CN115272854B - Palm land identification method and product based on multi-source information analysis - Google Patents
Palm land identification method and product based on multi-source information analysis Download PDFInfo
- Publication number
- CN115272854B CN115272854B CN202210896034.8A CN202210896034A CN115272854B CN 115272854 B CN115272854 B CN 115272854B CN 202210896034 A CN202210896034 A CN 202210896034A CN 115272854 B CN115272854 B CN 115272854B
- Authority
- CN
- China
- Prior art keywords
- brown
- land
- poi data
- map
- data
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a brown land identification method and a brown land identification product based on multi-source information analysis. By adopting the brown land identification method provided by the embodiment of the invention, the identification target area (the area where the potential brown land is located) can be determined based on the POI data in the open source map service interface, and then the potential brown land in the remote sensing image of the target area is visually interpreted based on the spatial characteristics of the identification target area, so that the spatial boundary and distribution of brown land categories such as raw material mining, tailing pond, raw material processing and manufacturing, non-raw material processing and manufacturing, infrastructure, landfill and the like are obtained, and the non-idle land is removed by utilizing the multi-source space and non-spatial data to correct the identification result, so that the final brown land identification result of the target area is obtained. Therefore, the brown land identification method provided by the embodiment of the invention can obtain a batch brown land identification result of the target area based on the remote sensing image and the open source POI data of the large-scale target area.
Description
Technical Field
The embodiment of the invention relates to the technical field of information processing, in particular to a brown land identification method and a brown land identification product based on multi-source information analysis.
Background
Brown land generally refers to sites where there is known or potential contamination due to human activity, and its reuse needs to be based on site risk assessment and repair based on the intended use. Brown land and its regeneration are global issues that require serious treatment worldwide due to their tremendous number and wide distribution throughout the world.
In the related art, students at home and abroad have conducted several researches on a brown land identification method, and the conventional brown land identification technology can be divided into 3 main types. The method is efficient (automatic identification), but the identification result is greatly influenced by image data, open source data cannot be obtained, and universality and popularization value are not achieved. Secondly, the palm land manual identification method based on the non-open source information is low in efficiency, key information does not have a public obtaining way, and universality and popularization value are not achieved. Thirdly, a palm land manual identification method based on open source information, wherein the method has a certain popularization value although the identification technical process is reproducible, but the identified palm land type is limited. In addition, the 3-class identification method has a single way of judging the abandoned state of the field, and most of the 3-class identification methods are studied in the field, so that the time and labor cost are increased.
In addition, because the types of brown lands are more, the remote sensing image features with uniform discrimination are not provided, and the remote sensing technology is utilized to automatically identify a large number of multi-type brown lands in a large range in the field of landscape architecture science at present, so that the method is difficult to realize. Compared with the recognition of urban land cover by using high-resolution remote sensing images, the fine recognition of urban land utilization distribution by using remote sensing supervision and sub-supervision classification technology has less research.
Different from land cover, land utilization refers to a use mode of people in the aspect of social and economic functions, and the land utilization mode is difficult to directly extract from remote sensing image data. In the case of brown land, because of various types, high heterogeneity, and no unified spectral, geometric and texture features with discrimination, when the brown land is identified by using the remote sensing images of Landsat series with 30m resolution, the images are easily confused with bare land, sand land, roads and other construction lands, and the effect is poor. Therefore, the method for identifying vegetation, water body, urban buildings, roads and other ground features based on Landsat series free remote sensing images by using supervised and unsupervised classification is not suitable for brown land identification.
It follows that a new method for identifying brown land is currently needed.
Disclosure of Invention
Embodiments of the present invention provide a brown land identification method, apparatus, electronic device, computer readable storage medium and computer program product based on multi-source information analysis, so as to solve at least some of the problems in the related art.
An embodiment of the present invention provides a method for identifying brown land based on multi-source information analysis, where the method includes:
determining the area where the potential brown land is located in the remote sensing image of the target area according to the map data of the target area and the POI data of the target area;
determining potential brown land from the area where the potential brown land is located according to the spatial characteristics contained in the remote sensing image of the target area, and classifying the potential brown land to obtain a multi-category potential brown land distribution map;
correcting the multi-category potential brown land distribution map according to multi-source space and non-space data to obtain the identification result of the brown lands of a plurality of categories, wherein the multi-source space and non-space data at least comprises: multiple time sequence human flow thermodynamic diagrams;
wherein, the brown land of multiple categories includes: landfill site, raw material mining brown-like land, tailing pond brown-like land, raw material processing and manufacturing brown-like land, non-raw material processing and manufacturing brown-like land and infrastructure brown-like land.
Optionally, determining, according to map data of a target area and POI data of the target area, an area where a potential brown land is located in a remote sensing image of the target area includes:
acquiring map POI data of a target area, and selecting industrial POI data related to industry from the map POI data;
acquiring mining place POI data of a target area, and screening idle mining class POI data from the mining place POI data;
acquiring map POI data of a target area, and selecting landfill type POI data related to landfill from the map POI data;
and determining the area where the potential brown land is located according to the map data of the target area, the industrial POI data, the mining POI data and the landfill POI data.
Optionally, selecting industry-class POI data related to industry from the map POI data, including:
acquiring map POI data of a target area;
selecting POI data of a category related to industrial brown land from map POI data of the target area as first industrial POI data;
keyword screening is carried out on data except the first industrial POI data in the map POI data, so that supplementary industrial POI data are obtained;
And obtaining industrial POI data according to the first industrial POI data and the supplementary industrial POI data.
Optionally, screening idle mining POI data from the mining POI data includes:
screening idle mining class POI data from the mining site POI data according to the attribute of each mining site in the mining site POI data of the target area;
the attributes of each of the mineral sites include at least: the current situation is utilized.
Optionally, selecting landfill type POI data related to landfill from the map POI data includes:
acquiring map POI data of a target area;
selecting POI data of a class related to landfill from map POI data of the target area as first landfill POI data;
keyword screening is carried out on data except the first landfill type POI data in the map POI data, so that supplementary landfill type POI data are obtained;
and obtaining the landfill type POI data according to the first landfill type POI data and the supplementary landfill type POI data.
Optionally, determining a potential brown land from the area where the potential brown land is located according to the spatial feature included in the remote sensing image of the target area, and classifying the potential brown land to obtain a multi-category potential brown land distribution map, including:
Obtaining the category and the space boundary of each potential brown land included in the area where the potential brown land is located according to the space boundary, facility, hue, elevation, area and texture of the remote sensing image of the target area;
and marking in the remote sensing image of the target area according to the category and the space boundary of each potential brown land, and obtaining a multi-category potential brown land distribution map.
Optionally, the multi-source spatial and non-spatial data further comprises: the current urban land map, the urban land planning map and Shi Zhi data are used for correcting the multi-category potential brown land distribution map according to multi-source space and non-space data, and the method comprises the following steps:
and rejecting land parcels still in operation in the multi-category potential brown land distribution map according to the urban land use current situation map, the urban land use planning map, the Shi Zhi data and the multi-time sequence people flow thermodynamic diagram, and supplementing the missing brown land identified in the multi-category potential brown land distribution map.
A second aspect of an embodiment of the present invention provides a brown land identification device based on multi-source information analysis, the device including:
the determining module is used for determining the area where the potential brown land is located in the remote sensing image of the target area according to the map data of the target area and the POI data of the target area;
The classification module is used for determining potential brown land from the area where the potential brown land is located according to the spatial characteristics contained in the remote sensing image of the target area, and classifying the potential brown land to obtain a multi-category potential brown land distribution map;
the correction module is used for correcting the multi-category potential brown land distribution map according to multi-source space and non-space data to obtain the identification result of the brown lands of various categories, and the multi-source space and non-space data at least comprises: multiple time sequence human flow thermodynamic diagrams;
wherein, the brown land of multiple categories includes: landfill site, raw material mining brown-like land, tailing pond brown-like land, raw material processing and manufacturing brown-like land, non-raw material processing and manufacturing brown-like land and infrastructure brown-like land.
Optionally, the determining module includes:
the first acquisition sub-module is used for acquiring map POI data of a target area and selecting industrial POI data related to industry from the map POI data;
the second acquisition submodule is used for acquiring mining area POI data of the target area and screening idle mining class POI data from the mining area POI data;
a third obtaining sub-module, configured to obtain map POI data of a target area of the target area, and select landfill type POI data related to landfill from the map POI data;
And the determining submodule is used for determining the potential brown land area according to the map data of the target area, the industrial POI data, the mining POI data and the landfill POI data.
Optionally, the first obtaining sub-module is specifically configured to:
acquiring map POI data of a target area;
selecting POI data of a category related to industrial brown land from map POI data of the target area as first industrial POI data;
keyword screening is carried out on data except the first industrial POI data in the map POI data, so that supplementary industrial POI data are obtained;
and obtaining industrial POI data according to the first industrial POI data and the supplementary industrial POI data.
Optionally, the second obtaining sub-module is specifically configured to:
screening idle mining class POI data from the mining site POI data according to the attribute of each mining site in the mining site POI data of the target area;
the attributes of each of the mineral sites include at least: the current situation is utilized.
Optionally, the third obtaining sub-module is specifically configured to:
acquiring map POI data of a target area;
selecting POI data of a class related to landfill class from map POI data of the target area as first landfill class POI data;
Keyword screening is carried out on data except the first landfill type POI data in the map POI data, so that supplementary landfill type POI data are obtained;
and obtaining the landfill type POI data according to the first landfill type POI data and the supplementary landfill type POI data.
Optionally, the classification module is specifically configured to:
obtaining the category and the space boundary of each potential brown land included in the area where the potential brown land is located according to the space boundary, facility, hue, elevation, area and texture of the remote sensing image of the target area;
and marking in the remote sensing image of the target area according to the category and the space boundary of each potential brown land, and obtaining a multi-category potential brown land distribution map.
Optionally, the multi-source spatial and non-spatial data further comprises: the correction module is specifically used for correcting the current map of the urban land, the map of the urban land and Shi Zhi data:
and rejecting land parcels still in operation in the multi-category potential brown land distribution map according to the urban land use current situation map, the urban land use planning map, the Shi Zhi data and the multi-time sequence people flow thermodynamic diagram, and supplementing the missing brown land identified in the multi-category potential brown land distribution map.
A third aspect of an embodiment of the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for brown land identification based on multi-source information analysis according to the first aspect of the present invention when the program is executed.
A fourth aspect of the embodiments of the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method for brown land identification based on multi-source information analysis according to the first aspect of the present invention.
A fifth aspect of the embodiments of the present invention provides a computer program product comprising computer programs/instructions which when executed by a processor implement the steps in the method for brown land identification based on multi-source information analysis according to the first aspect of the present invention.
By adopting the brown land identification method based on multi-source information analysis provided by the embodiment of the invention, the identification target area (the area where the potential brown land is located) can be determined based on POI data in the open source map service interface, then the potential brown land in the remote sensing image of the target area is visually interpreted based on the spatial characteristics of the identification target area, the distribution of brown land categories such as raw material mining, tailing pond, raw material processing and manufacturing, non-raw material processing and manufacturing, infrastructure, refuse landfill and the like is obtained, and the non-idle land is removed based on multi-source space and non-spatial data to correct the identification result, so that the final brown land identification result of the target area is obtained. Therefore, the brown land identification method provided by the embodiment of the invention can obtain a batch brown land identification result of the target area based on the remote sensing image and the open source POI data of the large-scale target area.
In the embodiment of the invention, the open source data POI is utilized to actually identify the target area, and then brown land identification and classification are carried out, so that the identification efficiency can be improved; in addition, in the embodiment of the invention, the multi-source space and non-space data are used for land block correction, so that the investigation on the spot is avoided, and the time and the labor cost can be saved; in addition, in the embodiment of the invention, six types of brown lands can be identified in batches from a large-scale target area, which is beneficial to follow-up research and practice of area brown lands at a macroscopic and integral view angle.
In the brown land identification method provided by the embodiment of the invention, the used data (including POI data of the target area, map data of the target area, remote sensing images of the target area and multisource space and non-space data) are all open source data, the acquisition path is simple, the universality is high, and the method is easy to popularize (for example, the method is applicable to brown land identification of any city capable of acquiring the data).
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method of brown land identification in accordance with an embodiment of the present invention;
FIG. 2 is a schematic illustration of an area of a potential brown land obtained by an embodiment of a brown land identification method according to an embodiment of the present invention;
FIG. 3 is a graph of a multi-category potential brown distribution obtained by a specific embodiment of a brown identification method in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of the recognition results of various types of brown lands obtained by the specific embodiment of the brown land recognition method according to the embodiment of the present invention;
fig. 5 is a block diagram of another brown land identification device according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Referring to fig. 1, a flowchart of a brown land identification method based on multi-source information analysis according to an embodiment of the present invention is shown, and specifically, the brown land identification method provided by the embodiment of the present invention may include the following steps:
s101, determining the area where the potential brown land is located in the remote sensing image of the target area according to the map data of the target area and the POI data of the target area.
Wherein the POI data refers to information points (Point of Interest), each POI data contains at least four aspects of information: name, category, longitude, latitude.
In the embodiment of the invention, the map data of the target area can be derived from an open source map service interface such as a God map, a Baidu map, google Earth (Google Earth), and the like, and the POI data of the target area can be derived from POI data of an open source map service interface such as a God map, a Baidu map, and the like, and national mineral databases and other related databases. Based on the map data and POI data of the target area, specific coordinates of the potential brown land can be obtained, so that the areas where the potential brown land is located can be identified in the remote sensing image.
In the embodiment of the invention, the target area refers to a brown land identification research area, for example: a province, a city, a district, etc.
Specifically, the step S101 may include the following sub-steps:
s1011, acquiring map POI data of a target area, and selecting industrial POI data related to industry from the map POI data.
In the embodiment of the invention, the industrial POI data can be determined by utilizing the map POI data of the target area, and the map POI data of the target area can be derived from POI data in open source map service interfaces such as a Goldmap, a Baidu map and the like.
After the map POI data of the target area is obtained, the embodiment of the invention firstly needs to clean the data to obtain the required target POI data due to complex data types, and specifically comprises the following substeps:
S10111, map POI data of the target area is acquired.
In the embodiment of the invention, the multisource map POI data can be fused (for example, the Goldmap POI data and the Baidu map POI data are fused) so as to obtain the map POI data of the target area.
S10112, selecting POI data of category related to industrial brown land from map POI data of the target area as first industrial POI data.
S10113, keyword screening is carried out on the data except the first industrial POI data in the map POI data, and the supplementary industrial POI data are obtained.
S10114, obtaining industrial POI data according to the first industrial POI data and the supplementary industrial POI data.
In the embodiment of the invention, the data of factories, metallurgical chemical industry, construction companies and mechanical electronic companies 5 subclasses in the company enterprise subclasses with highest correlation with the industrial type brown land and the data of the industry park subclasses in business houses can be selected from the map POI data (the data description comprises POI names, classifications, addresses, longitudes and latitudes, location province names, location city names, location area codes and the like) as first industrial type POI data, and then keywords (such as 'coal', 'iron', 'lime', 'factory', 'processing', 'manufacturing' and the like) are screened on the rest of the map POI data to obtain supplementary industrial type POI data. And finally, merging the first industrial POI data and the supplementary industrial POI data to obtain industrial POI data.
S1012, acquiring mining place POI data of a target area, and screening idle mining class POI data from the mining place POI data.
In the embodiment of the invention, the POI data of the mineral places of the target area can be derived from a national mineral place database. And determining idle mining POI data according to the data description corresponding to each mining place in the national mining place database.
The method specifically comprises the following steps: screening idle mining class POI data from the mining site POI data according to the attribute of each mining site in the mining site POI data of the target area; the attributes of each of the mineral sites include at least: the current situation is utilized.
In the embodiment of the invention, the relevant database has corresponding data description (such as mineral place, longitude, latitude, mineral species, scale, utilization status, mineral deposit cause, geological working procedure, traffic position and the like) for each stored data, so that idle mining POI data can be determined according to attribute labels (such as undeveloped, developing, idle and the like) of the utilization status of each mineral place in the national mineral place database.
And S1013, acquiring map POI data of a target area, and selecting landfill type POI data related to landfill from the map POI data.
In the embodiment of the invention, the map POI data of the target area can be utilized to determine the landfill POI data, and the POI data of the target area can be derived from POI data in open source map service interfaces such as a Goldmap, a Baidu map and the like.
After the map POI data of the target area is obtained, the embodiment of the invention firstly needs to clean the data to obtain the required target POI data due to complex data types, and specifically comprises the following substeps:
s10131, map POI data of the target area is acquired.
In the embodiment of the invention, the multisource map POI data can be fused (for example, the Goldmap POI data and the Baidu map POI data are fused) so as to obtain the map POI data of the target area.
S10132, selecting POI data of a class related to landfill from map POI data of the target area as first landfill POI data.
S10133, keyword screening is carried out on the data except the first landfill type POI data in the map POI data, so that the supplementary landfill type POI data is obtained.
S10134, obtaining landfill POI data according to the first landfill POI data and the supplementary landfill POI data.
In the embodiment of the invention, data of a landfill site, a sanitary landfill site, a landfill site and the like related to landfill can be selected from the map POI data (the data description comprises POI names, classifications, addresses, longitudes and latitudes, location province names, location city names, location area codes and the like) as first landfill site POI data, and then keywords (such as 'landfill', 'sanitary', 'pile' and the like) are screened and inspected on the rest of map POI data to obtain supplementary landfill site POI data. And finally, merging the first landfill POI data and the supplementary landfill POI data to obtain the landfill POI data.
S1014, determining the area where the potential brown land is located according to the map data of the target area, the industrial POI data, the mining POI data and the landfill POI data.
In the embodiment of the invention, after the industrial POI data, idle mining POI data and landfill POI data are determined, specific coordinates of the industrial POI data, idle mining POI data and landfill POI data can be determined according to the data description corresponding to the data, and the area where the potential brown land is located is identified in the remote sensing image.
In the embodiment of the invention, because most POI data space coordinate systems are GCJ-02 coordinate systems (also called Mars coordinate systems), certain space deviation exists, space deviation correction is needed, and finally, the area where the potential brown land is located is identified in the remote sensing image according to the specific coordinates after the space deviation correction.
In embodiments of the present invention, in determining potential brown land, reference may also be made to some other database material, such as: mine and tailing pond shut-down/management conditions, mineral distribution, important brown land projects and the like.
S102, determining potential brown land from the area where the potential brown land is located according to the spatial features contained in the remote sensing image of the target area, and classifying the potential brown land to obtain a multi-category potential brown land distribution map.
Considering that the spatial features corresponding to different types of brown lands are different, the embodiment of the invention provides that the potential brown lands are classified based on the spatial features contained in the remote sensing image of the target area. In the embodiment of the invention, the remote sensing image of the target area can be visually interpreted based on manual work to obtain a multi-category potential brown land distribution map. Machine learning models can also be utilized to learn the spatial features of various types of brown lands for automatic classification.
In the embodiment of the invention, the remote sensing image of the target area is a high-definition satellite image and can be derived from Google Earth satellite images.
In an alternative embodiment, the step S102 includes the substeps of:
s1021, obtaining the category and the space boundary of each potential brown land included in the area where the potential brown land is located according to the space boundary, facility, hue, elevation, area and texture of the remote sensing image of the target area.
And S1022, marking in the remote sensing image of the target area according to the category and the space boundary of each potential brown land, and obtaining a multi-category potential brown land distribution map.
In the embodiment of the invention, the spatial characteristics of various types of brown lands are predetermined as follows:
1) Landfill site: the space boundary is clear; the field is internally provided with a leachate and biogas drainage treatment facility; the whole is in an irregular or regular mountain shape, the top is relatively flat, and two sides are multi-stage side slopes with controlled gradient.
2) Digging a brown land: the working surface is clear, the boundary is irregular, and the ground surface is damaged to different degrees; facilities such as a digging machine, a large bracket, a conveyor belt and the like are arranged on the pile body or in the pit; the elevation change is large, or the elevation change is concave in a pit shape or is in a step shape at the mountain waist; different colors and areas of the raw material mining sites of different resources are different; the road in the field is rugged.
3) Tailing pond brown land: has more regular and clear boundaries; the elevation change is larger, or the elevation change is upward convex or is in a table shape at the mountain waist, and the migration is higher and higher along with the time; the area is generally large; there is substantially no road in the field.
4) Processing raw materials to manufacture brown-like land: the space boundary is clear, and obvious enclosing walls are generally arranged; the field is internally provided with a built structure with obvious industrial characteristics; the field is generally flat; the area is large, and building groups which are closely connected together through pipelines, conveyor belts, railways and the like are often used; traffic in the site is regular, and railways are arranged in the site or the site is directly connected with the railways.
5) Processing non-raw materials to manufacture brown-like land: the space boundary is clear, and obvious enclosing walls are generally arranged; a large-area blue or red color steel shed or solar panel is arranged in the field; the field is generally flat; the building group has a large number of buildings, and the area of the building group is larger than that of residential buildings; the road rules in the ground.
6) Infrastructure brown land: the space boundary is clearer; marking structures such as rails are arranged in the field; the field is generally flat.
Based on the spatial characteristics of the six types of brown lands, the embodiment of the invention can visually interpret, research, judge and refine the distribution and spatial boundaries of the types of the subdivided brown lands such as raw material mining, tailing pond, raw material processing and manufacturing, non-raw material processing and manufacturing, infrastructure, landfill and the like according to the spatial boundaries, facilities, hue, elevation, area and texture of the remote sensing image of the target area.
S103, correcting the multi-category potential brown land distribution map according to multi-source space and non-space data to obtain the identification result of the brown lands of the plurality of categories, wherein the multi-source space and non-space data at least comprises: multiple time sequence human flow thermodynamic diagrams.
After the multi-category potential brown distribution map is obtained, it also needs to be corrected. The embodiment of the invention provides that multisource space and non-space data (such as human flow thermodynamic diagram data, urban planning diagram data and the like) are corrected so as to reject land parcels still in operation and supplement missing brown lands.
In an alternative embodiment, the non-spatial multi-source data further comprises: in this case, step S103 specifically includes:
and rejecting land parcels still in operation in the multi-category potential brown land distribution map according to the urban land use current situation map, the urban land use planning map, the Shi Zhi data and the multi-time sequence people flow thermodynamic diagram, and supplementing the missing brown land identified in the multi-category potential brown land distribution map.
For ease of understanding, a method for brown land identification based on multi-source information analysis provided in the embodiments of the present invention will be further explained below by way of a specific embodiment, which is to be understood as an example only:
1. Determining a target area using the POI data: firstly, the pretreatment work such as cleaning, space correction and the like is carried out on the industrial, mining and landfill POI data of the duckweed city to obtain a POI distribution diagram of the duckweed city, as shown in figure 2.
2. Identifying brown land: on the basis of the POI determined spatial identification target area, the potential brown land of the refuse landfill, the potential brown land of the raw material mining type, the potential brown land of the tailing pond type, the potential brown land of the raw material and non-raw material processing type and the potential brown land of the infrastructure type which are positioned on the ground surface are identified through established visual interpretation rules, and a multi-category potential brown land distribution map is obtained, as shown in figure 3.
3. Land parcel correction: and on the basis of obtaining a multi-category potential brown land distribution map, rejecting the still-running field on the basis of a field current map, a field planning map, a multi-time-sequence hundred-degree human flow thermodynamic diagram and history log data of the field, and supplementing the brown land which is identified to be missed. Thus, a corrected brown plot is obtained, as shown in fig. 4.
Based on the same inventive concept, an embodiment of the present invention provides a brown land identification device based on multi-source information analysis, and referring to fig. 5, fig. 5 is a schematic diagram of the brown land identification device provided by the embodiment of the present invention. As shown in fig. 5, the apparatus includes:
The determining module 501 is configured to determine, according to map data of a target area and POI data of the target area, an area where a potential brown land is located in a remote sensing image of the target area;
the classification module 502 is configured to determine a potential brown land from an area where the potential brown land is located according to spatial features included in the remote sensing image of the target area, and classify the potential brown land to obtain a multi-category potential brown land distribution map;
the correction module 503 is configured to correct the multi-category potential brown land distribution map according to multi-source spatial and non-spatial data, so as to obtain a recognition result of a plurality of categories of brown lands, where the multi-source spatial and non-spatial data at least includes: multiple time sequence human flow thermodynamic diagrams;
wherein, the brown land of multiple categories includes: landfill site, raw material mining brown-like land, tailing pond brown-like land, raw material processing and manufacturing brown-like land, non-raw material processing and manufacturing brown-like land and infrastructure brown-like land.
Optionally, the determining module 501 includes:
the first acquisition sub-module is used for acquiring map POI data of a target area and selecting industrial POI data related to industry from the map POI data;
the second acquisition submodule is used for acquiring mining area POI data of the target area and screening idle mining class POI data from the mining area POI data;
A third obtaining sub-module, configured to obtain map POI data of a target area, and select landfill type POI data related to landfill from the map POI data;
and the determining submodule is used for determining the area where the potential brown land is located according to the map data of the target area, the industrial POI data, the mining POI data and the landfill POI data and identifying the area in the remote sensing image of the target area.
Optionally, the first obtaining sub-module is specifically configured to:
acquiring map POI data of a target area;
selecting POI data of a category related to industrial brown land from map POI data of the target area as first industrial POI data;
keyword screening is carried out on data except the first industrial POI data in the map POI data, so that supplementary industrial POI data are obtained;
and obtaining industrial POI data according to the first industrial POI data and the supplementary industrial POI data.
Optionally, the second obtaining sub-module is specifically configured to:
screening idle mining class POI data from the mining site POI data according to the attribute of each mining site in the mining site POI data of the target area;
The attributes of each of the mineral sites include at least: the current situation is utilized.
Optionally, the third obtaining sub-module is specifically configured to:
acquiring map POI data of a target area;
selecting POI data of a class related to landfill from map POI data of the target area as first landfill POI data;
keyword screening is carried out on data except the first landfill type POI data in the map POI data, so that supplementary landfill type POI data are obtained;
and obtaining the landfill type POI data according to the first landfill type POI data and the supplementary landfill type POI data.
Optionally, the classification module 502 is specifically configured to:
obtaining the category and the space boundary of each potential brown land included in the area where the potential brown land is located according to the space boundary, facility, hue, elevation, area and texture of the remote sensing image of the target area;
and marking in the remote sensing image of the target area according to the category and the space boundary of each potential brown land, and obtaining a multi-category potential brown land distribution map.
Optionally, the multi-source spatial and non-spatial data further comprises: the correction module 503 is specifically configured to:
And rejecting land parcels still in operation in the multi-category potential brown land distribution map according to the urban land use current situation map, the urban land use planning map, the Shi Zhi data and the multi-time sequence people flow thermodynamic diagram, and supplementing the missing brown land identified in the multi-category potential brown land distribution map.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps in the brown land identification method based on multi-source information analysis according to any of the embodiments described above when the processor executes the program.
Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps in the brown land identification method based on multi-source information analysis as described in any of the above embodiments.
Based on the same inventive concept, embodiments of the present invention provide a computer program product comprising a computer program/instruction which, when executed by a processor, implements the steps of the brown land identification method based on multi-source information analysis described in any of the above embodiments.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing has outlined rather broadly the principles and embodiments of the present invention in order that the detailed description of the invention that follows may be better understood, such as a method, apparatus, electronic device, computer readable storage medium, and computer program product that are provided herein; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (7)
1. A method for brown land identification based on multi-source information analysis, the method comprising:
determining the area where the potential brown land is located in the remote sensing image of the target area according to the map data of the target area and the POI data of the target area;
based on the predetermined spatial characteristics of each type of brown land, performing visual interpretation according to the spatial boundary, facility, hue, elevation, area and texture of the remote sensing image of the target area, and performing research and judgment to extract the distribution and spatial boundary of the types of subdivided brown lands including raw material mining brown lands, tailing pond brown lands, raw material processing and manufacturing brown lands, non-raw material processing and manufacturing brown lands, infrastructure brown lands and refuse landfill, so as to obtain the types and spatial boundaries of each potential brown land included in the area where the potential brown land is located;
marking in the remote sensing image of the target area according to the category and the space boundary of each potential brown land to obtain a multi-category potential brown land distribution map;
correcting the multi-category potential brown land distribution map according to multi-source space and non-space data to obtain the identification result of the brown lands of a plurality of categories, wherein the multi-source space and non-space data at least comprises: multiple time sequence human flow thermodynamic diagrams;
Wherein, the brown land of multiple categories includes: landfill site, raw material mining brown-like land, tailing pond brown-like land, raw material processing and manufacturing brown-like land, non-raw material processing and manufacturing brown-like land and infrastructure brown-like land;
according to the map data of the target area and the POI data of the target area, determining the area where the potential brown land is located in the remote sensing image of the target area comprises the following steps:
acquiring map POI data of a target area, and selecting industrial POI data related to industry from the map POI data;
acquiring mining place POI data of a target area, and screening idle mining class POI data from the mining place POI data;
acquiring map POI data of a target area, and selecting landfill type POI data related to landfill from the map POI data;
determining an area where a potential brown land is located according to the map data of the target area, the industrial POI data, the mining POI data and the landfill POI data;
the multi-source spatial and non-spatial data further includes: the current urban land map, the urban land planning map and Shi Zhi data are used for correcting the multi-category potential brown land distribution map according to multi-source space and non-space data, and the method comprises the following steps:
And rejecting land parcels still in operation in the multi-category potential brown land distribution map according to the urban land use current situation map, the urban land use planning map, the Shi Zhi data and the multi-time sequence people flow thermodynamic diagram, and supplementing the missing brown land identified in the multi-category potential brown land distribution map.
2. The method of claim 1, wherein selecting industry-class POI data associated with an industry from the map POI data comprises:
acquiring map POI data of a target area;
selecting POI data of a category related to industrial brown land from map POI data of the target area as first industrial POI data;
keyword screening is carried out on data except the first industrial POI data in the map POI data, so that supplementary industrial POI data are obtained;
and obtaining industrial POI data according to the first industrial POI data and the supplementary industrial POI data.
3. The method of claim 1, wherein screening idle mining class POI data from the mining site POI data comprises:
screening idle mining class POI data from the mining site POI data according to the attribute of each mining site in the mining site POI data of the target area;
The attributes of each of the mineral sites include at least: the current situation is utilized.
4. The method of claim 1, wherein selecting landfill-like POI data associated with landfill from the map POI data comprises:
acquiring map POI data of a target area;
selecting POI data of a class related to landfill from map POI data of the target area as first landfill POI data;
keyword screening is carried out on data except the first landfill type POI data in the map POI data, so that supplementary landfill type POI data are obtained;
and obtaining the landfill type POI data according to the first landfill type POI data and the supplementary landfill type POI data.
5. A brown land identification device based on multi-source information analysis, the device comprising:
the determining module is used for determining the area where the potential brown land is located in the remote sensing image of the target area according to the map data of the target area and the POI data of the target area;
the classification module is used for carrying out visual interpretation according to the spatial boundary, facilities, hue, elevation, area and texture of the remote sensing image of the target area based on the spatial characteristics of each predetermined type of brown land, and carrying out research and refinement to obtain the distribution and spatial boundary of the types of subdivided brown lands including raw material mining brown lands, tailing pond brown lands, raw material processing brown lands, non-raw material processing brown lands, infrastructure brown lands and refuse landfill, so as to obtain the types and spatial boundary lands of each potential brown land included in the area where the potential brown land is located; marking in the remote sensing image of the target area according to the category and the space boundary of each potential brown land to obtain a multi-category potential brown land distribution map;
The correction module is used for correcting the multi-category potential brown land distribution map according to multi-source space and non-space data to obtain the identification result of the brown lands of various categories, and the multi-source space and non-space data at least comprises: multiple time sequence human flow thermodynamic diagrams;
wherein, the brown land of multiple categories includes: landfill site, raw material mining brown-like land, tailing pond brown-like land, raw material processing and manufacturing brown-like land, non-raw material processing and manufacturing brown-like land and infrastructure brown-like land;
the determining module includes:
the first acquisition sub-module is used for acquiring map POI data of a target area and selecting industrial POI data related to industry from the map POI data;
the second acquisition submodule is used for acquiring mining area POI data of the target area and screening idle mining class POI data from the mining area POI data;
a third obtaining sub-module, configured to obtain map POI data of a target area of the target area, and select landfill type POI data related to landfill from the map POI data;
a determining submodule, configured to determine a potential brown land area according to map data of the target area, the industrial POI data, the mining POI data and the landfill POI data;
The multi-source spatial and non-spatial data further includes: the correction module is specifically used for correcting the current map of the urban land, the map of the urban land and Shi Zhi data:
and rejecting land parcels still in operation in the multi-category potential brown land distribution map according to the urban land use current situation map, the urban land use planning map, the Shi Zhi data and the multi-time sequence people flow thermodynamic diagram, and supplementing the missing brown land identified in the multi-category potential brown land distribution map.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the multi-source information analysis based brown land identification method according to any of claims 1-4 when the program is executed by the processor.
7. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method for brown land identification based on multi-source information analysis according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210896034.8A CN115272854B (en) | 2022-07-27 | 2022-07-27 | Palm land identification method and product based on multi-source information analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210896034.8A CN115272854B (en) | 2022-07-27 | 2022-07-27 | Palm land identification method and product based on multi-source information analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115272854A CN115272854A (en) | 2022-11-01 |
| CN115272854B true CN115272854B (en) | 2023-08-15 |
Family
ID=83770923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210896034.8A Active CN115272854B (en) | 2022-07-27 | 2022-07-27 | Palm land identification method and product based on multi-source information analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272854B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5323317A (en) * | 1991-03-05 | 1994-06-21 | Hampton Terry L | Method and apparatus for determining runoff using remote geographic sensing |
| CN102096816A (en) * | 2011-01-28 | 2011-06-15 | 武汉大学 | Multi-scale multi-level image segmentation method based on minimum spanning tree |
| CN104463168A (en) * | 2014-11-25 | 2015-03-25 | 中国科学院地理科学与资源研究所 | Automatic waste empty house site information extraction method based on remote-sensing image |
| CN105654226A (en) * | 2014-11-28 | 2016-06-08 | 西门子公司 | Common plant model for modelling of physical plant items of production plant |
| CN107193877A (en) * | 2017-04-24 | 2017-09-22 | 中国科学院遥感与数字地球研究所 | Land cover classification system and method |
| CN109284706A (en) * | 2018-09-12 | 2019-01-29 | 北京英视睿达科技有限公司 | Hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing |
| CN112733781A (en) * | 2021-01-20 | 2021-04-30 | 中国科学院地理科学与资源研究所 | City functional area identification method combining POI data, storage medium and electronic equipment |
| CN113475040A (en) * | 2019-02-25 | 2021-10-01 | 思科技术公司 | Learning by inference from brown deployment |
| CN216226137U (en) * | 2021-11-17 | 2022-04-08 | 安徽井田环保科技有限公司 | Brown field pollution repair device |
| CN114331206A (en) * | 2022-01-06 | 2022-04-12 | 重庆紫光华山智安科技有限公司 | Point location addressing method and device, electronic equipment and readable storage medium |
-
2022
- 2022-07-27 CN CN202210896034.8A patent/CN115272854B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5323317A (en) * | 1991-03-05 | 1994-06-21 | Hampton Terry L | Method and apparatus for determining runoff using remote geographic sensing |
| CN102096816A (en) * | 2011-01-28 | 2011-06-15 | 武汉大学 | Multi-scale multi-level image segmentation method based on minimum spanning tree |
| CN104463168A (en) * | 2014-11-25 | 2015-03-25 | 中国科学院地理科学与资源研究所 | Automatic waste empty house site information extraction method based on remote-sensing image |
| CN105654226A (en) * | 2014-11-28 | 2016-06-08 | 西门子公司 | Common plant model for modelling of physical plant items of production plant |
| CN107193877A (en) * | 2017-04-24 | 2017-09-22 | 中国科学院遥感与数字地球研究所 | Land cover classification system and method |
| CN109284706A (en) * | 2018-09-12 | 2019-01-29 | 北京英视睿达科技有限公司 | Hot spot grid agglomeration of industries area recognizing method based on Multi-sensor satellite remote sensing |
| CN113475040A (en) * | 2019-02-25 | 2021-10-01 | 思科技术公司 | Learning by inference from brown deployment |
| CN112733781A (en) * | 2021-01-20 | 2021-04-30 | 中国科学院地理科学与资源研究所 | City functional area identification method combining POI data, storage medium and electronic equipment |
| CN216226137U (en) * | 2021-11-17 | 2022-04-08 | 安徽井田环保科技有限公司 | Brown field pollution repair device |
| CN114331206A (en) * | 2022-01-06 | 2022-04-12 | 重庆紫光华山智安科技有限公司 | Point location addressing method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115272854A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Park et al. | Patch-based crack detection in black box images using convolutional neural networks | |
| Kheir et al. | On the quantitative relationships between environmental parameters and heavy metals pollution in Mediterranean soils using GIS regression-trees: The case study of Lebanon | |
| CN103544550B (en) | A kind of Forecasting Methodology of Some Mining Districts soil-water termination heavy metal burden | |
| Lei et al. | Does Urban planning affect urban growth pattern? A case study of Shenzhen, China | |
| Rate | Multielement geochemistry identifies the spatial pattern of soil and sediment contamination in an urban parkland, Western Australia | |
| CN106529738A (en) | Groundwater polluted site repair technology optimization method | |
| CN102999927B (en) | Fine partition method of soil pollutant content spatial distribution | |
| CN113033381B (en) | Remote sensing data-based automatic extraction method and device for mine and solid waste landfill | |
| CN110826236A (en) | Method for judging soil remediation pollution range | |
| Liu et al. | A century of the evolution of the urban area in Shenyang, China | |
| Alzraiee et al. | Detecting of pavement marking defects using faster R-CNN | |
| Zhang et al. | Novel method for industrial sewage outfall detection: Water pollution monitoring based on web crawler and remote sensing interpretation techniques | |
| CN114662820A (en) | Environmental pollution risk grading method and system | |
| CN103049655A (en) | Mining area land ecological damage information acquisition method based on multiple data sources | |
| Dereli et al. | Comparison of GIS-based surrogate weighting methods for multi-directional landfill site selection in West Mediterranean Planning Region in Turkey | |
| CN114544913A (en) | Soil investigation encrypted sampling stationing optimization method | |
| CN112329706A (en) | Mining land identification method based on remote sensing technology | |
| Calijuri et al. | Multi-criteria analysis for the identification of waste disposal areas | |
| CN115330720A (en) | Unmanned aerial vehicle image earth surface solid waste detection model and detection method | |
| CN113762784B (en) | Quantitative comprehensive evaluation method and system for layout planning scheme of sewage treatment system | |
| CN115272854B (en) | Palm land identification method and product based on multi-source information analysis | |
| CN107862484B (en) | Mine ecological restoration scheme guidance system based on mine ecological detection | |
| CN115272853B (en) | Industrial abandoned land identification method and product based on artificial intelligence technology and big data | |
| Yong et al. | Automatic identification of illegal construction and demolition waste landfills: A computer vision approach | |
| CN116500697A (en) | Hydrogeological investigation method |
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 |