CN108052876A - Regional development appraisal procedure and device based on image identification - Google Patents
Regional development appraisal procedure and device based on image identification Download PDFInfo
- Publication number
- CN108052876A CN108052876A CN201711216014.7A CN201711216014A CN108052876A CN 108052876 A CN108052876 A CN 108052876A CN 201711216014 A CN201711216014 A CN 201711216014A CN 108052876 A CN108052876 A CN 108052876A
- Authority
- CN
- China
- Prior art keywords
- main body
- type
- satellite
- area
- region
- 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.)
- Granted
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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the regional development condition evaluation methods identified based on image, comprise the following steps：Obtain the satellite photo in region to be identified；The satellite photo is divided by corresponding multiple block pictures according to color cluster；Feature extraction is carried out to each block picture and draws corresponding feature vector, and the feature vector according to corresponding to each block picture draws the main body corresponding to each block picture with established main body identification model；The block picture of adjacent same human subject is merged and then the satellite photo is divided into multiple type areas；Longitude and latitude degrees of data according to the map draws the geographical location of each type area of the satellite photo, and the size of each area type of areal calculation according to each area type.The invention also discloses a kind of electronic equipment, storage medium and devices.The present invention is identified by the satellite map to region draws the area change of corresponding main body and main body to realize the assessment to regional development situation.
Description
Technical field
The present invention relates to city evaluation areas more particularly to a kind of co-melting appraisal procedures in city and dress based on image identification
It puts.
Background technology
At present, modern city is UN's Commission on Human Settlements, culture and education center, complex business center, knowledge and technology innovation center
With the center of gravity of environmental improvement.As urban population accounts for the continuous improvement of total population proportion, accelerate city dilatation, drive neighboring area
It builds, the co-melting development in Radiation Satellite city has become the very urgent Major Strategic in China.And how to urban development, co-melting situation
Objective evaluation is carried out, ripe planning calibration and optimization is promoted using assessment result, promotes the coordinated development in city, realize city hair
It is evidence-based to open up strategic decision, it has also become one of people's growing interest and worth the problem of inquiring into.
However, traditional cities Development Assessment method, typically using urban population index or economic indicator etc. because usually into
Row assessment, but be a complicated human engineering ecosystem, it includes natural, humane, ecology, warps for a city
The various dynamic factors such as Ji, society.Therefore, the overall function and comprehensive function in city can not be embodied using Traditional measurements method
State of development there are data unicity, evaluation one-sidedness, and can not assess the co-melting feelings of urban construction and periphery urban construction
Condition；If consider many factors, due to sufficiently complex to the requirements such as data sampling and processing and calculating process, cause data acquisition
It is incomplete；In addition, when data acquisition is different with the standard for calculating when institute's foundation, obtained every data target there is also
Larger difference, it is impossible to effectively and rapidly be assessed the co-melting state of development in city.In addition, it is not only for a city
The variation in city, such as the variation for some such as harbours, forest, ocean region, it is also desirable to be assessed, but equally existed
The problem of identical so that the requirements such as data sampling and processing and calculating process are sufficiently complex, are unable to have a region
Effect, quickly assessment.
The content of the invention
For overcome the deficiencies in the prior art, one of the objects of the present invention is to provide the regional developments identified based on image
Condition evaluation method can solve in the prior art can not carry out a certain regional development situation effective, rapid evaluation
Problem.
The second object of the present invention is to provide a kind of electronic equipment, and can solve in the prior art can not be to a certain
The problem of progress of regional development situation is effective, rapid evaluation.
The third object of the present invention is to provide a kind of computer readable storage medium, can solve in the prior art not
Can to a certain regional development situation carry out effectively, rapid evaluation the problem of.
The fourth object of the present invention is to provide the regional development condition evaluation device based on image identification, can solve
In the prior art can not to a certain regional development situation carry out effectively, rapid evaluation the problem of.
An object of the present invention adopts the following technical scheme that realization：
Based on the regional development condition evaluation method of image identification, comprise the following steps：
Model foundation step：Establish main body identification model；The main body identification model stores each type of main body
The set of the feature vector of satellite photo；
Obtaining step：Obtain the satellite photo in region to be identified；
Segmentation step：The satellite photo is divided by corresponding multiple block pictures according to color cluster；
Identification step：Feature extraction is carried out to each block picture and draws corresponding feature vector, and according to each block
Feature vector corresponding to picture draws the main body corresponding to each block picture with main body identification model；
Merge step：The block picture of adjacent same human subject is merged and then is divided into the satellite photo more
A type area；
Calculation procedure：Longitude and latitude degrees of data according to the map draws the geographical position of each type area of the satellite photo
It puts, and the size of each area type of areal calculation according to each area type.
Further, processing step is further included：Obtain multiple satellites in the region to be identified in measurement period respectively first
Picture, and perform segmentation step, identification step, merging step and calculation procedure successively to every satellite photo and draw every
The geographical location of each type area of satellite photo and the size of each area type；Then according to the priority of time
The face in the different type region in the order counting statistics cycle in the same geographic location of every satellite photo in region to be identified
Product size variation data.
Further, after described multiple satellite photoes for obtaining the region to be identified in measurement period, also according to the date
Multiple satellite photoes that sequencing treats identification region are ranked up.
Further, evaluation procedure is further included：According in measurement period every satellite photo in region to be identified it is identical
The area change data of type area on geographical location and default Rating Model treat identification region and score.
Further, the model foundation step further includes：Multiple satellite photoes of each type of main body are obtained first；
Then feature extraction is carried out to every satellite photo of each type of main body and draws corresponding feature vector；Finally to every species
The satellite photo that training draws each type of main body is identified in the corresponding feature vector of multiple satellite photoes of the main body of type
The set of corresponding feature vector, i.e. main body identification model.
Further, pre-treatment step is further included after obtaining step：Preprocessing process is carried out to the satellite photo；Its
Middle preprocessing process includes the combination of one or more of method：Image binaryzation, removal noise spot, barycenter alignment schemes with
And linear interpolation amplification method.
The second object of the present invention adopts the following technical scheme that realization：
A kind of electronic equipment can be run on a memory and on a processor including memory, processor and storage
Computer program realizes that the regional development situation as previously described based on image identification is commented when the processor performs described program
The step of estimating method.
The third object of the present invention adopts the following technical scheme that realization：
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of regional development condition evaluation method as previously described based on image identification is realized during row.
The fourth object of the present invention adopts the following technical scheme that realization：
Based on image identification regional development condition evaluation device, including：
Model building module, for establishing main body identification model；The main body identification model stores each type of master
The set of the feature vector of the satellite photo of body；
Acquisition module, for obtaining the satellite photo in region to be identified；Split module, described in being incited somebody to action according to color cluster
Satellite photo is divided into corresponding multiple block pictures；
Characteristic extracting module draws corresponding feature vector for carrying out feature extraction to each block picture；
Identification module draws each area for the feature vector according to corresponding to each block picture and main body identification model
Main body corresponding to block diagram piece；
Merging module, for being merged the block picture of adjacent same human subject and then dividing the satellite photo
For multiple type areas；
Computing module draws the geography of each type area of the satellite photo for longitude and latitude degrees of data according to the map
Position, and the size of each area type of areal calculation according to each area type.
Further, processing module is further included, for obtaining multiple satellites in the region to be identified in measurement period respectively
Picture, and perform segmentation step, identification step, merging step and calculation procedure successively to every satellite photo and draw every
The geographical location of each type area of satellite photo and the size of each area type；Then according to the priority of time
The face in the different type region in the order counting statistics cycle in the same geographic location of every satellite photo in region to be identified
Product size variation data.
Compared with prior art, the beneficial effects of the present invention are：The present invention is by pre-establishing various types of master
The identification model of body, then some region of satellite photo is handled and identify draw included in satellite photo it is main
Body, and then draw the size of corresponding main body, it is real so as to the size data of the main body according to included in satellite photo
Now to the statistics of the state of development data in the region, effectively and rapidly assessed so as to fulfill the state of development to the region.
Description of the drawings
Fig. 1 is one of flow chart of regional development condition evaluation method provided by the invention based on image identification；
Fig. 2 is the two of the flow chart of the regional development condition evaluation method provided by the invention based on image identification；
Fig. 3 is the module map of the regional development condition evaluation device provided by the invention based on image identification.
Specific embodiment
In the following, with reference to attached drawing and specific embodiment, the present invention is described further, it is necessary to which explanation is, not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
Embodiment
The technology identified by image is analyzed a certain region by the present invention, such as city, harbour, forest, ocean etc.
Satellite photo, the development and change in the region to be identified.For example periodically some region of satellite photo is identified, so
It compares the periodic front and rear variation of various factors in the region afterwards, corresponding region is assessed with the variation according to various factors
State of development.
Such as by analyzing the satellite photo in two 10 kilometer ranges of city intersection, and identify and draw in the region
The site coverage variation in business, school, standardized house area etc., and then the co-melting development shape in city can be assessed according to these data
Condition.For example, the area in standardized house area is increasing, then illustrate that the city is more suitable for the inhabitation of people；The area of commercial center
It is increasing, then illustrate that economic development etc. is more focused in the region.
For example be identified by the satellite photo to flood and field intersection, identification draws ocean area and land
Cyclically-varying, ratio of the size of area etc. obtain the delta data of extra large land area, and then assess ring caused by global warming
Border influences situation.
For example identified by the satellite photo to city, draw the variation of Regional Urban Greening, forest cover, farmland area etc.,
And then assess improvement of desertifying, the situation for the environmental construction that vegetation terminates.Such as green coverage, farmland area, the face of forest cover
Product gradually increase, then illustrate that environmental improvement is increasingly taken seriously, environment can become better and better.
For example be identified by the satellite photo to coastal cities, show whether coastal cities have harbour, harbour, goods
Object stacks the data such as situation of change, and then judges the Foreign trade economy state of development in coastal cities.
As shown in Figure 1, the present invention provides a kind of embodiment, based on the regional development condition evaluation method of image identification,
Specifically include following steps：
S1, multiple satellite photoes for obtaining region to be identified in measurement period, satellite photo is different in measurement period
The satellite photo on date.Here region to be identified can be intersection, a certain city, coastal cities, the Hai Lu in two cities
Intersection, harbour etc..Such as in the measurement period of 10 years, once adopted every the satellite photo that 1 year treats identification region
Collection, so can be obtained by 10 satellite photoes.For a region its in development, the correspondingly infrastructure of its map
Deng can all be varied from, for example, park becomes larger, residential quarters are increased etc. can be in corresponding satellite map, each basis is set
Shared ratio can all increased in satellite photo where applying.
S2, multiple satellite photoes for treating identification region according to the sequencing on date are ranked up.Meanwhile it is getting
During satellite photo, preprocessing process is carried out to satellite photo first, is by that can be improved after being pre-processed to satellite photo
The process performance united to picture.Preprocessing process may include following one or more method combinations：Image binaryzation, removal interference
Point, barycenter alignment schemes and linear interpolation amplification method.For example picture is uniformly converted to identical size, form etc..It is right
Multiple pretreated satellite photoes are ranked up according to the sequencing on date, thus can be by comparing measurement period
Interior, main body is with the front and rear variation of time in multiple satellite photoes, so as to carry out the hair to the region with the front and rear variation of the main body
Exhibition situation is evaluated.
S3, the satellite photo chosen successively in multiple satellite photoes in region to be identified are identified processing and draw pair
Answer size and the geographical location of type area included in satellite photo.
S4, the identical geography that every satellite photo in region to be identified in measurement period is compared according to the sequencing of time
The size delta data of type area on position, and cog region is treated according to the variation of the size of each type area
Domain carries out evaluation and draws evaluation result.
In addition, the size variation of the type area according to corresponding to same geographic location is treated identification region and is commented
It during valency, being carried out by the scoring pre-established, for example is denoted as when area increase 1-5 points, area is denoted as when reducing-
1--5 points；0 is denoted as when area does not change to grade.It can also be according to the corresponding fraction of specific range set of area change.Certainly
Scoring is specifically set according to specific demand.
For example, according to longitude and latitude degrees of data, by analyzing in satellite map, in two 10 kilometer ranges of city intersection, business
Geographical location corresponding to industry body, school, standardized house area etc. type area.
Compare City Building in measurement period in front and rear map and infrastructure construction (such as business complex zone,
School, park, residential quarters etc.) front and rear area size variation, and then can be 10 public to have a common boundary for the city according to scoring
In region in scope score, to judge urban residence region, center commercial circle, the construction of culture and education and migration situation.
Such as：In assessment Guangzhou, 10 kilometer range of Foshan intersection, standardized house, school, business, traffic, road etc.
The variation of main body, for example the area of each main body in the region is ranked up according to the sequencing of time, draw each master
The area of the area change of body and each type of subject occupies the data such as the area percentage in the region to assess in certain week
The changing condition of the various buildings of wide Buddhist intersection in phase, such as the area of standardized house change with time, and area is gradual
Increasing, then explanation is more and more in the resident family of wide Buddhist intersection；Road is more and more, illustrates Guangzhou and the city of Foshan intersection
The co-melting development in city is good.
Work of renovating shantytowns situation as counted certain city, then extract according to the longitude and latitude degrees of data in the city in the measurement period in the city
All satellite maps, judge all slum-dweller regions in map and successively in calculating cycle in all maps shanty town it is front and rear each
The area change data of the building of type can obtain the work of renovating shantytowns in the city according to area statistics data and time cycle
Progress situation.
Border house, the extension of business type construction area such as certain city is rapid, reaches the border for closing on city and still has
The expansion sign in building site is built, is closely connected by track, traffic between two cities, the cut zone of no significant difference, then
It may determine that city development has been radiated the adjacent cities and counties in periphery, two cities are apparent with city integration sign.
In addition, it as shown in Fig. 2, is handled to draw the class area that the satellite photo is included for a satellite photo
The size in domain and the concrete methods of realizing in geographical location include the following steps：
S31, satellite photo is divided by corresponding multiple block pictures according to color cluster.Due to the characteristic of map, pin
To different main bodys, the color shown in map is different, such as aobvious for river, land, building, ocean, road etc.
The color shown is different, thus satellite photo can be divided into multiple and different blocks according to color cluster technology.
S32, the progress feature extraction of each block picture is drawn into corresponding feature vector.
S33, the feature vector according to corresponding to each block picture and main body identification model draw each block picture institute
Corresponding main body.
Main body identification model stores the set of the feature vector of the satellite photo of each type of main body, then to area
When main body in domain identifies, the satellite photo in region is divided into multiple blocks first, then each block picture is carried out special
Sign extraction draws feature vector, and by any one type in the feature vector of each block picture and main body identification model
Feature vector corresponding to the satellite photo of main body is matched, and then can draw the main body corresponding to each block picture,
It is main body included in every satellite photo.
For a city, including various types of standardized house cells, business, school, farmland, port and pier,
The building foundations facility such as municipal park, sports center, then will be corresponded to for each type of infrastructure in the city
Satellite map shows corresponding region.Main body included in satellite photo is drawn in order to identify, the present invention by collecting in advance
The satellite photo of various types of main bodys, and the extraction of feature vector, identification and training are carried out to it, establish various types of masters
The set of the feature vector of the satellite photo of body that is to say main body identification model, it is as follows to establish process：
A, by obtaining the satellite photo of same type of subject and carrying out preprocessing process to every satellite photo.Such as
For a urban area or city juncture area, which can be various types of building body；For
One land and sea junction region, the type of subject can be ocean, land etc.；During for urban area, can also be forest cover,
Farmland, desert etc.；For coastal cities region, which can be harbour construction body, port etc..
B, corresponding feature vector is drawn to carrying out feature extraction by pretreated every satellite photo.It is special in extraction
During sign vector, such as the assemblage characteristic according to the face shaping of type of subject, color, size and spatial distribution, by main body
Satellite photo be divided into 25 grid spaces of 5*5, and calculate the points in each grid spaces and article always the ratio between points,
To obtain 25 dimensional feature vectors.
In addition, there are respective appearance and color combination, face for the main body of various types of buildings or infrastructure
Product size and spatial arrangement feature, for example, school：The one piece of road network cut zone built including sports ground and roof plan；Body
Educate center：There are surface area building and sports ground；Business：The area of continuous curve surface is included after road network cutting；Farmland：Green face
The block of product division and pool, pool part have apparent retroreflective feature；Park：The green area of large area and blue block
Lake；Standardized house：In the similar plane roof color lump of the shape of rule shape arrangement, size；Shanty town：In a jumble, it is close
Collect the similar plane roof color block of the area of shape arrangement.
It therefore, can be according to the appearance, color, area space of main body when the satellite photo to main body carries out feature extraction
Distribution etc. extracts.
C, training is identified to multiple satellite photoes of the same type of main body, extracts the same type of main body
Multiple standards feature vector, establish the standard feature vector storehouse of the type main body.In recognition training, it is necessary to indicate main body
Type right value.
The set of multiple feature vectors of various types of main body can be established by the above method, that is to say that main body is known
Other model.
In identification, multiple block pictures are drawn by the way that the satellite photo in region to be identified is carried out division, then to every
A block picture carries out feature extraction and draws corresponding feature vector, most the feature vector of each block picture and identification mould at last
Multiple feature vectors of the satellite photo of any type of main body in type compare one by one.When similarity reaches more than 80%,
The main body corresponding to feature vector in the identification model is for the main body corresponding to the block, draw in the satellite photo
Comprising all main bodys.
S34, the block picture of adjacent same type main body is merged, and then the satellite photo is divided into multiple classes
Type region.Include the main body of same type in each type area.One at classified types region, also according to type of subject
Type area after merging is defined.For example the main body that it is included for adjacent block picture A, block picture B is equal
For residential quarters, then block picture A and block picture B can be merged and draw a type area, the type region can be named
For residential quarters.Certainly may be more due to the identical type area in satellite photo, it can be numbered in name,
Such as residential quarters 1, residential quarters 2 etc..For example the area type after merging can be commercial center region, school zone, ask
Inscribe central area, shanty town, ocean, land, port, port structure etc..
S35, the size that each type area is drawn according to the areal calculation of each type area；
S36, drawn according to the longitude and latitude degrees of data of the satellite photo satellite photo each type area geographical location.
In addition, there is no sequencings in actual implementation procedure for S35 and S36.
For example, to illustrate the above method to the co-melting Development Assessment of city juncture area in the present embodiment：
A：Multiple satellite maps of the city intersection in measurement period are obtained, and every satellite photo is located in advance
Reason.
Such as the region in two 10 kilometer ranges of city intersection：Measurement period is determined first, and obtains the system
Count the satellite photo on multiple dates of the city juncture area in the cycle.For example measurement period is 5 years, then obtains every half a year
The satellite photo of city juncture area collects 10 satellite photoes：A1, A2, A3, A4 ..., A10, then according to the elder generation on date
The satellite photo got is ranked up by order afterwards, and every satellite photo is pre-processed.
B：Every satellite map is divided by multiple block pictures according to color cluster.For example utilize edge detecting technology root
According to the colouring discrimination of the main bodys such as land, ocean, the border of the flood and field in satellite map is found out, respectively obtains ocean portion
Divide the satellite map with land part.And the network of highways in map can be judged the satellite map of land part by color cluster
Network carries out region segmentation to satellite map using the color belt of highway network, obtains multiple blocks.Highway network is in color cluster
After processing, cash as continuous banding color region.Due to for satellite map, color of the different regions corresponding to it
It is different, therefore region segmentation division can be carried out to satellite map by color cluster and draw multiple block pictures.
C：It is drawn according to each block picture of every satellite map with main body identification model every in every satellite map
Main body corresponding to a block picture.
D：The block picture of the main body of adjacent same type is merged into corresponding type area.Such as by adjacent business
Centerbody is merged into commercial center region, adjacent residential quarters is merged into residential quarters region, by adjacent School Buildings
Object etc. is merged into school zone, adjacent style education structure is merged into style central area, closing adjacent shanty town
And into slum-dweller region.
E：The size in corresponding types region is drawn according to the areal calculation of each type area.
F：The geography of each type area in corresponding satellite map is judged according to the longitude and latitude degrees of data of every satellite map
Position.
G：Every satellite map of city juncture area in measurement period is compared in the same manner according to the sequencing of time
Manage the size delta data of the type area on position.
H：According to the type area in measurement period in the same geographic location of every satellite map of city juncture area
Area change and default Rating Model come for the appraisal result of city juncture area.So people can just be commented by this
Point result draws the state of development of city juncture area, for example appraisal result is higher, illustrates that the development of city juncture area is better,
City integration is better.
The present invention, which not only can be only used for that the main bodys such as the building facilities at the juncture area of city are identified, draws city
Develop co-melting situation to be assessed, can also be identified for main bodys such as ocean, land in global satellite picture come to the whole world
Environment influence is assessed, by the knowledge to main bodys such as greenery patches, forest cover, the farmlands in a certain region caused by climate warming
Not come realize city desertify administer, vegetation plantation environmental construction situation assessment, by bases such as the harbours to coastal cities
The identification of main body, the main body of cargo of stacking that plinth is set etc. judges the Foreign trade economy development in city.
The present invention also provides a kind of electronic equipment, including memory, processor and storage on a memory and can
The computer program run in processing, the processor realize following steps when performing described program：
Model foundation step：Establish main body identification model；The main body identification model stores each type of main body
The set of the feature vector of satellite photo；
Obtaining step：Obtain the satellite photo in region to be identified；
Segmentation step：The satellite photo is divided by corresponding multiple block pictures according to color cluster；
Identification step：Feature extraction is carried out to each block picture and draws corresponding feature vector, and according to each block
Feature vector corresponding to picture draws the main body corresponding to each block picture with main body identification model；
Merge step：The block picture of adjacent same human subject is merged and then is divided into the satellite photo more
A type area；
Calculation procedure：Longitude and latitude degrees of data according to the map draws the geographical position of each type area of the satellite photo
It puts, and the size of each area type of areal calculation according to each area type.
Further, processing step is further included：Obtain multiple satellites in the region to be identified in measurement period respectively first
Picture, and perform segmentation step, identification step, merging step and calculation procedure successively to every satellite photo and draw every
The geographical location of each type area of satellite photo and the size of each area type；Then according to the priority of time
The face in the different type region in the order counting statistics cycle in the same geographic location of every satellite photo in region to be identified
Product size variation data.
Further, after described multiple satellite photoes for obtaining the region to be identified in measurement period, also according to the date
Multiple satellite photoes that sequencing treats identification region are ranked up.
Further, evaluation procedure is further included：According in measurement period every satellite photo in region to be identified it is identical
The area change data of type area on geographical location and default Rating Model treat identification region and score.
Further, the model foundation step further includes：Multiple satellite photoes of each type of main body are obtained first；
Then feature extraction is carried out to every satellite photo of each type of main body and draws corresponding feature vector；Finally to every species
The satellite photo that training draws each type of main body is identified in the corresponding feature vector of multiple satellite photoes of the main body of type
The set of corresponding feature vector, i.e. main body identification model.
Further, pre-treatment step is further included after obtaining step：Preprocessing process is carried out to the satellite photo；Its
Middle preprocessing process includes the combination of one or more of method：Image binaryzation, removal noise spot, barycenter alignment schemes with
And linear interpolation amplification method.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, computer program
Such as following steps are realized when being executed by processor：
Model foundation step：Establish main body identification model；The main body identification model stores each type of main body
The set of the feature vector of satellite photo；
Obtaining step：Obtain the satellite photo in region to be identified；
Segmentation step：The satellite photo is divided by corresponding multiple block pictures according to color cluster；
Identification step：Feature extraction is carried out to each block picture and draws corresponding feature vector, and according to each block
Feature vector corresponding to picture draws the main body corresponding to each block picture with main body identification model；
Merge step：The block picture of adjacent same human subject is merged and then is divided into the satellite photo more
A type area；
Calculation procedure：Longitude and latitude degrees of data according to the map draws the geographical position of each type area of the satellite photo
It puts, and the size of each area type of areal calculation according to each area type.
Further, processing step is further included：Obtain multiple satellites in the region to be identified in measurement period respectively first
Picture, and perform segmentation step, identification step, merging step and calculation procedure successively to every satellite photo and draw every
The geographical location of each type area of satellite photo and the size of each area type；Then according to the priority of time
The face in the different type region in the order counting statistics cycle in the same geographic location of every satellite photo in region to be identified
Product size variation data.
Further, after described multiple satellite photoes for obtaining the region to be identified in measurement period, also according to the date
Multiple satellite photoes that sequencing treats identification region are ranked up.
Further, evaluation procedure is further included：According in measurement period every satellite photo in region to be identified it is identical
The area change data of type area on geographical location and default Rating Model treat identification region and score.
Further, the model foundation step further includes：Multiple satellite photoes of each type of main body are obtained first；
Then feature extraction is carried out to every satellite photo of each type of main body and draws corresponding feature vector；Finally to every species
The satellite photo that training draws each type of main body is identified in the corresponding feature vector of multiple satellite photoes of the main body of type
The set of corresponding feature vector, i.e. main body identification model.
Further, pre-treatment step is further included after obtaining step：Preprocessing process is carried out to the satellite photo；Its
Middle preprocessing process includes the combination of one or more of method：Image binaryzation, removal noise spot, barycenter alignment schemes with
And linear interpolation amplification method.
As shown in figure 3, the regional development condition evaluation device based on image identification, including：
Model building module, for establishing main body identification model；The main body identification model stores each type of master
The set of the feature vector of the satellite photo of body；
Acquisition module, for obtaining the satellite photo in region to be identified；Split module, described in being incited somebody to action according to color cluster
Satellite photo is divided into corresponding multiple block pictures；
Characteristic extracting module draws corresponding feature vector for carrying out feature extraction to each block picture；
Identification module draws each area for the feature vector according to corresponding to each block picture and main body identification model
Main body corresponding to block diagram piece；
Merging module, for being merged the block picture of adjacent same human subject and then dividing the satellite photo
For multiple type areas；
Computing module draws the geography of each type area of the satellite photo for longitude and latitude degrees of data according to the map
Position, and the size of each area type of areal calculation according to each area type.
Further, processing module is further included, for obtaining multiple satellites in the region to be identified in measurement period respectively
Picture, and perform segmentation step, identification step, merging step and calculation procedure successively to every satellite photo and draw every
The geographical location of each type area of satellite photo and the size of each area type；Then according to the priority of time
The face in the different type region in the order counting statistics cycle in the same geographic location of every satellite photo in region to be identified
Product size variation data.
Further, evaluation module is further included, for according to every satellite photo in region to be identified in measurement period
The area change data of type area in same geographic location and default Rating Model treat identification region and score.
Further, preprocessing module is further included after acquisition module, it is pretreated for being carried out to the satellite photo
Journey, wherein preprocessing process include the combination of one or more of method：Image binaryzation, removal noise spot, barycenter alignment
Method and linear interpolation amplification method.
The above embodiment is only the preferred embodiment of the present invention, it is impossible to the scope of protection of the invention is limited with this,
The variation and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed scope.
Claims (10)
1. the regional development condition evaluation method based on image identification, it is characterised in that comprise the following steps：
Model foundation step：Establish main body identification model；The main body identification model stores the satellite of each type of main body
The set of the feature vector of picture；
Obtaining step：Obtain the satellite photo in region to be identified；
Segmentation step：The satellite photo is divided by corresponding multiple block pictures according to color cluster；
Identification step：Feature extraction is carried out to each block picture and draws corresponding feature vector, and according to each block picture
Corresponding feature vector draws the main body corresponding to each block picture with main body identification model；
Merge step：The block picture of adjacent same human subject is merged and then the satellite photo is divided into multiple classes
Type region；
Calculation procedure：Longitude and latitude degrees of data according to the map draws the geographical location of each type area of the satellite photo, and
According to the size of each area type of the areal calculation of each area type.
2. the method as described in claim 1, it is characterised in that：Further include processing step：It obtains respectively in measurement period first
Region to be identified multiple satellite photoes, and to every satellite photo successively perform segmentation step, identification step, merge walk
Rapid and calculation procedure draws the geographical location of each type area of every satellite photo and the area of each area type
Size；Then according to the identical geographical position of every satellite photo in region to be identified in the sequencing counting statistics cycle of time
The size delta data in the different type region put.
3. method as claimed in claim 2, it is characterised in that：Multiple of region to be identified in the acquisition measurement period are defended
After star chart piece, treat multiple satellite photoes of identification region also according to the sequencing on date and be ranked up.
4. method as claimed in claim 2, it is characterised in that：Further include evaluation procedure：According to area to be identified in measurement period
The area change data of type area in the same geographic location of every satellite photo in domain and default Rating Model pair
It scores in region to be identified.
5. the method as described in claim 1, it is characterised in that：The model foundation step further includes：It is obtained first per species
Multiple satellite photoes of the main body of type；Then feature extraction is carried out to every satellite photo of each type of main body and draws correspondence
Feature vector；Finally the corresponding feature vector of multiple satellite photoes of each type of main body is identified training to draw often
The set of feature vector corresponding to the satellite photo of the main body of type, i.e. main body identification model.
6. the method as described in claim 1, it is characterised in that：Pre-treatment step is further included after obtaining step：It is defended to described
Star chart piece carries out preprocessing process；Wherein preprocessing process includes the combination of one or more of method：Image binaryzation is gone
Except noise spot, barycenter alignment schemes and linear interpolation amplification method.
7. a kind of electronic equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, it is characterised in that：It is realized when the processor performs described program as claim 1-6 any one of them is based on
The step of regional development condition evaluation method of image identification.
8. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that：The computer program quilt
The regional development condition evaluation method based on image identification as any one of claim 1-6 is realized when processor performs
The step of.
9. the regional development condition evaluation device based on image identification, it is characterised in that including：
Model building module, for establishing main body identification model；The main body identification model stores each type of main body
The set of the feature vector of satellite photo；
Acquisition module, for obtaining the satellite photo in region to be identified；Split module, for according to color cluster by the satellite
Picture is divided into corresponding multiple block pictures；
Characteristic extracting module draws corresponding feature vector for carrying out feature extraction to each block picture；
Identification module draws each block diagram for the feature vector according to corresponding to each block picture and main body identification model
Main body corresponding to piece；
Merging module, for merging and then being divided into the satellite photo more by the block picture of adjacent same human subject
A type area；
Computing module draws the geographical position of each type area of the satellite photo for longitude and latitude degrees of data according to the map
It puts, and the size of each area type of areal calculation according to each area type.
10. device as claimed in claim 9, it is characterised in that：Processing module is further included, for obtaining respectively in measurement period
Region to be identified multiple satellite photoes, and to every satellite photo successively perform segmentation step, identification step, merge walk
Rapid and calculation procedure draws the geographical location of each type area of every satellite photo and the area of each area type
Size；Then according to the identical geographical position of every satellite photo in region to be identified in the sequencing counting statistics cycle of time
The size delta data in the different type region put.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711216014.7A CN108052876B (en) | 2017-11-28 | 2017-11-28 | Regional development assessment method and device based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711216014.7A CN108052876B (en) | 2017-11-28 | 2017-11-28 | Regional development assessment method and device based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108052876A true CN108052876A (en) | 2018-05-18 |
| CN108052876B CN108052876B (en) | 2022-02-11 |
Family
ID=62120840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711216014.7A Active CN108052876B (en) | 2017-11-28 | 2017-11-28 | Regional development assessment method and device based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108052876B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110290426A (en) * | 2019-06-24 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Method, apparatus, equipment and the storage medium of showing resource |
| CN110398902A (en) * | 2019-06-19 | 2019-11-01 | 上海机电工程研究所 | Photosignal phantom error analysis method |
| CN110827048A (en) * | 2018-08-08 | 2020-02-21 | 菜鸟智能物流控股有限公司 | Geographic region segmentation method and device based on road network and electronic equipment |
| CN111241881A (en) * | 2018-11-29 | 2020-06-05 | 中国移动通信集团四川有限公司 | Method, apparatus, device and medium for region identification |
| CN111861834A (en) * | 2020-07-14 | 2020-10-30 | 自然资源部第一海洋研究所 | Coastal zone land area space usage monitoring and surveying method based on water resource dependence degree |
| CN112200012A (en) * | 2020-09-15 | 2021-01-08 | 汉海信息技术(上海)有限公司 | Map data processing method and device and electronic equipment |
| CN112613426A (en) * | 2020-12-26 | 2021-04-06 | 北京国腾联信科技有限公司 | Resource area determination method, device, equipment and storage medium |
| CN114581786A (en) * | 2021-12-28 | 2022-06-03 | 深圳市城市产业发展集团有限公司 | Method and device for estimating building area according to ground image |
| CN115619712A (en) * | 2022-09-06 | 2023-01-17 | 江苏省水利科学研究院 | Unmanned aerial vehicle aerial photography technology-based water area monitoring and evaluating method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140254923A1 (en) * | 2011-10-19 | 2014-09-11 | The University Of Sydney | Image processing and object classification |
| CN104102928A (en) * | 2014-06-26 | 2014-10-15 | 华中科技大学 | Remote sensing image classification method based on texton |
| CN104881681A (en) * | 2015-05-22 | 2015-09-02 | 浙江大学 | Image sequence category labeling method based on mixed graph model |
| CN104036507B (en) * | 2014-06-13 | 2017-02-15 | 中国地质大学（武汉） | Light satellite based urban change area and evolution type rapid extraction method |
| CN107247938A (en) * | 2017-06-08 | 2017-10-13 | 中国科学院遥感与数字地球研究所 | A kind of method of high-resolution remote sensing image City Building function classification |
| CN107392925A (en) * | 2017-08-01 | 2017-11-24 | 西安电子科技大学 | Remote sensing image terrain classification method based on super-pixel coding and convolutional neural networks |
-
2017
- 2017-11-28 CN CN201711216014.7A patent/CN108052876B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140254923A1 (en) * | 2011-10-19 | 2014-09-11 | The University Of Sydney | Image processing and object classification |
| CN104036507B (en) * | 2014-06-13 | 2017-02-15 | 中国地质大学（武汉） | Light satellite based urban change area and evolution type rapid extraction method |
| CN104102928A (en) * | 2014-06-26 | 2014-10-15 | 华中科技大学 | Remote sensing image classification method based on texton |
| CN104881681A (en) * | 2015-05-22 | 2015-09-02 | 浙江大学 | Image sequence category labeling method based on mixed graph model |
| CN107247938A (en) * | 2017-06-08 | 2017-10-13 | 中国科学院遥感与数字地球研究所 | A kind of method of high-resolution remote sensing image City Building function classification |
| CN107392925A (en) * | 2017-08-01 | 2017-11-24 | 西安电子科技大学 | Remote sensing image terrain classification method based on super-pixel coding and convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 乔伟峰: "土地利用视角下的南京城市空间多维扩展研究", 《中国博士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827048A (en) * | 2018-08-08 | 2020-02-21 | 菜鸟智能物流控股有限公司 | Geographic region segmentation method and device based on road network and electronic equipment |
| CN110827048B (en) * | 2018-08-08 | 2023-05-23 | 菜鸟智能物流控股有限公司 | Geographic region segmentation method and device based on road network and electronic equipment |
| CN111241881B (en) * | 2018-11-29 | 2022-12-27 | 中国移动通信集团四川有限公司 | Method, apparatus, device and medium for region identification |
| CN111241881A (en) * | 2018-11-29 | 2020-06-05 | 中国移动通信集团四川有限公司 | Method, apparatus, device and medium for region identification |
| CN110398902A (en) * | 2019-06-19 | 2019-11-01 | 上海机电工程研究所 | Photosignal phantom error analysis method |
| CN110398902B (en) * | 2019-06-19 | 2021-09-24 | 上海机电工程研究所 | Photoelectric signal simulation error analysis method |
| CN110290426A (en) * | 2019-06-24 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Method, apparatus, equipment and the storage medium of showing resource |
| CN110290426B (en) * | 2019-06-24 | 2022-04-19 | 腾讯科技（深圳）有限公司 | Method, device and equipment for displaying resources and storage medium |
| CN111861834A (en) * | 2020-07-14 | 2020-10-30 | 自然资源部第一海洋研究所 | Coastal zone land area space usage monitoring and surveying method based on water resource dependence degree |
| CN112200012A (en) * | 2020-09-15 | 2021-01-08 | 汉海信息技术(上海)有限公司 | Map data processing method and device and electronic equipment |
| CN112613426A (en) * | 2020-12-26 | 2021-04-06 | 北京国腾联信科技有限公司 | Resource area determination method, device, equipment and storage medium |
| CN114581786B (en) * | 2021-12-28 | 2022-11-25 | 深圳市城市产业发展集团有限公司 | Method and device for estimating building area according to ground image |
| CN114581786A (en) * | 2021-12-28 | 2022-06-03 | 深圳市城市产业发展集团有限公司 | Method and device for estimating building area according to ground image |
| CN115619712A (en) * | 2022-09-06 | 2023-01-17 | 江苏省水利科学研究院 | Unmanned aerial vehicle aerial photography technology-based water area monitoring and evaluating method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108052876B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108052876A (en) | Regional development appraisal procedure and device based on image identification | |
| Yu et al. | View-based greenery: A three-dimensional assessment of city buildings’ green visibility using Floor Green View Index | |
| Liu et al. | Towards feasibility of photovoltaic road for urban traffic-solar energy estimation using street view image | |
| Wu et al. | Land use dynamics, built-up land expansion patterns, and driving forces analysis of the fast-growing Hangzhou metropolitan area, eastern China (1978–2008) | |
| CN106780089B (en) | Permanent basic farmland planning method based on neural network cellular automaton model | |
| CN110348506B (en) | Land use classification method based on remote sensing image, storage medium and computing device | |
| CN104850853B (en) | City rapid extracting method and device | |
| Faour et al. | GIS-based approach to the assessment of coastal vulnerability to sea level rise: Case study on the Eastern Mediterranean | |
| Wu et al. | Automatic building rooftop extraction using a digital surface model derived from aerial stereo images | |
| Yang et al. | The spatial distribution and expansion of subsided wetlands induced by underground coal mining in eastern China | |
| Tang et al. | Assessing the visibility of urban greenery using MLS LiDAR data | |
| Tian et al. | Suburban sprawl measurement and landscape analysis of cropland and ecological land: A case study of Jiangsu Province, China | |
| Lu et al. | Mapping the terraces on the Loess Plateau based on a deep learning-based model at 1.89 m resolution | |
| CN116152668B (en) | Method for obtaining block scale LCZ based on artificial intelligence | |
| Kohli et al. | Local ontologies for object-based slum identification and classification | |
| Marinescu et al. | Evaluation of urban fragmentation in Craiova city, Romania | |
| CN112166688B (en) | Method for monitoring desert and desertification land based on minisatellite | |
| Imam et al. | Remote sensing efficiency for urban analysis of Mecca and surrounds | |
| Wang et al. | Characterizing Urban growth of Nanjing, China, by using multi-stage remote sensing images and landscape metrics | |
| Chen et al. | Estimating Land Use/Cover of Foshan City in Southern China with Landsat Remote Sensing Imagery for Flood Modelling | |
| Bhuyan | Spatio temporal analysis of urban expansion and its impact on land use land cover: A case study of Guwahati metropolitan area. | |
| Shui et al. | An integrated planning method for open space of urban street landscape based on remote sensing technology | |
| CN102810157B (en) | TIN (Triangulated Irregular Network) data-based river network extraction method | |
| Xiang et al. | Research and Evaluation of Geographic Information System Based on Highway Ecological Landscape | |
| CN117893923B (en) | Method for constructing space scene based on blue-green gray scale |
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 |