and the second layer is road half
Static nature, third layer are half behavioral characteristics of road, and the 4th layer is road behavioral characteristics;
S5, same road information is spliced, first completes roadway characteristic data fusion in roadway characteristic level, will finally locates in advance
Image after reason completes image mosaic in image level, and the result of splicing generates the downward projection figure of road;
S6, road information is marked on downward projection figure, the road information and downward projection figure marked collectively constitutes high-precision
The map datum of map;
S7, calibration verification is carried out to the road information marked;
S8, map datum is carried out to visual edit, generates Dynamic High-accuracy map.
8. the Dynamic High-accuracy map data processing method according to claim 7 based on trackside sensor, feature exist
In in step S1, using the original road image data of map of camera acquisition magnanimity, using GPS, Temperature Humidity Sensor, product
Water sensor locality primitive beginning road conditions data;
The camera is the camera of carry on security monitoring camera used in urban transportation and Internet of Things wisdom light pole;
GPS is the GPS Base Station in current smart city, and Temperature Humidity Sensor, ponding sensor are to integrate on Internet of Things wisdom light pole
Temperature Humidity Sensor, ponding sensor;The original road image data of map and the original road conditions data of map pass through Internet of Things
The Common Gateway module transfer configured on net wisdom light pole generates server-side to high-precision map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710359395.8A CN107229690B (en) | 2017-05-19 | 2017-05-19 | Dynamic High-accuracy map datum processing system and method based on trackside sensor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710359395.8A CN107229690B (en) | 2017-05-19 | 2017-05-19 | Dynamic High-accuracy map datum processing system and method based on trackside sensor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107229690A CN107229690A (en) | 2017-10-03 |
CN107229690B true CN107229690B (en) | 2019-01-25 |
Family
ID=59933329
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710359395.8A Active CN107229690B (en) | 2017-05-19 | 2017-05-19 | Dynamic High-accuracy map datum processing system and method based on trackside sensor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107229690B (en) |
Families Citing this family (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107958451A (en) * | 2017-12-27 | 2018-04-24 | 深圳普思英察科技有限公司 | Vision high accuracy map production method and device |
CN108010360A (en) * | 2017-12-27 | 2018-05-08 | 中电海康集团有限公司 | A kind of automatic Pilot context aware systems based on bus or train route collaboration |
CN108334078A (en) * | 2018-01-16 | 2018-07-27 | 宁波吉利汽车研究开发有限公司 | A kind of automatic Pilot method and system navigated based on high-precision map |
CN108469815A (en) * | 2018-02-27 | 2018-08-31 | 重庆嵩岳贸易服务有限公司 | A kind of self-navigation of computer deep learning and control loop and its method based on intention |
CN108762245B (en) * | 2018-03-20 | 2022-03-25 | 华为技术有限公司 | Data fusion method and related equipment |
US10867510B2 (en) * | 2018-04-05 | 2020-12-15 | Toyota Jidosha Kabushiki Kaisha | Real-time traffic monitoring with connected cars |
CN111699679B (en) * | 2018-04-27 | 2023-08-01 | 上海趋视信息科技有限公司 | Traffic system monitoring and method |
CN108846027A (en) * | 2018-05-24 | 2018-11-20 | 百度在线网络技术(北京)有限公司 | Map dynamic data acquisition methods, equipment and storage medium |
CN110599762A (en) * | 2018-06-12 | 2019-12-20 | 光宝电子(广州)有限公司 | Road condition sensing system and method |
AU2018278993A1 (en) | 2018-06-22 | 2020-01-16 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for updating highly automated driving maps |
DE102018211604A1 (en) * | 2018-07-12 | 2020-01-16 | Robert Bosch Gmbh | Mobile device and method for operating the mobile device |
CN109147317B (en) * | 2018-07-27 | 2021-07-27 | 中国科学院深圳先进技术研究院 | Automatic driving navigation system, method and device based on vehicle-road cooperation |
CN109215487A (en) * | 2018-08-24 | 2019-01-15 | 宽凳(北京)科技有限公司 | A kind of high-precision cartography method based on deep learning |
CN110940347B (en) * | 2018-09-21 | 2024-04-12 | 斑马智行网络(香港)有限公司 | Auxiliary vehicle navigation method and system |
CN110941684B (en) * | 2018-09-21 | 2023-06-13 | 阿里巴巴(中国)有限公司 | Map data production method, related device and system |
CN109189077B (en) * | 2018-10-30 | 2021-09-07 | 深圳市微科信息技术有限公司 | Intelligent driving assistance system and dynamic position navigator with satellite positioning function |
CN109515439B (en) * | 2018-11-13 | 2021-02-02 | 北京四维图新科技股份有限公司 | Automatic driving control method, device, system and storage medium |
CN111223302B (en) * | 2018-11-23 | 2021-12-03 | 明创能源股份有限公司 | External coordinate real-time three-dimensional road condition auxiliary device for mobile carrier and system |
CN109636881A (en) * | 2018-12-19 | 2019-04-16 | 沈阳天择智能交通工程有限公司 | Based on AI identification technology traffic accident situ sketch drafting method |
CN111354206B (en) * | 2018-12-21 | 2021-12-07 | 长沙智能驾驶研究院有限公司 | Road information processing method, road side unit, vehicle-mounted device and storage medium |
CN109657031B (en) * | 2018-12-28 | 2020-08-04 | 国汽(北京)智能网联汽车研究院有限公司 | High-precision dynamic map generation and application method based on intelligent networked automobile |
CN109976332A (en) * | 2018-12-29 | 2019-07-05 | 惠州市德赛西威汽车电子股份有限公司 | One kind being used for unpiloted accurately graph model and autonomous navigation system |
CN110082123A (en) * | 2019-05-05 | 2019-08-02 | 中国汽车工程研究院股份有限公司 | A kind of automatic Pilot automatization test system |
CN110208787A (en) * | 2019-05-05 | 2019-09-06 | 北京航空航天大学 | A kind of intelligent network connection autonomous driving vehicle auxiliary perception road lamp system based on V2I |
CN110470311A (en) * | 2019-07-08 | 2019-11-19 | 浙江吉利汽车研究院有限公司 | A kind of ground drawing generating method, device and computer storage medium |
CN110164157A (en) * | 2019-07-16 | 2019-08-23 | 华人运通(上海)新能源驱动技术有限公司 | Roadside device, the method for roadside device and bus or train route cooperative system |
CN110544376B (en) * | 2019-08-19 | 2021-06-22 | 新奇点智能科技集团有限公司 | Automatic driving assistance method and device |
CN110488830B (en) * | 2019-08-26 | 2021-11-19 | 吉林大学 | High-precision map information pre-analysis system and pre-analysis method for intelligent vehicle speed energy-saving planning |
CN110609502A (en) * | 2019-09-26 | 2019-12-24 | 武汉市珞珈俊德地信科技有限公司 | Assembled map data processing system |
CN110827578B (en) * | 2019-10-23 | 2022-05-10 | 江苏广宇协同科技发展研究院有限公司 | Vehicle anti-collision prompting method, device and system based on vehicle-road cooperation |
CN111176279B (en) * | 2019-12-31 | 2023-09-26 | 北京四维图新科技股份有限公司 | Determination method, device, equipment and storage medium for vulnerable crowd area |
CN111210622B (en) * | 2020-01-02 | 2021-02-26 | 北京启心明智科技有限公司 | Automatic driving road point data acquisition and maintenance method for non-fixed road |
CN111583630B (en) * | 2020-04-10 | 2022-01-07 | 河北德冠隆电子科技有限公司 | Brand-new road high-precision map rapid generation system and method based on space-time trajectory reconstruction |
CN111540237B (en) * | 2020-05-19 | 2021-09-28 | 河北德冠隆电子科技有限公司 | Method for automatically generating vehicle safety driving guarantee scheme based on multi-data fusion |
CN114088059B (en) * | 2020-07-29 | 2024-06-11 | 珠海星客合创科技有限公司 | Map information acquisition method based on intelligent street lamp and environment map construction method |
CN114079884A (en) * | 2020-08-14 | 2022-02-22 | 大唐高鸿智联科技(重庆)有限公司 | Transmission control method, device, equipment and terminal for map data |
CN112097779A (en) * | 2020-09-15 | 2020-12-18 | 黑龙江省交投千方科技有限公司 | Data service system based on roadside high-precision map |
CN112256811B (en) * | 2020-10-19 | 2022-04-29 | 武汉中海庭数据技术有限公司 | Map information representation method and device based on map structure |
CN112991808B (en) * | 2020-12-29 | 2022-09-30 | 杭州海康威视数字技术股份有限公司 | Parking space display method and device for parking area and electronic equipment |
CN113077632A (en) * | 2021-06-07 | 2021-07-06 | 四川紫荆花开智能网联汽车科技有限公司 | V2X intelligent network connection side system and realizing method |
CN113701770A (en) * | 2021-07-16 | 2021-11-26 | 西安电子科技大学 | High-precision map generation method and system |
CN114120631B (en) * | 2021-10-28 | 2023-03-24 | 新奇点智能科技集团有限公司 | Method and device for constructing dynamic high-precision map and traffic cloud control platform |
CN114419572B (en) * | 2022-03-31 | 2022-06-17 | 国汽智控(北京)科技有限公司 | Multi-radar target detection method and device, electronic equipment and storage medium |
CN114822026A (en) * | 2022-04-22 | 2022-07-29 | 南京泛在地理信息产业研究院有限公司 | Intelligent fusion method for acquiring scene data of holographic map |
CN114937367A (en) * | 2022-05-20 | 2022-08-23 | 苏州天准科技股份有限公司 | Intelligent camera system for cooperative monitoring of vehicle and road and control method |
CN115002196B (en) * | 2022-05-25 | 2024-01-26 | 国汽智图(北京)科技有限公司 | Data processing method and device and vehicle end acquisition equipment |
CN115100631A (en) * | 2022-07-18 | 2022-09-23 | 浙江省交通运输科学研究院 | Road map acquisition system and method for multi-source information composite feature extraction |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036277A (en) * | 2014-06-03 | 2014-09-10 | 中国科学院电子学研究所 | Method and equipment for extracting road characteristics |
CN104296763A (en) * | 2013-07-17 | 2015-01-21 | 哈曼贝克自动系统股份有限公司 | Method of displaying a map view and navigation device |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001142393A (en) * | 1999-11-17 | 2001-05-25 | Asia Air Survey Co Ltd | Method for preparing green coverage ratio map or green view map |
CN101893443B (en) * | 2010-07-08 | 2012-03-21 | 上海交通大学 | System for manufacturing road digital orthophoto map |
CN103294775B (en) * | 2013-05-10 | 2016-12-28 | 苏州祥益网络科技有限公司 | Police service cloud image recognition vehicle administrating system based on geographic space-time constraint |
CN103700261A (en) * | 2014-01-03 | 2014-04-02 | 河海大学常州校区 | Video-based road traffic flow feature parameter monitoring and traffic comprehensive information service system |
CN104535070B (en) * | 2014-12-26 | 2017-11-14 | 上海交通大学 | Graph data structure, collection and processing system and method in high-precision |
CN106441319B (en) * | 2016-09-23 | 2019-07-16 | 中国科学院合肥物质科学研究院 | A kind of generation system and method for automatic driving vehicle lane grade navigation map |
CN106525057A (en) * | 2016-10-26 | 2017-03-22 | 陈曦 | Generation system for high-precision road map |
-
2017
- 2017-05-19 CN CN201710359395.8A patent/CN107229690B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104296763A (en) * | 2013-07-17 | 2015-01-21 | 哈曼贝克自动系统股份有限公司 | Method of displaying a map view and navigation device |
CN104036277A (en) * | 2014-06-03 | 2014-09-10 | 中国科学院电子学研究所 | Method and equipment for extracting road characteristics |
Also Published As
Publication number | Publication date |
---|---|
CN107229690A (en) | 2017-10-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107229690B (en) | Dynamic High-accuracy map datum processing system and method based on trackside sensor | |
CN111542860B (en) | Sign and lane creation for high definition maps of autonomous vehicles | |
CN106441319B (en) | A kind of generation system and method for automatic driving vehicle lane grade navigation map | |
US9222786B2 (en) | Methods and systems for creating digital transportation networks | |
CN110378293B (en) | Method for producing high-precision map based on live-action three-dimensional model | |
US11521487B2 (en) | System and method to generate traffic congestion estimation data for calculation of traffic condition in a region | |
CN109643367A (en) | Crowdsourcing and the sparse map of distribution and lane measurement for autonomous vehicle navigation | |
CN110702132B (en) | Method for acquiring map data of micro-road network based on road marking points and road attributes | |
CN111797001A (en) | Method for constructing automatic driving simulation test model based on SCANeR | |
CN111566664A (en) | Method, apparatus and system for generating synthetic image data for machine learning | |
CN102110128A (en) | Traffic information conversion method and device based on traffic information element knowledge base | |
CN108428254A (en) | The construction method and device of three-dimensional map | |
CN106568456A (en) | Non-stop toll collection method based on GPS/Beidou positioning and cloud computing platform | |
CN113358125B (en) | Navigation method and system based on environment target detection and environment target map | |
CN103853155A (en) | Intelligent vehicle road junction passing method and system | |
CN108388995B (en) | Method and system for establishing road asset management system | |
CN114518122A (en) | Driving navigation method, driving navigation device, computer equipment, storage medium and computer program product | |
CN116597690B (en) | Highway test scene generation method, equipment and medium for intelligent network-connected automobile | |
CN109101743A (en) | A kind of construction method of high-precision road net model | |
CN115063978A (en) | Bus arrival time prediction method based on digital twins | |
Kang et al. | Hidam: A unified data model for high-definition (hd) map data | |
CN115393745A (en) | Automatic bridge image progress identification method based on unmanned aerial vehicle and deep learning | |
CN115965755A (en) | High-precision map data storage medium and high-precision map automatic generation method | |
Taal et al. | Procedural Generation of Traffic Signs. | |
Wang et al. | Lightweight High-precision Map for Specific Scenes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |