CN111832527B - Residential area extraction and type identification method based on remote sensing and social sensing data - Google Patents
Residential area extraction and type identification method based on remote sensing and social sensing data Download PDFInfo
- Publication number
- CN111832527B CN111832527B CN202010718096.0A CN202010718096A CN111832527B CN 111832527 B CN111832527 B CN 111832527B CN 202010718096 A CN202010718096 A CN 202010718096A CN 111832527 B CN111832527 B CN 111832527B
- Authority
- CN
- China
- Prior art keywords
- residential
- poi
- remote sensing
- extraction
- social
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
Abstract
The invention relates to a residential area extraction and type recognition method based on remote sensing and social sensing data, which comprises the steps of preprocessing remote sensing images, calculating angle difference characteristics, recognizing residential areas Point of Interest, extracting residential area boundaries and recognizing residential area types; aiming at the blank of extraction and type identification of the urban resident cells at present, remote sensing and social sensing data are fused, a technical scheme for rapidly and effectively developing an extraction and type identification method of the urban resident cells is provided, and an accurate data source is provided for urban planning departments and urban researchers; the effect of extracting residential areas in real time can be achieved; in addition, due to the combination of text similarity analysis, the method can quickly and effectively provide residential area face vector files for city researchers and city planning departments.
Description
Technical Field
The invention relates to the technical field of application of remote sensing and geographic information systems, in particular to a residential area extraction and type identification method based on remote sensing and social sensing data.
Background
Urban land is only 1% of full sphere land, but certainly contains more than 50% of urban population; one of the main advantages of the residential community of the medium-high-rise building is the intensive utilization of urban land, and for the health of residents, it is very important to build good residential community climate and environment;
at present, studies have been started to take residential communities as subjects, to explore the suitability of residential communities (Zhang et al, 2019), microclimate (Wu et al, 2016; zhang et al, 2018) and influence on resident health (Zeng and Li, 2018); the rapid and efficient residential area extraction and type identification method can provide a data source for research institutions taking residential areas as research objects;
in the prior art, urban residential land extraction can be performed by combining a remote sensing and geographic information system (Zhang et al, 2015); however, this technique is only suitable for extracting coarse-grained residential areas, and is not suitable for fine-grained residential area extraction and type identification.
Disclosure of Invention
The invention aims to provide a residential area extraction and type identification method based on remote sensing and social sensing data. Aiming at the blank of extraction and type identification of the urban residential area at present, remote sensing and social sensing data are fused, and a scientific method design is adopted to develop the method for extracting and type identification of the urban residential area, a quick and effective technical scheme is provided, and an accurate data source is provided for urban planning departments and urban researchers.
The residential area extraction and type identification method based on remote sensing and social sensing data comprises the following technical steps:
step 1: preprocessing a remote sensing image;
further, the front view, front view and rear view remote sensing images provided by the resource satellites are adopted to extract angle difference features (Angular Difference Feature (ADF)), and the angle difference features are used for identifying residential community types;
as an illustration, the resource satellite uses a resource number 3 satellite 02;
further, before the angle difference feature extraction, the resolution (2.5 meters) of the front-view remote sensing image and the resolution (2.1 meters) of the rear-view remote sensing image provided by the resource satellite are required to be resampled, so that the resolution is the same as the resolution (2.1 meters) of the front-view remote sensing image;
further, after resampling, taking the front-view remote sensing image as a reference, and carrying out histogram matching on the front-view, front-view and rear-view remote sensing images;
as an illustration, the resampling and histogram matching operation tool employs ENVI software;
step 2: calculating angle difference characteristics;
further, when the first operation is completed, the angle difference feature is calculated by the formula (1):
ADF＝max(X b -X n ,X n -X f ,X b -X f ) formula (1)
Wherein X is n 、X f 、X b The front view, the front view and the rear view remote sensing images are respectively; the extraction result is shown with reference to fig. 1;
step 3: identifying residential areas Point of Interest;
further, point of Interest is abbreviated as POI, and the POI data is collected by an intelligent map and used for map navigation service;
as an illustration, the smart map is: one or a combination of a hundred degree map, a high-altitude map, or a Tencel map;
further, each piece of POI data is presented in a vector format, and each piece of POI data has three attribute information, namely: type, name, latitude and longitude location;
as an illustration, the original POI type classification framework can refer to the record in the links https:// lbs. amap.com/api/webservice/download, which classifies POI types into 23 major classes, 264 middle classes, 870 minor classes;
wherein the categories related to the residential area include (in major-middle-minor format): commercial home-residential district-villa, commercial home-residential district, commercial home-residential district-community center; in place name address information-house number information-building number, passing facilities-building door-building main door, passing facilities-courtyard door-courtyard main door, there are POIs related to residential areas, which are scattered in building number and door inside residential areas, as shown with reference to fig. 2; because the smart map classifies these POI points as types unrelated to the residential area, we need to identify the POI points related to the residential area but classified as unrelated from the "place name address information" and "traffic facilities" categories through text similarity analysis, and the specific operations include:
1. reclassifying POI categories: reclassifying the POI categories according to table 1;
table 1.Poi reclassifying operation reference table
2. Performing text similarity analysis on the POI to be identified and the POI of residence;
according to the method, jaro-winkler text similarity measurement is used for calculating the text similarity between the POI to be identified and the POI of the residence; if the similarity is greater than 0.85, the "POI to be identified" will be identified as a "residential" POI, and if the similarity is less than 0.85, the "POI to be identified" will not be identified as a "residential" POI;
as an illustration, an analysis function package implementing text similarity measurement calculation adopts a Python package;
step 4: extracting residential area boundaries;
1. extracting land parcels;
the invention uses the road network data provided by the Openstreet Map to generate a land block which is used as an analysis unit for extracting the residential area boundary;
as an illustration, the Open Street Map is an Open-source, editable Map service application commonly created by the network public;
the road network data are presented in a vector format, and the roads are divided into different levels according to the relative importance of the roads; the invention reclassifies the original classification of the road into 3 stages, as shown in table 2, and establishes a buffer zone with a radius of 40 meters, 20 meters and 10 meters; the extraction result is shown with reference to fig. 3;
TABLE 2 road class reclassification and buffer radius specification
2. Identifying POI cluster clusters of residential areas;
performing text similarity measurement clustering on character strings of POI names, wherein an analysis object is a 'residential' POI, and an analysis unit gathers the 'residential' POIs with similar names into one type through similarity measurement for each land block; according to the method, the Jaro-winkler text similarity is adopted to calculate the text similarity, 0.85 is selected as a threshold value of the text similarity to generate different residential POI clusters, and the residential POIs after clustering form different residential community POI cluster clusters;
as an illustration, the residential area POI cluster recognition is the same as the third step, and a Jaro-winkler text similarity calculation method is also adopted;
3. extracting residential area boundaries;
adopting concave packet analysis to obtain residential area boundaries from the residential area POI cluster; adopting a concave-convex algorithm based on a triangular irregular network;
further, the concavity algorithm refers to: searching a neighborhood point in the cluster by calculating the circle center and the radius of a triangle circumscribing circle, constructing a Lanner triangle network by a recursion growth method, and finally obtaining a concave packet of the cluster based on the outer boundary of the generated triangle network; the result of the POI cluster of the residential area and the result of the boundary extraction are shown by referring to FIG. 4;
as an illustration, the concave bag analysis refers to finding its smallest polygon boundary based on a set of clusters;
as an illustration, the triangular irregular network is preferably a TIN;
step 5: identifying the type of residential areas;
taking a residential area face vector file as a unit, and extracting an average value of the in-plane ADF; setting an ADF threshold value, and dividing the ADF threshold value into a low-rise residential district (ADF < 60), a middle-rise residential district (ADF is more than or equal to 60 and less than or equal to 80) and a high-rise residential district (ADF is more than 80); the extraction result is shown with reference to fig. 5;
the invention has the following beneficial effects:
according to the invention, remote sensing data and social sensing data are fused, a text analysis technology and POI data name analysis are combined for the first time, and the effect of extracting residential areas in real time can be achieved; in addition, the ADF feature is used for identifying the residential area type for the first time, and the text similarity analysis is combined, so that the invention can quickly and effectively provide residential area face vector files for city researchers and city planning departments.
Drawings
FIG. 1 is a diagram showing the result of extracting the angle difference characteristics of the No. 3 02 satellite of the resident area based on the remote sensing and social sensing data and the type recognition method of the invention
FIG. 2 is a schematic diagram of the relationship between a residential POI and a building door and building number POI based on the residential district extraction and type recognition method of the present invention based on remote sensing and social sensing data
FIG. 3 is a plot extraction result diagram of a residential area extraction and type identification method based on remote sensing and social sensing data according to the present invention
FIG. 4 is a graph of clustering results and boundary extraction results of residential area POIs based on the remote sensing and social sensing data and the type recognition method of the present invention
FIG. 5 is a diagram showing the result of residential district type recognition based on the remote sensing and social sensing data in the residential district extraction and type recognition method of the present invention
Detailed Description
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings;
referring to fig. 1 to 5, the residential area extraction and type identification method based on remote sensing and social sensing data comprises the following technical steps:
step 1: preprocessing a remote sensing image;
further, the front view, front view and rear view remote sensing images provided by the resource satellites are adopted to extract angle difference features (Angular Difference Feature (ADF)), and the angle difference features are used for identifying residential community types;
as an illustration, the resource satellite uses a resource number 3 satellite 02;
further, before the angle difference feature extraction, the resolution (2.5 meters) of the front-view remote sensing image and the resolution (2.1 meters) of the rear-view remote sensing image provided by the resource satellite are required to be resampled, so that the resolution is the same as the resolution (2.1 meters) of the front-view remote sensing image;
further, after resampling, taking the front-view remote sensing image as a reference, and carrying out histogram matching on the front-view, front-view and rear-view remote sensing images;
as an illustration, the resampling and histogram matching operation tool employs ENVI software;
step 2: calculating angle difference characteristics;
further, when the first operation is completed, the angle difference feature is calculated by the formula (1):
ADF＝max(X b -X n ,X n -X f ,X b -X f ) Formula (1)
Wherein X is n 、X f 、X b The front view, the front view and the rear view remote sensing images are respectively; the extraction result is shown with reference to fig. 1;
step 3: identifying residential areas Point of Interest;
further, point of Interest is abbreviated as POI, and the POI data is collected by an intelligent map and used for map navigation service;
as an illustration, the smart map is: one or a combination of a hundred degree map, a high-altitude map, or a Tencel map;
further, each piece of POI data is presented in a vector format, and each piece of POI data has three attribute information, namely: type, name, latitude and longitude location;
as an illustration, the original POI type classification framework can refer to the record in the links https:// lbs. amap.com/api/webservice/download, which classifies POI types into 23 major classes, 264 middle classes, 870 minor classes;
wherein the categories related to the residential area include (in major-middle-minor format): commercial home-residential district-villa, commercial home-residential district, commercial home-residential district-community center; in place name address information-house number information-building number, passing facilities-building door-building main door, passing facilities-courtyard door-courtyard main door, there are POIs related to residential areas, which are scattered in building number and door inside residential areas, as shown with reference to fig. 2; because the smart map classifies these POI points as types unrelated to the residential area, we need to identify the POI points related to the residential area but classified as unrelated from the "place name address information" and "traffic facilities" categories through text similarity analysis, and the specific operations include:
1. reclassifying POI categories; reclassifying the POI categories according to table 1;
table 1.Poi reclassifying operation reference table
2. Performing text similarity analysis on the POI to be identified and the POI of residence;
according to the method, jaro-winkler text similarity measurement is used for calculating the text similarity between the POI to be identified and the POI of the residence; if the similarity is greater than 0.85, the "POI to be identified" will be identified as a "residential" POI, and if the similarity is less than 0.85, the "POI to be identified" will not be identified as a "residential" POI;
as an illustration, an analysis function package implementing text similarity measurement calculation adopts a Python package;
step 4: extracting residential area boundaries;
1. extracting land parcels;
the invention uses the road network data provided by the Openstreet Map to generate a land block which is used as an analysis unit for extracting the residential area boundary;
as an illustration, the Open Street Map is an Open-source, editable Map service application commonly created by the network public;
the road network data are presented in a vector format, and the roads are divided into different levels according to the relative importance of the roads; the invention reclassifies the original classification of the road into 3 stages, as shown in table 2, and establishes a buffer zone with a radius of 40 meters, 20 meters and 10 meters; the extraction result is shown with reference to fig. 3;
TABLE 2 road class reclassification and buffer radius specification
2. Identifying POI cluster clusters of residential areas;
performing text similarity measurement clustering on character strings of POI names, wherein an analysis object is a 'residential' POI, and an analysis unit gathers the 'residential' POIs with similar names into one type through similarity measurement for each land block; according to the method, the Jaro-winkler text similarity is adopted to calculate the text similarity, 0.85 is selected as a threshold value of the text similarity to generate different residential POI clusters, and the residential POIs after clustering form different residential community POI cluster clusters;
as an illustration, the residential area POI cluster recognition is the same as the third step, and a Jaro-winkler text similarity calculation method is also adopted;
3. extracting residential area boundaries;
adopting concave packet analysis to obtain residential area boundaries from the residential area POI cluster; adopting a concave-convex algorithm based on a triangular irregular network;
further, the concavity algorithm refers to: searching a neighborhood point in the cluster by calculating the circle center and the radius of a triangle circumscribing circle, constructing a Lanner triangle network by a recursion growth method, and finally obtaining a concave packet of the cluster based on the outer boundary of the generated triangle network; the result of the POI cluster of the residential area and the result of the boundary extraction are shown by referring to FIG. 4;
as an illustration, the concave bag analysis refers to finding its smallest polygon boundary based on a set of clusters;
as an illustration, the triangular irregular network is preferably a TIN;
step 5: identifying the type of residential areas;
taking a residential area face vector file as a unit, and extracting an average value of the in-plane ADF; setting an ADF threshold value, and dividing the ADF threshold value into a low-rise residential district (ADF < 60), a middle-rise residential district (ADF is more than or equal to 60 and less than or equal to 80) and a high-rise residential district (ADF is more than 80); the extraction result is shown with reference to fig. 5;
the invention combines the remote sensing data and the social sensing data, and can achieve the effect of extracting residential areas in real time; in addition, due to the combination of text similarity analysis, the method can quickly and effectively provide residential area face vector files for city researchers and city planning departments.
The foregoing description of the preferred embodiments of the present invention has been presented only to facilitate the understanding of the principles of the invention and its core concepts, and is not intended to limit the scope of the invention in any way, however, any modifications, equivalents, etc. which fall within the spirit and principles of the invention should be construed as being included in the scope of the invention.
Claims (10)
1. The residential area extraction and type identification method based on remote sensing and social sensing data is characterized by comprising the following technical steps of:
step 1: preprocessing a remote sensing image;
extracting angle difference features by adopting front view, front view and rear view remote sensing images provided by a resource satellite, wherein the angle difference features are used for identifying residential community types;
before the angle difference feature extraction is carried out, the resolution ratio of the front-view remote sensing image and the resolution ratio of the rear-view remote sensing image provided by the resource satellite are required to be resampled, so that the resolution ratio is the same as that of the front-view remote sensing image;
after resampling, taking the front-view remote sensing image as a reference, and carrying out histogram matching on the front-view, front-view and rear-view remote sensing images;
step 2: calculating angle difference characteristics;
when the first operation is completed, the angle difference feature is calculated by equation 1:
ADF＝max(X b -X n ,X n -X f ,X b -X f ) Formula (1)
Wherein X is n 、X f 、X b The front view, the front view and the rear view remote sensing images are respectively; ADF is special for angle differenceSign, angular Difference Feature;
step 3: identifying residential areas Point of Interest;
the Point of Interest POI is short for POI, and the POI data is collected by an intelligent map and used for map navigation service;
each piece of POI data is presented in a vector format, and each piece of POI data has three attribute information, namely: type, name, latitude and longitude location;
wherein the categories related to the residential quarter include, according to the major-middle-minor format: commercial home-residential district-villa, commercial home-residential district, commercial home-residential district-community center; in place name address information-house number information-building number, passing facilities-building door-building main door, passing facilities-courtyard door-courtyard main door, there are also POIs related to residential areas, which are scattered inside the residential areas in the building number and door because the smart map classifies these POI points into types unrelated to the residential areas, it is necessary to identify the POI points related to the residential areas but classified as unrelated from the "place name address information" and "passing facilities" categories by text similarity analysis, and the specific operations include:
1. reclassifying POI categories; reclassifying the POI categories according to table 1;
TABLE 1
2. Performing text similarity analysis on the POI to be identified and the POI of residence;
calculating the text similarity between the POI to be identified and the POI of the house by using Jaro-winkler text similarity measurement; if the similarity is greater than 0.85, the "POI to be identified" will be identified as a "residential" POI, and if the similarity is less than 0.85, the "POI to be identified" will not be identified as a "residential" POI;
step 4: extracting residential area boundaries;
1. extracting land parcels;
generating a land block using road network data provided by the Open Street Map, the land block being to be an analysis unit for residential cell boundary extraction;
the road network data are presented in a vector format, and the roads are divided into different levels according to the relative importance of the roads; the invention reclassifies the original classification of the road into 3 stages, as shown in table 2, and establishes a buffer zone with a radius of 40 meters, 20 meters and 10 meters;
TABLE 2 road class reclassification and buffer radius specification
2. Identifying POI cluster clusters of residential areas;
performing text similarity measurement clustering on character strings of POI names, wherein an analysis object is a 'residential' POI, and an analysis unit gathers the 'residential' POIs with similar names into one type through similarity measurement for each land block; calculating text similarity by adopting Jaro-winkler text similarity, and selecting 0.85 as a threshold value of the text similarity to generate different residential POI clusters, wherein the residential POIs after clustering form different residential area POI cluster clusters;
3. extracting residential area boundaries;
adopting concave packet analysis to obtain residential area boundaries from the residential area POI cluster; adopting a concave-convex algorithm based on a triangular irregular network;
step 5: identifying the type of residential areas;
taking a residential area face vector file as a unit, and extracting an average value of the in-plane ADF; ADF threshold is set, and the ADF threshold is divided into low-rise residential areas ADF <60, middle-rise residential areas ADF 60-80 and high-rise residential areas ADF > 80.
2. The method for residential quarter extraction and type identification based on remote sensing and social sensing data as claimed in claim 1, wherein said resource satellite uses resource number 3 satellite 02.
3. The method for residential quarter extraction and type identification based on remote sensing and social sensing data as claimed in claim 1, wherein said resampling and histogram matching operation tool uses ENVI software.
4. The method for residential quarter extraction and type identification based on remote sensing and social sensing data according to claim 1, wherein the intelligent map is: one or a combination of a hundred degree map, a high-german map, or a Tencel map.
5. The method for residential quarter extraction and type identification based on remote sensing and social sensing data as claimed in claim 1, wherein POI types are classified into 23 major categories, 264 middle categories and 870 minor categories by frame.
6. The residential area extraction and type identification method based on remote sensing and social sensing data according to claim 1, wherein the analysis function package for realizing text similarity measurement calculation adopts a Python package.
7. The method for residential quarter extraction and type identification based on remote sensing and social sensing data according to claim 1, wherein the Open Street Map is an Open source, editable Map service application commonly created by the internet masses.
8. The residential quarter extraction and type identification method based on remote sensing and social sensing data according to claim 1, wherein the concave-convex algorithm is: searching neighborhood points in the cluster by calculating the circle center and the radius of a triangle circumscribing circle, constructing a Lanner triangle network by a recursion growth method, and finally obtaining the concave packet of the cluster based on the outer boundary of the generated triangle network.
9. The method for residential quarter extraction and type identification based on remote sensing and social sensing data as claimed in claim 1, wherein said concave analysis is based on a group of clusters to find its minimum polygon boundary.
10. The method for residential quarter extraction and type identification based on remote sensing and social sensing data as claimed in claim 1, wherein said triangular irregular network is TIN.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010718096.0A CN111832527B (en) | 2020-07-23 | 2020-07-23 | Residential area extraction and type identification method based on remote sensing and social sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010718096.0A CN111832527B (en) | 2020-07-23 | 2020-07-23 | Residential area extraction and type identification method based on remote sensing and social sensing data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111832527A CN111832527A (en) | 2020-10-27 |
| CN111832527B true CN111832527B (en) | 2023-09-05 |
Family
ID=72925213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010718096.0A Active CN111832527B (en) | 2020-07-23 | 2020-07-23 | Residential area extraction and type identification method based on remote sensing and social sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832527B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247938A (en) * | 2017-06-08 | 2017-10-13 | 中国科学院遥感与数字地球研究所 | A kind of method of high-resolution remote sensing image City Building function classification |
| CN108764193A (en) * | 2018-06-04 | 2018-11-06 | 北京师范大学 | Merge the city function limited region dividing method of POI and remote sensing image |
| CN109299673A (en) * | 2018-09-05 | 2019-02-01 | 中国科学院地理科学与资源研究所 | The green degree spatial extraction method of group of cities and medium |
| CN109325085A (en) * | 2018-08-08 | 2019-02-12 | 中南大学 | A kind of urban land identification of function and change detecting method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102016012139A1 (en) * | 2016-10-10 | 2018-04-12 | Niveen Raafat Adib Ghattas | Toolbox for Sustainability Analysis of Land Use (A Toolbox for the Evaluation of the Land Use Structure of Small Urban Residential Areas) |
-
2020
- 2020-07-23 CN CN202010718096.0A patent/CN111832527B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247938A (en) * | 2017-06-08 | 2017-10-13 | 中国科学院遥感与数字地球研究所 | A kind of method of high-resolution remote sensing image City Building function classification |
| CN108764193A (en) * | 2018-06-04 | 2018-11-06 | 北京师范大学 | Merge the city function limited region dividing method of POI and remote sensing image |
| CN109325085A (en) * | 2018-08-08 | 2019-02-12 | 中南大学 | A kind of urban land identification of function and change detecting method |
| CN109299673A (en) * | 2018-09-05 | 2019-02-01 | 中国科学院地理科学与资源研究所 | The green degree spatial extraction method of group of cities and medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于矢量数据的城市建成区范围提取方法;姚君兰;王红;胡斌斌;;测绘通报(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111832527A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Du et al. | Large-scale urban functional zone mapping by integrating remote sensing images and open social data | |
| Serna et al. | Paris-rue-Madame database: A 3D mobile laser scanner dataset for benchmarking urban detection, segmentation and classification methods | |
| Yang et al. | Automatic change detection in lane-level road networks using GPS trajectories | |
| Laumer et al. | Geocoding of trees from street addresses and street-level images | |
| Liu et al. | Recognizing urban functional zones by a hierarchical fusion method considering landscape features and human activities | |
| CN112733781B (en) | City functional area identification method combining POI data, storage medium and electronic equipment | |
| CN107133900A (en) | Urban land mixing utilizes feature grid computational methods and device | |
| Zhang et al. | Using street view images to identify road noise barriers with ensemble classification model and geospatial analysis | |
| Qian et al. | Vectorized dataset of roadside noise barriers in China using street view imagery | |
| Yu et al. | Urban impervious surface estimation from remote sensing and social data | |
| Chen et al. | Uvlens: urban village boundary identification and population estimation leveraging open government data | |
| Yang et al. | Road intersection identification from crowdsourced big trace data using Mask‐RCNN | |
| Hu et al. | A framework to detect and understand thematic places of a city using geospatial data | |
| Huang et al. | Mining crowdsourced trajectory and geo‐tagged data for spatial‐semantic road map construction | |
| Jing et al. | A hierarchical spatial unit partitioning approach for fine‐grained urban functional region identification | |
| He et al. | Global 30 meters spatiotemporal 3D urban expansion dataset from 1990 to 2010 | |
| Zhang et al. | Street‐level traffic flow and context sensing analysis through semantic integration of multisource geospatial data | |
| CN111832527B (en) | Residential area extraction and type identification method based on remote sensing and social sensing data | |
| CN113672788B (en) | Urban building function classification method based on multi-source data and weight coefficient method | |
| Liu et al. | 3D point cloud segmentation using GIS | |
| Wang et al. | Urban function zoning using geotagged photos and openstreetmap | |
| Li | Mapping urban land use by combining multi-source social sensing data and remote sensing images | |
| CN112015937B (en) | Picture geographic positioning method and system | |
| CN113807305A (en) | Road destructive prediction automatic driving method based on naive Bayes classification algorithm | |
| Tutzauer et al. | Processing of crawled urban imagery for building use classification |
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 |