CN104280036B - A kind of detection of transport information and localization method, device and electronic equipment - Google Patents
A kind of detection of transport information and localization method, device and electronic equipment Download PDFInfo
- Publication number
- CN104280036B CN104280036B CN201310280993.8A CN201310280993A CN104280036B CN 104280036 B CN104280036 B CN 104280036B CN 201310280993 A CN201310280993 A CN 201310280993A CN 104280036 B CN104280036 B CN 104280036B
- Authority
- CN
- China
- Prior art keywords
- described image
- space coordinates
- gps
- pixel
- laser scanner
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
-
- 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
- G08G1/09623—Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The embodiment of the present invention provides a kind of detection of transport information and localization method, device and electronic equipment.Including：Obtain the laser distance data for image and the laser scanner scanned point that scanning object obtains when image collecting device shoots object that image collecting device shooting object obtains；According to the space coordinates and the scanned space coordinates put of spatial attitude determination of calibrating parameters, laser distance data and mobile collection equipment when image collecting device shoots object；The space coordinates of corresponding relation and scanned point according to corresponding to objects in images between pixel point set and the corresponding angle set of scanned point determines space coordinates corresponding to each pixel；Judge traffic mark whether is included in image, obtain judged result；Pixel corresponding to traffic mark and the space coordinates using space coordinates corresponding to pixel as traffic mark in image are selected from pixel point set when judged result is to be.The embodiment of the present invention improves detection and the location efficiency of traffic mark thing.
Description
Technical field
The present invention relates to electronic map technique field, more particularly to a kind of detection of transport information and localization method, device
And electronic equipment.
Background technology
One of important working link is the traffic such as extraction traffic sign, traffic marking in navigation map data production process
Marker, mainly extract with properties：Locus；Species；Particular content.
The detection of existing traffic sign with positioning is carried out by manual type, for example, operator holds PDA collection traffic
The attribute of label.
The detection of existing traffic marking with positioning is carried out by manual type, for example, operator holds PDA, using beating
Point operating type, every fixed range, gather the point position information on traffic marking.
However, detection and positioning method using above-mentioned traffic mark thing, operator needs to stop in operation field, so as to
Need to consume substantial amounts of manpower and materials, efficiency is low.
The content of the invention
In view of this, the purpose of the embodiment of the present invention be to provide a kind of detection of transport information and localization method, device and
Electronic equipment, to improve the detection of traffic mark thing and location efficiency.
In order to solve the above technical problems, offer of embodiment of the present invention scheme is as follows：
The embodiment of the present invention, which provides a kind of detection of transport information and localization method, methods described, to be included：
Object obtains in image collecting device shooting described image harvester angular field of view image and laser is obtained to sweep
Retouch instrument described image harvester shoot the object when, scan the object that the object obtains scanned point swash
Electrical distance data；
According to the calibrating parameters of the laser scanner, the laser distance data and mobile collection equipment in described image
Harvester shoots the space coordinates and spatial attitude during the object, determines the space coordinates of the scanned point；
The pixel point set corresponding to object according to described image and the scanned point pair in the angular field of view
The space coordinates of corresponding relation and the scanned point between the angle set answered, determines each picture in the pixel point set
Space coordinates corresponding to vegetarian refreshments；
Judge traffic mark whether is included in described image, obtain judged result；
When the judged result for when being, traffic mark is corresponding described in selection described image from the pixel point set
Pixel, and using space coordinates corresponding to pixel corresponding to the traffic mark as the traffic mark space sit
Mark；
Wherein, described image harvester and the laser scanner are arranged in the mobile collection equipment；It is described to swash
The calibrating parameters of photoscanner are relative position and relative attitude of the laser scanner relative to the mobile collection equipment
Calibrating parameters.
Preferably, methods described also includes：
GPS/IMU harvesters are obtained when described image harvester shoots the object, the movement of collection is adopted
Collect the GPS/IMU data of equipment and the gps data of GPS Base Station collection；
According to the GPS/IMU data and the gps data, determine that the mobile collection equipment gathers in described image and fill
Put the space coordinates and spatial attitude when shooting the object；
Wherein, the GPS/IMU harvesters are arranged in the mobile collection equipment, the GPS Base Station and the shifting
Geographical position matching of the dynamic collecting device when described image harvester shoots the object.
Preferably, methods described also includes：
According to the camera calibration parameter of the calibrating parameters of the laser scanner and described image harvester, it is determined that described
Corresponding relation；
Wherein, the camera calibration parameter is relative position of the described image harvester relative to the mobile collection equipment
Put and relative attitude calibrating parameters.
Preferably, when the judged result for when being, methods described also includes：
The property parameters of the traffic mark are determined according to described image.
Preferably, described image harvester is video acquisition device, and the acquisition image collecting device shoots the figure
As the image that object obtains in harvester angular field of view specifically includes：
Described image is extracted from the frame of video of video acquisition device collection.
The embodiment of the present invention also provides detection and the positioner of a kind of transport information, and described device includes：
First acquisition module, obtained for obtaining object in image collecting device shooting described image harvester angular field of view
The image and laser scanner arrived scans the thing that the object obtains when described image harvester shoots the object
The laser distance data of the scanned point of body；
First determining module, for the calibrating parameters according to the laser scanner, the laser distance data and movement
Space coordinates and spatial attitude of the collecting device when described image harvester shoots the object, determine the scanned point
Space coordinates；
Second determining module, for pixel point set corresponding to the object according to described image and the angular field of view
The space coordinates of corresponding relation and the scanned point between angle set corresponding to the interior scanned point, determines the picture
Each space coordinates corresponding to pixel in vegetarian refreshments set；
Judge module, for judging traffic mark whether is included in described image, obtain judged result；
First processing module, for when the judged result is to be, described image to be selected from the pixel point set
Described in pixel corresponding to traffic mark, and using space coordinates corresponding to pixel corresponding to the traffic mark as described in
The space coordinates of traffic mark；
Wherein, described image harvester and the laser scanner are arranged in the mobile collection equipment；It is described to swash
The calibrating parameters of photoscanner are relative position and relative attitude of the laser scanner relative to the mobile collection equipment
Calibrating parameters.
Preferably, described device also includes：
Second acquisition module, for obtaining GPS/IMU harvesters when described image harvester shoots the object,
The gps data of GPS/IMU data and the GPS Base Station collection of the mobile collection equipment of collection；
3rd determining module, for according to the GPS/IMU data and the gps data, determining that the mobile collection is set
Standby space coordinates and spatial attitude when described image harvester shoots the object；
Wherein, the GPS/IMU harvesters are arranged in the mobile collection equipment, the GPS Base Station and the shifting
Geographical position matching of the dynamic collecting device when described image harvester shoots the object.
Preferably, described device also includes：
4th determining module, for the calibrating parameters according to the laser scanner and the camera of described image harvester
Calibrating parameters, determine the corresponding relation；
Wherein, the camera calibration parameter is relative position of the described image harvester relative to the mobile collection equipment
Put and relative attitude calibrating parameters.
Preferably, described device also includes：
5th determining module, for when the judged result is to be, the traffic mark to be determined according to described image
Property parameters.
The embodiment of the present invention also provides a kind of detection including above-described transport information and the electronics of positioner is set
It is standby.
The embodiment of the present invention at least has the advantages that：
The image and swash that object obtains in described image harvester angular field of view are shot by obtaining image collecting device
Photoscanner scans the scanned point for the object that the object obtains when described image harvester shoots the object
Laser distance data, determine therefrom that the space coordinates of the scanned point, determine therefrom that picture corresponding to object described in image
Each space coordinates corresponding to pixel in vegetarian refreshments set, will be from pixel point set when including traffic mark in described image
Sky of the space coordinates as the traffic mark described in the described image of selection corresponding to traffic mark corresponding to pixel
Between coordinate, and image collecting device and laser scanner are arranged in mobile collection equipment, so as to be set using mobile collection
The standby space coordinates that traffic mark is automatically derived by way of image taking and laser scanning, reduces disappearing for manpower and materials
Consumption, improve detection and the location efficiency of traffic mark thing.
Brief description of the drawings
Fig. 1 represents a kind of detection of transport information provided in an embodiment of the present invention and the step flow chart of localization method；
Fig. 2 represents the collection of traffic sign graticule, detection and the positioning process stream of the preferred embodiment of the embodiment of the present invention
Cheng Tu；
Fig. 3 A represent the front view of the panoramic view data collecting vehicle of the preferred embodiment of the embodiment of the present invention；
Fig. 3 B represent the top view of the panoramic view data collecting vehicle of the preferred embodiment of the embodiment of the present invention；
Fig. 4 represents traffic sign detection and the positioning schematic diagram of the preferred embodiment of the embodiment of the present invention；
Fig. 5 represents traffic marking detection and the positioning schematic diagram of the preferred embodiment of the embodiment of the present invention.
Embodiment
It is below in conjunction with accompanying drawing and specifically real to make the purpose, technical scheme and advantage of the embodiment of the present invention clearer
Example is applied the embodiment of the present invention is described in detail.
Fig. 1 represents a kind of detection of transport information provided in an embodiment of the present invention and the step flow chart of localization method, ginseng
According to Fig. 1, the embodiment of the present invention provides a kind of detection of transport information and localization method, methods described comprise the following steps：
Step 101, the image that object obtains in image collecting device shooting described image harvester angular field of view is obtained
With laser scanner when described image harvester shoots the object, being swept for the object that the object obtains is scanned
The laser distance data of described point；
Step 102, existed according to the calibrating parameters of the laser scanner, the laser distance data and mobile collection equipment
Described image harvester shoots the space coordinates and spatial attitude during the object, determines that the space of the scanned point is sat
Mark；
Step 103, the pixel point set corresponding to object according to described image and the quilt in the angular field of view
The space coordinates of corresponding relation and the scanned point between angle set corresponding to scanning element, determines the pixel point set
In space coordinates corresponding to each pixel；
Step 104, judge traffic mark whether is included in described image, obtain judged result；
Step 105, when the judged result is to be, traffic described in described image is selected from the pixel point set
Pixel corresponding to mark, and using space coordinates corresponding to pixel corresponding to the traffic mark as the traffic mark
Space coordinates；
Wherein, described image harvester and the laser scanner are arranged in the mobile collection equipment；It is described to swash
The calibrating parameters of photoscanner are relative position and relative attitude of the laser scanner relative to the mobile collection equipment
Calibrating parameters.
It can be seen that shoot the image that object obtains in described image harvester angular field of view by obtaining image collecting device
When shooting the object with laser scanner described image harvester, the scanned of the object that the object obtains is scanned
The laser distance data of point, determine therefrom that the space coordinates of the scanned point, determine therefrom that described in image corresponding to object
Each space coordinates corresponding to pixel in pixel point set, will be from pixel point set when including traffic mark in described image
Space coordinates described in the described image of middle selection corresponding to traffic mark corresponding to pixel is as the traffic mark
Space coordinates, but image collecting device and laser scanner are arranged in mobile collection equipment, so as to utilize mobile collection
Equipment automatically derives the space coordinates of traffic mark by way of image taking and laser scanning, reduces disappearing for manpower and materials
Consumption, improve detection and the location efficiency of traffic mark thing.
Wherein, the traffic mark is for example：Traffic sign, traffic marking etc..
Pixel corresponding to the traffic mark is for example：Central pixel point in regional extent corresponding to the traffic mark.
In embodiments of the present invention, space of the mobile collection equipment when described image harvester shoots the object is sat
Mark and spatial attitude can obtain in several ways, for example, have recorded the space coordinates of relatively low precision in vehicle GPS
With the attitude information recorded in IMU, or, can then have by way of ground GPS base station aids in：
Methods described also includes：
GPS/IMU harvesters are obtained when described image harvester shoots the object, the movement of collection is adopted
Collect the GPS/IMU data of equipment and the gps data of GPS Base Station collection；
According to the GPS/IMU data and the gps data, determine that the mobile collection equipment gathers in described image and fill
Put the space coordinates and spatial attitude when shooting the object；
Wherein, the GPS/IMU harvesters are arranged in the mobile collection equipment, the GPS Base Station and the shifting
Geographical position matching of the dynamic collecting device when described image harvester shoots the object.
Here, the GPS Base Station and the mobile collection equipment are when described image harvester shoots the object
Geographical position matching specifically refers to：The space of the base station to the effect that at different moments of the gps data of GPS Base Station collection is sat
Mark, these data and vehicle GPS data are combined, and are handled by GPS difference processings mode, time match and interpolation etc., can
To obtain moving the space coordinates and spatial attitude of collecting device during image collecting device shooting.
Mention in embodiments of the present invention, the calibrating parameters of the laser scanner are the laser scanner relative to institute
The relative position and relative attitude calibrating parameters of mobile collection equipment are stated, relative position therein and relative attitude calibrating parameters can
To be the absolute coordinate space of the mobile collection equipment（Longitude, latitude, elevation）And spatial attitude（Course angle, the angle of pitch, turn over
Roll angle）One timing, the absolute coordinate space and spatial attitude of the laser scanner, such as：The laser scanned to left front is swept
The parameter for retouching instrument is as follows（To pass through guiding center as three-dimensional system of coordinate origin, pass through and lead immediately ahead of major axis sensing car body, denotation coordination system
X-axis, vertically upward direction is z-axis, pass through lead barycenter point to car body front-right direction be y-axis）：
The angle of laser scanner major axis and direct north is -44.396744 degree（Course angle）, laser scanner with it is horizontal
The angle in face is 7.095467 degree（The angle of pitch）, angle that laser scanner is rotated using the line from barycenter to front as axis
It is 5.713794 degree（Roll angle）.The offset x-axis direction that laser scanner barycenter leads barycenter relative to passing through is -0.672257
Rice, offset y-axis direction are 0.316548 meter, and offset z-axis direction is 0.824497 meter.
In accordance with same coordinate system and method, the parameter of the laser scanner scanned to right front is as follows：Laser scanner
The angle of major axis and direct north is 45.512610 degree（Course angle）, the angle of laser scanner and horizontal plane is 6.891124
Degree（The angle of pitch）, angle degree of being -6.071868 that laser scanner is rotated using the line from barycenter to front as axis（Rolling
Angle）.The offset x-axis direction that laser scanner barycenter leads barycenter relative to passing through is 0.708636 meter, and offset y-axis direction is
0.579373 meter, offset z-axis direction is 1.011257 meters.
It is to the following laser scanner major axis of parameter of laser scanner and the angle of direct north of front scanning
8.797984 degree（Course angle）, the angle of laser scanner and horizontal plane is -22.203003（The angle of pitch）, laser scanner with
From barycenter to the angle degree of being 3.377729 that the line in front is axis rotation（Roll angle）.Laser scanner barycenter relative to
Pass through lead barycenter offset x-axis direction be -0.822082 meter, offset y-axis direction be 0.620520 meter, offset z-axis direction
For 1.205419 meters.
Correspondingly, it is described to be set according to the calibrating parameters of the laser scanner, the laser distance data and mobile collection
Standby space coordinates and spatial attitude when described image harvester shoots the object, determine the space of the scanned point
Coordinate is for example：（39.235763 116.382385,37.238789）（Latitude under wgs84 coordinate systems（Unit degree）, longitude（Unit
Degree）, elevation（Unit rice））.
In embodiments of the present invention, pixel point set regards with described corresponding to object according to described image described
The space coordinates of corresponding relation and the scanned point in angular region between angle set corresponding to the scanned point, it is determined that
In the pixel point set it is each corresponding to pixel the step of space coordinates in, to any pixel point in the pixel point set
The determination mode of corresponding space coordinates is specifically as follows：
According to the corresponding relation, first angle corresponding to any pixel point is selected in the angle set；
The space coordinates of corresponding to the first angle in the scanned point first scanned point is defined as described any
Space coordinates corresponding to pixel.
In embodiments of the present invention, the corresponding relation can be according to described image harvester and the laser scanner
The specific setting in the mobile collection equipment is arranged on to determine.
Thus, methods described can also include：
According to the camera calibration parameter of the calibrating parameters of the laser scanner and described image harvester, it is determined that described
Corresponding relation；
Wherein, the camera calibration parameter is relative position of the described image harvester relative to the mobile collection equipment
Put and relative attitude calibrating parameters.
Here relative position therein and relative attitude calibrating parameters can be the absolute sky of the mobile collection equipment
Between coordinate（Longitude, latitude, elevation）And spatial attitude（Course angle, the angle of pitch, roll angle）One timing, described image harvester
Absolute coordinate space and spatial attitude, such as：The camera calibration parameter is as follows：
Panorama camera（Assembled by 8 individual camera splicings, numbered from 0 to 7, it is complete in image below figure 3A and Fig. 3 B
Shown in scape camera schematic diagram）In the angle of No. 0 camera axis and direct north be 35 degree（Course angle）, panorama camera and horizontal plane
Angle be 0.5 degree（The angle of pitch）, panorama camera is 0.6 degree by the angle that axis rotates of the line from barycenter to front
（Roll angle）.The offset x-axis direction that panorama camera barycenter leads barycenter relative to passing through is 0.219 meter, and offset y-axis direction is
0.755 meter, offset z-axis direction is 1.767 meters.
Correspondingly, it is described to be joined according to the calibrating parameters of the laser scanner and the camera calibration of described image harvester
Number, road surface camera is determined to pass through the calibrating parameters led under three-dimensional system of coordinate of the barycenter as the origin of coordinates, so that it is determined that corresponding
Skew and posture relation.
In embodiments of the present invention, in order to outside being positioned to traffic mark, realize the inspection to traffic mark attribute
Survey, Ke Yiyou：
When the judged result for when being, methods described also includes：
The property parameters of the traffic mark are determined according to described image.
Wherein, the property parameters are for example：The type of traffic sign, the type of traffic marking etc..The type of traffic sign
Such as：Label/the Pointing sign board/Warning board/that shows the way forbids label etc..The type of traffic marking is for example：Left-hand bend arrow/right-hand rotation
Curved arrow/straight trip arrow etc..
In embodiments of the present invention, described image harvester is for example：Camera, video acquisition device etc..For the figure
As the situation that harvester is video acquisition device, acquisition image collecting device shooting described image harvester visual angle model
Enclosing the image that interior object obtains can specifically include：
Described image is extracted from the frame of video of video acquisition device collection.
Wherein, the video acquisition device is for example：Camera, video camera etc..
It is clear in order to which the embodiment of the present invention is expanded on further, below with the detection for traffic sign graticule with being positioned as
Example, there is provided the preferred embodiment of the embodiment of the present invention.
In the preferred embodiment, the mobile collection equipment is panoramic view data collecting vehicle；Described image harvester
For panorama camera；The video acquisition device is road surface camera；The GPS/IMU harvesters are GPS/IMU collecting devices；
Panorama camera, road surface camera, GPS/IMU collecting devices and laser scanner are integrated in panoramic view data as sensor
On the vehicular platform of collecting vehicle roof.
Specifically, reference picture 3A and Fig. 3 B, panoramic view data collecting vehicle horizontal direction are placed；The angular field of view of panorama camera exists
Horizontal direction is 360 degree, is 290 degree in vertical direction；Road surface camera can shoot the video in car traveling road ahead face；Laser
Scanner has 3, be provided in respectively panorama camera Chinese herbaceous peony direction, can scanning car traveling road ahead face laser scanner
（Horizontal sweep）, be arranged on panorama camera car left direction, can scanning car travel left side object laser scanner（Hang down
Straight scanning）, and be arranged on panorama camera car right direction, can scanning car travel right side object laser scanner
（Vertical scanning）；GPS/IMU collecting devices can obtain high precision position, elevation information.
Also it is integrated with such as lower sensor on vehicular platform：
Wheel encoder, its effect include：Recoverable IMU（Pass through and lead）Rate error, improve system motion track precision；Match somebody with somebody
Panorama camera is closed, the distance interval of shooting is set, can effectively reduce the data volume of panoramic picture.
Fig. 2 represents the collection of traffic sign graticule, detection and the positioning process stream of the preferred embodiment of the embodiment of the present invention
Cheng Tu, reference picture 2, this preferred embodiment based on panoramic view data collecting vehicle, for traffic sign graticule, carry out data and adopt
Collection, processing, detection and the complete process flow of positioning include collection preparation, data acquisition, data processing and data application four
Stage.Wherein,
<Gather the preparatory stage>
The collection preparatory stage includes：Data collection arrangement and acquisition tasks planning, GPS Base Station are laid and acquisition system inspection
School.Specifically,
Firstly the need of according to actual task needs, collecting and with the arranging data acquisition road information of attributed region, traffic
Information, complete acquisition tasks planning is formulated, it is final to determine collection route.
In the preparation of collection, according to GPS signal cover and the actual state of the elevation of pickup area,
The decorating position of base station is determined, and performs a series of initial configurations operation when base station is opened so that base station can correctly adopt
Collect spatial coordinated information, the difference post processing for the GPS that can be used in post-processing stages.
Before acquisition, it is necessary to carry out the demarcation and self-test of various collecting devices to collection corollary equipment.Wherein,
Collecting device demarcation includes：GPS/IMU demarcation；The demarcation of panorama camera；The demarcation of laser scanner；Road surface
The demarcation of camera.
Collecting device demarcation is mainly to ensure the correctness and availability of gathered data, four collections included to system
The demarcation that equipment is carried out：
To gps antenna and IMU（Pass through and lead）Demarcated, gps antenna and IMU（Pass through and lead）Combination, turn into a complete survey
Measure the subsystem of car body position and vehicle body attitude.Calibration result is used for the difference processing in gps data later stage.
Demarcation to panorama camera, panorama camera are made up of multiple cameras, and these cameras are in same moment, synchronous acquisition
Image, by the splicing in later stage, the image of these multiple one cameras can splice includes 360 degree of scopes as horizontal direction
Panoramic picture.Calibration result needs to use in image mosaic.
Demarcation to laser scanner, collecting vehicle roof are mounted with 3 laser scanners, respectively scan front, left,
The direction of right three.The laser initial data of collection is the distance between entity such as laser scanner and both sides of the road building number
According to, it is necessary to position and posture with reference to collecting vehicle（There is provided by GPS difference post processing result data）, solution be counted as both sides of the road building
The absolute three dimensional space coordinate of thing entity（x,y,z）, need to use the calibration result of laser scanner in resolving.And
Demarcation to road surface camera, road surface camera are arranged on roof both sides, one on one side.What road surface camera obtained
Video flowing, for extracting the traffic marking on road surface, it is necessary to use the demarcation knot of these road surface cameras in extraction process
Fruit.
System is primarily referred to as before system starts formal collection comprising self-test, the state of collecting device check and true
Recognize, comprising check acquisition software whether normal work, whether hardware device intact and normal work etc..
<Data acquisition phase>
Data acquisition phase includes：GPS Base Station gathers corollary equipment collection on gps data and the vehicular platform of collecting vehicle
Data.Wherein, collecting vehicle corollary equipment gathered data includes：Positioning and orientation system (Position and Orientation
System, POS) collection GPS/IMU data（Space coordinates, spatial attitude and acceleration of specially GPS/IMU collection car bodies etc.
Information）, laser scanner collection laser distance data, panoramic picture camera collection multi aspect images（Specially multi-faceted list
Width image photograph）And road surface video camera collection road surface video.
<Data processing stage>
Data processing stage includes：GPS/IMU difference generates car body position and attitude data, laser distance generation laser spots
Cloud, Panorama Mosaic and GPS/ laser point clouds/panoramic picture fusion.Data processing includes GPS/IMU, panoramic picture, swashed
The post processing of a variety of data such as photoscanner, road surface video.Specifically,
GPS/IMU difference processings, using GPS difference the poster processing softs, the gps data and vehicular platform of base station collection are adopted
The gps data of collection, difference post processing is carried out, high-precision gps data can be obtained, determine collecting vehicle in the space at each moment
Coordinate and vehicle body attitude.The gps data of post processing needs unification to be exported according to given TXT file specifications.
The splicing of panoramic picture, comprising the splicing between multi-faceted Single frame camera, it is necessary to pass through characteristic point in image
Extraction and registration, determine the stitching position of adjacent image, and the lap of image is handled.Panoramic picture needs unification
Exported according to jpeg file specification.
Laser distance generates laser point cloud, and mainly by the range data collected, number of results is post-processed with reference to GPS
According to the space coordinates that generation is each put, so as to form spatial point cloud.Laser point cloud data needs unified according to given TXT texts
Part specification is exported.
GPS/ laser point clouds/panoramic picture fusion, refer mainly to the grey scale pixel value of the pixel of panoramic picture being assigned to
Corresponding laser point cloud.
In the spherical coordinate system of panoramic picture, panoramic picture can project the inner surface of spheroid, use collecting vehicle
Course angle and panorama camera in current vehicle body attitude put in order, it may be determined that the angular field of view selected under spherical coordinate
The region of corresponding panoramic picture.Laser point cloud has space coordinates, when by laser point cloud in spheric coordinate system with panorama
When image synchronization is projected, from any one ray of ball centre（Above water）, can intersect at panorama
Pixel in image, the pixel necessarily have corresponding laser point cloud phase registration therewith, so, can be by panoramic picture
The grey scale pixel value of pixel assigns the laser point cloud.
<The data application stage>
The data application stage includes：Traffic sign detects and positioning and traffic marking detection and positioning.Wherein,
The detection of traffic sign can refer to Fig. 4 with positioning, specifically,
From panoramic picture, the image of camera shooting that can be based on some orientation, use pattern identification technology, handed over
The detection of logical label, can obtain the pixel point coordinates of traffic sign in the picture, while obtain the attribute of traffic sign, such as mark
The type of board：Label/the Pointing sign board/Warning board/that shows the way forbids label etc..
The detection of traffic marking can refer to Fig. 5 with positioning, specifically,
By detecting whether to include traffic marking, the corresponding frame for including traffic marking can be extracted from road plane video
Image.
To the image comprising traffic marking, based on mode identification technology, the detection of traffic marking is carried out, traffic can be obtained
The attribute of graticule, such as the type of traffic marking：Left-hand bend arrow/right-turn arrow/straight trip arrow etc., while traffic can be obtained
Pixel point coordinates of the graticule in the two field picture.
Using laser scanner calibrating parameters and road surface camera calibration parameter, using the image for extracting to obtain from video
And laser point cloud data, realize merging for image and laser point cloud.
In embodiments, the result based on the various Data Posts of panorama car, can be detected from image or video
Traffic sign and traffic marking, using the image and laser point cloud after fusion, traffic marking can be gone out in image with Direct Recognition, schemed
As pixel with laser point cloud is one-to-one, using laser point cloud as background, each laser point cloud has accurate three-dimensional
Space coordinates, it is possible to be accurately positioned the space coordinates of traffic sign and traffic marking.The data finally obtained, it is traffic mark
Attribute information and the space coordinates such as type of board, traffic marking.Traffic sign and traffic marking, the pass as map of navigation electronic
One of key key element, by this programme, realize the automated production of procedure.
It can be seen that this preferred embodiment gives the various collecting device over all Integrations for forming panorama collecting vehicle and installation side
Method；Give the technological process of the acquisition process based on panorama car, contained in this flow from collection prepare, data acquisition and
The complete technological process of gathered data post processing, the basic traffic such as such a method energy Quick Acquisition and processing road traffic facility
Information, data source is provided for traffic sign and traffic marking.Flow and side of the detection of traffic sign, traffic marking with positioning
Method, such a method are unique, and the detection of traffic sign and traffic marking can be quickly realized according to this flow and method, and
On the basis of image and laser point cloud fusion, the space orientation of traffic sign, traffic marking is realized.
The embodiment of the present invention also provides detection and the positioner of a kind of transport information, and described device includes：
First acquisition module, obtained for obtaining object in image collecting device shooting described image harvester angular field of view
The image and laser scanner arrived scans the thing that the object obtains when described image harvester shoots the object
The laser distance data of the scanned point of body；
First determining module, for the calibrating parameters according to the laser scanner, the laser distance data and movement
Space coordinates and spatial attitude of the collecting device when described image harvester shoots the object, determine the scanned point
Space coordinates；
Second determining module, for pixel point set corresponding to the object according to described image and the angular field of view
The space coordinates of corresponding relation and the scanned point between angle set corresponding to the interior scanned point, determines the picture
Each space coordinates corresponding to pixel in vegetarian refreshments set；
Judge module, for judging traffic mark whether is included in described image, obtain judged result；
First processing module, for when the judged result is to be, described image to be selected from the pixel point set
Described in pixel corresponding to traffic mark, and using space coordinates corresponding to pixel corresponding to the traffic mark as described in
The space coordinates of traffic mark；
Wherein, described image harvester and the laser scanner are arranged in the mobile collection equipment；It is described to swash
The calibrating parameters of photoscanner are relative position and relative attitude of the laser scanner relative to the mobile collection equipment
Calibrating parameters.
It can be seen that shoot the image that object obtains in described image harvester angular field of view by obtaining image collecting device
With laser scanner when described image harvester shoots the object, being swept for the object that the object obtains is scanned
The laser distance data of described point, the space coordinates of the scanned point is determined therefrom that, determine therefrom that object described in image is corresponding
Pixel point set in space coordinates corresponding to each pixel, will be from pixel point set when including traffic mark in described image
Space coordinates described in the described image selected in conjunction corresponding to traffic mark corresponding to pixel is as the traffic mark
Space coordinates, and image collecting device and laser scanner are arranged in mobile collection equipment, so as to be adopted using movement
Collection equipment automatically derives the space coordinates of traffic mark by way of image taking and laser scanning, reduces manpower and materials
Consumption, improve detection and the location efficiency of traffic mark thing.
Further, described device can also include：
Second acquisition module, for obtaining GPS/IMU harvesters when described image harvester shoots the object,
The gps data of GPS/IMU data and the GPS Base Station collection of the mobile collection equipment of collection；
3rd determining module, for according to the GPS/IMU data and the gps data, determining that the mobile collection is set
Standby space coordinates and spatial attitude when described image harvester shoots the object；
Wherein, the GPS/IMU harvesters are arranged in the mobile collection equipment, the GPS Base Station and the shifting
Geographical position matching of the dynamic collecting device when described image harvester shoots the object.
In addition, described device can also include：
4th determining module, for the calibrating parameters according to the laser scanner and the camera of described image harvester
Calibrating parameters, determine the corresponding relation；
Wherein, the camera calibration parameter is relative position of the described image harvester relative to the mobile collection equipment
Put and relative attitude calibrating parameters.
In addition, described device can also include：
5th determining module, for when the judged result is to be, the traffic mark to be determined according to described image
Property parameters.
The embodiment of the present invention also provides a kind of electronic equipment, and the electronic equipment includes the inspection of above-described transport information
Survey and positioner.The electronic equipment is for example：The data processing equipments such as computer.
Described above is only the embodiment of the embodiment of the present invention, it is noted that for the ordinary skill of the art
For personnel, on the premise of principle of the embodiment of the present invention is not departed from, some improvements and modifications can also be made, these improve and
Retouching also should be regarded as the protection domain of the embodiment of the present invention.
Claims (10)
1. detection and the localization method of a kind of transport information, it is characterised in that methods described includes：
Obtain the image and laser scanner that object obtains in image collecting device shooting described image harvester angular field of view
Described image harvester shoot the object when, scan the object that the object obtains scanned point laser away from
From data；
Gathered according to the calibrating parameters of the laser scanner, the laser distance data and mobile collection equipment in described image
Device shoots the space coordinates and spatial attitude during the object, determines the space coordinates of the scanned point；
The pixel point set corresponding to object according to described image is corresponding with the scanned point in the angular field of view
The space coordinates of corresponding relation and the scanned point between angle set, determines each pixel in the pixel point set
Corresponding space coordinates；
Judge traffic mark whether is included in described image, obtain judged result；
When the judged result is to be, picture corresponding to traffic mark described in described image is selected from the pixel point set
Vegetarian refreshments, and using space coordinates corresponding to pixel corresponding to the traffic mark as the space coordinates of the traffic mark；
Wherein, described image harvester and the laser scanner are arranged in the mobile collection equipment；The laser is swept
The calibrating parameters for retouching instrument are demarcated for the laser scanner relative to the relative position and relative attitude of the mobile collection equipment
Parameter.
2. according to the method for claim 1, it is characterised in that methods described also includes：
GPS/IMU harvesters are obtained when described image harvester shoots the object, the mobile collection of collection is set
Standby GPS/IMU data and the gps data of GPS Base Station collection；
According to the GPS/IMU data and the gps data, determine that the mobile collection equipment is clapped in described image harvester
Take the photograph the space coordinates and spatial attitude during the object；
Wherein, the GPS/IMU harvesters are arranged in the mobile collection equipment, and the GPS Base Station is adopted with the movement
Collect geographical position matching of the equipment when described image harvester shoots the object.
3. according to the method for claim 1, it is characterised in that methods described also includes：
According to the camera calibration parameter of the calibrating parameters of the laser scanner and described image harvester, the correspondence is determined
Relation；
Wherein, the camera calibration parameter be described image harvester relative to the mobile collection equipment relative position and
Relative attitude calibrating parameters.
4. according to the method for claim 1, it is characterised in that when the judged result for when being, methods described also includes：
The property parameters of the traffic mark are determined according to described image.
5. according to the method for claim 1, it is characterised in that described image harvester is video acquisition device, described
The image that object obtains in image collecting device shooting described image harvester angular field of view is obtained to specifically include：
Described image is extracted from the frame of video of video acquisition device collection.
6. detection and the positioner of a kind of transport information, it is characterised in that described device includes：
First acquisition module, shoot what object in described image harvester angular field of view obtained for obtaining image collecting device
Image and laser scanner scan the object that the object obtains when described image harvester shoots the object
The laser distance data of scanned point；
First determining module, for the calibrating parameters according to the laser scanner, the laser distance data and mobile collection
Space coordinates and spatial attitude of the equipment when described image harvester shoots the object, determine the sky of the scanned point
Between coordinate；
Second determining module, for institute in pixel point set corresponding to the object according to described image and the angular field of view
The space coordinates of the corresponding relation and the scanned point between angle set corresponding to scanned point is stated, determines the pixel
Each space coordinates corresponding to pixel in set；
Judge module, for judging traffic mark whether is included in described image, obtain judged result；
First processing module, for when the judged result is to be, institute in described image to be selected from the pixel point set
Pixel corresponding to traffic mark is stated, and using space coordinates corresponding to pixel corresponding to the traffic mark as the traffic
The space coordinates of mark；
Wherein, described image harvester and the laser scanner are arranged in the mobile collection equipment；The laser is swept
The calibrating parameters for retouching instrument are demarcated for the laser scanner relative to the relative position and relative attitude of the mobile collection equipment
Parameter.
7. device according to claim 6, it is characterised in that described device also includes：
Second acquisition module, for obtaining GPS/IMU harvesters when described image harvester shoots the object, collection
The mobile collection equipment GPS/IMU data and GPS Base Station collection gps data；
3rd determining module, for according to the GPS/IMU data and the gps data, determining that the mobile collection equipment exists
Described image harvester shoots the space coordinates and spatial attitude during the object；
Wherein, the GPS/IMU harvesters are arranged in the mobile collection equipment, and the GPS Base Station is adopted with the movement
Collect geographical position matching of the equipment when described image harvester shoots the object.
8. device according to claim 6, it is characterised in that described device also includes：
4th determining module, for the calibrating parameters according to the laser scanner and the camera calibration of described image harvester
Parameter, determine the corresponding relation；
Wherein, the camera calibration parameter be described image harvester relative to the mobile collection equipment relative position and
Relative attitude calibrating parameters.
9. device according to claim 6, it is characterised in that described device also includes：
5th determining module, for when the judged result is to be, the attribute of the traffic mark to be determined according to described image
Parameter.
10. a kind of electronic equipment, it is characterised in that detection including the transport information as described in any one of claim 6 to 9 with
Positioner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310280993.8A CN104280036B (en) | 2013-07-05 | 2013-07-05 | A kind of detection of transport information and localization method, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310280993.8A CN104280036B (en) | 2013-07-05 | 2013-07-05 | A kind of detection of transport information and localization method, device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104280036A CN104280036A (en) | 2015-01-14 |
| CN104280036B true CN104280036B (en) | 2017-11-17 |
Family
ID=52255161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310280993.8A Active CN104280036B (en) | 2013-07-05 | 2013-07-05 | A kind of detection of transport information and localization method, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104280036B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112634643B (en) * | 2015-05-29 | 2022-06-14 | 荣耀终端有限公司 | Traffic information updating method and device |
| CN105069842A (en) * | 2015-08-03 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Modeling method and device for three-dimensional model of road |
| CN106560835B (en) * | 2015-09-30 | 2019-05-24 | 高德软件有限公司 | A kind of guideboard recognition methods and device |
| CN106595630B (en) * | 2015-10-14 | 2019-09-24 | 山东鲁能智能技术有限公司 | It is a kind of that drawing system and method are built based on laser navigation Intelligent Mobile Robot |
| CN105389777A (en) * | 2015-10-23 | 2016-03-09 | 首都师范大学 | Unmanned aerial vehicle sequential image rapid seamless splicing system |
| CN105678318B (en) * | 2015-12-31 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | The matching process and device of traffic sign |
| CN106996785B (en) * | 2016-01-25 | 2019-12-10 | 北京四维图新科技股份有限公司 | Method and device for updating navigation data |
| CN106998434A (en) * | 2016-07-08 | 2017-08-01 | 增城市城乡规划测绘院 | A kind of method of mobile video track in electronic map with video playback simultaneous display |
| CN106054896A (en) * | 2016-07-13 | 2016-10-26 | 武汉大学 | Intelligent navigation robot dolly system |
| CN107818288B (en) * | 2016-09-13 | 2019-04-09 | 腾讯科技（深圳）有限公司 | Sign board information acquisition method and device |
| CN107977995B (en) * | 2016-10-25 | 2022-05-06 | 菜鸟智能物流控股有限公司 | Target area position detection method and related device |
| CN106782032B (en) * | 2016-12-27 | 2019-02-12 | 中国船舶重工集团公司第七0七研究所 | A kind of trans-regional indicating means of laser galvanometer towards paper chart operation |
| KR102414676B1 (en) | 2017-03-07 | 2022-06-29 | 삼성전자주식회사 | Electronic apparatus and operating method for generating a map data |
| CN106932780A (en) * | 2017-03-14 | 2017-07-07 | 北京京东尚科信息技术有限公司 | Object positioning method, device and system |
| CN107992829A (en) * | 2017-12-05 | 2018-05-04 | 武汉中海庭数据技术有限公司 | A kind of traffic lights track level control planning extracting method and device |
| CN110148080B (en) * | 2018-02-13 | 2023-03-21 | 上海杰图天下网络科技有限公司 | Spatial information acquisition device and spatial information acquisition method |
| CN109029488A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术（北京）有限公司 | Navigating electronic map generating method, equipment and storage medium |
| CN109272554A (en) * | 2018-09-18 | 2019-01-25 | 北京云迹科技有限公司 | A kind of method and system of the coordinate system positioning for identifying target and semantic map structuring |
| CN110969592B (en) * | 2018-09-29 | 2024-03-29 | 北京嘀嘀无限科技发展有限公司 | Image fusion method, automatic driving control method, device and equipment |
| CN113450459B (en) * | 2020-03-25 | 2024-03-22 | 北京四维图新科技股份有限公司 | Method and device for constructing three-dimensional model of target object |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010091426A (en) * | 2008-10-08 | 2010-04-22 | Toyota Central R&D Labs Inc | Distance measuring device and program |
| WO2011047732A1 (en) * | 2009-10-22 | 2011-04-28 | Tele Atlas B.V. | Method for identifying moving foreground objects in an orthorectified photographic image |
| US8559673B2 (en) * | 2010-01-22 | 2013-10-15 | Google Inc. | Traffic signal mapping and detection |
| CN102339531B (en) * | 2010-07-14 | 2014-11-05 | 数伦计算机技术（上海）有限公司 | Road traffic detection system |
| CN101986348A (en) * | 2010-11-09 | 2011-03-16 | 上海电机学院 | Visual target identification and tracking method |
| CN102254318B (en) * | 2011-04-08 | 2013-01-09 | 上海交通大学 | Method for measuring speed through vehicle road traffic videos based on image perspective projection transformation |
| CN102509101B (en) * | 2011-11-30 | 2013-06-26 | 昆山市工业技术研究院有限责任公司 | Background updating method and vehicle target extracting method in traffic video monitoring |
| CN102722695B (en) * | 2012-05-11 | 2015-03-25 | 重庆邮电大学 | Method for identifying cone-shaped mark in miniature traffic environment |
-
2013
- 2013-07-05 CN CN201310280993.8A patent/CN104280036B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| IMU/DGPS辅助车载线阵CCD相机推扫路面图像的几何校正方法研究;冀翼;《中国优秀硕士学位论文全文数据库信息科技辑》;20090315;5-38 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104280036A (en) | 2015-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104280036B (en) | A kind of detection of transport information and localization method, device and electronic equipment | |
| CN110174093B (en) | Positioning method, device, equipment and computer readable storage medium | |
| JP6821712B2 (en) | Calibration of integrated sensor in natural scene | |
| JP4232167B1 (en) | Object identification device, object identification method, and object identification program | |
| CN105928498B (en) | Method, the geodetic mapping and survey system, storage medium of information about object are provided | |
| CN107505644A (en) | Three-dimensional high-precision map generation system and method based on vehicle-mounted multisensory fusion | |
| Chen et al. | Inexpensive multimodal sensor fusion system for autonomous data acquisition of road surface conditions | |
| KR102362714B1 (en) | Methods and systems for generating route data | |
| CN109446973B (en) | Vehicle positioning method based on deep neural network image recognition | |
| CN104204721B (en) | Single camera distance estimations | |
| CN110285793A (en) | A kind of Vehicular intelligent survey track approach based on Binocular Stereo Vision System | |
| CN106705962B (en) | A kind of method and system obtaining navigation data | |
| CN112184890B (en) | Accurate positioning method of camera applied to electronic map and processing terminal | |
| JP4978615B2 (en) | Target identification device | |
| CN106408611A (en) | Drive-by calibration from static targets | |
| CN109596121B (en) | Automatic target detection and space positioning method for mobile station | |
| Gerke | Using horizontal and vertical building structure to constrain indirect sensor orientation | |
| CN109520500A (en) | One kind is based on the matched accurate positioning of terminal shooting image and streetscape library acquisition method | |
| CN112308913B (en) | Vehicle positioning method and device based on vision and vehicle-mounted terminal | |
| Zhao et al. | Autonomous driving simulation for unmanned vehicles | |
| CN112446915B (en) | Picture construction method and device based on image group | |
| CN112749584B (en) | Vehicle positioning method based on image detection and vehicle-mounted terminal | |
| CN113296133A (en) | Device and method for realizing position calibration based on binocular vision measurement and high-precision positioning fusion technology | |
| CN108195359B (en) | Method and system for acquiring spatial data | |
| CN110223223A (en) | Street scan method, device and scanner |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |