CN106845321A - The treating method and apparatus of pavement markers information - Google Patents
The treating method and apparatus of pavement markers information Download PDFInfo
- Publication number
- CN106845321A CN106845321A CN201510882685.1A CN201510882685A CN106845321A CN 106845321 A CN106845321 A CN 106845321A CN 201510882685 A CN201510882685 A CN 201510882685A CN 106845321 A CN106845321 A CN 106845321A
- Authority
- CN
- China
- Prior art keywords
- road surface
- road
- cloud data
- reflectivity
- data
- 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.)
- Granted
Links
Classifications
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind for the treatment of method and apparatus of pavement markers information.Wherein, the processing method includes：Tracing point information and the laser point cloud data of target road based on laser collecting device, obtain the road surface cloud data of target road, wherein, laser point cloud data carries out a cloud measurement to target road and obtains by laser collecting device, and road surface cloud data is used to describe the information of road surface of target road；It is multiple road surfaces region by the region division belonging to the cloud data of road surface according to preset range；Obtain the reflectivity screening threshold value in road surface region, reflectivity screening threshold value and default extraction window according to road surface region, pavement markers data are screened from the road surface cloud data in road surface region, wherein, the reflectivity screening threshold value at least two road surfaces region is different in multiple road surface regions；Pavement markers in identification pavement markers data.The present invention solves the low technical problem of recognition accuracy of pavement markers.
Description
Technical field
The present invention relates to map datum process field, in particular to a kind of processing method of pavement markers information and
Device.
Background technology
Carrying out the method for pavement markers detection in the prior art substantially has following two：
The first is to do track figure using artificial and playing back videos.This method is very original, and field operation is responsible for video recording,
Interior industry primarily determines that the change of the lane width or track of road using the video recording of field operation, it is determined that lane width or
After track, track edge is defined as lane line, it is too low using this kind of scheme accuracy and efficiency.
The difference of the reflectivity of second laser point cloud using the road for collecting recognizes the mark on road.It is this
Method determines the laser point cloud data of pavement of road to the difference of the reflectivity of different colors using laser point cloud
Mark.During due to the laser point cloud for gathering road, with color pavement markers (such as the lane line of white) in different acquisition
Under the conditions of (angle such as towards sunlight different, positioned at the not homonymy of laser collecting vehicle) reflectivity it is different, obtain
Pavement of road flag data in be not belonging to pavement marker noise it is too many, so the poor effect of identification, this side
Method does not have practical value substantially.Such as, reflectivity of the white colour in a place is probably 3000, in another place
Reflectivity is probably 5000, with the acquisition target of color such as acquisition condition, such as daytime or night, or
Laser collecting vehicle acquisition precision in itself and it is different.
Design sketch as shown in Figure 1 is especially more by noise in the flag data that the program is obtained；As shown in Figure 2
In design sketch, the lane line of the centre shown in indicia arrow has no idea to recognize at all, the road surface in the Fig. 1 and Fig. 2
The recognition accuracy of mark is relatively low.
To sum up, need badly and provide that a kind of accuracy of identification is high and processing method and processing device of pavement markers information of efficiency high.
The content of the invention
One side according to embodiments of the present invention, there is provided a kind of processing method of pavement markers information, the treatment side
Method includes：Tracing point information and the laser point cloud data of target road based on laser collecting device, obtain target road
Road surface cloud data, wherein, laser point cloud data carries out a cloud and measures by laser collecting device to target road
Arrive, road surface cloud data is used to describe the information of road surface of target road；According to preset range, by road surface cloud data institute
The region division of category is multiple road surfaces region；The reflectivity screening threshold value in road surface region is obtained, according to the anti-of road surface region
Rate screening threshold value is penetrated, pavement markers data are screened from the road surface cloud data in road surface region, wherein, multiple road surface areas
The reflectivity screening threshold value at least two road surfaces region is different in domain；Pavement markers in identification pavement markers data.
Another aspect according to embodiments of the present invention, additionally provides a kind of processing unit of pavement markers information, the device
Including：Acquiring unit, for tracing point information and the laser point cloud data of target road based on laser collecting device,
The road surface cloud data of target road is obtained, wherein, laser point cloud data is entered by laser collecting device to target road
Row point cloud measurement is obtained, and road surface cloud data is used to describe the information of road surface of target road；Division unit, for according to
Preset range, is multiple road surfaces region by the region division belonging to the cloud data of road surface；Screening unit, for obtaining road
The reflectivity screening threshold value in face region, the reflectivity screening threshold value according to road surface region, from the road surface point cloud in road surface region
Pavement markers data are screened in data, wherein, the reflectivity screening at least two road surfaces region in multiple road surface regions
Threshold value is different；Recognition unit, for recognizing the pavement markers in pavement markers data.
Using the present invention, threshold is screened in different road surfaces region using different reflectivity in road pavement cloud data affiliated area
Value screening pavement markers data, the different point cloud of but reflectivity identical for color can be screened using different threshold values,
Caused recognition accuracy low and imitated so as to the pavement markers overcome to different reflectivity are processed using same threshold value
The low problem of rate, realizes efficiently and accurately identifies the effect of pavement markers.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention for explaining the present invention.In accompanying drawing
In：
Fig. 1 is a kind of recognition effect figure of the pavement markers according to prior art；
Fig. 2 is the recognition effect figure of another pavement markers according to prior art；
Fig. 3 is a kind of network environment schematic diagram of terminal according to embodiments of the present invention；
Fig. 4 is a kind of flow chart of the processing method of pavement markers information according to embodiments of the present invention；
Fig. 5 is a kind of preset range according to embodiments of the present invention and the default schematic diagram for extracting window；
Fig. 6 is a kind of flow chart of the processing method of alternatively pavement markers information according to embodiments of the present invention；
Fig. 7 is a kind of design sketch of the pavement markers data according to prior art；
Fig. 8 is a kind of design sketch of pavement markers data according to embodiments of the present invention；
Fig. 9 is a kind of design sketch of pavement markers for recognizing according to embodiments of the present invention；
Figure 10 is a kind of schematic diagram of the processing unit of pavement markers information according to embodiments of the present invention；
Figure 11 is a kind of schematic diagram of the processing unit of alternatively pavement markers information according to embodiments of the present invention；
Figure 12 is a kind of structured flowchart of terminal according to embodiments of the present invention.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment
The only embodiment of a present invention part, rather than whole embodiments.Based on the embodiment in the present invention, ability
The every other embodiment that domain those of ordinary skill is obtained under the premise of creative work is not made, should all belong to
The scope of protection of the invention.
It should be noted that term " first ", " in description and claims of this specification and above-mentioned accompanying drawing
Two " it is etc. for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that this
The data that sample is used can be exchanged in the appropriate case, so as to embodiments of the invention described herein can with except
Here the order beyond those for illustrating or describing is implemented.Additionally, term " comprising " and " having " and they
Any deformation, it is intended that covering is non-exclusive to be included, for example, containing process, the side of series of steps or unit
Method, system, product or equipment are not necessarily limited to those steps clearly listed or unit, but may include unclear
List or for these processes, method, product or other intrinsic steps of equipment or unit.
Embodiment 1
According to embodiments of the present invention, additionally provide a kind of embodiment of the method for the processing method of pavement markers information, it is necessary to
Illustrate, can be in the such as one group department of computer science of computer executable instructions the step of the flow of accompanying drawing is illustrated
Performed in system, and, although logical order is shown in flow charts, but in some cases, can be with difference
Shown or described step is performed in order herein.
The embodiment of the method that the embodiment of the present application one is provided can be in mobile terminal, terminal or similar fortune
Calculate execution in device.As a example by running on computer terminals, alternatively, in the present embodiment, above-mentioned three-dimensional map
Processing method can apply to the hardware environment that terminal 10 as shown in Figure 3 and server 30 are constituted, terminal
Can be set up by network with server and be connected.Wherein, processor can be set on terminal and server, the terminal
Can also set on the server.The example of above-mentioned network include but is not limited to internet, intranet, LAN,
Mobile radio communication and combinations thereof.
Above-mentioned terminal includes but is not limited to mobile terminal, and the mobile terminal includes：It is smart mobile phone, onboard system, flat
Plate computer etc..
Under above-mentioned running environment, this application provides the processing method of pavement markers information as shown in Figure 4.As schemed
Shown in 4, the method may include steps of：
Step S401：Tracing point information and the laser point cloud data of target road based on laser collecting device, obtain mesh
The road surface cloud data of road is marked, wherein, laser point cloud data carries out a cloud by laser collecting device to target road
Measurement is obtained, and road surface cloud data is used to describe the information of road surface of target road.
Step S403：It is multiple road surfaces region by the region division belonging to the cloud data of road surface according to preset range.
Step S405：Obtain road surface region reflectivity screening threshold value, according to road surface region reflectivity screening threshold value with
It is default to extract window, pavement markers data are screened from the road surface cloud data in road surface region, wherein, multiple road surface areas
The reflectivity screening threshold value at least two road surfaces region is different in domain.
Step S407：Pavement markers represented by identification pavement markers data.
Using the present invention, threshold is screened in different road surfaces region using different reflectivity in road pavement cloud data affiliated area
Value screening pavement markers data, the different point cloud of but reflectivity identical for color can be screened using different threshold values,
Caused recognition accuracy low and imitated so as to the pavement markers overcome to different reflectivity are processed using same threshold value
The low problem of rate, realizes efficiently and accurately identifies the effect of pavement markers.
In the above-described embodiments, can be carried out at dynamic self-adapting binaryzation with the different road surface regions of road pavement cloud data
Reason, screening obtains the pavement markers data in the road surface cloud data for belong to road surface region, such that it is able to representing different
The road surface cloud data in road surface region screens threshold value and carries out pavement markers data identification using different reflectivity.Wherein,
Dynamic self-adapting binaryzation is exactly that total data is divided into N number of window according to mobile rule, in this N number of window
Each window data therein are divided into two parts according to a unified threshold value and the default method for extracting window.
For the present embodiment, can be to the data in the different road surface regions of expression using dynamic self-adapting binary conversion treatment mode
Window carries out binary conversion treatment using different threshold values, and identical hence for different reflectivity is screened using different threshold values,
The different problem of mark.
Above-mentioned laser point cloud is also referred to as a cloud, be using laser obtained under the same space referential body surface each
A series of distribution of expression object spaces and the set of the massive point of target surface characteristic that the space coordinates of sampled point is obtained,
This point set is just referred to as " point cloud " (Point Cloud).Laser point cloud data is comprising a cloud under terrestrial coordinate system
The information of longitude, latitude, height and reflectivity.
In the above embodiment of the present invention, can by laser collecting device gather target road laser point cloud data and
The tracing point information of laser collecting device, after laser point cloud data and tracing point information is got, based on tracing point
Information determines the pavement-height of target road, extracts sign pavement of road from laser point cloud data based on the pavement-height
Information road surface cloud data, and to characterizing the data in different road surface regions in the road surface cloud data using different
Threshold value and the default method for extracting window carry out the Screening Treatment of different threshold values, pavement markers data are obtained, to the road surface
Flag data is identified obtaining pavement markers.
By above-described embodiment, recognition effect is clear, and success rate is high, will not omit pavement markers.
By application scenarios of automatic Pilot in detail above-described embodiment is described in detail below：
After automatic Pilot is started, can be by the laser collecting device Real-time Collection on automatic driving vehicle
The laser point cloud data and laser of automatic driving vehicle current driving road (target road i.e. in above-described embodiment) are adopted
The tracing point information of collection equipment, and the road surface point cloud number of target road is determined based on tracing point information and laser point cloud data
According to different road surface regions corresponding to the pavement markers cloud data carry out dynamic self-adapting binary conversion treatment (i.e. to not
The same corresponding data in road surface region are screened threshold values and are screened using different reflectivity), pavement markers data are obtained, and know
Pavement markers not in the pavement markers data, the pavement markers that will be recognized include the vehicle-mounted system in automatic driving vehicle
On the display of system.
In the above embodiment of the present invention, the reflectivity screening threshold value for obtaining road surface region includes：Using belonging to road surface
The reflectivity of the road surface cloud data in region, determines the corresponding reflectivity screening threshold value in the road surface region.
Wherein, using the reflectivity of the road surface cloud data for belonging to road surface region, the corresponding reflection in road surface region is determined
Rate screening threshold value includes：Acquisition belongs to the first average value of the reflectivity of the road surface cloud data in road surface region, by first
Average value is used as the corresponding reflectivity screening threshold value in road surface region.
Specifically, according to road surface region corresponding reflectivity screening threshold value and default extraction window, from the road surface region
Pavement markers data are screened in the cloud data of road surface to be included：The road surface point cloud in road surface region is traveled through using default extraction window
Data, the road surface cloud data in extracting in window to traversing performs following steps：Based on the anti-of road surface region
The reflectivity average value of rate screening threshold value and the road surface cloud data in default extraction window is penetrated, road surface area is filtered out
Pavement markers data in the road surface cloud data in domain.
In the above-described embodiments, based on road surface region reflectivity screening threshold value and the road surface in default extraction window
The reflectivity average value of cloud data, the pavement markers data filtered out in the road surface cloud data in road surface region include：
Obtain the ratio that the default reflectivity for extracting the reflectivity average value of road surface cloud data and road surface region in window screens threshold value
Value；
Whether the ratio is judged more than predetermined threshold value, if so, then by the default all road surface point clouds extracted in window
Data are defined as pavement markers data.
Wherein, preset to extract and at least include belonging in the road surface cloud data in the current road region two points in window
Data.
According to above-described embodiment, screening step can be performed since the first road surface region in multiple road surface regions,
Until traversal multiple road surfaces region, filters out all of pavement markers data, wherein, current road region is initialised
It is the first road surface region in multiple road surface regions.
Specifically, screening step includes：In reflectivity screening threshold value and default extraction window based on current road region
The reflectivity average value of road surface cloud data determines whether to retain in the default all road surface cloud datas extracted in window,
Pavement markers data of the road surface cloud data that will retain as current road region；By the next of current road region
Road surface region as screening operation next time current road region.
Alternatively, can be according to default slip using default extraction window traversal current road region in above-described embodiment
Step-length travels through the road surface cloud data in each current road region using default extraction window.
Alternatively, after road surface cloud data is obtained, as follows obtaining the road surface in the cloud data of road surface
Flag data：
S1:According to preset range by the region division multiple road surface region belonging to the cloud data of road surface；
S2:Obtain the reflectivity screening threshold value in current road region；
S3:Execution following steps are started the cycle over from the first road surface region in multiple road surface regions, until the multiple roads of traversal
Face region, wherein, current road region is initialized to the first road surface region in multiple road surface regions, and circulation is held
Row step includes：
S31:Current road region division is extracted into window for multiple using default extraction window, wherein, each is preset and carries
Taking window includes the data of 1 road surface points；
S32:First in windows is extracted from multiple extract window and start the cycle over and hold such as step S321 and S322, until
Traversal is multiple to extract window, wherein, the current window that extracts is initialized to multiple first extraction window extracted in window
Mouthful：
S321：If (i.e. above-mentioned reflectivity is average for the current average reflectance for extracting all road surface cloud datas in window
Value) be more than predetermined threshold value with the ratio of the reflectivity screening threshold value in current road region, then retain and extract window in default
Intraoral all road surface cloud datas are used as pavement markers data；
S322：Next extraction window of window as the current extraction window of circulate operation next time will currently be extracted.
S33：Using next road surface region in current road region as the current road region of circulate operation next time.
Pavement markers data in the cloud data of road surface in above-described embodiment include each in each current road region
Current preset extracts the pavement markers data in window.
As shown in figure 5, using two default frameworks (above-mentioned preset range and default extract window), using big frame (i.e.
Above-mentioned preset range, the frame B in Fig. 5) in average reflectance (the B average values i.e. shown in Fig. 5) determine
The parameter (such as reflectivity screening threshold value) of background (i.e. current road region), using (the i.e. above-mentioned default extraction of small frame
Window, the frame A in Fig. 5) in average reflectance (Aaverage i.e. shown in Fig. 5) it is determined that retain
Point cloud, the road surface cloud data of reservation is pavement markers data.
The reason for human eye is capable of identify that object, just because the pixel value of object and the pixel value of ambient background are different,
The thought is utilized in the above-described embodiments, preset range is set, and the average picture of background is determined with the reflectivity of wherein data
Element, can obtain accurate recognition result.
Preset range and the default window that extracts in above-described embodiment can be square, and the length of side of preset range can not
More than two distances of lane line (such as between 0.9m-1m), the length of side for presetting extraction window can be for pavement markers be long
1/3 or 1/2 (such as the 1/3 or 1/2 of marker arrow size, such as 0.5 meter) of degree or width.
Alternatively, preset range determines that e.g., preset area is 1 square metre, then the preset range based on preset area
Area coverage be 1 square metre；Preset range is also based on preset length and predetermined width determines, such as preset length
It it is 0.95 meter, predetermined width is 0.9 meter.
Alternatively, preset and extract window based on preset area determination, e.g., preset area is 0.25 square metre, then this is pre-
If the area coverage for extracting window is 0.25 square metre；Default window ranges of extracting are also based on preset length and preset
Width determines that such as preset length is 0.2 meter, and predetermined width is 0.3 meter.
Specifically, determined using the average value of the reflectivity of big frame (i.e. above-mentioned preset range) interior road surface cloud data
The parameter (such as reflectivity screening threshold value) of background, using the flat of small frame (i.e. above-mentioned default extraction window) internal reflection rate
Average it is determined that retain point cloud, if the average value of the reflectivity of small inframe point cloud more than big inframe point cloud reflection
(predetermined threshold value i.e. in above-described embodiment such as 1.5), then retains in small inframe the preset multiple of the average value of rate
Road surface cloud data；Otherwise, the road surface cloud data of small inframe is deleted.
In this embodiment, removal extracts the average reflectance of the road surface cloud data of window less than current window (big frame)
Reflectivity screen threshold value all road surface cloud datas, all road surface points in the default extraction window after being selected
Cloud data, as pavement markers data.
Alternatively, above-mentioned reflectivity screening threshold value can also take the flat of a reflectivity in all road surface cloud datas
A value between the average value of (such as arrow) reflectivity of average and pavement markers.
According to the abovementioned embodiments of the present invention, tracing point information and the laser spots of target road based on laser collecting device
Cloud data, the road surface cloud data for obtaining target road can include：
Tracing point is obtained from the tracing point information of laser collecting device highly；Laser collecting device is calculated relative to target
The relative altitude of road ground；The difference of tracing point height and the relative altitude, the difference for obtaining as target are calculated again
Pavement of road is highly；The difference of height and target road pavement-height in laser point cloud data is exceeded into preset height (such as 10
Centimetre) laser point cloud data removal, obtain the road surface cloud data of target road.
Specifically, laser collecting device may be mounted on the vehicle of automatic Pilot, it is also possible to installed in special laser
In collecting vehicle, the tracing point information of the laser collecting device can be gathered by laser collecting vehicle, in the tracing point information
Can include laser collecting device central point information, using the height of the central point as laser collecting device tracing point
Highly, target road road surface is determined using the tracing point information of laser collecting device and the laser point cloud data of target road
Highly, the difference of height and target road pavement-height exceedes the point cloud noise outside preset height in removal laser point cloud data,
Obtain the road surface cloud data of target road.
Specifically, laser collecting device central point and target can also be obtained from the tracing point information of laser collecting device
The relative altitude of road ground, calculates the difference of tracing point height and relative altitude, and the difference for obtaining is target road road
Face is highly.
By above-described embodiment, dynamic self-adapting binary conversion treatment can be carried out to the road surface cloud data for removing noise,
Obtain more accurately recognition result.
In the above-described embodiments, the pavement markers in identification pavement markers data can include：Obtain pavement markers data
Convex closure；The shape of convex closure is recognized, the pavement markers in pavement markers data are obtained.
Alternatively, after pavement markers data are obtained, the peripheral convex closure of pavement markers data is obtained, recognizes the periphery
The shape of convex closure obtains pavement markers (including word marking and pavement marker).
With reference to Fig. 6 to Fig. 9 in detail the above embodiment of the present invention is described in detail, as shown in fig. 6, the embodiment can be by such as
Lower step is realized：
Step S601：Determine target road road using the tracing point of laser collecting vehicle and the laser point cloud data of target road
Face highly, based on the point cloud noise in target road pavement-height removal laser point cloud data, obtains the road of target road
Face cloud data.
Due to having many vehicle or other noise data in original laser point cloud data, two-value is being carried out to it
Change and can remove these noise data before recognizing.The method of removal is to will be above or high less than target road road surface
The laser point cloud data of degree preset height (such as 10 centimetres) is all deleted.
Specifically, the laser point cloud data in the tracing point information and target road that obtain laser collecting device central point is obtained
After taking the road surface cloud data of target road；From tracing point information, laser collecting device central point is obtained corresponding
Tracing point is highly；Calculate relative altitude of the laser collecting device central point relative to target road ground；Track is calculated again
Put the difference of height and the relative altitude, the difference for obtaining as target road pavement-height；By in laser point cloud data
The laser point cloud data that the difference of height and target road pavement-height exceedes preset height (such as 10 centimetres) is removed, and is obtained
The road surface cloud data of target road.
Step S603：Default two frameworks of different sizes are obtained, the average value using big inframe reflectivity determines background,
Using the average value of small inframe reflectivity it is determined that the point cloud for retaining.
Alternatively, in this embodiment, the mean pixel that big frame is used for determining ambient background is set.As shown in figure 5,
The scope value of big frame typically not larger than two distances of lane line, can be 0.9-1m；The scope value of small frame is big
It is general by way of the 1/3 or 1/2 of road upward arrow size, and the point of small inframe minimum number：2.
When pavement markers data are obtained, if the average value of the reflectivity of small inframe point cloud is anti-more than big inframe point cloud
1.5 times (this 1.5 times is preset value) of the average value of rate are penetrated, then retains the point cloud in small inframe.
In this embodiment, big frame travels through whole road surface cloud data successively, and in each step, small frame travels through whole successively
Individual big frame, the data that final small inframe is retained are exactly pavement markers data to be determined.
Embodiment as shown in Figure 5, using two default frameworks (above-mentioned preset range and default extraction window), profit
The parameter (such as reflectivity screening threshold value) of background is determined with big frame (i.e. above-mentioned preset range) internal reflection rate, using small
The point cloud that the parameter determination of frame (i.e. above-mentioned default extraction window) internal reflection rate should retain, the road surface point cloud of reservation
Data are pavement markers data.
In this embodiment using the contrast of big frame and the average value of the reflectivity of the road surface cloud data of small inframe, come real
The colour recognition of existing background and pavement markers, recognition accuracy is high.
Step S605：The point cloud of the small inframe after reservation is pavement markers data, and lane markings are recognized using convex closure
Or Road letterings mark.
After pavement markers data are obtained, can be further processed come road pavement mark using methods such as convex closures.
As shown in Figure 7 and Figure 8, Fig. 7 is the pavement markers data obtained using method of the prior art, and Fig. 8 is
The pavement markers data obtained using above-described embodiment, it can be seen that the road marking numeration obtained using application scheme
There is no noise in.
After pavement markers data as shown in Figure 8 are obtained, its convex closure is obtained, convex closure is identified, obtained
Pavement markers as shown in Figure 9, the thicker line in Fig. 9 is the pavement markers for identifying, does in fig .9
Exemplary mark.
The detection of the pavement markers based on laser point cloud in the above embodiment of the present invention goes for following three kinds of applied fields
Scape：
(1) generation in high accuracy track：High-precision track needs the lane line could to generate, and track can be correctly detected
Line is exactly the key for generating high accuracy track.
(2) rotation arrow on road is correctly identified so that friendship rule can be properly generated.
(3) automatic Pilot of vehicle：Automatic driving vehicle needs the laser point cloud around real-time detection, so as to recognize
Label information on road, so that vehicle makes the decision-making of correct traveling.
With the application scenarios that are generated as in high accuracy track in detail the above embodiment of the present invention is described in detail below：
After the request of pavement markers of detection target road is received, can be by laser collecting vehicle
The laser point cloud data of laser collecting device Real-time Collection target road and the tracing point information of laser collecting device, utilize
The tracing point information of the central point of laser collecting vehicle and the laser point cloud data of target road determine target road pavement-height,
Highly higher or lower than the point cloud noise outside target road pavement-height preset height in removal laser point cloud data, obtain
The road surface cloud data of target road.
After the road surface cloud data for obtaining target road, the different framework of default two scopes is obtained, using big
Frame (i.e. above-mentioned road surface region) internal reflection rate determines the parameter (such as reflectivity screening threshold value) of background, using small frame (i.e.
Above-mentioned default extraction window) internal reflection rate the point cloud that should retain of parameter determination, the road surface cloud data of reservation is
It is pavement markers data.Specifically, whole road surface cloud data, in each step, small frame are traveled through successively using big frame
Whole big frame is traveled through successively, and the data that final small inframe is retained are exactly pavement markers data to be determined.
After pavement markers data to be determined are obtained, the road surface cloud data to the reservation in each small frame goes
Make an uproar treatment, (this value takes one putting down for a cloud road surface more than set-point will to be in the reflectivity average value of small inframe
One in the middle of the average value of average and arrow value) road surface cloud data as pavement markers data.Obtaining road surface
After flag data, can be identified come road pavement flag data using methods such as convex closures, obtain lane markings or road surface
The pavement markers of word marking etc..
Noise can be removed by the above embodiment of the present invention, and by the above-mentioned dynamic adaptive threshold two of the application
Value algorithm, can quickly recognize road, and discrimination is high, and False Rate is low；In addition, using above-described embodiment, by
In without manually operating, cost is very low, with very strong practicality.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as one it is
The combination of actions of row, but those skilled in the art should know, and the present invention is not limited by described sequence of movement
System, because according to the present invention, some steps can sequentially or simultaneously be carried out using other.Secondly, art technology
Personnel should also know that embodiment described in this description belongs to preferred embodiment, involved action and module
Not necessarily necessary to the present invention.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but
The former is more preferably implementation method in many cases.Based on such understanding, technical scheme substantially or
Say that the part contributed to prior art can be embodied in the form of software product, the computer software product is deposited
Storage is in a storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions are used to so that a station terminal
Equipment (can be mobile phone, computer, server, or network equipment etc.) is performed described in each embodiment of the invention
Method.
Embodiment 2
According to embodiments of the present invention, a kind for the treatment of for implementing the processing method of above-mentioned pavement markers information is additionally provided
Device, as shown in Figure 10, the device includes：Acquiring unit 20, division unit 40, screening unit 60 and identification
Unit 80.
Wherein, acquiring unit 20, for tracing point information and the laser point cloud of target road based on laser collecting device
The road surface cloud data of data acquisition target road, wherein, laser point cloud data is by laser collecting device to target track
Road carries out a cloud measurement and obtains, and road surface cloud data is used to describe the information of road surface of target road.
Division unit 40, for being multiple roads by the region division belonging to the road surface cloud data according to preset range
Face region；
Screening unit 60, the reflectivity for obtaining road surface region screens threshold value, the reflectivity screening according to road surface region
Threshold value and default extraction window, screen pavement markers data from the road surface cloud data in road surface region, wherein, it is multiple
The reflectivity screening threshold value at least two road surfaces region is different in the region of road surface.
Recognition unit 80, for recognizing the pavement markers in pavement markers data.
Using the present invention, different road surfaces region uses different reflections in screening unit road pavement cloud data affiliated area
Rate screening threshold value screening pavement markers data, the different point cloud of but reflectivity identical for color can use different threshold values
Screened, caused identification accurate so as to the pavement markers overcome to different reflectivity are processed using same threshold value
The problem that exactness is low and efficiency is low, realizes efficiently and accurately identifies the effect of pavement markers.
In the above-described embodiments, it is possible to use the different road surface regions of road surface cloud data carry out dynamic self-adapting binaryzation
Treatment, screening obtains the pavement markers data in the cloud data of road surface, such that it is able to the point to representing different road surface regions
Cloud data carry out pavement markers data identification using different threshold values.Wherein, dynamic self-adapting binaryzation is exactly according to shifting
Total data is divided into N number of window by dynamic rule, unified according to one to each window in this N number of window
Data therein are divided into two parts by the method that window is extracted in threshold value and setting.For the present embodiment, using dynamic
State self-adaption binaryzation processing mode can be to representing that the data window in different road surface regions carries out two using different threshold values
Value is processed, so as to overcome difference to be marked at the different problem of different places reflectivity.
Above-mentioned laser point cloud is also referred to as a cloud, be using laser obtained under the same space referential body surface each
A series of distribution of expression object spaces and the set of the massive point of target surface characteristic that the space coordinates of sampled point is obtained,
This point set is just referred to as " point cloud " (Point Cloud).Laser point cloud data is comprising a cloud under terrestrial coordinate system
The information of longitude, latitude, height and reflectivity.
In the above-described embodiments, can be carried out at dynamic self-adapting binaryzation with the different road surface regions of road pavement cloud data
Reason, screening obtains the pavement markers data in the road surface cloud data for belong to road surface region, such that it is able to representing different
The road surface cloud data in road surface region screens threshold value and carries out pavement markers data identification using different reflectivity.Wherein,
Dynamic self-adapting binaryzation is exactly that total data is divided into N number of window according to mobile rule, in this N number of window
Each window according to a unified threshold value and setting extract window method data therein are divided into two parts.
For the present embodiment, can be to the data in the different road surface regions of expression using dynamic self-adapting binary conversion treatment mode
Window carries out binary conversion treatment using different threshold values, and identical hence for different reflectivity is screened using different threshold values,
The different problem of mark.
By above-described embodiment, recognition effect is clear, and success rate is high, will not omit.
By application scenarios of automatic Pilot in detail above-described embodiment is described in detail below：
After automatic Pilot is started, can be by the laser collecting device Real-time Collection on automatic driving vehicle
The laser point cloud data and laser of automatic driving vehicle current driving road (target road i.e. in above-described embodiment) are adopted
The tracing point information of collection equipment, and the road surface point cloud number of target road is determined based on tracing point information and laser point cloud data
According to different road surface regions corresponding to the pavement markers cloud data carry out dynamic self-adapting binary conversion treatment (i.e. to not
The same corresponding data in road surface region are screened threshold values and are screened using different reflectivity), pavement markers data are obtained, and know
Pavement markers not in the pavement markers data, the pavement markers that will be recognized include the vehicle-mounted system in automatic driving vehicle
On the display of system.
Embodiment as shown in figure 11, screening unit 60 can include：Threshold determination module 41, belongs to for utilizing
The reflectivity of the road surface cloud data in road surface region, determines the corresponding reflectivity screening threshold value in the road surface region.
Wherein, the threshold determination module includes：Threshold value determination sub-module, the road surface in road surface region is belonged to for obtaining
First average value of the reflectivity of cloud data, using the first average value as the corresponding reflectivity screening in the road surface region
Threshold value.
Specifically, screening unit can include：Screening submodule 43, for extracting window traversal road surface area using default
The road surface cloud data in domain, the road surface cloud data in extracting in window to traversing performs following steps：It is based on
The reflectivity average value of the reflectivity screening threshold value in road surface region and the road surface cloud data in default extraction window,
Filter out the pavement markers data in the road surface cloud data in road surface region.
Wherein, screening submodule includes：Retain submodule, for acquisition submodule, for obtaining default extraction window
The reflectivity average value of interior road surface cloud data screens the ratio of threshold value with the reflectivity in road surface region；Retain submodule,
For whether judging ratio more than predetermined threshold value, if so, then by the default all road surface point cloud numbers extracted in window
According to being defined as pavement markers data.
Wherein, the reflectivity average value of all road surface cloud datas extracts window for default in above-mentioned default extraction window
The average reflectance of interior road surface cloud data.
Wherein, screening submodule 431 can in the following way obtain the pavement markers data in each current road region：
According to preset range by the region division multiple road surface region belonging to the cloud data of road surface；
Execution following steps are started the cycle over from the first road surface region in multiple road surface regions, until the multiple road surfaces of traversal
Region, wherein, current road region is initialized to the first road surface region in multiple road surface regions, and circulation is performed
Step includes：
It is multiple by current road region division using the reflectivity screening threshold value and default extraction window in current road region
Window is extracted, wherein, each default extraction window includes the data of 1 road surface points.
First in windows is extracted from multiple extract window and start the cycle over and hold such as step, until traversal is multiple to extract windows,
Wherein, the current window that extracts is initialized to multiple first extraction window extracted in window：If currently extracting window
The average reflectance of interior all road surface cloud datas is more than default with the ratio of the reflectivity screening threshold value in current road region
Threshold value, then retain in the default all road surface cloud datas extracted in window as pavement markers data；Premise will be worked as
Next extraction window of window is taken as the current extraction window of circulate operation next time.
Using next road surface region in current road region as the current road region of circulate operation next time.
Each is worked as during the pavement markers data in the cloud data of road surface in above-described embodiment include each current road region
Pavement markers data in preceding extraction window.
As shown in figure 5, using two default frameworks (above-mentioned preset range and default extract window), using big frame (i.e.
Above-mentioned preset range, the frame B in Fig. 5) in average reflectance (the B average values i.e. shown in Fig. 5) determine
The parameter (such as reflectivity screening threshold value) of background (i.e. current road region), using (the i.e. above-mentioned default extraction of small frame
Window, the frame A in Fig. 5) in average reflectance (Aaverage i.e. shown in Fig. 5) it is determined that retain
Point cloud, the road surface cloud data of reservation is pavement markers data.
The reason for human eye is capable of identify that object, just because the pixel value of object and the pixel value of ambient background are different,
The thought is utilized in the above-described embodiments, preset range is set, and the average picture of background is determined with the reflectivity of wherein data
Element, can obtain accurate recognition result.
Preset range and the default window that extracts in above-described embodiment can be square, and the length of side of preset range can not
More than two distances of lane line (such as between 0.9m-1m), the length of side for presetting extraction window can be for pavement markers be long
1/3 or 1/2 (such as 1/3 or the 1/2 of marker arrow size) of degree or width.
Alternatively, it is determined that before pavement markers data, obtaining and presetting all road surface cloud datas extracted in window
Second average value of reflectivity, the second average value is average as the reflectivity of road surface cloud data in default extraction window
Value.
Specifically, determined using the average value of the reflectivity of big frame (i.e. above-mentioned preset range) interior road surface cloud data
The parameter (such as reflectivity screening threshold value) of background, using the flat of small frame (i.e. above-mentioned default extraction window) internal reflection rate
Average it is determined that retain point cloud, if the average value of the reflectivity of small inframe point cloud more than big inframe point cloud reflection
(predetermined threshold value i.e. in above-described embodiment such as 1.5), then retains in small inframe the preset multiple of the average value of rate
Road surface cloud data；Otherwise, the road surface cloud data of small inframe is deleted.
In this embodiment, after based on preset range and the default road surface cloud data for extracting window acquisition reservation,
Pavement markers data are obtained, specifically, removal extracts the reflectivity average value of the road surface cloud data of window less than current
The reflectivity of window (big frame) screens all road surface cloud datas of threshold value, in the default extraction window after being selected
All road surface cloud datas, as pavement markers data.
Alternatively, above-mentioned reflectivity screening threshold value can also take the flat of a reflectivity in all road surface cloud datas
A value between the average value of (such as arrow) reflectivity of average and pavement markers.
Before road pavement flag data is identified, denoising is carried out to it, obtain more accurately clearly recognizing
As a result.
According to the abovementioned embodiments of the present invention, acquiring unit includes：Height acquisition module, for from laser collecting device
Tracing point information in obtain tracing point highly；First computing module, calculates laser collecting device relative to target road
The relative altitude on ground；Second computing module, calculates the difference of tracing point height and the relative altitude, the difference for obtaining
As target road pavement-height；Removal module, by the difference of height and target road pavement-height in laser point cloud data
Laser point cloud data more than preset height (such as 10 centimetres) is removed, and obtains the road surface cloud data of target road.
By above-described embodiment, dynamic self-adapting binary conversion treatment can be carried out to the road surface cloud data for removing noise,
Obtain more accurately recognition result.
Further alternatively, recognition unit includes：Acquisition module, the convex closure for obtaining pavement markers data；Know
Other module, the shape for recognizing convex closure, obtains the pavement markers in pavement markers data.
Alternatively, after pavement markers data are obtained, the peripheral convex closure of pavement markers data is obtained, recognizes the periphery
The shape of convex closure obtains pavement markers (including word marking and pavement marker).
Modules provided in the present embodiment are identical with the application method that the corresponding step of embodiment of the method is provided, should
Can also be identical with scene.It is noted, of course, that the scheme that above-mentioned module is related to can be not limited to above-mentioned implementation
Content and scene in example, and above-mentioned module may operate in terminal or mobile terminal, can by software or
Hardware is realized.
Embodiment 3
Embodiments of the invention can provide a kind of terminal, the terminal can be terminal group in
Any one computer terminal.Alternatively, in the present embodiment, above computer terminal can also be replaced with
The terminal devices such as mobile terminal.
As shown in figure 12, the terminal includes：One or more (one is only shown in figure) processors 201, memory
203 and transmitting device 205 (dispensing device in such as above-mentioned embodiment), as shown in figure 12, the terminal can be with
Including input-output equipment 207.
Wherein, memory 203 can be used to store software program and module, such as pavement markers in the embodiment of the present invention
Corresponding programmed instruction/the module for the treatment of method and apparatus of information, processor 201 is by running storage in memory 203
Interior software program and module, so as to perform various function application and data processing, that is, realize above-mentioned road marking
The processing method of note information.Memory 203 may include high speed random access memory, can also include nonvolatile memory,
Such as one or more magnetic storage device, flash memory or other non-volatile solid state memories.In some instances,
Memory 203 can further include the memory remotely located relative to processor 201, and these remote memories can be with
By network connection to terminal.The example of above-mentioned network include but is not limited to internet, intranet, LAN,
Mobile radio communication and combinations thereof.
Above-mentioned transmitting device 205 is used to that data to be received or sent via network, can be also used for processor with
Data transfer between memory.Above-mentioned network instantiation may include cable network and wireless network.In a reality
In example, transmitting device 205 includes a network adapter (Network Interface Controller, NIC),
It can be connected so as to be communicated with internet or LAN by netting twine and other network equipments with router.One
In individual example, transmitting device 205 is radio frequency (Radio Frequency, RF) module, and it is used for wirelessly
Communicated with internet.
Wherein, specifically, memory 203 is used to store application program.
In the present embodiment, the processor of above computer terminal can perform in the processing method of pavement markers information with
Lower step：Tracing point information and the laser point cloud data of target road based on laser collecting device, obtain target road
Road surface cloud data, wherein, laser point cloud data carries out a cloud and measures by laser collecting device to target road
Arrive, road surface cloud data is used to describe the information of road surface of target road；According to preset range, by road surface cloud data institute
The region division of category is multiple road surfaces region；The reflectivity screening threshold value in road surface region is obtained, according to the anti-of road surface region
Rate screening threshold value and default extraction window are penetrated, pavement markers data are screened from the road surface cloud data in road surface region, its
In, the reflectivity screening threshold value at least two road surfaces region is different in multiple road surface regions；Identification pavement markers data
In pavement markers.
In the present embodiment, above-mentioned processor can also carry out following steps：Using the road surface point cloud for belonging to road surface region
The reflectivity of data, determines the corresponding reflectivity screening threshold value in the road surface region.
In the present embodiment, above-mentioned processor can also carry out following steps：Acquisition belongs to the road surface point cloud in road surface region
First average value of the reflectivity of data, using the first average value as the corresponding reflectivity screening threshold value in road surface region.
In the present embodiment, above-mentioned processor can also carry out following steps：Using default extraction window traversal road surface area
The road surface cloud data in domain, the road surface cloud data in extracting in window to traversing performs following steps：It is based on
The reflectivity average value of the reflectivity screening threshold value in road surface region and the road surface cloud data in default extraction window,
Filter out the pavement markers data in the road surface cloud data in road surface region.
In the present embodiment, above-mentioned processor can also carry out following steps：Obtain road surface point cloud in default extraction window
The reflectivity average value of data screens the ratio of threshold value with the reflectivity in road surface region；Judge ratio whether more than default threshold
Value, if so, all road surface cloud datas in default extraction window then are defined as into pavement markers data.
Using the present invention, threshold is screened in different road surfaces region using different reflectivity in road pavement cloud data affiliated area
Value screening pavement markers data, the different point cloud of but reflectivity identical for color can be screened using different threshold values,
Caused recognition accuracy low and imitated so as to the pavement markers overcome to different reflectivity are processed using same threshold value
The low problem of rate, realizes efficiently and accurately identifies the effect of pavement markers.
It will appreciated by the skilled person that the structure shown in Figure 12 is only to illustrate, terminal can also be
Smart mobile phone (such as Android phone, iOS mobile phones), panel computer, applause computer and mobile internet device
The terminal device such as (Mobile Internet Devices, MID), PAD.Figure 12 its not to above-mentioned electronic installation
Structure cause limit.For example, terminal 10 may also include components more more than shown in Figure 12 or less
(such as network interface, display device), or with the configuration different from shown in Figure 12.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment can be
Completed come the device-dependent hardware of command terminal by program, the program can be stored in a computer-readable storage medium
In matter, storage medium can include：Flash disk, read-only storage (Read-Only Memory, ROM), deposit at random
Take device (Random Access Memory, RAM), disk or CD etc..
Embodiment 4
Embodiments of the invention additionally provide a kind of storage medium.Alternatively, in the present embodiment, above-mentioned storage medium
Can be used for preserving the program code performed by the processing method of the pavement markers information that above-described embodiment one is provided.
Alternatively, in the present embodiment, during above-mentioned storage medium may be located at computer network Computer terminal group
In any one terminal, or in any one mobile terminal in mobile terminal group.
Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps：
The laser point cloud data of tracing point information and target road based on laser collecting device obtains the road surface point cloud of target road
Data, wherein, laser point cloud data carries out a cloud measurement to target road and obtains by laser collecting device, road surface point
Cloud data are used to describe the information of road surface of target road；Reflectivity road pavement cloud data using road surface cloud data enters
The treatment of Mobile state self-adaption binaryzation, obtains the pavement markers data in the cloud data of road surface；Identification pavement markers data
In pavement markers.
In the present embodiment, storage medium is arranged to storage for performing the program code of following steps：Based on laser
The tracing point information and the laser point cloud data of target road of collecting device, obtain the road surface cloud data of target road,
Wherein, laser point cloud data carries out a cloud measurement to target road and obtains by laser collecting device, road surface cloud data
Information of road surface for describing target road；It is many by the region division belonging to the cloud data of road surface according to preset range
Individual road surface region；Obtain road surface region reflectivity screening threshold value, according to road surface region reflectivity screening threshold value with it is pre-
If extracting window, pavement markers data are screened from the road surface cloud data in road surface region, wherein, multiple road surface regions
In at least two road surfaces region reflectivity screening threshold value it is different；Pavement markers in identification pavement markers data.
In the present embodiment, storage medium is arranged to storage for performing the program code of following steps：Using belonging to
The reflectivity of the road surface cloud data in road surface region, determines the corresponding reflectivity screening threshold value in the road surface region.
In the present embodiment, storage medium is arranged to storage for performing the program code of following steps：Acquisition belongs to
First average value of the reflectivity of the road surface cloud data in road surface region, the first average value is corresponding as road surface region
Reflectivity screens threshold value.
In the present embodiment, storage medium is arranged to storage for performing the program code of following steps：Using default
The road surface cloud data that window travels through road surface region is extracted, to the road surface cloud data in extracting in window for traversing
Perform following steps：Reflectivity screening threshold value based on road surface region and the road surface point cloud number in default extraction window
According to reflectivity average value, filter out the pavement markers data in the road surface cloud data in road surface region.
In the present embodiment, storage medium is arranged to storage for performing the program code of following steps：Obtain default
Extract the ratio that the reflectivity average value of road surface cloud data in window screens threshold value with the reflectivity in road surface region；Judge
Whether ratio is more than predetermined threshold value, if so, being then defined as all road surface cloud datas in default extraction window
Pavement markers data.
Using the present invention, threshold is screened in different road surfaces region using different reflectivity in road pavement cloud data affiliated area
Value screening pavement markers data, the different point cloud of but reflectivity identical for color can be screened using different threshold values,
Caused recognition accuracy low and imitated so as to the pavement markers overcome to different reflectivity are processed using same threshold value
The low problem of rate, realizes efficiently and accurately identifies the effect of pavement markers.
The embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in certain embodiment
The part of detailed description, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents, can be by other
Mode realize.Wherein, device embodiment described above is only schematical, such as division of described unit,
It is only a kind of division of logic function, there can be other dividing mode when actually realizing, for example multiple units or component
Can combine or be desirably integrated into another system, or some features can be ignored, or do not perform.It is another, institute
Display or the coupling each other for discussing or direct-coupling or communication connection can be by some interfaces, unit or mould
The INDIRECT COUPLING of block or communication connection, can be electrical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to
On multiple NEs.Some or all of unit therein can be according to the actual needs selected to realize the present embodiment
The purpose of scheme.
In addition, during each functional unit in each embodiment of the invention can be integrated in a division unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is to realize in the form of SFU software functional unit and as independent production marketing or when using,
Can store in a computer read/write memory medium.Based on such understanding, technical scheme essence
On all or part of the part that is contributed to prior art in other words or the technical scheme can be with software product
Form is embodied, and the computer software product is stored in a storage medium, including some instructions are used to so that one
Platform computer equipment (can be personal computer, server or network equipment etc.) performs each embodiment institute of the invention
State all or part of step of method.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD
Etc. it is various can be with the medium of store program codes.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improve and moisten
Decorations also should be regarded as protection scope of the present invention.
Claims (14)
1. a kind of processing method of pavement markers information, it is characterised in that including：
Tracing point information and the laser point cloud data of target road based on laser collecting device, obtain the target
The road surface cloud data of road, wherein, the laser point cloud data is by the laser collecting device to the mesh
Mark road carries out a cloud measurement and obtains, and the road surface cloud data is used to describe the information of road surface of the target road；
It is multiple road surfaces region by the region division belonging to the road surface cloud data according to preset range；
Obtain road surface region reflectivity screening threshold value, according to the road surface region reflectivity screening threshold value with it is pre-
If extracting window, pavement markers data are screened from the road surface cloud data in the road surface region, wherein, it is described
The reflectivity screening threshold value at least two road surfaces region is different in multiple road surface regions；
Recognize the pavement markers in the pavement markers data.
2. processing method according to claim 1, it is characterised in that obtain the reflectivity screening threshold value in road surface region
Including：
Using the reflectivity of the road surface cloud data for belonging to the road surface region, determine that the road surface region is corresponding anti-
Penetrate rate screening threshold value.
3. processing method according to claim 2, it is characterised in that using the road surface point for belonging to the road surface region
The reflectivity of cloud data, determines that the corresponding reflectivity screening threshold value in the road surface region includes：
Acquisition belongs to the first average value of the reflectivity of the road surface cloud data in the road surface region, by described first
Average value is used as the corresponding reflectivity screening threshold value in the road surface region.
4. processing method according to claim 1, it is characterised in that according to the corresponding reflectivity sieve in the road surface region
Threshold value and default extraction window are selected, screening belongs to the pavement markers data in the road surface cloud data in the road surface region
Including：
Using the default road surface cloud data for extracting window traversal road surface region, to traversing in described
The road surface cloud data extracted in window performs following steps：
Reflectivity screening threshold value based on the road surface region and the road surface point cloud in the default extraction window
The reflectivity average value of data, filters out the pavement markers data in the road surface cloud data in the road surface region.
5. processing method according to claim 4, it is characterised in that the reflectivity screening based on the road surface region
The reflectivity average value of threshold value and the road surface cloud data in the default extraction window, filters out the road
Pavement markers data in the road surface cloud data in face region include：
Obtain the default reflectivity average value for extracting road surface cloud data in window anti-with the road surface region
Penetrate the ratio that rate screens threshold value；
Whether ratio is judged more than predetermined threshold value, if so, then by the default all roads extracted in window
Face cloud data is defined as pavement markers data.
6. processing method according to claim 1, it is characterised in that the tracing point information based on laser collecting device
With the laser point cloud data of target road, the road surface cloud data for obtaining the target road includes：
Tracing point is obtained from the tracing point information of the laser collecting device highly；
Calculate relative altitude of the laser collecting device relative to target road ground；
The difference of the tracing point height and relative altitude is calculated, the difference for obtaining is target road pavement-height；
The difference of height and the target road pavement-height in the laser point cloud data is exceeded into swashing for preset height
Light cloud data is removed, and obtains the road surface cloud data of the target road.
7. processing method according to claim 1, it is characterised in that the road surface in the identification pavement markers data
Mark includes：
Obtain the convex closure of the pavement markers data；
The shape of the convex closure is recognized, the pavement markers in the pavement markers data are obtained.
8. a kind of processing unit of pavement markers information, it is characterised in that including：
Acquiring unit, for tracing point information and the laser point cloud data of target road based on laser collecting device,
The road surface cloud data of the target road is obtained, wherein, the laser point cloud data is gathered by the laser
Equipment carries out a cloud measurement to the target road and obtains, and the road surface cloud data is used to describe the target track
The information of road surface on road；
Division unit, for being multiple by the region division belonging to the road surface cloud data according to preset range
Road surface region；
Screening unit, the reflectivity for obtaining road surface region screens threshold value, according to the reflection in the road surface region
Rate screens threshold value and default extraction window, and road marking numeration is screened from the road surface cloud data in the road surface region
According to, wherein, the reflectivity screening threshold value at least two road surfaces region is different in the multiple road surface region；
Recognition unit, for recognizing the pavement markers in the pavement markers data.
9. processing unit according to claim 8, it is characterised in that the screening unit includes：
Threshold determination module, for the reflectivity using the road surface cloud data for belonging to road surface region, determines the road
The corresponding reflectivity screening threshold value in face region.
10. processing unit according to claim 9, it is characterised in that the threshold determination module includes：
Threshold value determination sub-module, it is flat for obtaining the first of reflectivity of the road surface cloud data for belonging to road surface region
Average, using first average value as the corresponding reflectivity screening threshold value in the road surface region.
11. processing units according to claim 8, it is characterised in that the screening unit includes：
Screening submodule, it is right for using the default road surface cloud data for extracting window traversal road surface region
The road surface cloud data in the extraction window for traversing performs following steps：
Reflectivity screening threshold value based on the road surface region and the road surface point cloud in the default extraction window
The reflectivity average value of data, filters out the pavement markers data in the road surface cloud data in the road surface region.
12. processing units according to claim 11, it is characterised in that the screening submodule includes：
Acquisition submodule, for obtain it is described it is default extract window in road surface cloud data reflectivity average value with
The reflectivity in the road surface region screens the ratio of threshold value；
Retain submodule, for whether judging ratio more than predetermined threshold value, if so, will then be carried in described presetting
The all road surface cloud datas taken in window are defined as pavement markers data.
13. processing units according to claim 8, it is characterised in that the acquiring unit includes：
Height acquisition module, for obtaining tracing point highly from the tracing point information of the laser collecting device；
First computing module, for calculating relative altitude of the laser collecting device relative to target road ground；
Second computing module, the difference for calculating tracing point height and relative altitude, the difference for obtaining is
Target road pavement-height；
Removal module, for the difference of height and the target road pavement-height in the laser point cloud data to be surpassed
The laser point cloud data removal of preset height is crossed, the road surface cloud data of the target road is obtained.
14. processing units according to claim 8, it is characterised in that the recognition unit includes：
Acquisition module, the convex closure for obtaining the pavement markers data；
Identification module, the shape for recognizing the convex closure obtains the pavement markers in the pavement markers data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510882685.1A CN106845321B (en) | 2015-12-03 | 2015-12-03 | Method and device for processing pavement marking information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510882685.1A CN106845321B (en) | 2015-12-03 | 2015-12-03 | Method and device for processing pavement marking information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106845321A true CN106845321A (en) | 2017-06-13 |
| CN106845321B CN106845321B (en) | 2020-03-27 |
Family
ID=59148804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510882685.1A Active CN106845321B (en) | 2015-12-03 | 2015-12-03 | Method and device for processing pavement marking information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106845321B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109506672A (en) * | 2017-09-15 | 2019-03-22 | 高德软件有限公司 | A kind of acquisition methods and device of pavement markers laser point cloud |
| CN109508579A (en) * | 2017-09-15 | 2019-03-22 | 百度在线网络技术（北京）有限公司 | For obtaining the method and device of virtual point cloud data |
| CN109633681A (en) * | 2018-12-05 | 2019-04-16 | 芜湖智久机器人有限公司 | A kind of reflector recognition methods and device |
| CN109711336A (en) * | 2018-12-26 | 2019-05-03 | 深圳高速工程顾问有限公司 | Roadmarking determines method, apparatus, storage medium and computer equipment |
| CN109726728A (en) * | 2017-10-31 | 2019-05-07 | 高德软件有限公司 | A kind of training data generation method and device |
| CN110031822A (en) * | 2019-04-22 | 2019-07-19 | 上海禾赛光电科技有限公司 | It can be used for noise recognition methods and the laser radar system of laser radar |
| CN110361754A (en) * | 2019-07-15 | 2019-10-22 | 武汉中海庭数据技术有限公司 | A kind of road block letter growth formula clustering method and device based on laser point cloud data |
| CN111009040A (en) * | 2018-10-08 | 2020-04-14 | 阿里巴巴集团控股有限公司 | Point cloud entity marking system, method and device and electronic equipment |
| CN111174777A (en) * | 2018-11-09 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Positioning method and device and electronic equipment |
| CN111192322A (en) * | 2019-12-31 | 2020-05-22 | 武汉中海庭数据技术有限公司 | Method and system for automatically calculating height of signboard based on point cloud track |
| CN111649752A (en) * | 2020-05-29 | 2020-09-11 | 北京四维图新科技股份有限公司 | Map data processing method, device and equipment for congested road section |
| CN111670379A (en) * | 2019-01-09 | 2020-09-15 | 深圳市大疆创新科技有限公司 | Echo signal processing method, device and storage medium |
| WO2020215368A1 (en) * | 2019-04-22 | 2020-10-29 | 上海禾赛光电科技有限公司 | Noisy point identification method for laser radar, and laser radar system |
| CN112835055A (en) * | 2020-12-30 | 2021-05-25 | 潍柴动力股份有限公司 | Positioning method and system of laser SLAM equipment |
| CN113640823A (en) * | 2021-07-15 | 2021-11-12 | 北京三快在线科技有限公司 | Method and device for mapping based on laser reflectivity base map |
| CN113960572A (en) * | 2021-10-20 | 2022-01-21 | 北京轻舟智航科技有限公司 | Processing method and device for filtering noise point cloud of underground lamp |
| JP2022522385A (en) * | 2020-02-07 | 2022-04-19 | シェンチェン センスタイム テクノロジー カンパニー リミテッド | Road sign recognition methods, map generation methods, and related products |
| CN115824237A (en) * | 2022-11-29 | 2023-03-21 | 重庆赛迪奇智人工智能科技有限公司 | Track pavement identification method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103499343A (en) * | 2013-09-25 | 2014-01-08 | 武汉海达数云技术有限公司 | Automatic classifying and identifying method for road line point cloud based on three-dimensional laser reflection strength |
| CN103743383A (en) * | 2014-02-11 | 2014-04-23 | 天津市星际空间地理信息工程有限公司 | Automatic extraction method for road information based on point cloud |
| CN104197897A (en) * | 2014-04-25 | 2014-12-10 | 厦门大学 | Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud |
| CN105069395A (en) * | 2015-05-17 | 2015-11-18 | 北京工业大学 | Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology |
-
2015
- 2015-12-03 CN CN201510882685.1A patent/CN106845321B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103499343A (en) * | 2013-09-25 | 2014-01-08 | 武汉海达数云技术有限公司 | Automatic classifying and identifying method for road line point cloud based on three-dimensional laser reflection strength |
| CN103743383A (en) * | 2014-02-11 | 2014-04-23 | 天津市星际空间地理信息工程有限公司 | Automatic extraction method for road information based on point cloud |
| CN104197897A (en) * | 2014-04-25 | 2014-12-10 | 厦门大学 | Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud |
| CN105069395A (en) * | 2015-05-17 | 2015-11-18 | 北京工业大学 | Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology |
Non-Patent Citations (2)
| Title |
|---|
| BISHENG YANG 等: "Automated Extraction of Road Markings from Mobile Lidar Point Clouds", 《PHOTOGRAMMETRIC ENGINEERING & REMOTE SENSING》 * |
| 邹晓亮 等: "移动车载激光点云的道路标线自动识别与提取", 《测绘与空间地理信息》 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109508579A (en) * | 2017-09-15 | 2019-03-22 | 百度在线网络技术（北京）有限公司 | For obtaining the method and device of virtual point cloud data |
| CN109506672B (en) * | 2017-09-15 | 2023-05-12 | 阿里巴巴（中国）有限公司 | Method and device for acquiring laser point cloud of pavement marker |
| CN109506672A (en) * | 2017-09-15 | 2019-03-22 | 高德软件有限公司 | A kind of acquisition methods and device of pavement markers laser point cloud |
| CN109508579B (en) * | 2017-09-15 | 2022-02-22 | 百度在线网络技术（北京）有限公司 | Method and device for acquiring virtual point cloud data |
| CN109726728A (en) * | 2017-10-31 | 2019-05-07 | 高德软件有限公司 | A kind of training data generation method and device |
| CN111009040B (en) * | 2018-10-08 | 2023-04-18 | 阿里巴巴集团控股有限公司 | Point cloud entity marking system, method and device and electronic equipment |
| CN111009040A (en) * | 2018-10-08 | 2020-04-14 | 阿里巴巴集团控股有限公司 | Point cloud entity marking system, method and device and electronic equipment |
| CN111174777A (en) * | 2018-11-09 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Positioning method and device and electronic equipment |
| US20210263167A1 (en) * | 2018-11-09 | 2021-08-26 | Alibaba Group Holding Limited | Positioning method, device, and electronic apparatus |
| CN109633681A (en) * | 2018-12-05 | 2019-04-16 | 芜湖智久机器人有限公司 | A kind of reflector recognition methods and device |
| CN109711336A (en) * | 2018-12-26 | 2019-05-03 | 深圳高速工程顾问有限公司 | Roadmarking determines method, apparatus, storage medium and computer equipment |
| CN111670379A (en) * | 2019-01-09 | 2020-09-15 | 深圳市大疆创新科技有限公司 | Echo signal processing method, device and storage medium |
| CN110988847A (en) * | 2019-04-22 | 2020-04-10 | 上海禾赛光电科技有限公司 | Noise point identification method for laser radar and laser radar system |
| WO2020215369A1 (en) * | 2019-04-22 | 2020-10-29 | 上海禾赛光电科技有限公司 | Noise point recognition method applicable to lidar and lidar system |
| WO2020215368A1 (en) * | 2019-04-22 | 2020-10-29 | 上海禾赛光电科技有限公司 | Noisy point identification method for laser radar, and laser radar system |
| US10908268B2 (en) | 2019-04-22 | 2021-02-02 | Velodyne Lidar Usa, Inc. | Method for identification of a noise point used for LiDAR, and LiDAR system |
| US11982771B2 (en) | 2019-04-22 | 2024-05-14 | Hesai Technology Co., Ltd. | Method for identification of a noise point used for LiDAR, and LiDAR system |
| CN110031822A (en) * | 2019-04-22 | 2019-07-19 | 上海禾赛光电科技有限公司 | It can be used for noise recognition methods and the laser radar system of laser radar |
| CN110361754A (en) * | 2019-07-15 | 2019-10-22 | 武汉中海庭数据技术有限公司 | A kind of road block letter growth formula clustering method and device based on laser point cloud data |
| CN111192322A (en) * | 2019-12-31 | 2020-05-22 | 武汉中海庭数据技术有限公司 | Method and system for automatically calculating height of signboard based on point cloud track |
| CN111192322B (en) * | 2019-12-31 | 2022-09-30 | 武汉中海庭数据技术有限公司 | Method and system for automatically calculating height of signboard based on point cloud track |
| JP2022522385A (en) * | 2020-02-07 | 2022-04-19 | シェンチェン センスタイム テクノロジー カンパニー リミテッド | Road sign recognition methods, map generation methods, and related products |
| CN111649752B (en) * | 2020-05-29 | 2021-09-21 | 北京四维图新科技股份有限公司 | Map data processing method, device and equipment for congested road section |
| CN111649752A (en) * | 2020-05-29 | 2020-09-11 | 北京四维图新科技股份有限公司 | Map data processing method, device and equipment for congested road section |
| CN112835055A (en) * | 2020-12-30 | 2021-05-25 | 潍柴动力股份有限公司 | Positioning method and system of laser SLAM equipment |
| CN113640823A (en) * | 2021-07-15 | 2021-11-12 | 北京三快在线科技有限公司 | Method and device for mapping based on laser reflectivity base map |
| CN113640823B (en) * | 2021-07-15 | 2023-11-21 | 北京三快在线科技有限公司 | Method and device for map drawing based on laser reflectivity base map |
| CN113960572A (en) * | 2021-10-20 | 2022-01-21 | 北京轻舟智航科技有限公司 | Processing method and device for filtering noise point cloud of underground lamp |
| CN113960572B (en) * | 2021-10-20 | 2024-05-03 | 北京轻舟智航科技有限公司 | Processing method and device for filtering noise point cloud of buried lamp |
| CN115824237A (en) * | 2022-11-29 | 2023-03-21 | 重庆赛迪奇智人工智能科技有限公司 | Track pavement identification method and device |
| CN115824237B (en) * | 2022-11-29 | 2023-09-26 | 重庆赛迪奇智人工智能科技有限公司 | Rail pavement recognition method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106845321B (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106845321A (en) | The treating method and apparatus of pavement markers information | |
| CN111784685B (en) | Power transmission line defect image identification method based on cloud edge cooperative detection | |
| US10614562B2 (en) | Inventory, growth, and risk prediction using image processing | |
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| CN110619750B (en) | Intelligent aerial photography identification method and system for illegal parking vehicle | |
| CN104778721B (en) | The distance measurement method of conspicuousness target in a kind of binocular image | |
| WO2017041396A1 (en) | Driving lane data processing method, device, storage medium and apparatus | |
| CN106845324A (en) | The treating method and apparatus of guideboard information | |
| CN115631356B (en) | Method and device for identifying missing of road facility, storage medium and electronic device | |
| CN107918776A (en) | A kind of plan for land method, system and electronic equipment based on machine vision | |
| CN106897681A (en) | A kind of remote sensing images comparative analysis method and system | |
| CN106767854A (en) | mobile device, garage map forming method and system | |
| CN113378754B (en) | Bare soil monitoring method for construction site | |
| Neuhausen et al. | Automatic window detection in facade images | |
| CN111753610A (en) | Weather identification method and device | |
| CN110163109A (en) | A kind of lane line mask method and device | |
| CN113255444A (en) | Training method of image recognition model, image recognition method and device | |
| CN115841633A (en) | Power tower and power line associated correction power tower and power line detection method | |
| CN110188661B (en) | Boundary identification method and device | |
| CN114972646A (en) | Method and system for extracting and modifying independent ground objects of live-action three-dimensional model | |
| CN113033386B (en) | High-resolution remote sensing image-based transmission line channel hidden danger identification method and system | |
| CN108053409B (en) | Automatic construction method and system for remote sensing image segmentation reference library | |
| CN109657540A (en) | Withered tree localization method and system | |
| CN113505653A (en) | Object detection method, device, equipment, medium and program product | |
| CN108109125A (en) | Information extracting method and device based on remote sensing images |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200608 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: Alibaba (China) Co.,Ltd. Address before: 100102, No. 18, No., Changsheng Road, Changping District science and Technology Park, Beijing, China. 1-5 Patentee before: AUTONAVI SOFTWARE Co.,Ltd. |