CN110033482A - A kind of curb recognition methods and device based on laser point cloud - Google Patents
A kind of curb recognition methods and device based on laser point cloud Download PDFInfo
- Publication number
- CN110033482A CN110033482A CN201810027972.8A CN201810027972A CN110033482A CN 110033482 A CN110033482 A CN 110033482A CN 201810027972 A CN201810027972 A CN 201810027972A CN 110033482 A CN110033482 A CN 110033482A
- Authority
- CN
- China
- Prior art keywords
- curb
- point
- line
- scan
- laser point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
Abstract
The curb recognition methods and device that the invention discloses a kind of based on laser point cloud.The described method includes: extracting corresponding curb point from every scan line in laser point cloud；Effective curb line is generated according to the curb point extracted.It can accurately identify curb line, be suitable for any construction material curb, arbitrary shape curb, horizontal road and inclined-plane road etc.；And calculation amount is small, is suitable for the operation of scale high-accuracy data acquisition.
Description
Technical field
The present invention relates to technical field of geographic information, in particular to a kind of curb recognition methods and dress based on laser point cloud
It sets.
Background technique
With the continuous development of information technology, electronic map, electronic navigation etc. are gradually popularized in people's daily life,
The significant concern point that more accurate road information becomes each service provider is provided for user.
The range accuracy of laser radar has reached Centimeter Level at present, and the point cloud captured has that data volume is big, feedback letter
It ceases the advantages that abundant and is widely used in accurately diagram data Collecting operation.Curb identification based on laser point cloud is high-precision
The first step of data processing is how curb point to be extracted from cloud based on the emphasis that laser point cloud carries out curb identification.At present
There are many methods for extracting curb point, but all have the defects that certain.Such as:
The first, judges whether it is curb point according to the reflected intensity of laser scanning point.The construction material of road is different, instead
It is just different to penetrate intensity, therefore such method is not suitable for the acquisition of scale data.
Second, according to curb reflection point same scanning slice show stable serial number continuity and it is having the same tiltedly
Rate judges these continuous points for curb point.Such scheme is only applicable in the road that curb is striped blocks object.
As described above, prior art curb point seeks its scope of application all by the limitation of certain factor, it is poor for applicability.
And calculating is relative complex, computationally intensive, the curb point obstacle object point of acquisition is more, so as to cause the curb line accuracy finally sought
It is low.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
State a kind of curb recognition methods and device based on laser point cloud of problem.
In a first aspect, the embodiment of the present invention provides a kind of curb recognition methods based on laser point cloud, comprising:
Corresponding curb point is extracted from every scan line in laser point cloud；
Effective curb line is generated according to the curb point extracted.
In some alternative embodiments, corresponding curb is extracted in every scan line from laser point cloud
Point, comprising:
For every scan line, the sweep center point of the scan line is extracted；
Centered on the sweep center point of the scan line, the scan line is divided into the left and right sides, obtains the scanning
The left scan laser point sequence and right side scanning laser point sequence of line；
The scanning is extracted respectively from the left scan laser point sequence and the right side scanning laser point sequence
The left side curb point and right side curb point of line.
In some alternative embodiments, the sweep center point of scan line is extracted, comprising:
Extract the nearest scanning of the horizontal distance for the laser scanner that distance acquires the laser point cloud in every scan line
Point, the sweep center point as this scan line.
In some alternative embodiments, after obtaining left scan laser point sequence and right side scanning laser point sequence,
Further include:
Denoising is carried out to the left scan laser point sequence and the right side scanning laser point sequence respectively, is obtained
The right side scanning laser point sequence after left scan laser point sequence and denoising after denoising.
In some alternative embodiments, divide from the left scan laser point sequence and right side scanning laser point sequence
Indescribably take out the left side curb point and right side curb point of the scan line, comprising:
Operations described below is executed respectively to the left scan laser point sequence and the right side scanning laser point sequence:
All scanning elements are ranked up according to the size of reflective distance, wherein the equal scanning element of reflective distance according still further to
The size of height value is ranked up, and forms the queue of scanning element；
According to the sequence of reflective distance from small to large, successively adjacent scanning element two-by-two in the queue, finds out height
Degree difference is greater than first pair of adjacent scanning element of the difference in height threshold value of setting；
The biggish scanning element of wherein height value is extracted as this from the first pair of adjacent scanning element found out
Curb point of the scan line in the side.
In some alternative embodiments, the curb point that the basis extracts, generates effective curb line, packet
It includes:
The right side curb point of left side curb point and all scan lines to all scan lines executes operations described below respectively:
It carries out clustering and obtains curb cluster；
The curb cluster is subjected to regression fit, the curb line hashed；
The curb line of hash is merged, effective curb line of respective side is obtained.
In some alternative embodiments, after the curb line hashed, further includes:
Acquisition wheel paths by the sweep center point of every scan line in the laser point cloud, as this scan line
Point；
Regression fit is carried out to all collecting vehicle tracing points, obtains collecting vehicle trajectory line；
According to the curb line of the hash between the collecting vehicle trajectory line at a distance from, the curb line of the hash is carried out
Screening；
The curb line of the hash is merged, is specifically included:
The curb line of hash after screening is merged.
In some alternative embodiments, the curb line of described pair of hash screens, comprising:
The curb line of the hash is calculated to the maximum probability distance L of the collecting vehicle trajectory line；
Judge whether the curb line of every hash is greater than L × (1-n%) to the distance of the collecting vehicle trajectory line and is less than L
× (1+n%), the n% is less than 1；
If so, the curb line is effective, retain the curb line；
If it is not, then the curb line is barrier line, the curb line is deleted.
Second aspect, the embodiment of the present invention provide a kind of curb identification device based on laser point cloud, comprising:
Extraction module, for extracting corresponding curb point from every scan line in laser point cloud；Generation module is used
Effective curb line is generated in the curb point extracted according to the extraction module.
In some alternative embodiments, the extraction module, comprising:
First extracting sub-module extracts the sweep center point of the scan line for being directed to every scan line；
Submodule is divided, used in being with the sweep center point for the scan line extracted by first extracting sub-module
The scan line is divided into the left and right sides, obtains the left scan laser point sequence and right side scanning laser of the scan line by the heart
Point sequence；
Second extracting sub-module, for from the obtained left scan laser point sequence of division submodule and described
The left side curb point and right side curb point of the scan line are extracted in the scanning laser point sequence of right side respectively.
In some alternative embodiments, the extraction module, further includes:
Submodule is denoised, the left scan laser point sequence and the right side for obtaining to the division submodule
Scanning laser point sequence carries out denoising respectively, and the left scan laser point sequence after being denoised and the right side after denoising are swept
Retouch laser point sequence.
In some alternative embodiments, second extracting sub-module, is specifically used for: to the left scan laser point
Sequence and the right side scanning laser point sequence execute operations described below respectively: by all scanning elements according to reflective distance size into
Row sequence, wherein the equal scanning element of reflective distance is ranked up according still further to the size of height value, forms the queue of scanning element；It presses
According to the sequence of reflective distance from small to large, successively adjacent scanning element two-by-two in the queue finds out difference in height and is greater than and sets
First pair of adjacent scanning element of fixed difference in height threshold value；It is extracted from the first pair of adjacent scanning element found out wherein high
Curb point of the biggish scanning element of angle value as this scan line side.
In some alternative embodiments, the generation module, is specifically used for: extracting to second extracting sub-module
The left side curb point of all scan lines and the right side curb point of all scan lines execute operations described below respectively: carrying out clustering and obtain
To curb cluster；The curb cluster is subjected to regression fit, the curb line hashed；The curb line of hash is merged, is obtained
To effective curb line of respective side.
In some alternative embodiments, the generation module, is also used to: after obtaining the curb line of the hash,
Collecting vehicle tracing point by the sweep center point of every scan line in the laser point cloud, as this scan line；To all
The collecting vehicle tracing point carries out regression fit, obtains collecting vehicle trajectory line；According to the curb line of the hash and the acquisition
Distance between track trace screens the curb line of the hash；The curb line of hash after screening is merged.
In some alternative embodiments, the generation module, is specifically used for: calculating the curb line of the hash described in
The maximum probability distance L of collecting vehicle trajectory line；Judge every hash curb line to the collecting vehicle trajectory line distance whether
Greater than L × (1-n%) and it is less than L × (1+n%), the n% is less than 1；If so, the curb line is effective, retain the curb line；
If it is not, then the curb line is barrier line, the curb line is deleted.
The third aspect, the embodiment of the present invention provide a kind of data map collection of material equipment, comprising:
Point cloud obtains module, for obtaining the laser point cloud data；
Curb extraction module, for being obtained in every scan line in the laser point cloud that module obtains from described cloud
Extract corresponding curb point；Effective curb line is generated according to the curb point；
Road equipment extraction module, described in the effective curb line segmentation for being extracted according to the curb extraction module
Point cloud obtains the laser point cloud data that module obtains, and extracts the road equipment information of road surface earth's surface information and both sides of the road；
Map data creating and modeling module, effective curb line for being extracted according to the curb extraction module and
The road equipment information of the road surface earth's surface information and both sides of the road that the road equipment extraction module extracts, carries out map number
According to production and three-dimension modeling.
Fourth aspect, the embodiment of the present invention provide a kind of non-transitorycomputer readable storage medium, are stored thereon with meter
The instruction of calculation machine, performs the steps of when the instruction is executed by processor
Corresponding curb point is extracted from every scan line in laser point cloud；
Effective curb line is generated according to the curb point extracted.
The beneficial effect of above-mentioned technical proposal provided in an embodiment of the present invention includes at least:
1, this programme extracts corresponding curb point from every scan line in laser point cloud, according to the road extracted
Effective curb line is generated along point.The extraction of curb point is using single scan line as computing unit, and computation complexity is low, and calculation amount is small,
It can be suitable for the operation of scale high-accuracy data acquisition；And obstacle object point introduces few, accuracy in computation height.
2, all scanning elements of single scan line unilateral side are ranked up according to the size of reflective distance, wherein reflective distance
Equal scanning element is ranked up according still further to the size of height value, forms the queue of scanning element；From small to large according to reflective distance
Sequence, successively adjacent scanning element two-by-two in more above-mentioned queue finds out difference in height is greater than the difference in height threshold value of setting the
A pair of adjacent scanning element, is greater than in the adjacent scanning element of the difference in height threshold value of setting from the first pair of difference in height found out, mentions
Take curb point of the biggish scanning element of height value as this scan line in the side.Only consider single scan line scanning single side point
Data are not needed to read around currently processed point around point, be calculated simply, calculation amount is small, and the noise that calculated result includes
Point is considerably less, does not need the filtration treatment of subsequent complexity；Just terminate current scan line after calculating to a curb point when front side
Judgement, greatly reduces calculation amount, and reduce the introducing of obstacle object point in curb point, improves accuracy；Only it need to consider to sweep
The reflective distance and height value of described point, without considering the reflected intensity attribute of scanning element, thus this programme does not depend on curb material,
Curb suitable for any material；Suitable for any curb shape, because without the concern for the arrangement regulation of curb reflection point；Energy
Enough processing inclined-plane roads avoid judging by accident because not handling continuity point.This programme calculates simply, and introducing error is few, the scope of application
Extensively.
3, after obtaining the left and right side curb point of all scan lines, the left side curb of all scan lines is calculated separately
The right side curb point of point and all scan lines, obtains the curb line of both sides of the road, simplifies calculating process, reduce calculation amount,
Improve counting accuracy.
4, curb line seek be not directly obtained by curb point, but first by curb point generate curb cluster；The road Zai You
Along fasciation at the curb line of hash；And then using collecting vehicle trajectory line as benchmark line, the curb line of hash is calculated to acquiring wheel paths
The maximum probability distance of line screens the curb line of hash；Finally it is merged into effectively by the curb line of the hash after screening
Curb line.Each step of the method is all the process that curb line is sought, barrier Points And lines are rejected, and ensure that final meter layer by layer
Calculate the precision and accuracy of result.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the flow chart of the curb recognition methods based on laser point cloud described in the embodiment of the present invention；
Fig. 2 is laser point distribution schematic diagram described in the embodiment of the present invention；
Fig. 3 is the specific flow chart of step S100 shown in Fig. 1；
Fig. 4 is the specific flow chart of step S140 shown in Fig. 3；
Fig. 5 is that level road curb point described in the embodiment of the present invention identifies schematic diagram；
Fig. 6 is that tilted road surface curb point described in the embodiment of the present invention identifies schematic diagram；
Fig. 7 identifies schematic diagram for the curb point of curb in irregular shape described in the embodiment of the present invention；
Fig. 8 is the specific flow chart of step S200 shown in Fig. 1；
Fig. 9 is both sides of the road curb point described in the embodiment of the present invention, curb cluster, the curb line of hash and the signal of barrier line
Figure；
Figure 10 is the specific flow chart of step S230 shown in Fig. 8；
Figure 11 is that collecting vehicle tracing point regression fit described in the embodiment of the present invention obtains collecting vehicle trajectory line schematic diagram；
Figure 12 is the structural schematic diagram of the curb identification device based on laser point cloud described in the embodiment of the present invention；
Figure 13 is the structural schematic diagram of extraction module M100 shown in Figure 12；
Figure 14 is the structural schematic diagram of data map collection of material equipment described in the embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
In order to solve curb existing in the prior art identification dependent on curb material, curb shape, road level degree,
Laser Acquisition Instrument precision etc., and problem computationally intensive, that error rate is high, accuracy is low, the embodiment of the present invention provide one kind and are based on
The curb recognition methods of laser point cloud can accurately identify curb line, and calculate simply that calculation amount is small, can be suitable for appointing
Meaning construction material curb, arbitrary shape curb, horizontal road and inclined-plane road etc. are suitable for scale high-accuracy data acquisition and make
Industry.
Embodiment
The embodiment of the present invention provides a kind of curb recognition methods based on laser point cloud, and process is as shown in Figure 1, include such as
Lower step:
Step S100: corresponding curb point is extracted from every scan line in laser point cloud.
As shown in Fig. 2, laser point cloud is made of a large amount of laser scanning point, when storage, is swept according to laser one by one
Retouch line tissue.Using single scan line as computing unit, corresponding road is extracted from every scan line that laser point cloud includes
Along point.
Step S200: effective curb line is generated according to the curb point extracted.
Using single scan line as computing unit, computation complexity is low, and calculation amount is small, can for the extraction of the present embodiment curb point
Suitable for scale high-accuracy data acquisition operation；And obstacle object point introduces less, does not need the filtration treatment of subsequent complexity, calculates
Accuracy is high.
Specifically, as shown in figure 3, above-mentioned steps S100 can also be realized by following process:
Step S110: it is directed to every scan line, extracts the sweep center point of this scan line.
The nearest scanning element of the horizontal distance of the laser scanner of distance acquisition laser point cloud in every scan line is extracted, is made
For the sweep center point of this scan line.
According to the lateral distance attribute of laser scanning point, the laser that distance acquires the laser point cloud in every scan line is swept
The nearest scanning element of the horizontal distance of instrument is retouched, the scanning element of the sweep center point of this scan line is closest to, extracts every
The nearest scanning element of the horizontal distance of laser scanner described in distance in scan line, the sweep center point as this scan line.
Step S120: centered on the sweep center point of every scan line, this scan line is divided into the left and right sides, is obtained
The left scan laser point sequence and right side scanning laser point sequence of this scan line.
As shown in Fig. 2, using the sweep center point of a scan line in scheming as the coordinate origin of X-axis and Y-axis, wherein X-axis
Scanning element is represented to the lateral distance of sweep center point, Y-axis represents the height value of scanning element.Scan line shown in Fig. 2 is with this
Its scanning element is divided into the left and right sides centered on the sweep center point of bar line.Centered on the sweep center point of every scan line,
Scanning element in every scan line is divided into the left and right sides, the left scan laser point sequence and right side for obtaining this scan line are swept
Retouch laser point sequence.
Step S130: the left scan laser point sequence and right side scanning laser point sequence of every scan line are carried out respectively
Denoising, the right side scanning laser point sequence after left scan laser point sequence and denoising after being denoised.
The left scan laser point sequence and right side scanning laser point sequence for every scan line that above-mentioned steps obtain include
Have a large amount of Noise scan point, in order to reduce calculation amount and reduce curb point False Rate, curb point identification before, first have into
Row denoising.For example, lateral reflective distance to be less than to the laser point for acquiring the width half of collecting vehicle of the laser point cloud
It gets rid of, for example the width of collecting vehicle is 2 meters, is then got rid of respectively in left scan laser point cloud and right side scanning laser point cloud
Laser point of the lateral reflective distance less than 1 meter, can reduce calculation amount in this way；In addition, reading height value, that is, Y of laser scanning point
Value removes the laser point that Y value is greater than height threshold, for example height threshold is set as 2 meters, and laser point of the Y value greater than 2 meters may
Caused by being the electric wire above road, the laser point for getting rid of Y value greater than height threshold is also kept away while reducing calculation amount
Exempt from for the laser point to be mistaken for curb point, has reduced curb point False Rate.
Other types noise spot that may be present can also be removed according to the actual situation, is not limited to above two type, passed through
Cross the left scan laser point sequence after this scan line denoising is denoised and the right side scanning laser point sequence after denoising
Column.
Step S140: this scanning is extracted respectively from left scan laser point sequence and right side scanning laser point sequence
The left side curb point and right side curb point of line.
The present embodiment is divided into the left and right sides centered on the sweep center point of every scan line, by laser point cloud, with single
Scan line unilateral side is computing unit；Denoising first is carried out to scanning element before the extraction of curb point.Calculating step is simplified, is subtracted
Small calculation amount, and obstacle object point introduces few, does not need the filtration treatment of subsequent complexity, accuracy in computation height.
Specifically, in above-mentioned steps S140 left side the curb point and right side curb point of this scan line extraction, Ke Yitong
It crosses the left scan laser point sequence after the denoising of this scan line and the right side scanning laser point sequence after denoising, such as Fig. 4
It is shown, it proceeds as follows respectively:
Step S141: all scanning elements are ranked up according to the size of reflective distance, and wherein reflective distance is equal sweeps
Described point is ranked up according still further to the size of height value, forms the queue of scanning element.
Such as can arrange the side scanning element of this scan line according to the ascending sequence of reflective distance, if scanning
The reflective distance of point is equal, arranges according still further to the ascending sequence of its height value, obtains the queue of scanning element.Optionally,
The side scanning element of this scan line can be arranged according to the descending sequence of reflective distance, if the reflective distance of scanning element
It is equal, it is ordered from large to small according still further to its height value, obtains the queue of scanning element.
Step S142: according to the sequence of reflective distance from small to large, successively compare adjacent scanning two-by-two in scanning element queue
Point finds out first pair of adjacent scanning element that difference in height is greater than the difference in height threshold value of setting.
The difference in height threshold value be it is preset, can empirically be worth to set, such as can be set to
Other numerical value can also be arranged, herein without limitation in 20cm according to the actual situation.
Step S143: extraction height is worth curb point of the biggish scanning element as this scan line.
The biggish scanning element conduct of wherein height value is extracted from first pair of adjacent scanning element that above-mentioned steps are found out
The curb point of this scan line side.
The identification signal of curb point when Fig. 5, Fig. 6 and Fig. 7 are respectively road level, sideways inclined and curb in irregular shape
Figure.It can be seen that the identification of the present embodiment curb point is not influenced by sideways inclined, curb shape difference, it is applied widely.
The some of seeking of curb point uses following methods in the prior art: comparing laser scanning point height and acquisition truck position
Pavement-height be then determined as curb point after the difference in height of the two is more than certain threshold values.Such method can not handle inclined-plane road
Road, such as the turn fractions of super expressway, outside road is higher than inside road, and outside Road millet cake can be erroneously identified as
Curb point.And the above method of the present embodiment, as shown in fig. 6, can be very good to judge the curb point of tilted road surface.
The some of seeking of curb point also uses following methods in the prior art: according to curb reflection point in same scanning slice table
Reveal stable serial number continuity and slope having the same, judges these continuous points for curb point.Such scheme is only applicable in
Curb is the road of striped blocks object.And the above method of the present embodiment, as shown in fig. 7, being suitable for the curb of any shape.
After the side of a scan line recognizes a curb point, just terminate in this scan line side scanning point sequence
The judgement of curb point.
Acquire the left side curb point and right side curb point of this scan line respectively according to the above method.Left side curb point and right side
The extraction step of curb point is mutually indepedent, without sequencing, can first extract left side curb point, can also first extract right side road
Along point, can also left side curb point and right side curb point extract simultaneously, herein without limitation.
All scan lines are subjected to aforesaid operations respectively, obtain the left side curb point and right side curb point of all scan lines.
The present embodiment just terminates the judgement that current scan line works as front side after calculating to a curb point, greatly reduce calculating
Amount, and reduce the introducing of obstacle object point in curb point, improve accuracy；The extraction of curb point need to only consider the anti-of scanning element
Distance and height value are penetrated, without considering the reflected intensity attribute of scanning element, thus this programme does not depend on curb material, is suitable for appointing
The curb of what material；Suitable for any curb shape, because without the concern for the arrangement regulation of curb reflection point；It is capable of handling tiltedly
Face road avoids judging by accident because not handling continuity point.Therefore this programme calculates simply, introducing error is few, applied widely.
Specifically, above-mentioned steps S200 can also be realized in the following way, as shown in figure 8, by a left side for all scan lines
Dypass edge point and the right side curb point of all scan lines carry out operations described below respectively:
Step S210: it carries out clustering and obtains curb cluster.
Because of the reason of barrier, vehicle etc., the curb point that above-mentioned steps obtain is not continuous, it is therefore desirable to be gathered
Alanysis.A kind of clustering method is selected, curb point is subjected to clustering, obtains curb cluster.
A kind of clustering method is selected, curb point is subjected to clustering, obtains curb cluster.Such as kd-tree can be selected
Clustering method, with distance for main judgment basis, set distance threshold value, for example, it can be set to distance threshold is 5cm, the road Ruo Liangge
Distance between point is less than 5cm, then judges that the two curb points belong to same curb cluster.The distance can select Euclid
Distance can also select other distances.
When one cluster after the completion of, that is, after having obtained a curb cluster, judge it includes curb point number whether be greater than
The amount threshold of setting, if so, retaining the curb cluster；If it is not, then judging that the curb cluster for invalid curb cluster, is deleted.
Until getting all curb clusters.
Step S220: curb cluster is subjected to regression fit, the curb line hashed.
Curb cluster obtained by the above method is subjected to regression fit, obtains the curb line of a plurality of hash.
As shown in figure 9, left side is close to collecting vehicle, the curb point continuity of extraction is good, the obstacle object point that includes is few；Right side from
Farther out, curb cluster poor continuity that curb point and its clustering obtain, the obstacle object point for including are more for collecting vehicle.
Step S230: the curb line of hash is screened.
Step S240: the curb line of hash is merged, and obtains effective curb line.
The curb line of hash after screening is subjected to regression fit, finally obtains effective curb line.
In the above method of the present embodiment, seeking for curb line is not to be directly obtained by curb point, but elder generation is by curb
Point generates curb cluster, then by curb fasciation at the curb line of hash, and then screens to the curb line of the hash, finally by
The curb line of hash after screening is merged into effective curb line, each step of the method be all curb line seek, obstacle object point
The process rejected with line, ensure that the precision and accuracy of final calculation result layer by layer.
Specifically, as shown in Figure 10, above-mentioned steps S230 can also be realized by following process:
Step S231: collecting vehicle trajectory line is obtained.
By the sweep center point in every scan line in the laser point cloud, as the acquisition track in this scan line
Mark point；As shown in figure 11, regression fit is carried out to the sorted points of all collecting vehicle tracing points, obtains acquisition wheel paths
Line.
Step S232: the curb line of hash is calculated to the maximum probability distance L of collecting vehicle trajectory line.
By the curb line of the step S220 hash obtained, pass through curb line length and curb line to collecting vehicle trajectory line
Apart from the two parameters, to calculate curb line to the average distance of collecting vehicle trajectory line, as the distance L of maximum probability.
Step S233: judge whether the curb line of every hash is greater than L × (1- to the distance of the collecting vehicle trajectory line
N%) and it is less than L × (1+n%).
The ratio n% of maximum probability distance be it is preset, empirically can be set to 15%, can also be according to reality
The difference of border situation is set as different numerical value.Judge every hash curb line to the collecting vehicle trajectory line distance whether
Greater than L × (1-n%) and it is less than L × (1+n%).
For example, it is 5 meters that maximum probability distance, which is calculated, it is 15% that n%, which empirically can be set, judges every hash
Curb line to the collecting vehicle trajectory line distance whether be greater than 5 meters × (1-15%) and less than 5 meters × (1+15%), be
It is no to be greater than 4.25 meters and less than 5.75 meters.
If so, executing step S234；If it is not, step S235.
Step S234: retain the curb line.
If the distance of the curb line of hash to the collecting vehicle trajectory line is greater than L × (1-n%) and is less than L × (1+n%),
Then the curb line is effective, retains the curb line.
Step S235: the curb line is deleted.
If the distance of the curb line of hash to the collecting vehicle trajectory line not less than L × (1+n%) or is not more than L × (1-
N%), then the curb line is barrier line, deletes the curb line.
The present embodiment above method calculates the curb line of hash to collecting vehicle trajectory line using collecting vehicle trajectory line as benchmark line
Maximum probability distance, and then the curb line of hash is screened, has deleted barrier line, simplified subsequent calculating, make
The effective curb line accuracy rate finally acquired is higher.
Based on the same inventive concept, the embodiment of the present invention also provides a kind of curb identification device based on laser point cloud, energy
Enough realize the above-mentioned curb recognition methods based on laser point cloud.The device can be set in electronic navigation, electronic map, high-precision
In the equipment such as data map collection of material, the structure of the device is as shown in figure 12, comprising:
Extraction module M100, for extracting corresponding curb point from every scan line in laser point cloud；Generate mould
Block M200, the curb point for being extracted according to the extraction module M100 generate effective curb line.
Preferably, as shown in figure 13, said extracted module M100, comprising:
First extracting sub-module M110 extracts the sweep center point of the scan line for being directed to every scan line；It divides
Submodule M120, for centered on the sweep center point for the scan line extracted by the first extracting sub-module M110,
The scan line is divided into the left and right sides, obtains the left scan laser point sequence and right side scanning laser point sequence of the scan line
Column；Denoise submodule M130, the left scan laser point sequence for obtaining to the division submodule M120 and described
Right side scanning laser point sequence carries out denoising respectively, the left scan laser point sequence after being denoised and the right side after denoising
Side scanning laser point sequence；Second extracting sub-module M140, for from the left side after the denoising that the denoising submodule M130 is obtained
Corresponding left side curb point and the right side are extracted respectively in right side scanning laser point sequence after side scanning laser point sequence and denoising
Dypass is along point.
Preferably, above-mentioned first extracting sub-module M110, is specifically used for, and it is described sharp to extract distance acquisition in every scan line
The nearest scanning element of the horizontal distance of the laser scanner of luminous point cloud, the sweep center point as this scan line.
Preferably, above-mentioned second extracting sub-module M140, is specifically used for:
After left scan laser point sequence and the denoising after the denoising obtained to the denoising submodule M130
Right side scanning laser point sequence execute operations described below respectively:
All scanning elements are ranked up according to the size of reflective distance, wherein the equal scanning element of reflective distance according still further to
The size of height value is ranked up, and forms the queue of scanning element；
According to the sequence of reflective distance from small to large, successively adjacent scanning element two-by-two in the queue, finds out height
Degree difference is greater than first pair of adjacent scanning element of the difference in height threshold value of setting；
The biggish scanning element of wherein height value is extracted as this from the first pair of adjacent scanning element found out
The curb point of the scan line side.
Preferably, above-mentioned generation module M200, is specifically used for:
To the right side of left side the curb point and all scan lines of the second extracting sub-module M140 all scan lines extracted
Dypass edge point executes operations described below respectively:
It carries out clustering and obtains curb cluster；
The curb cluster is subjected to regression fit, the curb line hashed；
The curb line of hash is merged, effective curb line of respective side is obtained.
Preferably, above-mentioned generation module M200, is also used to: after obtaining the curb line of the hash, by the laser
The sweep center point of every scan line in point cloud, the collecting vehicle tracing point as this scan line；To all collecting vehicles
Tracing point carries out regression fit, obtains collecting vehicle trajectory line；According between the curb line of the hash and the collecting vehicle trajectory line
Distance, the curb line of the hash is screened；The curb line of hash after screening is merged.
Preferably, the generation module M200, is specifically used for:
The curb line of the hash is calculated to the maximum probability distance L of the collecting vehicle trajectory line；
Judge whether the curb line of every hash is greater than L × (1-n%) to the distance of the collecting vehicle trajectory line and is less than L
× (1+n%), the n% is less than 1；
If so, the curb line is effective, retain the curb line；
If it is not, then the curb line is barrier line, the curb line is deleted.
Based on the same inventive concept, the embodiment of the present invention also provides a kind of data map collection of material equipment, the equipment
Structure is as shown in figure 14, comprising:
Point cloud obtains module T100, for obtaining the laser point cloud data；Curb extraction module T200 is used for from described
Point cloud obtains in every scan line in the laser point cloud that module T100 is obtained and extracts corresponding curb point；According to described
Curb point generates effective curb line；Road equipment extraction module T300, for what is extracted according to the curb extraction module T200
Effective curb line divides described cloud and obtains the laser point cloud data that module T100 is obtained, and extracts road surface earth's surface information
With the road equipment information of both sides of the road；Map data creating and modeling module T400, for according to the curb extraction module
The road surface earth's surface information and road that the effective curb line and the road equipment extraction module T300 that T200 is extracted extract
The road equipment information of road two sides carries out map data creating and three-dimension modeling.
In some alternative embodiments, the earth's surface information that the road equipment extraction module T300 is extracted can wrap
Include lane rotation arrow, earth's surface text, stop line etc.；The road equipment information may include road information plate, caution board, every
From guardrail, lamp stand etc..
About the device and equipment in above-described embodiment, wherein modules execute the concrete mode of operation related
It is described in detail in the embodiment of this method, no detailed explanation will be given here.
Based on the same inventive concept, the embodiment of the invention also provides a kind of non-transitorycomputer readable storage medium,
It is stored thereon with computer instruction, is performed the steps of when the instruction is executed by processor
Corresponding curb point is extracted from every scan line in laser point cloud；
Effective curb line is generated according to the curb point extracted.
The above method and device of the embodiment of the present invention can accurately identify curb line, be suitable for any construction material
Curb, arbitrary shape curb, horizontal road and inclined-plane road etc.；And calculation amount is small, is suitable for scale high-accuracy data acquisition
Operation.
Unless otherwise specific statement, term such as handle, calculate, operation, determination, display etc. can refer to it is one or more
A processing or the movement and/or process of computing system or similar devices, the movement and/or process will be indicated as processing system
It the data manipulation of the register of system or physics (such as electronics) amount in memory and is converted into and is similarly represented as processing system
Memory, register or other this type of information storage, transmitting or display equipment in other data of physical quantity.Information
Any one of a variety of different technology and methods can be used with signal to indicate.For example, in above description
Data, instruction, order, information, signal, bit, symbol and the chip referred to can use voltage, electric current, electromagnetic wave, magnetic field or grain
Son, light field or particle or any combination thereof indicate.
It should be understood that the particular order or level of the step of during disclosed are the examples of illustrative methods.Based on setting
Count preference, it should be appreciated that in the process the step of particular order or level can be in the feelings for the protection scope for not departing from the disclosure
It is rearranged under condition.Appended claim to a method is not illustratively sequentially to give the element of various steps, and not
It is to be limited to the particular order or level.
In above-mentioned detailed description, various features are combined together in single embodiment, to simplify the disclosure.No
This published method should be construed to reflect such intention, that is, the embodiment of theme claimed needs clear
The more features of the feature stated in each claim to Chu.On the contrary, that reflected such as appended claims
Sample, the present invention are in the state fewer than whole features of disclosed single embodiment.Therefore, appended claims is special
This is expressly incorporated into detailed description, and wherein each claim is used as alone the individual preferred embodiment of the present invention.
It should also be appreciated by one skilled in the art that various illustrative logical boxs, mould in conjunction with the embodiments herein description
Electronic hardware, computer software or combinations thereof may be implemented into block, circuit and algorithm steps.In order to clearly demonstrate hardware and
Interchangeability between software surrounds its function to various illustrative components, frame, module, circuit and step above and carries out
It is generally described.Hardware is implemented as this function and is also implemented as software, depends on specific application and to entire
The design constraint that system is applied.Those skilled in the art can be directed to each specific application, be realized in a manner of flexible
Described function, still, this realization decision should not be construed as a departure from the scope of protection of this disclosure.
The step of method in conjunction with described in the embodiments herein or algorithm, can be embodied directly in hardware, be held by processor
Capable software module or combinations thereof.Software module can be located at RAM memory, flash memory, ROM memory, eprom memory,
The storage of eeprom memory, register, hard disk, mobile disk, CD-ROM or any other form well known in the art is situated between
In matter.A kind of illustrative storage medium is connected to processor, thus enable a processor to from the read information, and
Information can be written to the storage medium.Certainly, storage medium is also possible to the component part of processor.Pocessor and storage media
It can be located in ASIC.The ASIC can be located in user terminal.Certainly, pocessor and storage media can also be used as discrete sets
Part is present in user terminal.
For software implementations, technology described in this application can be with the module of the herein described function of execution (for example, mistake
Journey, function etc.) Lai Shixian.These software codes can store in memory cell and be executed by processor.Memory cell can
With realize in processor, also may be implemented outside the processor, in the latter case, it via various means by correspondence
It is coupled to processor, these are all well known in the art.
Description above includes the citing of one or more embodiments.Certainly, in order to describe above-described embodiment and description portion
The all possible combination of part or method is impossible, but it will be appreciated by one of ordinary skill in the art that each implementation
Example can do further combinations and permutations.Therefore, embodiment described herein is intended to cover fall into the appended claims
Protection scope in all such changes, modifications and variations.In addition, with regard to term used in specification or claims
The mode that covers of "comprising", the word is similar to term " includes ", just as " including " solved in the claims as transitional word
As releasing.In addition, the use of any one of specification in claims term "or" being to indicate " non-exclusionism
Or ".
Claims (10)
1. a kind of curb recognition methods based on laser point cloud characterized by comprising
Corresponding curb point is extracted from every scan line in laser point cloud；
Effective curb line is generated according to the curb point extracted.
2. the method as described in claim 1, which is characterized in that extracted in every scan line from laser point cloud pair
The curb point answered, comprising:
For every scan line, the sweep center point of the scan line is extracted；
Centered on the sweep center point of the scan line, the scan line is divided into the left and right sides, obtains the scan line
Left scan laser point sequence and right side scanning laser point sequence；
The scan line is extracted respectively from the left scan laser point sequence and the right side scanning laser point sequence
Left side curb point and right side curb point.
3. method according to claim 2, which is characterized in that from the left scan laser point sequence and right side scanning laser
The left side curb point and right side curb point of the scan line are extracted in point sequence respectively, comprising:
Operations described below is executed respectively to the left scan laser point sequence and the right side scanning laser point sequence:
All scanning elements are ranked up according to the size of reflective distance, wherein the equal scanning element of reflective distance is according still further to height
The size of value is ranked up, and forms the queue of scanning element；
According to the sequence of reflective distance from small to large, successively adjacent scanning element two-by-two in the queue, finds out difference in height
Greater than first pair of adjacent scanning element of the difference in height threshold value of setting；
The biggish scanning element of wherein height value is extracted from the first pair of adjacent scanning element found out to scan as this
Curb point of the line in the side.
4. method according to claim 2, which is characterized in that the curb point that the basis extracts generates effective
Curb line, comprising:
The right side curb point of left side curb point and all scan lines to all scan lines executes operations described below respectively:
It carries out clustering and obtains curb cluster；
The curb cluster is subjected to regression fit, the curb line hashed；
The curb line of hash is merged, effective curb line of respective side is obtained.
5. a kind of curb identification device based on laser point cloud characterized by comprising
Extraction module, for extracting corresponding curb point from every scan line in laser point cloud；
Generation module, the curb point for being extracted according to the extraction module generate effective curb line.
6. device as claimed in claim 5, which is characterized in that the extraction module, comprising:
First extracting sub-module extracts the sweep center point of the scan line for being directed to every scan line；
Submodule is divided, for centered on the sweep center point for the scan line extracted by first extracting sub-module,
The scan line is divided into the left and right sides, obtains the left scan laser point sequence and right side scanning laser point sequence of the scan line
Column；
Second extracting sub-module, the left scan laser point sequence and the right side for being obtained from the division submodule
The left side curb point and right side curb point of the scan line are extracted in scanning laser point sequence respectively.
7. device as claimed in claim 6, which is characterized in that second extracting sub-module is specifically used for: to the left side
Scanning laser point sequence and the right side scanning laser point sequence execute operations described below respectively: by all scanning elements according to reflection away from
From size be ranked up, wherein the equal scanning element of reflective distance is ranked up according still further to the size of height value, formed scanning
The queue of point；According to the sequence of reflective distance from small to large, successively adjacent scanning element two-by-two in the queue, finds out height
Degree difference is greater than first pair of adjacent scanning element of the difference in height threshold value of setting；From the first pair of adjacent scanning element found out
Extract wherein curb point of the biggish scanning element of height value as this scan line side.
8. device as claimed in claim 6, which is characterized in that the generation module is specifically used for:
The right side curb point of left side curb point and all scan lines to all scan lines of second extracting sub-module extraction
Operations described below is executed respectively: being carried out clustering and is obtained curb cluster；The curb cluster is subjected to regression fit, the road hashed
Along the line；The curb line of hash is merged, effective curb line of respective side is obtained.
9. a kind of data map collection of material equipment characterized by comprising
Point cloud obtains module, for obtaining the laser point cloud data；
Curb extraction module is extracted for obtaining in every scan line in the laser point cloud that module obtains from described cloud
Corresponding curb point out；Effective curb line is generated according to the curb point；
Road equipment extraction module, effective curb line for extracting according to the curb extraction module divide described cloud
The laser point cloud data that module obtains is obtained, the road equipment information of road surface earth's surface information and both sides of the road is extracted；
Map data creating and modeling module, effective curb line for being extracted according to the curb extraction module and described
The road equipment information of the road surface earth's surface information and both sides of the road that road equipment extraction module extracts, carries out map datum system
Work and three-dimension modeling.
10. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer instruction, when the instruction is held by processor
It is performed the steps of when row
Corresponding curb point is extracted from every scan line in laser point cloud；
Effective curb line is generated according to the curb point extracted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810027972.8A CN110033482A (en) | 2018-01-11 | 2018-01-11 | A kind of curb recognition methods and device based on laser point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810027972.8A CN110033482A (en) | 2018-01-11 | 2018-01-11 | A kind of curb recognition methods and device based on laser point cloud |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110033482A true CN110033482A (en) | 2019-07-19 |
Family
ID=67234672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810027972.8A Pending CN110033482A (en) | 2018-01-11 | 2018-01-11 | A kind of curb recognition methods and device based on laser point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110033482A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110736999A (en) * | 2019-10-24 | 2020-01-31 | 北京交通大学 | Railway turnout detection method based on laser radar |
| WO2021128777A1 (en) * | 2019-12-23 | 2021-07-01 | Suzhou Zhijia Science & Technologies Co., Ltd. | Method, apparatus, device, and storage medium for detecting travelable region |
| CN113835103A (en) * | 2021-09-22 | 2021-12-24 | 深圳市镭神智能系统有限公司 | Rail obstacle detection method and system and computer equipment |
| CN114425774A (en) * | 2022-01-21 | 2022-05-03 | 深圳优地科技有限公司 | Method and apparatus for recognizing walking path of robot, and storage medium |
| CN115015964A (en) * | 2022-05-13 | 2022-09-06 | 深圳优地科技有限公司 | Road edge detection method and device, terminal equipment and storage medium |
| CN116449335A (en) * | 2023-06-14 | 2023-07-18 | 上海木蚁机器人科技有限公司 | Method and device for detecting drivable area, electronic device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090271114A1 (en) * | 2008-04-28 | 2009-10-29 | Herbert William J | Curb detection device for motor vehicles |
| CN103778429A (en) * | 2014-01-24 | 2014-05-07 | 青岛秀山移动测量有限公司 | Method for automatically extracting road information in vehicle-mounted laser scanning point cloud |
| CN105551016A (en) * | 2015-12-02 | 2016-05-04 | 百度在线网络技术（北京）有限公司 | Method and device of road edge identification on the basis of laser-point cloud |
| US20170030706A1 (en) * | 2015-07-30 | 2017-02-02 | Keyence Corporation | Measurement Target Measuring Program, Measurement Target Measuring Method, And Magnifying Observation Device |
| CN106842231A (en) * | 2016-11-08 | 2017-06-13 | 长安大学 | A kind of road edge identification and tracking |
| CN107272019A (en) * | 2017-05-09 | 2017-10-20 | 深圳市速腾聚创科技有限公司 | Curb detection method based on Laser Radar Scanning |
-
2018
- 2018-01-11 CN CN201810027972.8A patent/CN110033482A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090271114A1 (en) * | 2008-04-28 | 2009-10-29 | Herbert William J | Curb detection device for motor vehicles |
| CN103778429A (en) * | 2014-01-24 | 2014-05-07 | 青岛秀山移动测量有限公司 | Method for automatically extracting road information in vehicle-mounted laser scanning point cloud |
| US20170030706A1 (en) * | 2015-07-30 | 2017-02-02 | Keyence Corporation | Measurement Target Measuring Program, Measurement Target Measuring Method, And Magnifying Observation Device |
| CN105551016A (en) * | 2015-12-02 | 2016-05-04 | 百度在线网络技术（北京）有限公司 | Method and device of road edge identification on the basis of laser-point cloud |
| CN106842231A (en) * | 2016-11-08 | 2017-06-13 | 长安大学 | A kind of road edge identification and tracking |
| CN107272019A (en) * | 2017-05-09 | 2017-10-20 | 深圳市速腾聚创科技有限公司 | Curb detection method based on Laser Radar Scanning |
Non-Patent Citations (2)
| Title |
|---|
| 刘如飞等: "一种车载激光点云数据中道路自动提取方法", 《武汉大学学报》 * |
| 段建民等: "基于多层激光雷达的道路信息提取算法", 《控制工程》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110736999A (en) * | 2019-10-24 | 2020-01-31 | 北京交通大学 | Railway turnout detection method based on laser radar |
| CN110736999B (en) * | 2019-10-24 | 2021-11-02 | 北京交通大学 | Railway turnout detection method based on laser radar |
| WO2021128777A1 (en) * | 2019-12-23 | 2021-07-01 | Suzhou Zhijia Science & Technologies Co., Ltd. | Method, apparatus, device, and storage medium for detecting travelable region |
| CN113835103A (en) * | 2021-09-22 | 2021-12-24 | 深圳市镭神智能系统有限公司 | Rail obstacle detection method and system and computer equipment |
| CN114425774A (en) * | 2022-01-21 | 2022-05-03 | 深圳优地科技有限公司 | Method and apparatus for recognizing walking path of robot, and storage medium |
| CN114425774B (en) * | 2022-01-21 | 2023-11-03 | 深圳优地科技有限公司 | Robot walking road recognition method, robot walking road recognition device, and storage medium |
| CN115015964A (en) * | 2022-05-13 | 2022-09-06 | 深圳优地科技有限公司 | Road edge detection method and device, terminal equipment and storage medium |
| CN116449335A (en) * | 2023-06-14 | 2023-07-18 | 上海木蚁机器人科技有限公司 | Method and device for detecting drivable area, electronic device and storage medium |
| CN116449335B (en) * | 2023-06-14 | 2023-09-01 | 上海木蚁机器人科技有限公司 | Method and device for detecting drivable area, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033482A (en) | A kind of curb recognition methods and device based on laser point cloud | |
| CN110084116B (en) | Road surface detection method, road surface detection device, computer equipment and storage medium | |
| CN109583280A (en) | Lane detection method, apparatus, equipment and storage medium | |
| He et al. | Lane marking detection based on convolution neural network from point clouds | |
| CN113366532B (en) | Point cloud based segmentation processing method and device, computer equipment and storage medium | |
| CN112200171B (en) | Road point cloud extraction method based on scanning lines | |
| CN105260701A (en) | Front vehicle detection method applied to complex scene | |
| CN115239644B (en) | Concrete defect identification method, device, computer equipment and storage medium | |
| CN108074232B (en) | Voxel segmentation-based airborne LIDAR building detection method | |
| CN110991215B (en) | Lane line detection method and device, storage medium and electronic equipment | |
| CN110660072B (en) | Method and device for identifying straight line edge, storage medium and electronic equipment | |
| CN112819700B (en) | Denoising method and device for point cloud data and readable storage medium | |
| CN113989765A (en) | Detection method and detection device for rail obstacle and readable storage medium | |
| CN114842166A (en) | Negative obstacle detection method, system, medium, and apparatus applied to structured road | |
| JP2023152480A (en) | Map data generating method, map data generating apparatus, and map data generating program | |
| CN116740670A (en) | Obstacle segmentation recognition method and system | |
| CN115728781A (en) | Small obstacle detection method and device based on laser radar point cloud | |
| CN112200868A (en) | Positioning method and device and vehicle | |
| CN113534170A (en) | Lane line detection method, data processing unit and vehicle-mounted laser radar system | |
| CN115661784B (en) | Intelligent traffic-oriented traffic sign image big data identification method and system | |
| CN116434189A (en) | Road edge detection method, device, equipment and storage medium | |
| CN114782925B (en) | Highway guardrail vectorization method and device based on vehicle-mounted LIDAR data | |
| CN115937454B (en) | Method and device for automatically placing tree models in large-scale city scene | |
| CN111737508B (en) | Map vector extraction method, device, equipment and storage medium | |
| CN114758096A (en) | Road edge detection method, device, terminal equipment and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 110000 No. 861-6, shangshengou village, Hunnan District, Shenyang City, Liaoning Province Applicant after: Shenyang Meihang Technology Co.,Ltd. Address before: 110167 International Software Park E06, Hunnan New District, Shenyang City, Liaoning Province Applicant before: SHENYANG MXNAVI Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190719 |