CN111259840A - Land occupation early warning method, device, equipment and storage medium - Google Patents
Land occupation early warning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111259840A CN111259840A CN202010068128.7A CN202010068128A CN111259840A CN 111259840 A CN111259840 A CN 111259840A CN 202010068128 A CN202010068128 A CN 202010068128A CN 111259840 A CN111259840 A CN 111259840A
- Authority
- CN
- China
- Prior art keywords
- land
- remote sensing
- longitude
- early warning
- occupation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000013145 classification model Methods 0.000 claims abstract description 55
- 238000012795 verification Methods 0.000 claims description 23
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 8
- 230000009193 crawling Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
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
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Remote Sensing (AREA)
- Educational Administration (AREA)
- Astronomy & Astrophysics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Library & Information Science (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a land occupation early warning method, which comprises the following steps: obtaining a land remote sensing image in a target longitude and latitude range; inputting the remote sensing image into an image classification model to obtain a current land type corresponding to the remote sensing image; searching a base land database by using the longitude and latitude information of the target boundary as an index to obtain a base land type corresponding to the longitude and latitude information of the target boundary in the base land database; comparing the current land type with a basic land type; and if the current land type is inconsistent with the basic land type, generating land occupation early warning information. The invention also discloses a land occupation early warning device, equipment and a storage medium. The invention can find the condition of land occupation development in time, and realizes convenient supervision of land resource occupation condition.
Description
Technical Field
The invention relates to the field of image processing, in particular to a land occupation early warning method, a land occupation early warning device, land occupation early warning equipment and a storage medium.
Background
With the continuous acceleration of industrialization and urbanization in China, the extensive land resource utilization mode occupies a leading position, so that the area of important production ecological land, such as important land resources of farmlands, forests and the like, is sharply reduced. The avoidance of occupation of important land resources by illegal buildings is an important problem in protecting land resources. At present, the occupation of the illegal and indiscriminate building of the land resources is not supervised by a good method, and the condition that whether important land resources are occupied or not can be regularly checked at fixed points through a local government, namely the condition of artificial on-site verification is checked, or corresponding treatment is carried out according to the report of illegal occupation by some local personnel, so that the time and labor are consumed, the efficiency is low, and the land occupation condition cannot be monitored in real time.
Therefore, at present, the problem that the condition that land resources are occupied is difficult to supervise exists.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a land occupation early warning method, a land occupation early warning device, land occupation early warning equipment and a storage medium, and aims to solve the technical problem that the existing land resource occupation condition is difficult to monitor.
In order to achieve the above object, the present invention provides a land occupation early warning method, comprising: obtaining a land remote sensing image in a target longitude and latitude range; the target longitude and latitude range is formed by target boundary longitude and latitude information; inputting the remote sensing image into an image classification model to obtain a current land type corresponding to the remote sensing image; searching a base land database by using the longitude and latitude information of the target boundary as an index to obtain a base land type corresponding to the longitude and latitude information of the target boundary in the base land database; the base land database comprises a mapping relation between longitude and latitude information and a base land type; comparing the current land type with a basic land type; and if the current land type is inconsistent with the basic land type, generating land occupation early warning information.
The step of obtaining the remote sensing image in the target longitude and latitude range specifically comprises the following steps: dividing a target monitoring range into a plurality of target longitude and latitude ranges; and sequentially acquiring remote sensing images in the latitude and longitude ranges of the targets, and sequentially executing the step of inputting the remote sensing images into an image classification model to obtain the current land types corresponding to the remote sensing images.
Before the step of obtaining the remote sensing image within the latitude and longitude range of the target, the land occupation early warning method further comprises the following steps: acquiring a data set consisting of classified remote sensing images containing multiple land types; and constructing an image classification model and a foundation land database by using the data set.
The acquiring of the data set comprising the classified remote sensing images of the multiple land types specifically comprises the following steps: and (4) crawling classified remote sensing images containing multiple land types from the target webpage to form a data set.
The step of constructing an image classification model using the data set specifically includes: and inputting the data set into a preset machine model so that the preset machine model learns the data set to obtain an image classification model.
The step of inputting the data set into a preset machine model to enable the preset machine model to learn the data set to obtain an image classification model specifically includes: dividing the data set into two sets according to a preset proportion, and respectively taking the two sets as a training set and a verification set; inputting the training set into a preset machine model so that the preset machine model learns the data set to obtain an intermediate model; inputting the verification set into the intermediate model to obtain a classification result of the verification set output by the intermediate model; and adjusting the model parameters of the intermediate model according to the classification result to obtain an image classification model.
The step of constructing a foundation land database by using the data set specifically comprises: acquiring longitude and latitude information and a basic land type of each classified remote sensing image in the data set; and generating a base land database according to the longitude and latitude information and the base land type of each classified remote sensing image.
In addition, in order to achieve the above object, the present invention also provides a land occupation early warning device, including: the acquisition module is used for acquiring a land remote sensing image in a target longitude and latitude range; the target longitude and latitude range is formed by target boundary longitude and latitude information; the classification module is used for inputting the remote sensing image into an image classification model to obtain the current land type corresponding to the remote sensing image; the searching module is used for searching a basic land database by using the longitude and latitude information of the target boundary as an index to obtain a corresponding basic land type of the longitude and latitude information of the target boundary in the basic land database; the base land database comprises a mapping relation between longitude and latitude information and a base land type; the comparison module is used for comparing the current land type with the basic land type; and the early warning module is used for generating land occupation early warning information if the current land type is inconsistent with the basic land type.
In addition, to achieve the above object, the present invention also provides a land occupation early warning device, including: the land occupation early warning method comprises a memory, a processor and a land occupation early warning program which is stored on the memory and can run on the processor, wherein the land occupation early warning program realizes the steps of the land occupation early warning method when being executed by the processor.
In addition, to achieve the above object, the present invention further provides a storage medium having a land occupation early warning program stored thereon, wherein the land occupation early warning program implements the steps of the land occupation early warning method as described above when executed by a processor.
According to the land occupation early warning method, device, equipment and storage medium provided by the embodiment of the invention, the land remote sensing image in the target longitude and latitude range is obtained, the remote sensing image is input into the image classification model to obtain the current land occupation type corresponding to the remote sensing image, the target boundary longitude and latitude information is used as an index to search the basic land occupation database to obtain the basic land occupation type corresponding to the target boundary longitude and latitude information in the basic land occupation database, the current land occupation type is compared with the basic land occupation type, and if the current land occupation type is inconsistent with the basic land occupation type, the land occupation early warning information is generated, so that the condition that land is occupied and developed privately can be found in time, and the convenient supervision on the land resource occupation condition is realized.
Drawings
Fig. 1 is a schematic terminal structure diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an embodiment of a land occupation early warning method of the present invention;
fig. 3 is a flowchart illustrating steps before step S202 of the land occupation early warning method according to the embodiment of the invention in fig. 2;
FIG. 4 is a schematic diagram of a detailed flow of the step "building an image classification model by using the data set" in the land occupation early warning method according to the embodiment of the present invention;
FIG. 5 is a detailed flowchart of the step "building a foundation land database using the data set" in the land occupation early warning method according to the embodiment of the present invention;
fig. 6 is a block diagram illustrating a structure of a land occupation warning device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic terminal structure diagram of a hardware operating environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, and can also be a mobile terminal device with a display function, such as a smart phone, a tablet computer, an electronic book reader, an MP3(Moving Picture Experts Group Audio Layer III, dynamic video Experts compress standard Audio Layer 3) player, an MP4(Moving Picture Experts Group Audio Layer IV, dynamic video Experts compress standard Audio Layer 4) player, a portable computer, and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the terminal may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. Such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the mobile terminal is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile terminal; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a land occupation warning program.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the land occupation warning program stored in the memory 1005, and perform the following operations: obtaining a land remote sensing image in a target longitude and latitude range; the target longitude and latitude range is formed by target boundary longitude and latitude information; inputting the remote sensing image into an image classification model to obtain a current land type corresponding to the remote sensing image; searching a base land database by using the longitude and latitude information of the target boundary as an index to obtain a base land type corresponding to the longitude and latitude information of the target boundary in the base land database; the base land database comprises a mapping relation between longitude and latitude information and a base land type; comparing the current land type with a basic land type; and if the current land type is inconsistent with the basic land type, generating land occupation early warning information.
Alternatively, the processor 1001 may call the land occupation warning program stored in the memory 1005, and further perform the following operations: the step of obtaining the remote sensing image in the target longitude and latitude range specifically comprises the following steps: dividing a target monitoring range into a plurality of target longitude and latitude ranges; and sequentially acquiring remote sensing images in the latitude and longitude ranges of the targets, and sequentially executing the step of inputting the remote sensing images into an image classification model to obtain the current land types corresponding to the remote sensing images.
Alternatively, the processor 1001 may call the land occupation warning program stored in the memory 1005, and further perform the following operations: before the step of obtaining the remote sensing image within the latitude and longitude range of the target, the land occupation early warning method further comprises the following steps: acquiring a data set consisting of classified remote sensing images containing multiple land types; and constructing an image classification model and a foundation land database by using the data set.
Alternatively, the processor 1001 may call the land occupation warning program stored in the memory 1005, and further perform the following operations: the acquiring of the data set comprising the classified remote sensing images of the multiple land types specifically comprises the following steps: and (4) crawling classified remote sensing images containing multiple land types from the target webpage to form a data set.
Alternatively, the processor 1001 may call the land occupation warning program stored in the memory 1005, and further perform the following operations: the step of constructing an image classification model using the data set specifically includes: and inputting the data set into a preset machine model so that the preset machine model learns the data set to obtain an image classification model.
Alternatively, the processor 1001 may call the land occupation warning program stored in the memory 1005, and further perform the following operations: the step of inputting the data set into a preset machine model to enable the preset machine model to learn the data set to obtain an image classification model specifically includes: dividing the data set into two sets according to a preset proportion, and respectively taking the two sets as a training set and a verification set; inputting the training set into a preset machine model so that the preset machine model learns the data set to obtain an intermediate model; inputting the verification set into the intermediate model to obtain a classification result of the verification set output by the intermediate model; and adjusting the model parameters of the intermediate model according to the classification result to obtain an image classification model.
Alternatively, the processor 1001 may call the land occupation warning program stored in the memory 1005, and further perform the following operations: the step of constructing a foundation land database by using the data set specifically comprises: acquiring longitude and latitude information and a basic land type of each classified remote sensing image in the data set; and generating a base land database according to the longitude and latitude information and the base land type of each classified remote sensing image.
Referring to fig. 2, an embodiment of a land occupation early warning method includes:
step S202, obtaining a remote sensing image of the land in a target longitude and latitude range; the target longitude and latitude range is formed by target boundary longitude and latitude information;
it should be noted that in the embodiment, the Beidou positioning and remote sensing technology is adopted to obtain the remote sensing image of the land within the target longitude and latitude range. Specifically, the terminal can establish a three-dimensional coordinate system, convert the longitude and latitude into a three-dimensional coordinate of the three-dimensional coordinate system, when the terminal needs to acquire a remote sensing image in a target longitude and latitude range, firstly acquire the three-dimensional coordinate of the target longitude and latitude range in the three-dimensional coordinate system, then convert the three-dimensional coordinate into target boundary longitude and latitude information, and acquire the remote sensing image in the target longitude and latitude range according to the target boundary longitude and latitude information. It should be noted that the three-dimensional coordinate system of the present embodiment includes information such as longitude, latitude, and altitude. In addition, the remote sensing image in the input image classification model of the embodiment only contains one land type. It should be further noted that, in the present embodiment, a monitoring period may be set to periodically acquire a sampled image, so as to perform an occupancy monitoring and early warning on the land.
In one embodiment, the step S202 specifically includes: dividing a target monitoring range into a plurality of target longitude and latitude ranges; and sequentially acquiring remote sensing images in the latitude and longitude ranges of the targets to sequentially execute the step S204.
The target monitoring range may be continuous in geographic space or may be formed by a plurality of dispersed geographic ranges. The target monitoring range of the embodiment can be selected and set by a user according to actual needs. It will be appreciated that the types of land used within the target monitoring area may be varied and may include, for example, farmlands, buildings, forests, rivers, bushes and the like. Specifically, the terminal queries a foundation land database, and divides a target monitoring range into a plurality of target latitude and longitude ranges according to latitude and longitude information corresponding to each continuous foundation remote sensing image stored in the foundation land database. And then the terminal sequentially collects the remote sensing images in the latitude and longitude ranges of the targets through the Beidou satellite and executes the step S204 according to the remote sensing images. It should be noted that the longitude and latitude information corresponding to each remote sensing image in the foundation land database is the boundary longitude and latitude information of the remote sensing image.
Step S204, inputting the remote sensing image into an image classification model to obtain a current land type corresponding to the remote sensing image;
the image classification model is a machine model having a classification function and capable of identifying the remote sensing image and the land type corresponding to the remote sensing image. The image classification model can be a neural network model, a mahalanobis distance model, a bayesian model and the like. The neural network model may be, but not limited to, a VGG (visual geometry group, super-resolution test sequence) 16 model, a ResNet (residual network) model, a densnet (delayed connected capacitive networks) model, and the like.
Specifically, the terminal inputs the remote sensing image into an image classification model, the image classification model automatically classifies the remote sensing image, and the current land type corresponding to the remote sensing image is output.
Step S206, searching a base land database by using the longitude and latitude information of the target boundary as an index to obtain a corresponding base land type of the longitude and latitude information of the target boundary in the base land database; the base land database comprises a mapping relation between longitude and latitude information and a base land type;
it should be noted that when the terminal acquires the remote sensing image by using the Beidou satellite, the terminal also acquires the target boundary longitude and latitude information corresponding to the remote sensing image. In one embodiment, the terminal also acquires the altitude information of the remote sensing image. Further, the terminal takes the longitude and latitude information of the target boundary of the remote sensing image as an index and searches a base land database. One record in the foundation land database comprises a foundation remote sensing image, a foundation land type corresponding to the foundation remote sensing image and longitude and latitude information. The terminal inquires a foundation land database according to the target boundary longitude and latitude information of the remote sensing image acquired by the Beidou satellite, and acquires the foundation land type corresponding to the longitude and latitude information when the longitude and latitude information consistent with the target boundary longitude and latitude information is found. The basic land type is the land type which is corresponding to the latitude and longitude information of the target boundary and accords with the land standard.
Step S208, comparing the current land type with the basic land type;
and step S210, if the current land type is inconsistent with the basic land type, generating land occupation early warning information.
Further, the terminal compares the current right-of-way type with the basic right-of-way type. If the current land type is consistent with the basic land type, the land in the target longitude and latitude range is not passively changed. If the current land type is inconsistent with the basic land type, indicating that the land in the target latitude and longitude range is unoccupied, and generating land occupation early warning information by the terminal. Specifically, the early warning information output by the terminal comprises longitude and latitude information of occupied land, and it can be understood that the occupied land is land corresponding to the remote sensing image in the current input image classification model, and the longitude and latitude information of the occupied land is target boundary longitude and latitude information. The early warning information can be output in the form of text to prompt the user that the land is occupied. In one embodiment, the step S210 further includes: and if the current land type is inconsistent with the basic land type and the basic land type is the target type, generating land occupation early warning information. The target type can be customized by a user, and can be farmlands, forests, rivers and the like. Therefore, the land conditions of important production ecological lands such as farmlands, forests and rivers can be timely monitored by managers, so that the conditions of the important production ecological lands such as the farmlands, the forests and the rivers which are occupied and developed privately can be timely found to be responded to, and the important production ecological lands such as the farmlands, the forests and the rivers which are not occupied privately can be protected.
In the embodiment, a land remote sensing image in a target longitude and latitude range is acquired, the remote sensing image is input into an image classification model to obtain a current land type corresponding to the remote sensing image, the target boundary longitude and latitude information is used as an index to search a basic land database to obtain a basic land type corresponding to the target boundary longitude and latitude information in the basic land database, the current land type is compared with the basic land type, and if the current land type is inconsistent with the basic land type, land occupation early warning information is generated, so that the condition that land is occupied and developed privately can be found in time, and the convenient supervision of land resource occupation conditions is realized.
In one embodiment, referring to fig. 3, before the step S202, the land occupation early warning method further includes:
step S302, acquiring a data set consisting of classified remote sensing images containing multiple land types;
the Data Set of the present embodiment includes, but is not limited to, at least one of UC commercial Land-Use DataSet (Data Set for Land Use in the university of california, university of massif, university, etc.), WHU-RS19 DataSet (remote sensing DataSet for military RS 19), SIRI-WHU DataSet (remote sensing image DataSet for military IRI), and RSSCN7 DataSet. The total number of pictures of the UCMercered Land-Use DataSet is 2100, the number of pictures of each Land type is 100, the number of categories of the Land types is 21, and the size of the pictures is 256 × 256. The total number of pictures of the WHU-RS19 DataSet is 1005, the number of pictures of each land type is 50, the number of categories of the land types is 19, and the size of the pictures is 600 × 600. The total number of pictures of the SIRI-WHU DataSet is 2400, the number of pictures of each land type is 200, the number of categories of the land types is 12, and the size of the pictures is 200 x 200. The total number of pictures of RSSCN7 DataSet is 2800, the number of pictures of each plot type is 400, the number of categories of the plot types is 7, and the size of the pictures is 400 × 400.
In one embodiment, the step S302 specifically includes: and (4) crawling classified remote sensing images containing multiple land types from the target webpage to form a data set. It should be noted that the data set may include classified remote sensing images crawled from web pages in addition to the types described above. Specifically, the terminal crawls the corresponding classified rocker image from the related professional website by using a crawler technology.
And S304, constructing an image classification model and a foundation land database by using the data set.
In this embodiment, the terminal respectively constructs an image classification model and a foundation land database by using the data sets. Specifically, the terminal learns the data set by using a machine model to learn the classification rule of the data set, so that an image classification model with the function of classifying the land types of the rocker images is obtained. In addition, the terminal also constructs a base land database by using the data set. Specifically, the terminal obtains a target data set in a target monitoring range, and a base land database is built according to the target data set. The foundation land database of the embodiment includes, but is not limited to, remote sensing images, longitude and latitude information, altitude information, and the like. The longitude and latitude information is presented in a form of separating longitude and latitude, namely, the foundation land database includes but is not limited to remote sensing images, longitude, latitude, altitude information and the like. In addition, the foundation land database can also comprise a timestamp obtained by recording the remote sensing image. After the administrator establishes the foundation land database, the foundation land database can be updated according to an official land change plan, and the time stamp comprises a time stamp corresponding to the updated remote sensing image. In this embodiment, an ID may be assigned to each record in the foundation land database, so as to facilitate management of each record. It should be understood that a record in the foundation site database contains information such as ID, remote sensing image, longitude, latitude, altitude information, timestamp, etc.
In the embodiment, the data set consisting of the classified remote sensing images with various land types is obtained, and the image classification model and the basic land database are constructed by using the data set, so that the image classification model with higher accuracy and the basic land database with wide coverage range and large coverage information can be obtained for real-time land monitoring to obtain a more accurate monitoring result.
In one embodiment, the step of constructing an image classification model using the data set specifically includes: and inputting the data set into a preset machine model so that the preset machine model learns the data set to obtain an image classification model.
It should be noted that the preset machine model includes, but is not limited to, a neural network model, a mahalanobis distance model, a bayesian model, and the like. The neural network model may be, but not limited to, a VGG (visual geometry group, super-resolution test sequence) 16 model, a ResNet (residual network) model, a densnet (delayed connected capacitive networks) model, and the like. The terminal inputs the data set into a preset machine model, and the preset machine model can automatically learn the classification rule of the data set, so that an image classification model with the function of classifying the land types of the rocker images is obtained. In the training process of the preset machine model, model parameters of the preset machine model need to be modified through manual interference so as to obtain a more accurate image classification model.
In one embodiment, referring to fig. 4, the step of constructing an image classification model by using the data set specifically includes:
step S402, dividing the data set into two sets according to a preset proportion, and respectively using the two sets as a training set and a verification set;
it should be noted that after the terminal acquires the data set, the data set is divided into two sets according to a preset proportion. For example, the data set may be divided into a training set and a validation set in an 8:2 ratio.
Step S404, inputting the training set into a preset machine model so that the preset machine model learns the data set to obtain an intermediate model;
it should be noted that the terminal inputs the training set into the preset machine model to train the preset machine model, and after the preset machine model is trained for multiple times, a preliminary intermediate model is obtained, and the intermediate model has a certain image classification function.
Step S406, inputting the verification set into the intermediate model to obtain a classification result of the verification set output by the intermediate model;
further, the terminal inputs the verification set into the intermediate model, the intermediate model classifies the classified remote sensing images in the verification set, and the classification result of the intermediate model is output.
And step S408, adjusting the model parameters of the intermediate model according to the classification result to obtain an image classification model.
Further, the terminal compares the classification result output by the intermediate model with the classified type of the classified remote sensing image, judges the misjudgment rate of the classification result, if the misjudgment rate is higher than the standard misjudgment rate, the model parameter of the intermediate model needs to be adjusted to improve the classification accuracy rate of the intermediate model, specifically, the terminal receives the modification parameter of the model parameter input by the user to modify the model parameter, the step S406 is further repeated by using the verification set until the misjudgment rate of the output classification result is lower than the standard misjudgment rate, the verification process is ended, and the image classification model is obtained.
In one embodiment, the image classification model is further tested by using a test set formed by classified remote sensing images so as to ensure the accuracy of the image classification model.
In this embodiment, the data set is divided into two sets according to a preset proportion, the two sets are respectively used as a training set and a verification set, the training set is input into a preset machine model, so that the preset machine model learns the data set to obtain an intermediate model, the verification set is input into the intermediate model to obtain a classification result of the verification set output by the intermediate model, model parameters of the intermediate model are adjusted according to the classification result to obtain an image classification model, and the classification accuracy of the image classification model is improved.
In one embodiment, referring to fig. 5, the step of constructing the foundation land database by using the data set specifically includes:
step S502, acquiring longitude and latitude information and a basic land type of each classified remote sensing image in the data set;
and step S504, generating a base land database according to the longitude and latitude information and the base land type of each classified remote sensing image.
It should be noted that each classified remote sensing image in the data set acquired by the terminal includes information such as longitude and latitude information and a type of a base land, and the terminal acquires the longitude and latitude information and the type of the base land of each classified remote sensing image and then generates a base land database according to a mapping relationship between the longitude and latitude information and the type of the base land of each classified remote sensing image. In this embodiment, one record in the foundation land database includes information such as an ID, a remote sensing image, longitude, latitude, altitude information, and a timestamp.
Referring to fig. 6, an embodiment of a land occupation early warning device includes:
the acquisition module 610 is used for acquiring a land remote sensing image in a target longitude and latitude range; the target longitude and latitude range is formed by target boundary longitude and latitude information;
the classification module 620 is used for inputting the remote sensing image into an image classification model to obtain a current land type corresponding to the remote sensing image;
the searching module 630 is configured to search a base land use database by using the target boundary longitude and latitude information as an index, and obtain a base land use type corresponding to the target boundary longitude and latitude information in the base land use database; the base land database comprises a mapping relation between longitude and latitude information and a base land type;
a comparing module 640, configured to compare the current land type with a basic land type;
and the early warning module 650 is configured to generate land occupation early warning information if the current land type is inconsistent with the basic land type.
In the embodiment, a land remote sensing image in a target longitude and latitude range is acquired, the remote sensing image is input into an image classification model to obtain a current land type corresponding to the remote sensing image, the target boundary longitude and latitude information is used as an index to search a basic land database to obtain a basic land type corresponding to the target boundary longitude and latitude information in the basic land database, the current land type is compared with the basic land type, and if the current land type is inconsistent with the basic land type, land occupation early warning information is generated, so that the condition that land is occupied and developed privately can be found in time, and the convenient supervision of land resource occupation conditions is realized.
Optionally, the obtaining module 610 is further configured to divide the target monitoring range into a plurality of target latitude and longitude ranges; and sequentially acquiring remote sensing images in the latitude and longitude ranges of all the targets.
Optionally, the building module 600 is configured to obtain a data set including classified remote sensing images of multiple land types; and constructing an image classification model and a foundation land database by using the data set.
Optionally, the building module 600 is further configured to crawl classified remote sensing images containing multiple land types from the target webpage to form a data set.
Optionally, the building module 600 is further configured to input the data set into a preset machine model, so that the preset machine model learns the data set to obtain an image classification model.
Optionally, the building module 600 is further configured to divide the data set into two sets according to a preset proportion, and the two sets are respectively used as a training set and a verification set; inputting the training set into a preset machine model so that the preset machine model learns the data set to obtain an intermediate model; inputting the verification set into the intermediate model to obtain a classification result of the verification set output by the intermediate model; and adjusting the model parameters of the intermediate model according to the classification result to obtain an image classification model.
Optionally, the building module 600 is further configured to obtain longitude and latitude information and a type of a base land of each classified remote sensing image in the data set; and generating a base land database according to the longitude and latitude information and the base land type of each classified remote sensing image.
In addition, an embodiment of the present invention further provides a land occupation early warning device, where the land occupation early warning device includes: the land occupation early warning method comprises a memory, a processor and a land occupation early warning program which is stored on the memory and can run on the processor, wherein the land occupation early warning program realizes the steps of the land occupation early warning method when being executed by the processor.
In addition, the embodiment of the present invention further provides a storage medium, where the storage medium stores a land occupation early warning program, and the land occupation early warning program, when executed by a processor, implements the steps of the land occupation early warning method as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A land occupation early warning method is characterized by comprising the following steps:
obtaining a remote sensing image in a target longitude and latitude range;
inputting the remote sensing image into an image classification model to obtain a current land type corresponding to the remote sensing image;
searching a base land database by using the longitude and latitude information of the remote sensing image as an index, and obtaining a corresponding base land type of the longitude and latitude information in the base land database; the base land database comprises a mapping relation between longitude and latitude information and a base land type;
comparing the current land type with a basic land type;
and if the current land type is inconsistent with the basic land type, generating land occupation early warning information.
2. The land occupation early warning method according to claim 1, wherein the step of obtaining a remote sensing image within a monitoring range specifically comprises:
dividing a target monitoring range into a plurality of target longitude and latitude ranges;
and sequentially acquiring remote sensing images in the latitude and longitude ranges of the targets, and sequentially executing the step of inputting the remote sensing images into an image classification model to obtain the current land types corresponding to the remote sensing images.
3. The land occupation early warning method according to claim 1, wherein before the step of obtaining the remote sensing image within the latitude and longitude of the target, the land occupation early warning method further comprises:
acquiring a data set consisting of classified remote sensing images containing multiple land types;
and constructing an image classification model and a foundation land database by using the data set.
4. The land occupation early warning method according to claim 3, wherein the acquiring a data set comprising classified remote sensing images of a plurality of land types specifically comprises:
and (4) crawling classified remote sensing images containing multiple land types from the target webpage to form a data set.
5. The land occupation early warning method according to claim 3, wherein the step of constructing an image classification model by using the data set specifically comprises:
and inputting the data set into a preset machine model so that the preset machine model learns the data set to obtain an image classification model.
6. The land occupation early warning method according to claim 5, wherein the step of inputting the data set into a preset machine model so that the preset machine model learns the data set to obtain an image classification model specifically comprises:
dividing the data set into two sets according to a preset proportion, and respectively taking the two sets as a training set and a verification set;
inputting the training set into a preset machine model so that the preset machine model learns the data set to obtain an intermediate model;
inputting the verification set into the intermediate model to obtain a classification result of the verification set output by the intermediate model;
and adjusting the model parameters of the intermediate model according to the classification result to obtain an image classification model.
7. The land occupation early warning method according to claim 3, wherein the step of constructing the database of the base land occupation by using the data set specifically comprises:
acquiring longitude and latitude information and a basic land type of each classified remote sensing image in the data set;
and generating a base land database according to the longitude and latitude information and the base land type of each classified remote sensing image.
8. A land occupation early warning device, characterized in that, the land occupation early warning device includes:
the acquisition module is used for acquiring a remote sensing image in a target longitude and latitude range;
the classification module is used for inputting the remote sensing image into an image classification model to obtain the current land type corresponding to the remote sensing image;
the searching module is used for searching a base land database by using the longitude and latitude information of the remote sensing image as an index to obtain a corresponding base land type of the longitude and latitude information in the base land database; the base land database comprises a mapping relation between longitude and latitude information and a base land type;
the comparison module is used for comparing the current land type with the basic land type;
and the early warning module is used for generating land occupation early warning information if the current land type is inconsistent with the basic land type.
9. A land occupation early warning device, characterized in that the land occupation early warning device comprises: a memory, a processor and a land occupation warning program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the land occupation warning method according to any one of claims 1 to 7.
10. A storage medium, characterized in that the storage medium has stored thereon a land occupation warning program, which when executed by a processor implements the steps of the land occupation warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010068128.7A CN111259840A (en) | 2020-01-21 | 2020-01-21 | Land occupation early warning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010068128.7A CN111259840A (en) | 2020-01-21 | 2020-01-21 | Land occupation early warning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111259840A true CN111259840A (en) | 2020-06-09 |
Family
ID=70954342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010068128.7A Pending CN111259840A (en) | 2020-01-21 | 2020-01-21 | Land occupation early warning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259840A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113141485A (en) * | 2020-10-22 | 2021-07-20 | 西安天和防务技术股份有限公司 | Alarm system |
| CN113780057A (en) * | 2021-07-23 | 2021-12-10 | 贵州图智信息技术有限公司 | Idle land identification method and device |
| CN114155433A (en) * | 2021-11-30 | 2022-03-08 | 北京新兴华安智慧科技有限公司 | Illegal land detection method and device, electronic equipment and storage medium |
| CN114170566A (en) * | 2021-11-30 | 2022-03-11 | 北京新兴华安智慧科技有限公司 | Large-area illegal target identification processing method, device and system |
| CN114782815A (en) * | 2022-04-26 | 2022-07-22 | 平安普惠企业管理有限公司 | Method, device and equipment for automatically supervising greenbelt and storage medium |
| CN116246175A (en) * | 2023-05-05 | 2023-06-09 | 西昌学院 | Land utilization information generation method, electronic device, and computer-readable medium |
| CN116562510A (en) * | 2023-07-11 | 2023-08-08 | 国家林业和草原局产业发展规划院 | Method, system, terminal and storage medium for measuring field investigation area |
| CN117688053A (en) * | 2024-02-02 | 2024-03-12 | 中国科学院空天信息创新研究院 | Remote sensing data retrieval method and device combined with land type and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110243354A (en) * | 2019-07-04 | 2019-09-17 | 桂林理工大学 | A kind of city illegal building object dynamic monitoring method and system |
| CN110263764A (en) * | 2019-07-09 | 2019-09-20 | 中国地质大学（北京） | Land use monitoring method and apparatus based on remote sensing image data |
| CN110348506A (en) * | 2019-07-03 | 2019-10-18 | 广州大学 | Land use classes method, storage medium and calculating equipment based on remote sensing images |
-
2020
- 2020-01-21 CN CN202010068128.7A patent/CN111259840A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348506A (en) * | 2019-07-03 | 2019-10-18 | 广州大学 | Land use classes method, storage medium and calculating equipment based on remote sensing images |
| CN110243354A (en) * | 2019-07-04 | 2019-09-17 | 桂林理工大学 | A kind of city illegal building object dynamic monitoring method and system |
| CN110263764A (en) * | 2019-07-09 | 2019-09-20 | 中国地质大学（北京） | Land use monitoring method and apparatus based on remote sensing image data |
Non-Patent Citations (4)
| Title |
|---|
| 周可法等: "基于RS和GIS技术下城镇空间变化分析及应用研究", vol. 25, no. 1, pages 61 - 64 * |
| 王明常等: "基于FLUS的长春市土地利用动态变化与预测分析", vol. 49, no. 6, pages 1795 - 1804 * |
| 赵小敏等: "《土地利用变化及其生态环境效应研究》", 地质出版社, pages: 17 - 18 * |
| 马兴委等: "大比例尺卫片在徐州市城区土地利用动态监测中的应用", vol. 35, no. 34, pages 11179 - 11180 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113141485A (en) * | 2020-10-22 | 2021-07-20 | 西安天和防务技术股份有限公司 | Alarm system |
| CN113141485B (en) * | 2020-10-22 | 2022-12-20 | 西安天和防务技术股份有限公司 | Alarm system |
| CN113780057A (en) * | 2021-07-23 | 2021-12-10 | 贵州图智信息技术有限公司 | Idle land identification method and device |
| CN114155433A (en) * | 2021-11-30 | 2022-03-08 | 北京新兴华安智慧科技有限公司 | Illegal land detection method and device, electronic equipment and storage medium |
| CN114170566A (en) * | 2021-11-30 | 2022-03-11 | 北京新兴华安智慧科技有限公司 | Large-area illegal target identification processing method, device and system |
| CN114155433B (en) * | 2021-11-30 | 2022-07-19 | 北京新兴华安智慧科技有限公司 | Illegal land detection method and device, electronic equipment and storage medium |
| CN114782815A (en) * | 2022-04-26 | 2022-07-22 | 平安普惠企业管理有限公司 | Method, device and equipment for automatically supervising greenbelt and storage medium |
| CN116246175A (en) * | 2023-05-05 | 2023-06-09 | 西昌学院 | Land utilization information generation method, electronic device, and computer-readable medium |
| CN116246175B (en) * | 2023-05-05 | 2023-07-14 | 西昌学院 | Land utilization information generation method, electronic device, and computer-readable medium |
| CN116562510A (en) * | 2023-07-11 | 2023-08-08 | 国家林业和草原局产业发展规划院 | Method, system, terminal and storage medium for measuring field investigation area |
| CN117688053A (en) * | 2024-02-02 | 2024-03-12 | 中国科学院空天信息创新研究院 | Remote sensing data retrieval method and device combined with land type and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259840A (en) | Land occupation early warning method, device, equipment and storage medium | |
| JP4032125B1 (en) | Mobile object position estimation system and mobile object position estimation method | |
| EP3627806A1 (en) | Method for generating user portrait, and terminal | |
| JP5716866B2 (en) | Device management apparatus and device search method | |
| EP2902913A1 (en) | Device management apparatus and device search method | |
| CN106874936B (en) | Image propagation monitoring method and device | |
| CN105009114B (en) | Search capability is predictably presented | |
| US20230267147A1 (en) | Systems and methods for searching for events within video content | |
| Zhao et al. | A network distance and graph-partitioning-based clustering method for improving the accuracy of urban hotspot detection | |
| CN113822460A (en) | Traffic flow prediction method and device, electronic equipment and storage medium | |
| Alamri et al. | Spatiotemporal indexing for moving objects in an indoor cellular space | |
| CN115017400A (en) | Application APP recommendation method and electronic equipment | |
| CN112748453B (en) | Road side positioning method, device, equipment and storage medium | |
| Cardinale et al. | Semantic framework of event detection in emergency situations for smart buildings | |
| CN110619090B (en) | Regional attraction assessment method and device | |
| Chang et al. | Safety risk assessment of electric power operation site based on variable precision rough set | |
| CN111314177A (en) | Work and rest time period identification method based on wireless signals and related device | |
| CN112257908B (en) | Mountain area agricultural multi-source heterogeneous data integration method and device | |
| KR102237505B1 (en) | Platform for processing spatial information of steep slope-land in real time based on Geo-cloud and data processing method therefor | |
| US20210256061A1 (en) | Systems and methods for identifying events within video content using intelligent search query | |
| CN113835139A (en) | Typhoon dynamic monitoring system | |
| CN113345095A (en) | Revolutionary cultural relic damage monitoring and early warning method and system based on digital twinning | |
| CN110070371B (en) | Data prediction model establishing method and equipment, storage medium and server thereof | |
| Burghardt et al. | Volunteered geographic information: Interpretation, visualisation and social computing (VGIscience) | |
| CN114415492B (en) | Method, terminal and storage medium for acquiring time in offline state |
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 |