CN108615452B - A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy - Google Patents
A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy Download PDFInfo
- Publication number
- CN108615452B CN108615452B CN201810286122.XA CN201810286122A CN108615452B CN 108615452 B CN108615452 B CN 108615452B CN 201810286122 A CN201810286122 A CN 201810286122A CN 108615452 B CN108615452 B CN 108615452B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- section
- people
- resolution ratio
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000000877 morphologic effect Effects 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims description 9
- 238000005530 etching Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 description 5
- 238000005054 agglomeration Methods 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/006—Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Ecology (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy, and steps are as follows: S1, being mapped to each tracing point in two-dimensional grid according to longitude and latitude, so that tracing point, which is changed into image, to be indicated；S2, to the image obtained in step S1, sampled to reduce resolution ratio；S3, to the image obtained in step S2, denoised, and reject isolated pixel point；S4, to the image obtained in step S3, carry out Morphological scale-space；S5, to the image obtained in step S4, denoise again and reduce resolution ratio again；S6, to the image obtained in step S5, identify section, and mark the joint between section and section；S7, to being obtained in step S6 as a result, every section is considered as node of graph, section joint is considered as the company side between node, depth-first traversal is carried out to graph structure, section is numbered.
Description
Technical field
The present invention relates to people's wheel paths technical field of data processing, and in particular to one kind is based at people's wheel paths point multiresolution
The unknown method for extracting roads of reason.
Background technique
Nowadays, electronic map have become building intelligent transportation system basis, and road net data be in electronic map not
The constituent that can lack accurately is extracted and timely updates road network information, very heavy for people's trip and automobile navigation
It wants.Traditional road network extracting method mainly divides three kinds, on the spot mapping, remote sensing image processing and the road based on track of vehicle data
It extracts on road.Specifically, first method is surveyed and drawn on the spot, this method accuracy rate is relatively high, but compares and take time and effort；Second
Kind method is remote sensing images to be carried out with image procossing, and then generate road network, and accuracy rate is relatively low.Above two method is to new logical
The modeling of capable road is not prompt enough, and is difficult to surveying and drawing promptly and accurately for some unknown roads in countryside.The third
Method is the method for extracting roads (patent publication No. CN106227726A) proposed in recent years based on track of vehicle data.With
Universal and location based service the extensive use of GPS mobile device, a large amount of mobile trajectory data can be collected and add
To utilize.These track datas are that the time and space to vehicle and pedestrian in road online mobile records, and can directly embody road friendship
The geometrical characteristic of logical net.In general, the sequence that the track of a mobile object is usually noted to be made of discrete tracing point
Column.Wherein each tracing point is represented in the position that some specific time object occurs, and is a discrete sampling to the track.
Sample rate is higher, and tracing point is spatially distributed closeer, and path accuracy is higher；On the contrary, sample rate is lower, then tracing point distribution is got over
Sparse, path accuracy is lower.The existing method for extracting roads (patent publication No. CN106227726A) based on track of vehicle is main
If finding new path by being clustered to track of vehicle path, this method compares the sampling essence for relying on track data
Degree, in the lower situation of sample rate, the precision of trajectory path is lower, also can by clustering obtained path to trajectory path
It is relatively rough, therefore generally require to combine existing road net data, further to be corrected.
For the deficiency of the above method, urgently put forward at present a kind of by being mentioned to tracing point progress multi-resolution hierarchy
The method for taking unknown road.
Summary of the invention
The purpose of the invention is to overcome the shortcomings of existing road network extracting method, one kind is provided by people's wheel paths
The method that point data carries out multiresolution analysis to extract unknown road, this method is by carrying out multiresolution to track point data
Denoising, sampling, interpolation and Morphological scale-space, unknown road and road joint are extracted, and to road carry out from
Dynamic segmentation and number.This method can carry out the standard of unknown road independent of existing road network information independently for track data
Really extract.
The purpose of the present invention can be reached by adopting the following technical scheme that:
A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy, is mapped to two-dimensional mesh for tracing point
It is one to obtain width by the method for the image procossings such as denoising, sampling and Morphological scale-space under multiresolution on lattice
The road axis of pixel unit, and the joint of road is further extracted on this basis, complete the segmentation and volume to road
Number.Specifically include the following steps:
S1, each tracing point is mapped in two-dimensional grid according to longitude and latitude, so that tracing point, which is changed into image, to be indicated；
S2, to the image I obtained in step S1, sampled to reduce resolution ratio；
S3, to the image I obtained in step S22, denoised, and reject isolated pixel point；
S4, to the image I obtained in step S33, carry out Morphological scale-space；
S5, to the image I obtained in step S44, denoise again and reduce resolution ratio again；
S6, to the image I obtained in step S55, identify section, and mark the joint between section and section；
S7, to being obtained in step S6 as a result, every section is considered as node of graph, section joint is considered as between node
Company side, to graph structure carry out depth-first traversal, section is numbered.
Further, step S1 specifically: each mobile object OiTrack SiIt can be expressed as the sequence of discrete loci point
Si={ τi,1,τi,2,…}.Wherein tracing point τi,k=< Oi,Ti,k,Xi,k,Yi,k> indicate mobile object OiIn time Ti,k, longitude
Xi,k, latitude Yi,kA position record.It, can be each event τ by the two-dimensional grid G by map partitioning at M × Ni,k
According to its latitude and longitude coordinates (Xi,k,Yi,k) be mapped in corresponding grid.Note is mapped to grid G (m, n) (1≤m≤M, (1≤n
≤ N) tracing point number be Υ (m, n).Construct resolution ratio be M × N image I, the image pixel I (m, n) (1≤m≤
M, the value setting of (1≤n≤N) are as follows:
Further, for the image I obtained in step S1, K is reduced1Resolution ratio (K again1It is normal number), it is differentiated
Rate isImage I1, by reducing K1Resolution ratio again can achieve down-sampled purpose, make high density pixel region
Agglomeration, and remove influence of the low-density pixel region to result.It can be convenient below after highdensity pixel region agglomeration
Denoising operation and Morphological scale-space operate.Low-density point pixel region is noise spot scattered on image, by low-density
The removal of pixel region can effectively remove influence of the noise to result.Specifically, image I1In each pixelValue be provided that
WhereinHere I (i, j) (1≤i≤M, 1≤j≤N) is
Image IM×NIn a pixel pixel value.S is a normal number threshold value.In order to only remove the noise of those low-density,
S is set as 10 in the present embodiment.
Then, for I1Each pixel I1(x, y), by itself and K around2*K2Average pixel value in region is compared
(K2It is normal number), and be by resolution ratio is obtained after its binaryzationImage I2, wherein I2The value of each pixel calculates such as
Under:
Wherein
Further, step S3 specifically: the low-resolution image I that will be obtained in step S22In isolated pixel block collection
Conjunction is removed, and is reduced influence of the noise to result, is obtained image I3。
Further, step S4 specifically: for the low-resolution image I obtained in step S33, carry out morphologic swollen
Swollen and etching operation, expansion and corrosion can make image more smooth and remove influence of the hole to result.Then it is refined
Operation, i.e., be thinned into the line that width is only a pixel for a wide line, obtain image I4。
Further, step S5 specifically: the image I that step S4 is obtained4In isolate pixel set of blocks be removed,
And it is down-sampled to achieve the purpose that reduce resolution ratio again.By reducing K3Times resolution ratio (K3<K2), obtaining resolution ratio isImage I5.Here down-sampled that the road disconnected after operation before can be made to be connected with each other.It is specific and
Speech, image I5Each pixelValue be provided that
Further, step S6 specifically: the image I that step S5 is obtained5In each pixel check its eight connectivity neighbour
Domain determines position corresponding to the pixel for the joint of road if non-zero pixels point number is greater than 2 in neighborhood.Scheming
As I5It is middle set zero for joint pixel after, the corresponding connection of the very big connected region of each non-zero pixels in the image
Section is connected by joint between section.
Further, step S7 specifically: section obtained for step S6 and joint are organized into graph structure, wherein
Each section is considered as the node of figure, if there are joints between two sections, joint is considered as even side, two nodes are connected
It connects, obtains graph structure.Depth-first traversal is carried out to the graph structure, successively node of graph (section) is compiled by traversal order
Number.
The present invention under multiresolution by denoising people's wheel paths point, sampling, interpolation and Morphological scale-space,
Efficiently extract road network information.Relative to the existing road network extracting method based on trajectory path cluster, the present invention has such as
Under advantage and effect:
1) present invention is analyzed and processed directly against people's wheel paths point, relative to traditional cluster based on trajectory path
The method of analysis present invention can be suitably applied to the lower rough track data of sample rate.
2) tracing point is handled using the method for multiresolution, by attenuating resolution ratio, highdensity tracing point is made to agglomerate,
And remove influence of the low-density tracing point region to result.
3) road network is extracted based entirely on people's wheel paths point, does not depend on existing road network information, can be directed to uncharted
Countryside carries out the extraction of accurately unknown road.
4) joint of road can be extracted simultaneously, and automatic segmentation and number are carried out to road, be conducive to statistics transfer
Probability.
Detailed description of the invention
Fig. 1 is the process of the unknown method for extracting roads disclosed by the invention based on people's wheel paths point multi-resolution hierarchy
Figure；
Fig. 2 is in the image display schematic diagram that tracing point is mapped to grid；
Fig. 3 is the result schematic diagram behind extraction section corresponding with Fig. 2；
Fig. 4 is the result schematic diagram for marking section joint, wherein five-pointed star represents joint.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Embodiment
The present embodiment is realized by process as shown in Figure 1, including seven key steps:
S1, each event on track is mapped in grid according to longitude and latitude, so that track is changed into image table
Show；
The specific implementation method of above-mentioned steps S1 is: by every track Si(1≤k≤m) can be expressed as discrete loci
The sequence S of eventi={ τi,k| k=1 ..., n }.Wherein event τi,k=< Oi,Ti,k,Xi,k,Yi,k> indicate mobile object Oi
In time Ti,k, longitude Xi,k, latitude Yi,kA position record.By map partitioning at the two-dimensional grid G of M*N, in the present embodiment
In, for two an equal amount of 2000*1300m2Area, do identical processing.The size for taking each grid is 5*5m2, institute
With available M=400, the best configuration of N=260.It can be each event τi,kAccording to its latitude and longitude coordinates (Xi,k,
Yi,k) be mapped in grid, the number that note is mapped to the tracing point of grid G (m, n) (1≤m≤M, 1≤n≤N) is Υ (m, n).
Construct the image I that resolution ratio is M × N, the value setting of the pixel I (m, n) (1≤m≤M, 1≤n≤N) of the image are as follows:
The result of image I is as shown in Figure 2.
S2, to the image I obtained in step S1, sampled to reduce resolution ratio；
Step S2 specifically: for the image I obtained in step S1, reduce K1Resolution ratio (K again1It is normal number), it obtains
Resolution ratioImage I1, by reducing K1Resolution ratio again can achieve down-sampled purpose, make high density pixel
The agglomeration of point region, and remove influence of the low-density pixel region to result.It can be square after highdensity pixel region agglomeration
Just subsequent denoising operation is operated with Morphological scale-space.Low-density point pixel region is noise spot scattered on image, by right
The removal of low-density pixel region can effectively remove influence of the noise to result.In the present embodiment, by K1It is set as 10,
Obtain resolution ratioImage I1, specifically, image I1In each pixelValue be provided that
WhereinHere I (i, j) (1≤i≤M, 1≤j≤N) is
Image IM×NIn a pixel pixel value.S is a normal number threshold value.In order to only remove the noise of those low-density,
S is set as 10 in the present embodiment.
Then for image I1In each pixel, by its pixel value and surrounding K2*K2Average pixel value in region carries out
Compare (K2It is normal number, K in this example2It can be set as 10), and be by resolution ratio is obtained after its binaryzationImage I2,
Middle I2The value of each pixel calculates as follows:
Wherein
S3, to the image I obtained in step S22, denoising is carried out, isolated point is picked；
The specific implementation method of above-mentioned steps S3 is: the collection for setting traversal range is combined into S={ s1,s2,s3,…,sn, it is right
Range s is traversed in eachi, each pixel in image is traversed, judges surrounding si*siOn boundary in (1≤i≤n) range
With the presence or absence of non-zero pixels point, if there is no non-zero pixels point then think the region pixel set of blocks be it is isolated, just will
si*siThe pixel value of all pixels point of range is set as zero.In order to can be very good to remove some isolated pixel set of blocks, this
S is taken as S={ 2,3,4 ..., 20 } in embodiment, after denoising, obtains image I3。
S4, to the image I obtained in step S33, carry out Morphological scale-space；
The specific implementation method of above-mentioned steps S4 is: for the image I obtained in S33, Morphological scale-space is carried out, first
The morphologic expansion of n times and etching operation are carried out, in the present embodiment, N is set as the natural number more than or equal to 5, because by 5
Expected result can be basically reached after secondary.
If A is image I3The set of the position of middle non-zero pixels, B are coordinate set { (b1,b2)|-1≤b1≤1,-1≤b2
≤ 1 }, to image I3Expansive working be specially calculate following location sets:
Wherein (B)zIndicate the translation of B: (B)z=c | and c=b+z, b ∈ B }, z ∈ Z2Indicate the amount of translation.By I3In belong toThe pixel value of position be set to 1, can be completed to I3Expansive working.The mathematical definition of corrosion is similar to expansion.DefinitionWherein AcIndicate the supplementary set of A, is defined as:
By I3In belong toThe pixel value of position be set to 1, be not belonging toThe pixel value of position be set to 0, can be completed to I3Corruption
Erosion operation.Then Refinement operation is carried out to image, a kind of common thinning algorithm look-up table is employed herein in we.Refinement operation
The line that width is only a pixel can be thinned into one wide line, finally obtain image I4。
S5, to the image I obtained in step S44, denoise and sample again to reduce resolution ratio again；
The specific implementation method of above-mentioned steps S5 is: the image I obtained to S44Two are carried out using the Denoising Algorithm in S3
Secondary denoising, the range for setting traversal here is identical with S3, takes S={ 2,3,4 ..., 20 }, then down-sampled again, i.e. reduction K3
Times resolution ratio (K3<K2), obtain image I5Resolution ratio beHere down-sampled to make by behaviour before
The road disconnected after work is connected with each other.In the present embodiment, K is taken3=2, it will can connect and protect between road well
Stay the shape feature of road, I5Each pixelValue setting
It is as follows:
It obtains extracting road network result images I5, as a result as shown in Figure 3.
S6, to the image I obtained in step S55, identify section, and mark the joint between section and section；
The specific implementation method of above-mentioned steps S6 is: the image I obtained to S55Each pixel I5(x, y), check its eight
Be connected to neighborhood (x+n, y+m) | and -1≤n≤1, -1≤m≤1, m and n not simultaneously be 0 pixel value, if non-zero picture in neighborhood
Vegetarian refreshments number is greater than 2, then determines position corresponding to the pixel for the joint of road.As a result as shown in figure 4, five-pointed star in figure
For the joint of road.
S7, to being obtained in step S6 as a result, every section is considered as node of graph, section joint is considered as between node
Company side, to graph structure carry out depth-first traversal, section is numbered.
The specific implementation method of above-mentioned steps S7 is: section obtained for step S6 and joint are organized into figure knot
Structure.Wherein each section is considered as the node of figure, if there are joints between two sections, joint is considered as even side, by two
A node connection, obtains graph structure.Depth-first traversal is carried out to graph structure, i.e., since a pixel, if surrounding eight
There is no joint in connected region, it is designated as same road segment with a upper pixel, it is more newly organized if surrounding has joint
Number and continue that next section is numbered.As a result as shown in table 1 below, -1 represents crossing in table 1, and other numbers represent road
Number.
1. road cross number table of table
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (8)
1. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy, which is characterized in that described is unknown
Method for extracting roads includes the following steps:
S1, each tracing point is mapped in two-dimensional grid according to longitude and latitude, so that tracing point, which is changed into image, to be indicated；
S2, to the image I obtained in step S1, sampled to reduce resolution ratio；
S3, to the image I obtained in step S22, denoised, and reject isolated pixel point；
S4, to the image I obtained in step S33, carry out Morphological scale-space；
S5, to the image I obtained in step S44, denoise again and reduce resolution ratio again；
S6, to the image I obtained in step S55, identify section, and mark the joint between section and section；
S7, to being obtained in step S6 as a result, every section is considered as node of graph, company section joint being considered as between node
Side carries out depth-first traversal to graph structure, section is numbered.
2. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S1 process is as follows:
By each mobile object OiTrack SiIt is expressed as the sequence S of discrete loci pointi={ τi,1,τi,2..., wherein tracing point
τi,k=< Oi,Ti,k,Xi,k,Yi,k> indicate mobile object OiIn time Ti,k, longitude Xi,k, latitude Yi,kA position record；
By the two-dimensional grid G by map partitioning at M × N, each event τi,kAccording to its latitude and longitude coordinates (Xi,k,Yi,k)
It is mapped in corresponding grid, note is mapped to grid G (m, n), and the number of 1≤m≤M, 1≤n≤N tracing point is Υ (m, n)；
Construct the image I that resolution ratio is M × N, the pixel I (m, n) of the image, the setting of 1≤m≤M, 1≤n≤N value are as follows:
3. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S2 process is as follows:
For the image I obtained in step S1, K is reduced1Times resolution ratio, wherein K1It is normal number, obtaining resolution ratio isImage I1；
Remove low-density pixel region, image I1In each pixel I1(x, y), 's
Value is provided that
Wherein,I (i, j), 1≤i≤M, 1≤j≤N are image IM×N
In a pixel pixel value, S is a normal number threshold value；
For I1Each pixel I1(x, y), by itself and K around2*K2Average pixel value in region is compared, wherein K2It is
Normal number, and be by resolution ratio is obtained after its binaryzationImage I2, wherein I2The value of each pixel calculates as follows:
Wherein,
4. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S3 process is as follows:
The low-resolution image I that will be obtained in step S22In isolated pixel set of blocks be removed, reduce noise to result
It influences, obtains image I3。
5. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S4 process is as follows:
For the image I obtained in step S33, morphologic expansion and etching operation are carried out, Refinement operation is then carried out, i.e., will
The line that width is only a pixel is thinned into one wide line, obtains image I4。
6. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S5 process is as follows:
The image I that step S4 is obtained4In isolate pixel set of blocks be removed, and again reduce resolution ratio adopted with reaching drop
The purpose of sample, by reducing K3Times resolution ratio, obtaining resolution ratio is Image I5, image I5Each pixel
I5(x, y),Value be provided that
7. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S6 process is as follows:
The image I that step S5 is obtained5In each pixel check its eight connectivity neighborhood, if non-zero pixels point number in neighborhood
Greater than 2, then position corresponding to the pixel is determined for the joint of road, in image I5It is middle to set zero for joint pixel
Afterwards, the very big connected region of each non-zero pixels in the image corresponds to the section of a connection, passes through joint between section and connects
It picks up and.
8. a kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy according to claim 1,
It is characterized in that, the step S7 process is as follows:
Section obtained for step S6 and joint are organized into graph structure, wherein each section is considered as the node of figure, if
There are joints between two sections, then joint are considered as even side, two nodes are connected, graph structure is obtained；
Depth-first traversal is carried out to the graph structure, successively node of graph and section are numbered by traversal order.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810286122.XA CN108615452B (en) | 2018-04-03 | 2018-04-03 | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810286122.XA CN108615452B (en) | 2018-04-03 | 2018-04-03 | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108615452A CN108615452A (en) | 2018-10-02 |
| CN108615452B true CN108615452B (en) | 2019-08-20 |
Family
ID=63659329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810286122.XA Expired - Fee Related CN108615452B (en) | 2018-04-03 | 2018-04-03 | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108615452B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008872B (en) * | 2019-03-25 | 2021-04-06 | 浙江大学 | Road network extraction method combining vehicle track and remote sensing image |
| CN110010062A (en) * | 2019-04-02 | 2019-07-12 | 福建华佳彩有限公司 | A kind of method and terminal for reducing OLED and showing picture power |
| CN111811525B (en) * | 2020-06-09 | 2022-05-10 | 广东国地规划科技股份有限公司 | Road network generation method and system based on remote sensing image and floating car track |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| KR101455835B1 (en) * | 2014-06-16 | 2014-11-04 | 주식회사 지티 | Lane Recognition and Tracking System Using Images, And Method For Recognition And Tracking Lane Using The Same |
| 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 |
| CN105862556A (en) * | 2016-05-30 | 2016-08-17 | 江苏智途科技股份有限公司 | Intelligent vehicle-mounted road information acquisition device and method for acquiring road information |
| CN106227726A (en) * | 2016-06-30 | 2016-12-14 | 北京航空航天大学 | A kind of path extraction method based on track of vehicle data |
| JP2016212031A (en) * | 2015-05-13 | 2016-12-15 | 西日本旅客鉄道株式会社 | Rail track locus creation system using laser point group, rail track locus creation method using laser point group, and rail track locus creation program using laser point group |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
-
2018
- 2018-04-03 CN CN201810286122.XA patent/CN108615452B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| KR101455835B1 (en) * | 2014-06-16 | 2014-11-04 | 주식회사 지티 | Lane Recognition and Tracking System Using Images, And Method For Recognition And Tracking Lane Using The Same |
| JP2016212031A (en) * | 2015-05-13 | 2016-12-15 | 西日本旅客鉄道株式会社 | Rail track locus creation system using laser point group, rail track locus creation method using laser point group, and rail track locus creation program using laser point group |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN105862556A (en) * | 2016-05-30 | 2016-08-17 | 江苏智途科技股份有限公司 | Intelligent vehicle-mounted road information acquisition device and method for acquiring road information |
| CN106227726A (en) * | 2016-06-30 | 2016-12-14 | 北京航空航天大学 | A kind of path extraction method based on track of vehicle data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108615452A (en) | 2018-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Seamless fusion of LiDAR and aerial imagery for building extraction | |
| CN103268358B (en) | Multi-source control point image database builds and update method | |
| CN107679498A (en) | A kind of airborne laser point cloud downtown roads recognition methods | |
| Matkan et al. | Road extraction from lidar data using support vector machine classification | |
| CN108615452B (en) | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy | |
| CN102804231A (en) | Piecewise planar reconstruction of three-dimensional scenes | |
| CN113192086A (en) | Generation method of geological disaster hidden danger deformation intensity distribution diagram and storage medium | |
| Awrangjeb et al. | Rule-based segmentation of LIDAR point cloud for automatic extraction of building roof planes | |
| Pandey et al. | Urban built-up area assessment of Ranchi township using Cartosat-I stereopairs satellite images | |
| CN104036295A (en) | Road center line auto-detection method employing multispectral remote sensing images | |
| Senthilnath et al. | Automatic road extraction using high resolution satellite image based on texture progressive analysis and normalized cut method | |
| Kim et al. | Generation of a DTM and building detection based on an MPF through integrating airborne lidar data and aerial images | |
| Mangala et al. | A new automatic road extraction technique using gradient operation and skeletal ray formation | |
| Kasemsuppakorn et al. | Pedestrian network extraction from fused aerial imagery (orthoimages) and laser imagery (lidar) | |
| Liu et al. | Color component–based road feature extraction from airborne lidar and imaging data sets | |
| Liu et al. | Automatic building height estimation with shadow correction over heterogeneous compact cities using stereo Gaofen-7 data at sub-meter resolution | |
| Mahphood et al. | Virtual first and last pulse method for building detection from dense LiDAR point clouds | |
| Grigillo et al. | Classification based building detection from GeoEye-1 images | |
| Wijnant et al. | Per-parcel classification of urban ikonos imagery | |
| Guo et al. | Population estimation in Singapore based on remote sensing and open data | |
| Castilla et al. | The Land-cover Change Mapper (LCM) and its application to timber harvest monitoring in Western Canada | |
| Teo | Deep-Learning for Lod1 Building Reconstruction from Airborne Lidar Data | |
| Yao et al. | Automatic vehicle extraction from airborne LiDAR data of urban areas using morphological reconstruction | |
| Yu et al. | A cue line based method for building modeling from LiDAR and satellite imagery | |
| Carpanese et al. | Automated estimation of building height through image processing |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190820 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |