CN104183132B - A kind of unknown walking facility locations defining method and system - Google Patents
A kind of unknown walking facility locations defining method and system Download PDFInfo
- Publication number
- CN104183132B CN104183132B CN201410364225.5A CN201410364225A CN104183132B CN 104183132 B CN104183132 B CN 104183132B CN 201410364225 A CN201410364225 A CN 201410364225A CN 104183132 B CN104183132 B CN 104183132B
- Authority
- CN
- China
- Prior art keywords
- track
- pedestrian
- data
- street
- subset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of unknown walking facility locations defining method, merged motion feature identification and Density Clustering two kinds of methods of pedestrian crossing behavior characteristic, excavate walking facility; First it excavate the pedestrian through road; Then, the pedestrian's track through road is divided into two parts, intensive pedestrian's track collection and sparse pedestrian's track collection.Density Clustering analysis is used to the former, the latter is used and analyzes through the motion feature of walking facility through road based on pedestrian.Finally, output is integrated in the walking facility geographic position provided of above-mentioned two kinds of methods.The present invention, in conjunction with the motion feature identification of pedestrian crossing behavior characteristic and Density Clustering two kinds of methods, can excavate walking facility (being defined as crossing, overpass, underpass) exactly.Density Clustering method can embody the feature of walking GPS track comparatively dense in addition, and the motion feature identification of pedestrian crossing behavior characteristic better can embody the more sparse feature of walking GPS track.
Description
Technical field
The present invention relates to a kind of unknown walking facility locations defining method, belong to the new road excavation applications of walking GPS track.
Background technology
Data mining (DataMining, DM) is the hot issue of current artificial intelligence and database field research, and so-called data mining refers to and to disclose implicit, previously unknown from the mass data of database and have the information of potential value.Data mining is by analyzing each data, finds the technology of its rule from mass data, mainly contains data encasement, rule finds and rule represents 3 steps.Data encasement from relevant data source, chooses required data and is integrated into the data set for data mining; It is with the rule contained by data set being found out someway that rule is found; Rule represents it is the rule found out showed in the intelligible mode of user (as visual) as far as possible.
Information extracting method based on vehicle GPS track is the important application of data mining, has occurred GPS navigation, and user behavior excavates, and user's travel pattern excavates, and focus tourism position is recommended, the various research directions such as detection urban transportation is abnormal.Many extraction vehicle GPS tracks are had to comprise the method for information, as the gravitation in analogies Neo-Confucianism and repulsion are optimized process to GPS track, generate the curve map (with reference to example text CaoL, KrummJ.FromGPStracetoaroutableroadmap [C] .Proceedingofthe17thACMSIGSPATIALInternationalConference onAdvancesinGeographicInformationSystems.2009:3-12.) of expressing road network information incrementally; Image thinning algorithm is utilized to obtain the framework information of road network, road network is built again (beautiful with reference to example text Jiang Yi by vector quantization mode, Li Xiang, Li little Jie etc. utilize track of vehicle data to extract geometric properties and the precision analysis [J] of road network. Earth Information Science journal, 2012,14 (2): 165-170.); Use the travel pattern of the discovery GPS track user of the segmentation of supervised learning, height and decision tree (with reference to example text ZhengY, ChenY, LiQ, etal.UnderstandingtransportationmodesbasedonGPSdataforwe bapplications [J] .ACMTransactionsontheWeb (TWEB), 2010,4 (1): 1.); Cacoplastic cause-effect relationship tree is used for detecting traffic abnormity (with reference to example text LiuW characteristic based on the Time and place of outlier detection, ZhengY, ChawlaS, etal.Discoveringspatio-temporalcausalinteractionsintraff icdatastreams [C] .Proceedingsofthe17thACMSIGKDDinternationalconferenceonK nowledgediscoveryanddatamining.ACM, 2011:1010-1018.); By semantic track, the clustering algorithm of the recommendation of general China, similarity, collaborative filtering, variance entropy is introduced in gps data analysis, the abnormal traffic in detection city is (with reference to example text PangLX, ChawlaS, LiuW, etal.Onmininganomalouspatternsinroadtrafficstreams [M] .AdvancedDataMiningandApplications.SpringerBerlinHeidelb erg, 2011:237-251.).
Along with the smart mobile phone of embedded GPS positioning function and the universal of mobile Internet, the location-based service based on smart mobile phone is used widely, and can obtain a large amount of walking GPS track data easily.Utilize walking GPS track data automatically to extract road network, supplementing based on vehicle GPS track road network extracting method can be become.Walking GPS track is more suitable for walking road network, path, the excavation of walking facility.The GPS track gathered during walking represents the position of the walking facility of pedestrian's process, and namely which pedestrian walkway pedestrian have passed through.Do not mate with the road in current road network by analyzing foot path, excavate walking facility (crossing, overline bridge, underpass etc.), the time of improving traditional road network acquisition mode is long, significantly shortens the update time of map, promotes the quality of Map Services.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of unknown walking facility locations defining method based on walking GPS track data.
The technical scheme that the present invention solves the problems of the technologies described above is as follows: a kind of unknown walking facility locations defining method, specifically comprises the following steps:
Step 1: the street trace information and the pedestrian's run trace information that gather a region, and the path locus data and the pedestrian's track data that carry out that pre-service obtains being convenient to process;
Step 2: adopt stroke identification method to analyze pedestrian's track data, obtain the street pedestrian's track set passed across a street;
Step 3: the set of street pedestrian's track is decomposed into multiple track subset according to the distribution of pedestrian's track data on street;
Step 4: carry out closeness analysis to a track subset, judges whether closeness is greater than predetermined threshold value, if be greater than, performs step 5; Otherwise, perform step 6;
Step 5: carry out Density Clustering to described track subset, obtain intensive subset, performs step 7;
Step 6: analyze described track subset according to motion feature recognition methods, obtains meeting pedestrian crosses the motion feature in street evacuation subset by walking facility, performs step 7;
Step 7: judge whether to exist the track subset of not carrying out closeness analysis, if had, performs step 4; Otherwise, perform step 8:
Step 8: the union of all evacuation subsets of all intensive subset sums is the set of walking facility locations, terminates.
The invention has the beneficial effects as follows: in conjunction with motion feature identification and Density Clustering two kinds of methods of pedestrian crossing behavior characteristic, walking facility (being defined as crossing, overpass, underpass) can be excavated exactly; Density Clustering method can embody the feature of walking GPS track comparatively dense, and the motion feature identification of pedestrian crossing behavior characteristic better can embody the more sparse feature of walking GPS track.
On the basis of technique scheme, the present invention can also do following improvement.
Further, described step 2 specifically comprises the following steps:
Step 2.1: obtain walking GPS track longitude and latitude, the maximal value of road GPS track longitude and latitude and minimum value according to pedestrian's track data and path locus data, according to described maximal value and minimum value, obtain the rectangle of multiple pedestrian's track data formation and the rectangle of path locus data formation respectively;
These path locus data are defined as path locus near this pedestrian's track by step 2.2: the rectangle that the rectangle form the pedestrian's track data that there is overlapping relation and path locus data are formed;
Step 2.3: judge that whether the line segment that the line segment of two adjacent track point compositions in pedestrian's track data and two adjacent track points of neighbouring path locus form is crossing, if so, perform step 2.5; Otherwise, perform step 2.4;
Step 2.4: abandon described pedestrian's track data, performs step 2.3;
Step 2.5: obtain the street pedestrian's track set passed across a street.
Further, the motion feature that in described step 6, pedestrian crosses street by walking facility is set as: by pedestrian through the angle of direction during road and section trajectory direction herein the track subset definition of about 90 degree for evacuate subset.
Further, the threshold value in described step 4 presets according to available data.
Technical matters to be solved by this invention is to provide a kind of unknown walking facility locations certainty annuity based on walking GPS track data.
The technical scheme that the present invention solves the problems of the technologies described above is as follows: a kind of unknown walking facility locations certainty annuity, comprises acquisition module, analysis module, decomposing module, density analysis module and collection modules:
Described acquisition module for gathering street trace information and pedestrian's run trace information, and carries out path locus data and the pedestrian's track data that pre-service obtains being convenient to process;
Described analysis module is analyzed pedestrian's track data for adopting stroke identification method, obtains the street pedestrian's track set passed across a street;
The set of street pedestrian's track is decomposed into multiple track subset according to the distribution of pedestrian's track data on street by described decomposing module;
Described density analysis module carries out closeness analysis to all track subsets, judges whether closeness is greater than predetermined threshold value, if be greater than, carried out Density Clustering, obtain intensive subset to described track subset; Otherwise, according to motion feature recognition methods, described track subset is analyzed, obtains meeting pedestrian crosses the motion feature in street evacuation subset by walking facility;
Described collection modules is for calculating the set of walking facility locations, and the set of described walking facility locations is the union of all evacuation subsets of all intensive subset sums.
The invention has the beneficial effects as follows: in conjunction with motion feature identification and Density Clustering two kinds of methods of pedestrian crossing behavior characteristic, walking facility (being defined as crossing, overpass, underpass) can be excavated exactly; Density Clustering method can embody the feature of walking GPS track comparatively dense, and the motion feature identification of pedestrian crossing behavior characteristic better can embody the more sparse feature of walking GPS track.
On the basis of technique scheme, the present invention can also do following improvement.
Further, described analysis module comprises rectangular path module, Cross module and crosses street data extraction module;
Described rectangular path module is used for obtaining walking GPS track longitude and latitude, the maximal value of road GPS track longitude and latitude and minimum value according to pedestrian's track data and path locus data, according to described maximal value and minimum value, obtain the rectangle of pedestrian's track data formation and the rectangle of path locus data formation respectively;
Described Cross module is used for the rectangle formed rectangle and the path locus data of the pedestrian's track data formation that there is overlapping relation, and these path locus data are defined as path locus near this pedestrian's track;
Described street data extraction module of crossing judges that whether the line segment that the line segment of two adjacent track point compositions in pedestrian's track data and two adjacent track points of neighbouring path locus form is crossing, if so, obtains the street pedestrian's track set passed across a street; Otherwise, abandon described pedestrian's track data.
Further, the motion feature that in described density analysis module, pedestrian crosses street by walking facility is set as: by pedestrian through the angle of direction during road and section trajectory direction herein the track subset definition of about 90 degree for evacuate subset.
Further, the threshold value in described density analysis module presets according to available data.
The basic ideas realizing object of the present invention are: first, excavate the pedestrian through road; Secondly, the pedestrian's track through road is divided into two parts, intensive pedestrian's track collection and sparse pedestrian's track collection.Density Clustering analysis is used to the former, the latter is used and analyzes through the motion feature of walking facility through road based on pedestrian.Then, the analysis result of above-mentioned two kinds of methods is integrated output.
Accompanying drawing explanation
Fig. 1 is one of the present invention unknown walking facility locations defining method process flow diagram;
Fig. 2 is one of the present invention unknown walking facility locations certainty annuity structured flowchart;
Fig. 3 is that in the method for the invention, rectangle pedestrian track data intersects schematic diagram;
Fig. 4 is relation schematic diagram between line segment that in the method for the invention, the line segment of two adjacent track points composition and two adjacent track points of neighbouring path locus form.
In accompanying drawing, the list of parts representated by each label is as follows:
1, acquisition module, 2, analysis module, 3, decomposing module, 4, density analysis module, 5, collection modules, 21, rectangular path module, 22, Cross module, 23, cross street data extraction module.
Embodiment
Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.
As shown in Figure 1, one of the present invention unknown walking facility locations defining method, specifically comprises the following steps:
Step 1: the street trace information and the pedestrian's run trace information that gather a region, and the path locus data and the pedestrian's track data that carry out that pre-service obtains being convenient to process;
Step 2: obtain walking GPS track longitude and latitude, the maximal value of road GPS track longitude and latitude and minimum value according to pedestrian's track data and path locus data, according to described maximal value and minimum value, obtain the rectangle of pedestrian's track data formation and the rectangle of path locus data formation respectively;
These path locus data are defined as path locus near this pedestrian's track by step 3: the rectangle that the rectangle form the pedestrian's track data that there is overlapping relation and path locus data are formed;
Step 4: judge that whether the line segment that the line segment of two adjacent track point compositions in pedestrian's track data and two adjacent track points of neighbouring path locus form is crossing, if so, perform step 6; Otherwise, perform step 5;
Step 5: abandon described pedestrian's track data, performs step 4;
Step 6: obtain the street pedestrian's track set passed across a street;
Step 7: the set of street pedestrian's track is decomposed into multiple track subset according to the distribution of pedestrian's track data on street;
Step 8: carry out closeness analysis to a track subset, judges whether closeness is greater than predetermined threshold value, if be greater than, performs step 9; Otherwise, perform step 10;
Step 9: carry out Density Clustering to described track subset, obtain intensive subset, performs step 11;
Step 10: analyze described track subset according to motion feature recognition methods, obtains meeting pedestrian crosses the motion feature in street evacuation subset by walking facility, performs step 11;
Step 11: judge whether to exist the track subset of not carrying out closeness analysis, if had, performs step 8; Otherwise, perform step 12:
Step 12: the union of all evacuation subsets of all intensive subset sums is the set of walking facility locations, terminates.
The motion feature that in described step 10, pedestrian crosses street by walking facility is set as: by pedestrian through the angle of direction during road and section trajectory direction herein the track subset definition of about 90 degree for evacuate subset.
Threshold value in described step 8 presets according to available data.
As shown in Figure 2, be one of the present invention unknown walking facility locations certainty annuity, comprise acquisition module 1, analysis module 2, decomposing module 3, density analysis module 4 and collection modules 5:
Described acquisition module 1 for street trace information and pedestrian's run trace information, and carries out path locus data and the pedestrian's track data that pre-service obtains being convenient to process;
Described analysis module 2 is analyzed pedestrian's track data for adopting stroke identification method, obtains the street pedestrian's track set passed across a street;
The set of street pedestrian's track is decomposed into multiple track subset according to the distribution of pedestrian's track data on street by described decomposing module 3;
Described density analysis module 4 carries out closeness analysis to all track subsets, judges whether closeness is greater than predetermined threshold value, if be greater than, carried out Density Clustering, obtain intensive subset to described track subset; Otherwise, according to motion feature recognition methods, described track subset is analyzed, obtains meeting pedestrian crosses the motion feature in street evacuation subset by walking facility;
Described collection modules 5 is for calculating the set of walking facility locations, and the set of described walking facility locations is the union of all evacuation subsets of all intensive subset sums.
Described analysis module 2 comprises rectangular path module 21, Cross module 22 and crosses street data extraction module 23;
Described rectangular path module 21 is for obtaining walking GPS track longitude and latitude, the maximal value of road GPS track longitude and latitude and minimum value according to pedestrian's track data and path locus data, according to described maximal value and minimum value, obtain the rectangle of pedestrian's track data formation and the rectangle of path locus data formation respectively;
These path locus data, for the rectangle of pedestrian's track data formation and the rectangle of path locus data formation that there is overlapping relation, are defined as path locus near this pedestrian's track by described Cross module 22;
Described street data extraction module 23 of crossing judges that whether the line segment that the line segment of two adjacent track point compositions in pedestrian's track data and two adjacent track points of neighbouring path locus form is crossing, if so, obtains the street pedestrian's track set passed across a street; Otherwise, abandon described pedestrian's track data.
The invention provides a kind of unknown walking facility locations method for digging based on walking GPS track data, comprise the steps:
Step 1: carry out pre-service to data, becomes the form being suitable for data mining, information extraction;
Step 2: excavate the pedestrian through road by neighbouring search, pedestrian's street crossing determination methods;
Search near 2.1:
Find out the max min of walking GPS track, road GPS track longitude and latitude respectively, the boundary rectangle of track can be obtained.Then judge whether two track rectangles intersect, two rectangular bit configuration states as shown in Figure 3, find the situation of two intersection of locus can find road near walking GPS track.
2.2 pedestrian's street crossings judge:
Judge that whether the line segment that the line segment of two adjacent tracing point compositions in pedestrian's GPS track and two adjacent tracing points of path locus near pedestrian form is crossing, the position relationship of two line segments as shown in Figure 4.If intersect, represent that the ad-hoc location of this pedestrian through road is through road, this ad-hoc location is walking facility.
Step 3: will be divided into two parts through road pedestrian track, one is the intensive pedestrian track collection of a lot of pedestrian through same section, and another is the sparse pedestrian track collection of little pedestrian through same section.Use Density Clustering to carry out next step analysis mining to the former to export this part walking facility locations collection A and to use the latter and carry out analysis mining through walking facility through the motion feature of road based on pedestrian and export this part walking facility locations collection A;
If 3.1 a lot of pedestrians are through same section, use density clustering algorithm.
Calculate the pedestrian density of same position scope through road of pedestrian's process, if density ratio is comparatively large, namely pedestrian concentrates on the same position in this section through road, thinks to there is walking facility herein, excavates and exports this part walking facility locations collection A.If density is smaller, namely pedestrian is dispersed in the diverse location in section through road, thinks that this section does not exist walking facility, and pedestrian is that oneself disorderly wears road.
If 3.2 little pedestrians are through same road, use the motion feature discriminance analysis of pedestrian.
The motion feature that pedestrian crosses street by walking facility if meet, then also can think to there is walking facility herein, excavates and export this part walking facility locations collection B.Pedestrian crosses street feature by walking facility and is set to, pedestrian through walking facility through road, pedestrian through the angle of direction during road and section trajectory direction herein at about 90 °.
Step 4: the Output rusults of algorithm is the union of output walking facility locations collection A, B of the 3rd step; Other situations do not judge.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (8)
1. a unknown walking facility locations defining method, is characterized in that, specifically comprise the following steps:
Step 1: the street trace information and the pedestrian's run trace information that gather a region, and the path locus data and the pedestrian's track data that carry out that pre-service obtains being convenient to process;
Step 2: adopt stroke identification method to analyze pedestrian's track data, obtain the street pedestrian's track set passed across a street;
Step 3: the set of street pedestrian's track is decomposed into multiple track subset according to the distribution of pedestrian's track data on street;
Step 4: carry out closeness analysis to a track subset, judges whether closeness is greater than predetermined threshold value, if be greater than, performs step 5; Otherwise, perform step 6;
Step 5: carry out Density Clustering to described track subset, obtain intensive subset, performs step 7;
Step 6: analyze described track subset according to motion feature recognition methods, obtains meeting pedestrian crosses the motion feature in street evacuation subset by walking facility, performs step 7;
Step 7: judge whether to exist the track subset of not carrying out closeness analysis, if had, performs step 4; Otherwise, perform step 8:
Step 8: the union of all evacuation subsets of all intensive subset sums is the set of walking facility locations, terminates.
2. one according to claim 1 unknown walking facility locations defining method, is characterized in that, described step 2 specifically comprises the following steps:
Step 2.1: obtain walking GPS track longitude and latitude, the maximal value of road GPS track longitude and latitude and minimum value according to pedestrian's track data and path locus data, according to described maximal value and minimum value, obtain the rectangle of pedestrian's track data formation and the rectangle of path locus data formation respectively;
These path locus data are defined as path locus near this pedestrian's track by step 2.2: the rectangle that the rectangle form the pedestrian's track data that there is overlapping relation and path locus data are formed;
Step 2.3: judge that whether the line segment that the line segment of two adjacent track point compositions in pedestrian's track data and two adjacent track points of neighbouring path locus form is crossing, if so, perform step 2.5; Otherwise, perform step 2.4;
Step 2.4: abandon described pedestrian's track data, performs step 2.3;
Step 2.5: obtain the street pedestrian's track set passed across a street.
3. one according to claim 1 and 2 unknown walking facility locations defining method, it is characterized in that, the motion feature that in described step 6, pedestrian crosses street by walking facility is set as: by pedestrian through the angle of direction during road and section trajectory direction herein the track subset definition of 90 degree for evacuate subset.
4. one according to claim 1 unknown walking facility locations defining method, is characterized in that, the threshold value in described step 4 presets according to available data.
5. a unknown walking facility locations certainty annuity, is characterized in that, comprises acquisition module, analysis module, decomposing module, density analysis module and collection modules:
Described acquisition module for gathering street trace information and pedestrian's run trace information, and carries out path locus data and the pedestrian's track data that pre-service obtains being convenient to process;
Described analysis module is analyzed pedestrian's track data for adopting stroke identification method, obtains the street pedestrian's track set passed across a street;
The set of street pedestrian's track is decomposed into multiple track subset according to the distribution of pedestrian's track data on street by described decomposing module;
Described density analysis module carries out closeness analysis to all track subsets, judges whether closeness is greater than predetermined threshold value, if be greater than, carried out Density Clustering, obtain intensive subset to described track subset; Otherwise, according to motion feature recognition methods, described track subset is analyzed, obtains meeting pedestrian crosses the motion feature in street evacuation subset by walking facility;
Described collection modules is for calculating the set of walking facility locations, and the set of described walking facility locations is the union of all evacuation subsets of all intensive subset sums.
6. one according to claim 5 unknown walking facility locations certainty annuity, is characterized in that, described analysis module comprises rectangular path module, Cross module and crosses street data extraction module;
Described rectangular path module is used for obtaining walking GPS track longitude and latitude, the maximal value of road GPS track longitude and latitude and minimum value according to pedestrian's track data and path locus data, according to described maximal value and minimum value, obtain the rectangle of pedestrian's track data formation and the rectangle of path locus data formation respectively;
Described Cross module is used for the rectangle formed rectangle and the path locus data of the pedestrian's track data formation that there is overlapping relation, and these path locus data are defined as path locus near this pedestrian's track;
Described street data extraction module of crossing judges that whether the line segment that the line segment of two adjacent track point compositions in pedestrian's track data and two adjacent track points of neighbouring path locus form is crossing, if so, obtains the street pedestrian's track set passed across a street; Otherwise, abandon described pedestrian's track data
。
7. the unknown walking facility locations of the one according to claim 5 or 6 certainty annuity, it is characterized in that, the motion feature that in described density analysis module, pedestrian crosses street by walking facility is set as: by pedestrian through the angle of direction during road and section trajectory direction herein the track subset definition of 90 degree for evacuate subset.
8. one according to claim 5 unknown walking facility locations certainty annuity, is characterized in that, the threshold value in described density analysis module presets according to available data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410364225.5A CN104183132B (en) | 2014-07-28 | 2014-07-28 | A kind of unknown walking facility locations defining method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410364225.5A CN104183132B (en) | 2014-07-28 | 2014-07-28 | A kind of unknown walking facility locations defining method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104183132A CN104183132A (en) | 2014-12-03 |
| CN104183132B true CN104183132B (en) | 2016-01-06 |
Family
ID=51964134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410364225.5A Active CN104183132B (en) | 2014-07-28 | 2014-07-28 | A kind of unknown walking facility locations defining method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104183132B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491895A (en) * | 2017-08-30 | 2017-12-19 | 国信优易数据有限公司 | A kind of shared bicycle parks determination method and device a little |
| CN114220295B (en) * | 2021-11-10 | 2023-03-14 | 岚图汽车科技有限公司 | Traffic early warning system, control method, storage medium, control device, and vehicle |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556162A (en) * | 2008-04-07 | 2009-10-14 | 吴波 | GPS route recording device and route forming system |
| CN102799897A (en) * | 2012-07-02 | 2012-11-28 | 杨飞 | Computer recognition method of GPS (Global Positioning System) positioning-based transportation mode combined travelling |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2427726B1 (en) * | 2009-05-04 | 2019-01-16 | TomTom North America Inc. | Methods and systems for creating digital transportation networks |
-
2014
- 2014-07-28 CN CN201410364225.5A patent/CN104183132B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556162A (en) * | 2008-04-07 | 2009-10-14 | 吴波 | GPS route recording device and route forming system |
| CN102799897A (en) * | 2012-07-02 | 2012-11-28 | 杨飞 | Computer recognition method of GPS (Global Positioning System) positioning-based transportation mode combined travelling |
Non-Patent Citations (2)
| Title |
|---|
| 基于GPS轨迹的矢量路网地图自动生成方法;孔庆杰等;《中国科学技术大学学报》;20120831;第42卷(第8期);第623-627页 * |
| 基于步行GPS轨迹的路网提取方法;欧阳鸿等;《计算机与现代化》;20140228(第2期);第124-128页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104183132A (en) | 2014-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Automatic intersection and traffic rule detection by mining motor-vehicle GPS trajectories | |
| Yang et al. | Generating lane-based intersection maps from crowdsourcing big trace data | |
| CN108961758B (en) | Road junction widening lane detection method based on gradient lifting decision tree | |
| Woźniak et al. | Hex2vec: Context-aware embedding h3 hexagons with openstreetmap tags | |
| Xu et al. | Scribble-supervised semantic segmentation inference | |
| CN104217593B (en) | A kind of method for obtaining road condition information in real time towards mobile phone travelling speed | |
| CN104850604A (en) | Tensor-based user track mining method | |
| CN107330422A (en) | A kind of method for carrying out mima type microrelief classification to semiarid zone based on high accuracy number elevation model | |
| CN108091134B (en) | Universal data set generation method based on mobile phone signaling position track data | |
| Stanislawski et al. | Generalisation operators | |
| CN111291811A (en) | Region dividing and classifying method, device and computer readable storage medium | |
| CN102183259A (en) | Navigation method based on electronic map road characteristic recognition | |
| Karagiorgou et al. | A layered approach for more robust generation of road network maps from vehicle tracking data | |
| Li et al. | Bounding box–based technique for pavement crack classification and measurement using 1 mm 3D laser data | |
| CN112163166A (en) | Method and device for detecting road attribute, computer readable medium and electronic equipment | |
| Yang et al. | DuARE: Automatic road extraction with aerial images and trajectory data at Baidu maps | |
| Baraka et al. | Machine learning for glacier monitoring in the Hindu Kush Himalaya | |
| Yang et al. | Attributing pedestrian networks with semantic information based on multi-source spatial data | |
| CN104183132B (en) | A kind of unknown walking facility locations defining method and system | |
| Zhang et al. | APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks | |
| CN110737931A (en) | ArcGIS-based railway bridge crossing hydrological key parameter extraction method | |
| Treccani et al. | Automating the inventory of the navigable space for pedestrians on historical sites: Towards accurate path planning | |
| Ghosh et al. | A machine learning approach to find the optimal routes through analysis of gps traces of mobile city traffic | |
| CN108399200B (en) | Construction method of time-space buffer zone of road network constrained track | |
| Liu et al. | Extracting campus’ road network from walking gps trajectories |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |