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
- resolution
- road
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title abstract description 24
- 230000000877 morphologic effect Effects 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 8
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- VYQRBKCKQCRYEE-UHFFFAOYSA-N ctk1a7239 Chemical compound C12=CC=CC=C2N2CC=CC3=NC=CC1=C32 VYQRBKCKQCRYEE-UHFFFAOYSA-N 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 230000007704 transition Effects 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 invention relates to the technical field of human-vehicle track data processing, in particular to an unknown road extraction method based on human-vehicle track point multi-resolution processing.
Background
Nowadays, electronic maps increasingly become the basis for constructing intelligent traffic systems, and road network data are indispensable components in electronic maps, so that accurate extraction and timely updating of road network information are very important for people going out and vehicle navigation. The traditional road network extraction method mainly comprises three types, namely field mapping, remote sensing image processing and road extraction based on vehicle track data. In particular, the first method maps in the field, which is relatively accurate but time and labor consuming; the second method is to process the remote sensing image to generate the road network, and the accuracy is relatively low. The two methods are not timely enough for modeling the newly-passed road, and are difficult to accurately map some unknown roads in suburbs in time. The third method is a road extraction method based on vehicle trajectory data proposed in recent years (patent publication No. CN 106227726A). With the popularization of GPS mobile devices and the widespread use of location-based services, a large amount of movement trajectory data can be collected and utilized. The track data is a time-space record of the movement of vehicles and pedestrians on the road network, and can directly reflect the geometric characteristics of the road traffic network. In general, the trajectory of a moving object is usually recorded as a sequence of discrete trajectory points. Where each trace point represents the position where the object appears at a particular time, is a discrete sample of the trace. The higher the sampling rate is, the denser the track points are distributed in space, and the higher the track precision is; conversely, the lower the sampling rate, the more sparsely the trace points are distributed, and the lower the trace accuracy is. The conventional road extraction method based on vehicle tracks (patent publication No. CN106227726A) mainly finds a new path by clustering vehicle track paths, and this method relies on the sampling accuracy of track data relatively, and when the sampling rate is low, the accuracy of the track paths is low, and the paths obtained by clustering the track paths are also relatively coarse, so that the existing road network data often needs to be combined to perform further correction.
In view of the above disadvantages, a method for extracting an unknown road by performing multi-resolution processing on track points is urgently needed.
Disclosure of Invention
The invention aims to overcome the defects of the existing road network extraction method and provides a method for extracting an unknown road by carrying out multi-resolution analysis on the trajectory point data of a pedestrian. The method does not depend on the existing road network information, and can independently and accurately extract the unknown road aiming at the track data.
The purpose of the invention can be achieved by adopting the following technical scheme:
the unknown road extraction method based on human-vehicle track point multi-resolution processing comprises the steps of mapping track points onto a two-dimensional grid, obtaining a road center line with the width of one pixel unit through image processing methods such as denoising, sampling and morphological processing under multi-resolution, further extracting intersection points of roads on the basis, and completing segmentation and numbering of the roads. The method specifically comprises the following steps:
s1, mapping each track point to a two-dimensional grid according to the longitude and latitude, and converting the track points into image representation;
s2, sampling the image I obtained in the step S1 to reduce the resolution;
s3, comparing the image I obtained in the step S22Denoising and eliminating isolated pixel points;
s4, step alignmentImage I obtained in step S33Performing morphological treatment;
s5, comparing the image I obtained in the step S44Denoising again and reducing the resolution again;
s6, comparing the image I obtained in the step S55Identifying road sections and marking junction points among the road sections;
and S7, regarding each road section as a graph node and regarding road section junction points as connecting edges between the nodes according to the result obtained in the step S6, performing depth-first traversal on the graph structure, and numbering the road sections.
Further, step S1 is specifically: each moving object OiTrack S ofiCan be expressed as a sequence S of discrete track pointsi＝{τi,1,τi,2… }. Wherein the track point taui,k＝<Oi,Ti,k,Xi,k,Yi,k>Represents a moving object OiAt time Ti,kLongitude Xi,kLatitude Yi,kA location record of. By dividing the map into an M N two-dimensional grid G, each space-time point τ can be dividedi,kAccording to its longitude and latitude coordinates (X)i,k,Yi,k) Mapping into the corresponding grid. Noting the number of the track points mapped to grid G (M, N) (1. ltoreq. m.ltoreq.M, (1. ltoreq. n.ltoreq.N) as y (M, N), constructing an image I with resolution of M × N, whose pixels I (M, N) (1. ltoreq. m.ltoreq.M, (1. ltoreq. n.ltoreq.N) have values set as:
further, for the image I acquired in step S1, K is lowered1Multiple resolution (K)1Is a normal number) to a resolution ofImage I1By lowering K1Multiple resolution can be achievedAnd (4) to the purpose of down-sampling, caking is carried out on the high-density pixel point region, and the influence of the low-density pixel point region on the result is removed. After the high-density pixel point regions are agglomerated, the subsequent denoising operation and morphological processing operation can be facilitated. The low-density pixel regions are scattered noise points on the image, and the influence of noise on the result can be effectively removed by removing the low-density pixel regions. Specifically, image I1Each pixel point inThe values of (c) are set as follows:
whereinWhere I (I, j) (1. ltoreq. i.ltoreq.M, 1. ltoreq. j.ltoreq.N) is the image IM×NThe pixel value of one pixel point in (1). S is a normal norm threshold. In order to remove only those low-density noises, S is set to 10 in the present embodiment.
Then, for I1Each pixel point I1(x, y) and mixing it with the surrounding K2*K2The average pixel values within the region are compared (K)2Is a normal number) and binarized to obtain a resolution ofImage I2In which I2The value of each pixel is calculated as follows:
wherein
Further, step S3 is specifically: the low resolution image I acquired in step S22Removing the isolated pixel block set in the image, reducing the influence of noise on the result and obtaining an image I3。
Further, step S4 is specifically: for the low resolution image I acquired in step S33And performing morphological expansion and corrosion operations, wherein the expansion and corrosion operations can make the image smoother and remove the influence of the holes on the result. Then thinning operation is carried out, namely, one wide line is thinned into a line with the width of only one pixel point, and an image I is obtained4。
Further, step S5 is specifically: for the image I acquired in step S44And removing the isolated pixel block set, and reducing the resolution again to achieve the purpose of down-sampling. By lowering K3Multiple resolution (K)3<K2) To obtain a resolution ofImage I5. The down-sampling here may interconnect roads that were disconnected after previous operations. Specifically, image I5Each pixel point ofThe values of (c) are set as follows:
further, step S6 is specifically: for the image I obtained in step S55And (4) checking the eight-connected neighborhood of each pixel, and if the number of non-zero pixel points in the neighborhood is more than 2, judging that the position corresponding to the pixel is the intersection point of the road. In picture I5After the pixels of the junction points are set to be zero, each non-zero pixel maximum connected area in the image corresponds to a connected road section, and the road sections are connected through intersectionThe points are connected.
Further, step S7 is specifically: and organizing the road segments and the junction points obtained in the step S6 into a graph structure, wherein each road segment is regarded as a node of the graph, and if the junction point exists between two road segments, the junction point is regarded as a connecting edge, and the two nodes are connected to obtain the graph structure. And carrying out depth-first traversal on the graph structure, and numbering the graph nodes (road sections) in sequence according to the traversal sequence.
The invention extracts road network information efficiently by denoising, sampling, interpolating and morphological processing the pedestrian path points under multi-resolution. Compared with the existing road network extraction method based on track path clustering, the method has the following advantages and effects:
1) the invention directly analyzes and processes the human-vehicle track points, and is applicable to rough track data with lower sampling rate compared with the traditional track path-based clustering analysis method.
2) And (3) processing the track points by adopting a multi-resolution method, agglomerating the high-density track points by reducing the resolution, and removing the influence of a low-density track point area on the result.
3) The road network is extracted completely based on the human-vehicle track points, the existing road network information is not relied on, and accurate extraction of unknown roads can be carried out in the non-mapped suburb.
4) The method can simultaneously extract the junction of the roads, automatically segment and number the roads, and is favorable for counting the transition probability.
Drawings
FIG. 1 is a flow chart of an unknown road extraction method based on multi-resolution processing of human and vehicle track points, disclosed by the invention;
FIG. 2 is a schematic diagram of an image display during mapping of trace points to a grid;
fig. 3 is a diagram illustrating the result after the link is extracted corresponding to fig. 2;
FIG. 4 is a diagram illustrating the results of marking road junction points, wherein the five-pointed star represents the junction point.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
This embodiment is implemented by a process as shown in fig. 1, which includes seven main steps:
s1, mapping each space-time point on the track into a grid according to the longitude and latitude, so that the track is converted into an image representation;
the specific implementation method of step S1 is as follows: every track Si(1. ltoreq. k. ltoreq.m) can be expressed as a sequence S of discrete trajectory space-time pointsi＝{τi,k1, …, n }. Wherein the space-time point taui,k＝<Oi,Ti,k,Xi,k,Yi,k>Represents a moving object OiAt time Ti,kLongitude Xi,kLatitude Yi,kA location record of. The map is divided into two-dimensional grids G of M x N, in this embodiment, for two equally sized 2000 x 1300M2The same treatment is performed in the area (2). Taking the size of each grid as 5 x 5m2Therefore, an optimal arrangement of M400 and N260 can be obtained. Can convert each space-time point taui,kAccording to its longitude and latitude coordinates (X)i,k,Yi,k) The number of the trace points mapped to grid G (M, N) (M is more than or equal to 1 and less than or equal to M, N is more than or equal to 1 and less than or equal to N) is y (M, N). Constructing an image I with a resolution of M × N, the value of a pixel I (M, N) (1. ltoreq. M, 1. ltoreq. n.ltoreq.n) of the image is set as:
the results of image I are shown in fig. 2.
S2, sampling the image I obtained in the step S1 to reduce the resolution;
step S2 specifically includes: for the image I acquired in step S1, K is lowered1Multiple resolution (K)1Is a normal number) to obtain a resolution ofImage I1By lowering K1The multiplied resolution ratio can achieve the purpose of down-sampling, so that the high-density pixel point region is agglomerated, and the influence of the low-density pixel point region on the result is removed. After the high-density pixel point regions are agglomerated, the subsequent denoising operation and morphological processing operation can be facilitated. The low-density pixel regions are scattered noise points on the image, and the influence of noise on the result can be effectively removed by removing the low-density pixel regions. In this embodiment, K is1Set to 10, obtain a resolution ofImage I1More specifically, image I1Each pixel point inThe values of (c) are set as follows:
whereinWhere I (I, j) (1. ltoreq. i.ltoreq.M, 1. ltoreq. j.ltoreq.N) is the image IM×NThe pixel value of one pixel point in (1). S is a normal norm threshold. In order to remove only those low-density noises, S is set to 10 in the present embodiment.
Then for image I1In each pixel point, the pixel value and the surrounding K are calculated2*K2The average pixel values within the region are compared (K)2Is a normal number, K in this example2May be set to 10) and binarized to obtain a resolution ofImage I2In which I2The value of each pixel is calculated as follows:
wherein
S3, comparing the image I obtained in the step S22Carrying out denoising treatment and picking isolated points;
the specific implementation method of step S3 is as follows: let the set of traversal ranges be S ═ S1,s2,s3,…,snFor each traversal range siTraversing each pixel point in the image to judge surrounding si*si(i is more than or equal to 1 and less than or equal to n) whether a nonzero pixel point exists on the boundary within the range, if the nonzero pixel point does not exist, the pixel block set of the region is considered to be isolated, and s is addedi*siThe pixel values of all the pixels of the range are set to zero. To be very goodRemoving some isolated pixel block sets, in this embodiment, S is taken as {2,3,4, …,20}, and after denoising, the image I is obtained3。
S4, comparing the image I obtained in the step S33Performing morphological treatment;
the specific implementation method of step S4 is as follows: for image I acquired in S33The morphological treatment is performed by first performing morphological dilation and erosion operations N times, where N is set to a natural number equal to or greater than 5 in this embodiment, since the expected results are substantially achieved after 5 passes.
Let A be image I3A set of positions of non-zero pixels, B is a coordinate set { (B)1,b2)|-1≤b1≤1,-1≤b2Less than or equal to 1}, for image I3The dilation operation of (2) is specifically to calculate the following set of positions:
wherein (B)zRepresents the translation of B: (B)z＝{c|c＝b+z,b∈B},z∈Z2indicating the amount of translation. Will I3In (A) belong toThe pixel value of the position of (1) is set to 1, i.e. the pair I can be completed3The expansion operation of (2). The mathematical definition of corrosion is similar to swelling. Definition ofWherein A iscThe complement of A, defined as:will I3In (A) belong toThe pixel value of the location of (a) is set to 1,do not belong toThe pixel value of the position of (1) is set to 0, i.e. the pair I can be completed3The etching operation of (1). Then, the image is refined, and a table look-up method of a commonly used refining algorithm is adopted. The thinning operation can thin a wide line into a line with the width of only one pixel, and finally, the image I is obtained4。
S5, comparing the image I obtained in the step S44Denoising again and sampling again to reduce the resolution;
the specific implementation method of step S5 is as follows: for image I acquired at S44Performing secondary denoising by using the denoising algorithm in S3, wherein the traversal range is the same as that in S3, taking S {2,3,4, …,20}, and then performing down-sampling again, namely reducing K3Multiple resolution (K)3<K2) Obtaining an image I5Has a resolution ofThe down-sampling here may interconnect roads that were disconnected after previous operations. In this example, take K32, namely, the roads can be well connected and the shape characteristics of the roads are kept, I5Each pixel point ofThe values of (c) are set as follows:
obtaining an image I of the extracted road network result5The results are shown in FIG. 3.
S6, comparing the image I obtained in the step S55Identifying road sections and marking junction points among the road sections;
the above step SThe specific implementation method of 6 is as follows: for the image I obtained in S55Each pixel of (1)5(x, y), checking the pixel value of the eight-connected neighborhood { (x + n, y + m) | -1 ≦ n ≦ 1, -1 ≦ m ≦ 1, and m and n are not 0 at the same time, and if the number of non-zero pixel points in the neighborhood is greater than 2, judging that the position corresponding to the pixel is the intersection point of the road. The result is shown in fig. 4, where the five-pointed star is the intersection of the roads.
And S7, regarding each road section as a graph node and regarding road section junction points as connecting edges between the nodes according to the result obtained in the step S6, performing depth-first traversal on the graph structure, and numbering the road sections.
The specific implementation method of the step S7 is as follows: the map structure is organized for the links and junctions obtained in step S6. And if an intersection exists between the two road sections, the intersection is regarded as a connecting edge, and the two nodes are connected to obtain the graph structure. And performing depth-first traversal on the graph structure, namely starting from one pixel point, marking the pixel point as the same road section as the previous pixel point if no junction point exists in the surrounding eight-connected region, and updating the number and continuing numbering the next road section if the junction point exists around. The results are shown in Table 1 below, where-1 in Table 1 represents the intersection and the other numbers represent the road number.
TABLE 1. road junction numbering table
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (8)
1. An unknown road extraction method based on multi-resolution processing of human and vehicle track points is characterized by comprising the following steps:
s1, mapping each track point to a two-dimensional grid according to the longitude and latitude, and converting the track points into image representation;
s2, sampling the image I obtained in the step S1 to reduce the resolution;
s3, comparing the image I obtained in the step S22Denoising and eliminating isolated pixel points;
s4, comparing the image I obtained in the step S33Performing morphological treatment;
s5, comparing the image I obtained in the step S44Denoising again and reducing the resolution again;
s6, comparing the image I obtained in the step S55Identifying road sections and marking junction points among the road sections;
and S7, regarding each road section as a graph node and regarding road section junction points as connecting edges between the nodes according to the result obtained in the step S6, performing depth-first traversal on the graph structure, and numbering the road sections.
2. The unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S1 is as follows:
each moving object OiTrack S ofiSequence S expressed as discrete trace pointsi＝{τi,1,τi,2… } in which the locus points τ are locatedi,k＝<Oi,Ti,k,Xi,k,Yi,k>Represents a moving object OiAt time Ti,kLongitude Xi,kLatitude Yi,kA location record of;
dividing the map into an M N two-dimensional grid G, each space-time point Ti,kAccording to its longitude and latitude coordinates (X)i,k,Yi,k) Mapping to a corresponding grid, and recording the number of the trace points mapped to the grid G (M, N), wherein M is more than or equal to 1 and less than or equal to M, and N is more than or equal to 1 and less than or equal to N as y (M, N);
constructing an image I with the resolution of M multiplied by N, wherein the pixel I (M, N) of the image is that M is more than or equal to 1 and less than or equal to M, and the value of N is more than or equal to 1 and less than or equal to N is set as:
3. the unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S2 is as follows:
for the image I acquired in step S1, K is lowered1Multiple resolution of where K1Is a normal number, and the resolution is obtained asImage I1；
Removing low density pixel regions, image I1In each pixel point I1(x,y)， The values of (c) are set as follows:
wherein,i (I, j), I is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to N is the image IM×NThe pixel value of one pixel point in (1), S is a normal norm threshold;
for I1Each pixel point I1(x, y) and mixing it with the surrounding K2*K2The average pixel values within the region are compared, where K2Is a normal number and is binarized to obtain a resolution ofImage I2In which I2The value of each pixel is calculated as follows:
wherein,
4. the unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S3 is as follows:
the low resolution image I acquired in step S22Removing the isolated pixel block set in the image, reducing the influence of noise on the result and obtaining an image I3。
5. The unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S4 is as follows:
for the image I acquired in step S33Performing morphological expansion and corrosion operation, and then performing thinning operation, namely thinning a wide line into a line with the width of only one pixel point to obtain an image I4。
6. The unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S5 is as follows:
for the image I acquired in step S44Removing the isolated pixel block set, and reducing the resolution again to achieve the purpose of down-sampling by reducing K3Multiplying the resolution to obtain a resolution of Image I5Image I5Each pixel point I5(x,y)，The values of (c) are set as follows:
7. the unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S6 is as follows:
for the image I obtained in step S55Checking the eight-connected neighborhood of each pixel in the image I, if the number of non-zero pixel points in the neighborhood is more than 2, judging that the position corresponding to the pixel is the intersection point of the road, and displaying the image I5After the intersection point pixels are set to be zero, each non-zero pixel maximum connected region in the image corresponds to a connected road section, and the road sections are connected through the intersection points.
8. The unknown road extraction method based on human-vehicle track point multi-resolution processing as claimed in claim 1, wherein the step S7 is as follows:
organizing the road segments and the junction points obtained in the step S6 into a graph structure, wherein each road segment is regarded as a node of the graph, and if a junction point exists between two road segments, the junction point is regarded as a connecting edge, and the two nodes are connected to obtain the graph structure;
and carrying out depth-first traversal on the graph structure, and numbering the graph nodes and the road sections in sequence according to the traversal sequence.
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 |
|---|---|---|
| CN111222474B (en) | Method for detecting small target of high-resolution image with any scale | |
| CN111709420B (en) | Text detection method, electronic device and computer readable medium | |
| CN111179152B (en) | Road identification recognition method and device, medium and terminal | |
| CN109949340A (en) | Target scale adaptive tracking method based on OpenCV | |
| Matkan et al. | Road extraction from lidar data using support vector machine classification | |
| CN109389163B (en) | Unmanned aerial vehicle image classification system and method based on topographic map | |
| Canaz Sevgen et al. | An improved RANSAC algorithm for extracting roof planes from airborne lidar data | |
| CN108615452B (en) | A kind of unknown method for extracting roads based on people's wheel paths point multi-resolution hierarchy | |
| WO2007001314A2 (en) | Automatically and accurately conflating road vector data, street maps, and orthoimagery | |
| CN108509950B (en) | Railway contact net support number plate detection and identification method based on probability feature weighted fusion | |
| CN111986164A (en) | Road crack detection method based on multi-source Unet + Attention network migration | |
| CN111967341A (en) | Method for identifying contour of target object in satellite map | |
| CN115294066A (en) | Sandstone particle size detection method | |
| CN115731257A (en) | Leaf form information extraction method based on image | |
| Youn et al. | Extracting urban road networks from high-resolution true orthoimage and lidar | |
| CN104036295A (en) | Road center line auto-detection method employing multispectral remote sensing images | |
| CN114283343A (en) | Map updating method, training method and equipment based on remote sensing satellite image | |
| CN113836484A (en) | Self-adaptive point cloud rarefying method based on path point adjacent domain and ground filtering | |
| CN117541652A (en) | Dynamic SLAM method based on depth LK optical flow method and D-PROSAC sampling strategy | |
| CN112446353A (en) | Video image trace line detection method based on deep convolutional neural network | |
| Mangala et al. | A new automatic road extraction technique using gradient operation and skeletal ray formation | |
| CN116863357A (en) | Unmanned aerial vehicle remote sensing dyke image calibration and intelligent segmentation change detection method | |
| CN116129386A (en) | Method, system and computer readable medium for detecting a travelable region | |
| Liu et al. | Color component–based road feature extraction from airborne lidar and imaging data sets | |
| Mahphood et al. | Virtual first and last pulse method for building detection from dense LiDAR point clouds |
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 |