CN105760421A - Land-use type classifying method - Google Patents
Land-use type classifying method Download PDFInfo
- Publication number
- CN105760421A CN105760421A CN201610039024.7A CN201610039024A CN105760421A CN 105760421 A CN105760421 A CN 105760421A CN 201610039024 A CN201610039024 A CN 201610039024A CN 105760421 A CN105760421 A CN 105760421A
- Authority
- CN
- China
- Prior art keywords
- land
- hard spot
- use pattern
- sorted
- hard
- 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.)
- Pending
Links
Classifications
-
- 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
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Abstract
The invention discloses a land-use type classifying method. The method includes the following steps of establishing a dynamics model of a plurality of land-use types through the ADAMS to obtain an ADAMS hard spot file, reading the numerical values of coordinates of all hard spots in the ADAMS hard spot file to form a modifiable hard spot list, establishing a plurality of hard spot land-use type establishing models according to the hard spot list, conducting parameterization treatment on the hard spot land-use type establishing models to link the hard spot land-use type establishing models with the hard spot list, issuing all the linked hard spots in the hard spot land-use type establishing models, collecting land vector data and remote-sensing image raster data of a to-be-classified land, inputting the hard spot list to obtain a hard spot land-use type establishing model of the to-be-classified land, and comparing the two models to obtain land classifying information of the to-be-classified land. By means of the method, the precise and unified-standard classification and the automatic classification of land-use types are achieved, and efficiency is greatly improved.
Description
Technical field
The present invention relates to land use classes technical field, the method being specifically related to the classification of a kind of land use pattern.
Background technology
Along with going deep into of global change research due, Land_use change/cover Changeement has become as the core realm content of global environmental change research.Application remote sensing technology combining geographic information system (GeographicInformationSystem, be called for short GIS), computer technology and traditional investigation method carry out the interpretation of land use pattern and classification has become as the important means currently obtaining large scale, high-timeliness Land_use change space-time data.
In the research of remote sensing technology, differentiating that various target is an important ring of development of remote sensing by remote sensing image, the foundation of Remote Sensing Database concerns the importances such as specialty information extraction, dynamic variation prediction and Thematic Cartography.
Land_use change Classification in Remote Sensing Image is actually the process of the automatic Classification and Identification of remote sensing images, namely by computer simulating human consciousness, completes the process of remote Sensing Image Analysis and understanding.Namely the key problem of Land_use change Classification in Remote Sensing Image is one and to Characteristics of The Remote Sensing Images analysis extraction, image segmentation and clusters, and carries out the process of Classification and Identification.The detailed process of Land_use change Classification in Remote Sensing Image is the kind that each pixel or region in remote sensing images are classified as in land use pattern categorizing system, namely by the Spectral Characteristics Analysis of all kinds of atural objects is selected characteristic parameter, mark off feature space, the pixel of remote sensing images is divided in feature space.In the prior art, conventional Land_use change Classification in Remote Sensing Image method has: visual interpretation method, supervised classification and unsupervised classification method.
Visual interpretation method, mainly by remote sensing image processing software remote sensing images are carried out arbitrarily enlarged, reduce and image enhancement processing, to reach best improvement of visual effect, interpretation personnel directly sketch out along image feature edge class boundary line, ground.The shortcoming of this method is that the mode relying primarily on human interpretation is classified, and not only expend time in length, and the interpretation result of different personnel is different, causes that classification results there are differences, it is impossible to realize classification automatically.
Supervised classification, also known as training center classification method, basic characteristics are by sampling survey on the spot before classification, coordinate artificial visual interpretation, realize the atural object category attribute in some sampling region on remote sensing images previously known, namely choose training center, then make computer go to draw up decision function according to known type feature, thus realizing the classification to land use pattern.The defect of the method is similar with visual interpretation method, and the process choosing training center in this method is manually judge equally, so workload is big, and length consuming time, and also result there are differences, it is impossible to realize automatization.
Unsupervised classification method, is namely that the regularity of distribution of only spectral signature with remote sensing images is classified, and realizes distinguishing to different types, is a kind of mode automatically carrying out and classifying.The method has the disadvantage that, classifies in the method, can only distinguish different types of soil, it is impossible to determine its land use pattern, and degree of accuracy is relatively low, it is impossible to meet the needs of practical application.
Summary of the invention
For solving the problems referred to above, the method that the invention provides the classification of a kind of land use pattern, the land use pattern to realize high efficiency, automatization and pinpoint accuracy is classified.
For achieving the above object, the technical scheme that the present invention takes is:
The method of land use pattern classification, comprises the steps:
S1, according to history Land_use change vector data, ADAMS is used to set up the kinetic model of some land use pattern, obtain ADAMS hard spot file, ADAMS hard spot file at least includes the land use pattern information of each pixel in Land_use change vector data, remote sensing image raster data, satellite remote-sensing image raster data；
S2, reading the coordinate values of each hard spot in ADAMS hard spot file, form a revisable hard spot table, hard spot table includes each hard spot fix name, and at distance value between corresponding coordinate values and adjacent two coordinates of each hard spot；
S3, according to hard spot table, set up some hard spot land use pattern tectonic models, land use pattern tectonic model includes all hard spot coordinates of history Land_use change；
S4, hard spot land use pattern tectonic model is carried out parameterized treatment, make hard spot land use pattern tectonic model set up with hard spot table and associate, and issue each hard spot associated in hard spot Land_use change tectonic model；
S5, the soil vector data collecting area to be sorted and remote sensing image raster data, input hard spot table, it is thus achieved that the hard spot Land_use change tectonic model in area to be sorted；
S6, the hard spot Land_use change tectonic model in the area to be sorted of gained and some hard spot land use pattern tectonic models are compared, obtain the information of land use classification in area to be sorted.
Preferably, in described satellite remote-sensing image raster data, the land use pattern information of each pixel is obtained by following steps:
(1) grid division is utilized to obtain pixel the satellite remote-sensing image in area to be sorted；
(2) it is overlapped processing by described history Land_use change vector data and satellite remote-sensing image raster data, it is thus achieved that the land use pattern information of each pixel in satellite remote-sensing image raster data.
Preferably, the concrete steps of described step (2) including: is superposed with the satellite remote-sensing image raster data through standardization by history Land_use change vector data and is overlapped analyzing, obtains the normal light modal data containing multiple wave bands；Described normal light modal data represents with a matrix type, and every a line of described matrix represents multiple features that in normal light modal data, a pixel comprises, and the feature quantity that each pixel comprises is equal with the wave band quantity of normal light modal data；Described normal light modal data being carried out principal component analysis, obtains the main constituent of spectroscopic data, the quantity of described main constituent is equal with wave band quantity, and chooses and comprise three main constituents that feature is maximum；Wherein, described principal component analysis is specially Orthogonal Decomposition conversion.
Preferably, described step S6 concretely comprises the following steps: calculates the distance between the hard spot Land_use change tectonic model and the individual hard spot land use pattern tectonic model that obtain area to be sorted, and finds a hard spot land use pattern tectonic model closest with the hard spot Land_use change tectonic model in this area to be sorted；The hard spot Land_use change tectonic model in area to be sorted is converted to the land use pattern that the hard spot land use pattern tectonic model closest with the hard spot Land_use change tectonic model in this area to be sorted is corresponding.
The method have the advantages that
By choosing sample vector data, set up the hard spot table of change, establish the hard spot Land_use change tectonic model in some hard spot Land_use change tectonic models and the area to be sorted associated with hard spot table simultaneously, thus utilizing the hard spot Land_use change tectonic model in some hard spot Land_use change tectonic models and area to be sorted to contrast, it is thus achieved that the land classification model in area to be sorted；Thus the method for the invention realize land use pattern accurately, the classification of unified standard, and realize automatically classification, improve efficiency greatly.
Detailed description of the invention
In order to make objects and advantages of the present invention clearly understand, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.
The method embodiments providing the classification of a kind of land use pattern, comprises the steps:
S1, according to history Land_use change vector data, ADAMS is used to set up the kinetic model of some land use pattern, obtain ADAMS hard spot file, ADAMS hard spot file at least includes the land use pattern information of each pixel in Land_use change vector data, remote sensing image raster data, satellite remote-sensing image raster data；
S2, reading the coordinate values of each hard spot in ADAMS hard spot file, form a revisable hard spot table, hard spot table includes each hard spot fix name, and at distance value between corresponding coordinate values and adjacent two coordinates of each hard spot；
S3, according to hard spot table, set up some hard spot land use pattern tectonic models, land use pattern tectonic model includes all hard spot coordinates of history Land_use change；
S4, hard spot land use pattern tectonic model is carried out parameterized treatment, make hard spot land use pattern tectonic model set up with hard spot table and associate, and issue each hard spot associated in hard spot Land_use change tectonic model；
S5, the soil vector data collecting area to be sorted and remote sensing image raster data, input hard spot table, it is thus achieved that the hard spot Land_use change tectonic model in area to be sorted；
S6, the hard spot Land_use change tectonic model in the area to be sorted of gained and some hard spot land use pattern tectonic models are compared, obtain the information of land use classification in area to be sorted.
In described satellite remote-sensing image raster data, the land use pattern information of each pixel is obtained by following steps:
(1) grid division is utilized to obtain pixel the satellite remote-sensing image in area to be sorted；
(2) it is overlapped processing by described history Land_use change vector data and satellite remote-sensing image raster data, it is thus achieved that the land use pattern information of each pixel in satellite remote-sensing image raster data.
The concrete steps of described step (2) including: is superposed with the satellite remote-sensing image raster data through standardization by history Land_use change vector data and is overlapped analyzing, obtains the normal light modal data containing multiple wave bands；Described normal light modal data represents with a matrix type, and every a line of described matrix represents multiple features that in normal light modal data, a pixel comprises, and the feature quantity that each pixel comprises is equal with the wave band quantity of normal light modal data；Described normal light modal data being carried out principal component analysis, obtains the main constituent of spectroscopic data, the quantity of described main constituent is equal with wave band quantity, and chooses and comprise three main constituents that feature is maximum；Wherein, described principal component analysis is specially Orthogonal Decomposition conversion.
Described step S6 concretely comprises the following steps: calculates the distance between the hard spot Land_use change tectonic model and the hard spot land use pattern tectonic model that obtain area to be sorted, and finds a hard spot land use pattern tectonic model closest with the hard spot Land_use change tectonic model in this area to be sorted；The hard spot Land_use change tectonic model in area to be sorted is converted to the land use pattern that the hard spot land use pattern tectonic model closest with the hard spot Land_use change tectonic model in this area to be sorted is corresponding.
Described hard spot table is set up by following steps:
Use Matlab to read the coordinate values of each hard spot in described ADAMS hard spot file and import in an EXCEL file, the first list of described EXCEL file is deposited the distance between described each hard spot title, coordinate values and adjacent two coordinates；First row at the second list of described EXCEL file places hard spot fix name, secondary series is linked in the first list corresponding coordinate values, 3rd row are connected to the distance between corresponding two coordinates in the first list, and described EXCEL file is described revisable hard spot table
Below it is only the preferred embodiment of the present invention; it should be pointed out that, for those skilled in the art, under the premise without departing from the principles of the invention; can also making some improvements and modifications, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (4)
1. the method for land use pattern classification, it is characterised in that comprise the steps:
S1, according to history Land_use change vector data, ADAMS is used to set up the kinetic model of some land use pattern, obtain ADAMS hard spot file, ADAMS hard spot file at least includes the land use pattern information of each pixel in Land_use change vector data, remote sensing image raster data, satellite remote-sensing image raster data；
S2, reading the coordinate values of each hard spot in ADAMS hard spot file, form a revisable hard spot table, hard spot table includes each hard spot fix name, and at distance value between corresponding coordinate values and adjacent two coordinates of each hard spot；
S3, according to hard spot table, set up some hard spot land use pattern tectonic models, land use pattern tectonic model includes all hard spot coordinates of history Land_use change；
S4, hard spot land use pattern tectonic model is carried out parameterized treatment, make hard spot land use pattern tectonic model set up with hard spot table and associate, and issue each hard spot associated in hard spot Land_use change tectonic model；
S5, the soil vector data collecting area to be sorted and remote sensing image raster data, input hard spot table, it is thus achieved that the hard spot Land_use change tectonic model in area to be sorted；
S6, the hard spot Land_use change tectonic model in the area to be sorted of gained and some hard spot land use pattern tectonic models are compared, obtain the information of land use classification in area to be sorted.
2. the method for land use pattern according to claim 1 classification, it is characterised in that in described satellite remote-sensing image raster data, the land use pattern information of each pixel is obtained by following steps:
(1) grid division is utilized to obtain pixel the satellite remote-sensing image in area to be sorted；
(2) it is overlapped processing by described history Land_use change vector data and satellite remote-sensing image raster data, it is thus achieved that the land use pattern information of each pixel in satellite remote-sensing image raster data.
3. the method for land use pattern according to claim 2 classification, it is characterized in that, the concrete steps of described step (2) including: is superposed with the satellite remote-sensing image raster data through standardization by history Land_use change vector data and is overlapped analyzing, obtains the normal light modal data containing multiple wave bands；Described normal light modal data represents with a matrix type, and every a line of described matrix represents multiple features that in normal light modal data, a pixel comprises, and the feature quantity that each pixel comprises is equal with the wave band quantity of normal light modal data；Described normal light modal data being carried out principal component analysis, obtains the main constituent of spectroscopic data, the quantity of described main constituent is equal with wave band quantity, and chooses and comprise three main constituents that feature is maximum；Wherein, described principal component analysis is specially Orthogonal Decomposition conversion.
4. the method for land use pattern according to claim 1 classification, it is characterized in that, described step S6 concretely comprises the following steps: calculates the distance between the hard spot Land_use change tectonic model and each the hard spot land use pattern tectonic model that obtain area to be sorted, and finds a hard spot land use pattern tectonic model closest with the hard spot Land_use change tectonic model in this area to be sorted；The hard spot Land_use change tectonic model in area to be sorted is converted to the land use pattern that the hard spot land use pattern tectonic model closest with the hard spot Land_use change tectonic model in this area to be sorted is corresponding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610039024.7A CN105760421A (en) | 2016-01-12 | 2016-01-12 | Land-use type classifying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610039024.7A CN105760421A (en) | 2016-01-12 | 2016-01-12 | Land-use type classifying method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105760421A true CN105760421A (en) | 2016-07-13 |
Family
ID=56342475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610039024.7A Pending CN105760421A (en) | 2016-01-12 | 2016-01-12 | Land-use type classifying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105760421A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599338A (en) * | 2016-10-09 | 2017-04-26 | 钦州学院 | Three-dimensional geologic modeling method for shale gas reservoirs |
| CN107066572A (en) * | 2017-04-10 | 2017-08-18 | 山东师范大学 | Ground mulching sorting technique and system based on many source geodata space clusterings |
| CN117541940A (en) * | 2024-01-10 | 2024-02-09 | 日照市自然资源和规划局 | Land utilization classification method and system based on remote sensing data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521624A (en) * | 2011-12-20 | 2012-06-27 | 中国科学院地理科学与资源研究所 | Classification method for land use types and system |
| CN102750732A (en) * | 2011-04-20 | 2012-10-24 | 张公达 | Land resource utilization change dynamic prediction model based on GIS (Geographic Information System) and using method of dynamic prediction model |
| US20120287273A1 (en) * | 2011-05-09 | 2012-11-15 | Abengoa Bioenergia Nuevas Tecnologias, S.A. | System for identifying sustainable geographical areas by remote sensing techniques and method thereof |
| CN104573163A (en) * | 2013-10-29 | 2015-04-29 | 广州汽车集团股份有限公司 | Automobile suspension parameterization design method |
-
2016
- 2016-01-12 CN CN201610039024.7A patent/CN105760421A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750732A (en) * | 2011-04-20 | 2012-10-24 | 张公达 | Land resource utilization change dynamic prediction model based on GIS (Geographic Information System) and using method of dynamic prediction model |
| US20120287273A1 (en) * | 2011-05-09 | 2012-11-15 | Abengoa Bioenergia Nuevas Tecnologias, S.A. | System for identifying sustainable geographical areas by remote sensing techniques and method thereof |
| CN102521624A (en) * | 2011-12-20 | 2012-06-27 | 中国科学院地理科学与资源研究所 | Classification method for land use types and system |
| CN104573163A (en) * | 2013-10-29 | 2015-04-29 | 广州汽车集团股份有限公司 | Automobile suspension parameterization design method |
Non-Patent Citations (2)
| Title |
|---|
| WU GUI-PING 等: "Dynamic simulation of land use change based on the improved CLUE-S model: A case study of Yongding County, Zhangjiajie", 《GEOGRAPHICAL RESEARCH》 * |
| 钱国英等: "基于遥感与系统动力学模型的土地利用/覆被变化研究", 《遥感信息》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599338A (en) * | 2016-10-09 | 2017-04-26 | 钦州学院 | Three-dimensional geologic modeling method for shale gas reservoirs |
| CN107066572A (en) * | 2017-04-10 | 2017-08-18 | 山东师范大学 | Ground mulching sorting technique and system based on many source geodata space clusterings |
| CN107066572B (en) * | 2017-04-10 | 2019-07-23 | 山东师范大学 | Ground mulching classification method and system based on crowd-sourced geodata space clustering |
| CN117541940A (en) * | 2024-01-10 | 2024-02-09 | 日照市自然资源和规划局 | Land utilization classification method and system based on remote sensing data |
| CN117541940B (en) * | 2024-01-10 | 2024-03-22 | 日照市自然资源和规划局 | Land utilization classification method and system based on remote sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shahtahmassebi et al. | Remote sensing of urban green spaces: A review | |
| Xu et al. | Wheat ear counting using K-means clustering segmentation and convolutional neural network | |
| Ran et al. | Large-scale land cover mapping with the integration of multi-source information based on the Dempster–Shafer theory | |
| Jasiewicz et al. | Landscape similarity, retrieval, and machine mapping of physiographic units | |
| CN108256116B (en) | Method for rapidly acquiring current situation data of agricultural land | |
| CN108846832A (en) | A kind of change detecting method and system based on multi-temporal remote sensing image and GIS data | |
| CN108268527B (en) | A method of detection land use pattern variation | |
| CN102521624B (en) | Classification method for land use types and system | |
| Qin et al. | Object-based land cover change detection for cross-sensor images | |
| Lu et al. | Application of time series Landsat images to examining land-use/land-cover dynamic change | |
| Li et al. | An automatic approach for urban land-cover classification from Landsat-8 OLI data | |
| Yu et al. | Analysis of large-scale UAV images using a multi-scale hierarchical representation | |
| CN113780174B (en) | Storm-type landslide identification method for high vegetation platform combined with random forest algorithm | |
| Lu et al. | P_SegNet and NP_SegNet: New neural network architectures for cloud recognition of remote sensing images | |
| Jasiewicz et al. | GeoPAT: A toolbox for pattern-based information retrieval from large geospatial databases | |
| CN104239890A (en) | Method for automatically extracting coastal land and earth cover information through GF-1 satellite | |
| Vidal-Macua et al. | Developing spatially and thematically detailed backdated maps for land cover studies | |
| CN113705990A (en) | Natural resource information processing method and device, electronic equipment and storage medium | |
| Lang et al. | Combined object-based classification and manual interpretation–synergies for a quantitative assessment of parcels and biotopes | |
| CN105760421A (en) | Land-use type classifying method | |
| Assarkhaniki et al. | Using open data to detect the structure and pattern of informal settlements: an outset to support inclusive SDGs’ achievement | |
| CN109325522B (en) | Heavy industry time sequence heat source region identification algorithm based on improved kmeans | |
| Oshan et al. | A scoping review on the multiplicity of scale in spatial analysis | |
| Khalid et al. | Evaluation the accuracy of oil palm tree detection using deep learning and support vector machine classifiers | |
| Yesilnacar et al. | A land‐cover classification for landslide susceptibility mapping by using feature components |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160713 |
|
| RJ01 | Rejection of invention patent application after publication |