CN101114385A - Digital city full-automatic generating method - Google Patents
Digital city full-automatic generating method Download PDFInfo
- Publication number
- CN101114385A CN101114385A CNA2007100756822A CN200710075682A CN101114385A CN 101114385 A CN101114385 A CN 101114385A CN A2007100756822 A CNA2007100756822 A CN A2007100756822A CN 200710075682 A CN200710075682 A CN 200710075682A CN 101114385 A CN101114385 A CN 101114385A
- Authority
- CN
- China
- Prior art keywords
- image
- model
- remote sensing
- similarity
- characteristic
- 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
Images
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method of automatic generation for digital cities, applied to a general-purpose computer system and comprising the following steps: obtaining the remote sensing land image of a presumptive area and monitoring the shadow lengths of all the objects in the remote sensing land image through an algorithm for detecting shadows; vectoring the remote sensing image to obtain the shapes of different objects and match with the position of the shadow to obtain the lengths of the objects; recognizing the different objects in the remote sensing image according to the characteristics of the image in an image database; forming automatically the three dimensional model of the objects in the area according to the types, the shapes of the base, the shapes of the footstock and a highly combined model base of the objects in the area. The method of the invention can form automatically large range digital cities to meet the need of time effectiveness in city application, and only needs remote sensing images and DEM as basic data so that the invention has low cost and the possibility of application in government, commerce, living, etc.
Description
Technical field
The present invention relates to a kind of geographical space analogue technique, the full-automatic method that generates in particular a kind of digital city.
Background technology
Notion involved in the present invention below at first is described:
1, digital city (Digital city): can realize the overall management of the urban area and decision support, virtual, as to have opening city model for one;
2, three-dimensional model (3D model): the three-dimensional polygon of object represents that logical conventional computer or other video equipment show.Objects displayed is can be the entity of real world, also can be the thing of fabricating, and both may diminish to atom, also can arrive very big size greatly.The thing that any physics nature exists can be represented with three-dimensional model.
3, texture (Texture): in fact a texture is exactly a bitmap.In this sense, when texture one speech is used to computer graphical class hour, it has just had a clear and definite definition.From the semantics angle, texture one speech both had been meant the pattern of color on the object, was meant that again body surface is coarse or smooth.
4, knowledge base (Knowledge Base): structuring in the knowledge engineering, easy to operate, easily utilize, comprehensive organized knowledge cluster, be the needs of finding the solution at a certain (or some) field question, the knowledge sheet that the interknits set of adopting certain (or some) knowledge representation mode in computer memory, to store, organize, manage and use.These knowledge sheets comprise the knowwhy relevant with the field, factual data, and the heuristic knowledge that is obtained by expertise is as definition relevant in certain field, theorem and algorithm and common sense knowledge etc.It is intelligent that knowledge base has KBS Knowledge Based System (or expert system), and not all program with intelligence all has knowledge base, has only KBS Knowledge Based System just to have knowledge base.Present many application programs are all utilized knowledge, and what wherein have has also reached very high level, and still, these application programs may not be KBS Knowledge Based System, and they do not have knowledge base yet.General application program and the difference between the KBS Knowledge Based System are: general application program is impliedly to be coded in the knowledge of problem solving in the program, KBS Knowledge Based System is then expressed the problem solving knowledge explicitly of application, and forms a relatively independent program entity individually.
The characteristics of knowledge base are as follows:
1) knowledge in the knowledge base is configured the organizational form of being convenient to utilize, structure is arranged according to their application feature, background characteristics (background information when obtaining), use characteristic, attributive character etc.The knowledge sheet generally is modular.
2) knowledge of knowledge base is stratified.Lowermost layer is " fact knowledge ", and the middle layer is the knowledge (representing with rule, process etc. usually) that is used for controlling " fact "; Highest level is " strategy ", and it is a controlling object with middle layer knowledge.Strategy also usually is considered to the rule of rule.Therefore the basic structure of knowledge base is hierarchical structure, is determined by the characteristic of its knowledge itself.In knowledge base, all there is relation of interdependence between the knowledge sheet usually.Rule is typical, the most the most frequently used a kind of knowledge sheet.
3) a kind of knowledge that not only belongs to the special shape of a certain level (level in office in other words all exists) can be arranged in the knowledge base---confidence level (or claiming degree of belief, confidence measure etc.).To a certain problem, relevant facts, rule and strategy all can be marked with confidence level.Like this, just formed the augmentation knowledge base.In database, there is not uncertainty measure.Because all belong to " determining type " in the processing of database.
4) also can there be a special part that is commonly referred to as the typical method storehouse in the knowledge base.If the solution route for some problem is to affirm with inevitable, just can directly be stored in it in typical method storehouse as the quite sure problem solution route of a part.The storage of this macroscopic view will constitute another part of knowledge base.When using this part, machine inference will be only limited to certain one deck body portion of selecting for use in the typical method storehouse.
In addition, knowledge base also can realize on distributed network.Like this, just need to build distributed knowledge base.The superiority of building distributed knowledge base has 3 points:
(1) can under lower price, construct bigger knowledge base;
(2) problem-solving task of the knowledge base correspondence of different levels or different field is relatively more simple comparatively speaking, thereby can constitute the system of more efficient;
(3) can be suitable for geographic distribution vast in territory.
The structure of knowledge base must make knowledge access and search effectively in the process that is used wherein, and the knowledge in the storehouse can be revised and edit easily, simultaneously, the consistance and the complete performance of knowledge in the storehouse is tested.
5, images match (image matching): be meant that two different sensors are enrolled two width of cloth images that get off from same scenery spatially aims at, determining the process of relative translation between this two width of cloth image, it can be widely used in aspects such as target following, resource analysis, medical diagnosis is important techniques very in the present information process field.
6, image similarity (image semblance): the probability that is meant another width of cloth image of piece image " screw-in ". provided a succinct image similarity algorithm simultaneously.By repeatedly experiment, this image similarity is effective and satisfied for the identification of complex patterns, can be used for the systematic searching of image.Similarity is included in the similarity degree of aspects such as shape, structure, statistics, texture, environment, height size.
7, digital city image library: the storehouse that image constituted by all objects in the digital city is the digital city image library, this storehouse can be divided into according to the type of object architectural drawing as word bank, road image word bank, bridge image word bank, plant image word bank, animal painting word bank, waters image word bank, aerography as word bank, formation map as word bank.
8, digital city model bank: the three-dimensional model by all objects in the digital city constitutes, and its classification is corresponding with the digital city image library.Comprise all characteristic informations on the object dimensional in the model, comprised shape, color, texture or the like.
9, digital elevation model (DEM) also claims digital terrain model (DTM), is a kind of continuous representation method to the space fluctuations.Because DTM is implied with the meaning of landform landscape, so DEM commonly used is with simple expression elevation.Can download the free global altitude figures of 30 meters precision from the Internet.
The digital city is technology such as integrated use GIS, remote sensing, remote measurement, broadband network, multimedia and virtual emulation, infrastructure, the functional mechanism in city is carried out the technological system of automatic information collecting, dynamic monitoring management and aid decision making service; It has the powers such as digitizing, networking, virtual emulation, optimum decision support and visual representing of complication systems such as urban geography, resource, ecologic environment, population, economy, society.The digital city provides important supporting tool for the city sustainable development.
Visual is to realize digital city and mutual window and the instrument of people, does not have visualization technique, and a pile numeral in the computing machine does not have in all senses, and a distinguishing feature of digital city is a virtual reality technology.After having set up the digital city, the user puts on and shows the helmet or from computer screen or from large screen projection, just can see that the city occurs from the earth, uses mouse or keyboard amplifier digital image; Along with improving constantly of resolution, the user can see private accommodation, shop, trees and other natural and man-made tourist site, when the user is interested in commodity, can enter in the shop, appreciate the clothes in the market, and can construct the virtual scene that oneself tries on a dress according to the build of oneself.
Virtual reality technology is human observation of nature, appreciates view, and understanding entity provides sensation on the spot in person.Recent years, the virtual reality technology development is very fast, and virtual reality modeling language (VRML) is a kind of towards Web, OO three-dimensional modeling language, and it is a kind of interpreted language.It not only supports the three dimensional representation of data and process, and can make the user come into audio visual effect virtual world true to nature, thereby realizes the expression of digital earth and realize the research of various earth phenomenons and people's daily use by digital earth.In fact, artificial virtual reality technology is proven technique already in photogrammetric, the development of digital photogrammetry in recent years, and can set up on computers can be for the digital virtual technology that is survey.Certainly, current technology is that same entity is taken pictures, and produces parallax, and the constructing stereo model is normally worked as models treated.Further development is the whole earth to be carried out seamless spliced, roams arbitrarily and amplifies, by the method for three-dimensional data by artificial parallax, constructing virtual solid.
The technology of existing structure digital city as Fig. 1, Fig. 2, shown in Figure 3, is the way of three kinds of structure digital citys commonly used, and is similar with other scheme, and just modeling is different with the instrument of playing up.The common trait of such scheme is: the photo according to collection in worksite arrives, carry out manual three-dimensional modeling, and the manual position of each object in the scene of city of demarcating, then with the manual relevant position that joins in the scene of city of the three-dimensional model of each object.
In each scheme of prior art, need with camera to all objects in the city take pictures one by one, manual modeling one by one, workload is very big, the correct position in the scene of digital city is demarcated and be arranged to the model that also needs to build up one by one by hand.This process will expend great amount of manpower, comprise and gather photo, manual modeling, the manual demarcation and the arrangement model, can expend a large amount of financial resources simultaneously, for example need a lot of cameras to use for gathering photo, need a lot of computing machines for manual modeling, demarcate and settle that model is used etc. by hand, also can expend a large amount of time, for example build a model and sometimes just need 1 day, have thousands of object to need modeling in the city, for example the digital city, Shenzhen just can be finished with the minimum time in 3 years of needs of prior art.
And make rapid progress along with urban development at present, that official thinks to command on the spot in personly is emergent, it is violating the regulations to investigate and prosecute, and the resident thinks to travel home-confinedly, or the like, these only just can be accomplished in the digital city.If need spend long time but do a digital city, as utilize existing technology, numeral Shenzhen needed for 3 years, and people can give city emergency, the consequence of the bringing on a disaster property such as monitoring of breaking rules and regulations before seen in the digital city all are 3 years so.In fact, making rapid progress really of the variation in Shenzhen, every day, the looks in city all can change, unless so within one day, the digital city is built out at least, otherwise the digital city of drawing can't authentic representative and the real city of reflection, the digital city of prior art can't really play a role in actual applications, can not accomplish in real time.
Therefore, prior art also has defective, and awaits improving and development.
Summary of the invention
The object of the present invention is to provide the full-automatic method that generates in a kind of digital city, mode by knowledge base, realize the automatic generation of digital city, so that can generate the digital city in real time, for city emergency, monitoring violating the regulations, point duty, digital living etc. provide real-time support.
Technical scheme of the present invention comprises:
The full-automatic method that generates in a kind of digital city, it is applied to a general-purpose computing system, may further comprise the steps:
A, obtain the remote sensing image on a presumptive area ground, and, monitor out the shade length of all objects on the remote sensing image by the shadow Detection algorithm;
B, described remote sensing image is carried out vector quantization, obtain the shape of different objects, and mate the position of described shade, obtain the height of each object;
C, the image of gathering each object in this region and corresponding model form knowledge base;
D, the characteristic according to image in image library are discerned different objects in remote sensing image;
E, the type according to object in this region, base shape, footstock shape, height combination model storehouse generate the three-dimensional model of this region object automatically;
F, according to the two-dimensional coordinate position of corresponding each object, the three-dimensional model of this region object is inlayed in the remote sensing image with elevation.
Described method, wherein, the two-dimensional coordinate position in the described step F obtains according to digital elevation model and remote sensing image.
Described method, wherein, described step D also comprises:
D1, from remote sensing image, extract the representational image of various types of individualities, and these representational images are classified, extract its general character, form first order characteristic image;
D2, in this rank, mark off subclass, and in all images of each subclass, extract general character respectively, give a characteristic image respectively for each subclass;
So analogize, up to its divide represented basically should the representational all kinds of individuality till.
Described method, wherein, the taxonomic structure of described model bank is consistent with the taxonomic structure of described image library, and an image in the image library is corresponding with a model in the model bank.
Described method, wherein, the static model that the model in the described model bank is to use the instrument of modeling to build up.
Described method, wherein, the model in the described model bank is to use parametric description and the three-dimensional model of real-time rendering when needed.
Described method wherein, is used static model earlier when generating the digital city automatically, replace previous static model with revised dynamic model gradually again.
Described method, wherein, the mapping relations between described image library and the model bank may further comprise the steps:
D3, the object in the remote sensing image is extracted and discerns according to image library;
D4, the subclass of the object that extracts and the respective classes in the image library is carried out similarity relatively, and retrieve in the image library image with this object similarity maximum, and be mapped to corresponding model in the model bank;
D5, the individuality in the remote sensing image is carried out automatic modeling by knowledge base.
Described method, wherein, described step D5 also comprises:
D51, remote sensing image is scanned, obtain the set of the object of each big class, judge the similarity between this object and these characteristic images according to the first order characteristic image in the image library;
D52, from image library, find out the accurate classification under this object.
Described method, wherein, described step D52 comprises:
D521, the characteristic image that the next stage of this subject image and classification under it is classified compare, if the characteristic image similarity of this individual images and a certain class is the highest, judge that then this individual images belongs to such;
D522, this individual images and each characteristic image of such next stage are mated respectively, and calculate its similarity, find the classification under the maximum characteristic image of similarity, as the classification under this subject image;
So analogize, reach the expection requirement up to its similarity.
The full-automatic method that generates in a kind of digital city provided by the present invention can automatically generate large-scale digital city in real time, has satisfied ageing demanding urban applications; And only need remote sensing image, DEM to get final product as basic data, cost is very low, has satisfied in the whole nation and even the digital city is promoted in the whole world, and makes it to be applied in government, commerce, life etc. and become possibility.
Description of drawings
Fig. 1 is the digital city generation technique synoptic diagram of prior art;
Fig. 2 is the another kind of digital city generation technique synoptic diagram of prior art;
Fig. 3 is another digital city generation technique synoptic diagram of prior art;
Fig. 4 is for building the storehouse schematic flow sheet in the full-automatic method that generates in digital city of the present invention;
Fig. 5 is the automatic generation digital city process synoptic diagram of the inventive method;
Fig. 6 is the synoptic diagram of the image library of the inventive method;
Fig. 7 is the recognition rule storehouse synoptic diagram of the inventive method;
Fig. 8 is the model bank synoptic diagram of the inventive method;
Fig. 9 is the synoptic diagram of the mapping relations between image library and the model bank in the inventive method;
Figure 10 is the remote sensing image of the inventive method one embodiment;
Figure 11 is the shade synoptic diagram after the inventive method is handled according to Figure 10;
Figure 12 by the inventive method the effect synoptic diagram of drafting digital city.
Embodiment
Below in conjunction with accompanying drawing, will be described in more detail each preferred embodiment of the present invention.
The full-automatic method that generates in digital city of the present invention, it has utilized remote sensing image, specifically may further comprise the steps at a multi-purpose computer:
The 1st step, by shade monitoring algorithm, monitor out the length of all shades on the remote sensing image, be that prior art is known about the shade length calculation;
The 2nd step, the remote sensing image in city is carried out vector quantization, thereby obtain the shape of different cities object; And the position of object and the position of shade mated, thereby obtain the height of object; Computation process about vector quantization also is that prior art is known, therefore, repeats no more;
The 3rd step, the image and the corresponding model thereof of gathering various buildings, vehicle etc. in the city, put into knowledge base, as shown in Figure 4, at first analyze the city data in the remote sensing image, with the individual segregation in the city, for example vehicle, building etc., and from remote sensing image, extract individual characteristic image, add image library automatically, according to the personal feature image, judge through the identification of human eye to add and gathers this individual three-dimensional information on the spot, then modeling and add model bank;
The 4th step, in remote sensing image, discern different objects, thereby obtain the type and the footstock shape thereof of different cities object according to the characteristic of the image of different objects in the image library; Secondary characteristics image according to each type objects in the image library in this process mates this type objects in the remote sensing image, belongs to which subclass thereby discern each object; So analogize, know that the effect of identification has reached requirement, thereby obtain the particular type of all city objects in the image;
The 5th step, dissimilar, the base shape according to the city object, footstock shape, height combination model storehouse generate the three-dimensional model of city object automatically;
The 6th step, obtain the landforms of digital city and the height of landform rises and falls according to DEM and remote sensing image;
The 7th step, with the three-dimensional model of these above-mentioned city objects, inlay in the remote sensing image with elevation according to the position of their two-dimensional coordinates, just generated the digital city automatically to this step.
The whole process of above-mentioned automatic generation below is introduced several committed steps that the present invention generates the digital city automatically as shown in Figure 5 in detail:
The first step: the three-dimensional model of setting up the city object automatically;
Before the automatic generation of carrying out the digital city, the inventive method need at first be set up the recognition rule storehouse, image library, model bank, as Fig. 6, Fig. 7 and shown in Figure 8, rule in recognition rule storehouse shown in Figure 7 is divided according to the coupling of different aspect, as: the detection rule of shape similarity and difference, the detection rule of structural similarity and difference, the detection rule of statistics similarity and difference, the detection rule of color similarity degree and difference, the detection rule of gray scale similarity and difference, the detection rule of texture similarity and difference, detection rule of environment similarity of living in and difference or the like.
Image sampling in described image library shown in Figure 6 is specially from remote sensing image: extract the representational image of various types of individualities from remote sensing image, and these representational images are classified, extract general character, first order characteristic image; And then mark off subclass in this rank, and in all images of subclass, extract general character, give a characteristic image for this subclass, so analogize, up to its divide represented basically should the representational all kinds of individuality till.
The taxonomic structure basically identical of the taxonomic structure of model bank and image library as shown in Figure 8 in the inventive method, an image in the image library is corresponding with a model in the model bank basically, but the static model that the model in the model bank can be to use the instrument of modeling to build up also can be to use the three-dimensional model of the real-time rendering when needed of parametric description.Dynamic model is than the easier correction of static model, and it is more real-time than using dynamic model to use static model, but that the authenticity of expressing is not passed through revised dynamic model is good.So the inventive method can be used static model earlier when generating the digital city automatically, replace previous static model with revised dynamic model gradually again.
Be illustrated in figure 9 as image library of the inventive method and the mapping relations between the model bank, earlier the object in the remote sensing image is extracted and discerns according to image library, then the subclass of the object that extracts and the respective classes in the image library is carried out similarity relatively, and retrieve in the image library image with this object similarity maximum, and be mapped to corresponding model in the model bank.As follows by knowledge base: as according to the first order characteristic image in the image library remote sensing image to be scanned, obtain the set of the object of each big class to the process that the individuality in the remote sensing image carries out automatic modeling.For example first order classification has the characteristic image of building, the characteristic image of bridge, the characteristic image on square, the characteristic image of flowers, plants and trees, characteristic image of water or the like.Judge the similarity between this object and these characteristic images.
This similarity comprises: the similarity of the similarity of the similarity of shape, the similarity of structure, statistics, the similarity of color, gray scale, the similarity of texture, similarity of environment of living in or the like.As seen similarity has a lot of components, the present invention decides by the initial analysis to individuality and adopts which similarity, and in judging this individuality and image library, give different weights for dissimilar similarities during the similarity of image, the method for employing weighting when differentiating final similarity then.
The inventive method extracts from remote sensing image after some objects, from image library, find out the accurate classification (as: building/high building/office building) under this object, its method is: at first the characteristic image that the next stage of this subject image and classification under it is classified relatively, if the characteristic image similarity of this individual images and X class is the highest, just can judge that so this individual images belongs to the X class; Each characteristic image of next stage with this individual images and X class mates respectively again, and calculate its similarity, find the affiliated classification of this subject image of conduct of the affiliated classification (being assumed to be Y) of the maximum characteristic image of similarity, can continue then to compare with the next stage characteristic image of Y, so analogize, reach the expection requirement up to its similarity.
Stipulate as required as the inventive method: similarity reaches 80% and gets final product for building.The characteristic image of the subclass of its final coupling and similarity maximum is the twin image of this individual images so, and this twin image just can obtain the pairing twin three-dimensional model of this twin image by the mapping ruler between image library and the model bank.The priori that has contained a large amount of people in this three-dimensional model, and from contain between nature and the digital city a large amount of fuzzy beyond expression of words but in esse a large amount of knowledge, these knowledge all are to imply into when setting up image library and model bank and the mapping relations between them.
Example with aforementioned building, if should individuality and the similarity of its twin image in image library reach 80%, the inventive method can also be judged their 20% and where differ from, according to this difference of 20%, and this difference decomposed the difference of shape, the difference of structure, the difference of statistics, the difference of color, the difference of gray scale, the difference of texture, environmental differences of living in or the like.And the difference on these two dimensional images will have a mapping ruler with the difference on the three-dimensional model, and according to this rule, the inventive method just can be revised the twin model of this individuality, finally obtains the model true to nature of this more satisfactory individuality.
Second step: the height that generates the city object automatically
The inventive method is calculated the length of each shade according to the shade in the remote sensing image, again registration is carried out in the position of each shade and each object, just can obtain the height of each object.Remote sensing image as shown in figure 10, the echo that the inventive method detects is as shown in figure 11.
The 3rd step: automatically object is implanted in the remote sensing image (landforms) in city
The process of object model in the remote sensing image being implanted again remote sensing image is as follows: from remote sensing image, extract individual the time, the inventive method just in program, write down should individuality two-dimensional coordinate, and the orientation on different limit that should individuality.According to coordinate and the orientation of this individual images in remote sensing image, the inventive method just can be implanted its model true to nature that automatically generates by previous step in the remote sensing image, thereby can reappear various object images in the city automatically towards, angle, position with correct.
The 4th step: the inventive method covers remote sensing image on the digital elevation model DEM, make remote sensing image rise and fall to some extent according to the data of DEM, all individual three-dimensional models rise and fall too thereupon on the remote sensing image simultaneously, thereby this is the actual geographic shape in a city of simulation.
Just realized fully generating three-dimensional digital city automatically through above several steps from single remote sensing image and corresponding elevation map, the digital city image that the inventive method generates by remote sensing image Figure 10 as shown in figure 12, can see, the inventive method can automatically generate large-scale digital city in real time, satisfies ageing demanding urban applications; And only need remote sensing image, DEM to get final product as basic data, cost is very low, has satisfied in the whole nation and even the whole world is promoted the digital city and made it to be applied in government, commerce, life etc. and becomes possibility.
The inventive method can be the city emergency commading system service, merge various remotely-sensed datas and generate the digital city automatically real-time, based on information such as the layout in real-time digital city, landform, roads, and in conjunction with meteorological measuring (wind-warm syndrome data) simcity wind field, thereby can the dynamic similation air pollution diffusion etc. the development trend of accident, and can Real-time and Dynamic be shown to the city cammander realistically, decision references is provided.
Utilize the inventive method can be city architecture against regulations Monitoring Service, generate the digital city automatically real-time by merging various remotely-sensed datas, by building in the comparative figures city and layout data, just the different architectures against regulations can be found exactly and the person that is shown to the urban planning administration.
Utilize the inventive method can also be used for a lot of other aspects, for example the resident can not go out door enjoyment dummy market, the service of aspects such as Virtual Hospital, virtual theatre and virtual tourism; City emergency disaster relief commanding does not go out command post just can see best rescue route and field condition; The police need not go out the position that the police office just can navigate to the offender at once, monitors offender's every act and every move, and can determine the best route of arresting immediately; Planning department just can be seen all lands used and house without on-the-spot investigation, thereby makes the most rational decision-making; Vehicle supervision department need not stand in the traffic that just can see all roads on the road, thereby makes the most rational scheduling.
Must explanation be, the inventive method can also adopt other ways generate height, the inspected object of objects type, generate elevation etc., and, can also use photo, microwave remote sensing, wireless senser etc. to obtain data except remote sensing image.
Should be understood that above-mentioned description at the specific embodiment of the invention is comparatively concrete, can not therefore be interpreted as the restriction to scope of patent protection of the present invention, scope of patent protection of the present invention should be as the criterion with claims.
Claims (10)
1. the full-automatic method that generates in a digital city, it is applied to a general-purpose computing system, may further comprise the steps:
A, obtain the remote sensing image on a presumptive area ground, and, monitor out the shade length of all objects on the remote sensing image by the shadow Detection algorithm;
B, described remote sensing image is carried out vector quantization, obtain the shape of different objects, and mate the position of described shade, obtain the height of each object;
C, the image of gathering each object in this region and corresponding model form knowledge base;
D, the characteristic according to image in image library are discerned different objects in remote sensing image;
E, the type according to object in this region, base shape, footstock shape, height combination model storehouse generate the three-dimensional model of this region object automatically;
F, according to the two-dimensional coordinate position of corresponding each object, the three-dimensional model of this region object is inlayed in the remote sensing image with elevation.
2. method according to claim 1 is characterized in that, the two-dimensional coordinate position in the described step F obtains according to digital elevation model and remote sensing image.
3. method according to claim 1 is characterized in that, described step D also comprises:
D1, from remote sensing image, extract the representational image of various types of individualities, and these representational images are classified, extract its general character, form first order characteristic image;
D2, in this rank, mark off subclass, and in all images of each subclass, extract general character respectively, give a characteristic image respectively for each subclass;
So analogize, up to its divide represented basically should the representational all kinds of individuality till.
4. method according to claim 3 is characterized in that the taxonomic structure of described model bank is consistent with the taxonomic structure of described image library, and an image in the image library is corresponding with a model in the model bank.
5. method according to claim 4 is characterized in that, the static model that the model in the described model bank is to use the instrument of modeling to build up.
6. method according to claim 4 is characterized in that, the model in the described model bank is to use parametric description and the three-dimensional model of real-time rendering when needed.
7. according to claim 5 or 6 described methods, it is characterized in that, when generating the digital city automatically, use static model earlier, replace previous static model with revised dynamic model gradually again.
8. method according to claim 1 is characterized in that, the mapping relations between described image library and the model bank may further comprise the steps:
D3, the object in the remote sensing image is extracted and discerns according to image library;
D4, the subclass of the object that extracts and the respective classes in the image library is carried out similarity relatively, and retrieve in the image library image with this object similarity maximum, and be mapped to corresponding model in the model bank;
D5, the individuality in the remote sensing image is carried out automatic modeling by knowledge base.
9. method according to claim 8 is characterized in that, described step D5 also comprises:
D51, remote sensing image is scanned, obtain the set of the object of each big class, judge the similarity between this object and these characteristic images according to the first order characteristic image in the image library;
D52, from image library, find out the accurate classification under this object.
10. method according to claim 9 is characterized in that, described step D52 comprises:
D521, the characteristic image that the next stage of this subject image and classification under it is classified compare, if the characteristic image similarity of this individual images and a certain class is the highest, judge that then this individual images belongs to such;
D522, this individual images and each characteristic image of such next stage are mated respectively, and calculate its similarity, find the classification under the maximum characteristic image of similarity, as the classification under this subject image;
So analogize, reach the expection requirement up to its similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100756822A CN100533486C (en) | 2007-08-07 | 2007-08-07 | Digital city full-automatic generating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100756822A CN100533486C (en) | 2007-08-07 | 2007-08-07 | Digital city full-automatic generating method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101114385A true CN101114385A (en) | 2008-01-30 |
| CN100533486C CN100533486C (en) | 2009-08-26 |
Family
ID=39022712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007100756822A Expired - Fee Related CN100533486C (en) | 2007-08-07 | 2007-08-07 | Digital city full-automatic generating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100533486C (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101545775B (en) * | 2009-05-05 | 2011-06-08 | 东南大学 | Method for calculating orientation elements of photo and the height of building by utilizing digital map |
| CN102119402A (en) * | 2008-06-16 | 2011-07-06 | Eyefi研发有限公司 | Spatial predictive approximation and radial convolution |
| CN102254350A (en) * | 2011-07-05 | 2011-11-23 | 中国测绘科学研究院 | 3D (three-dimensional) model matching method |
| WO2012012943A1 (en) * | 2010-07-28 | 2012-02-02 | Shenzhen Institute Of Advanced Technology Chinese Academy Of Sciences | Method for reconstruction of urban scenes |
| CN102393971A (en) * | 2011-07-07 | 2012-03-28 | 东北林业大学 | Seamless linkage method of highway three-dimensional model database and digital elevation model database |
| CN102521273A (en) * | 2011-11-23 | 2012-06-27 | 中国科学院地理科学与资源研究所 | High-resolution remote-sensing multifunctional urban land spatial information generation method |
| CN102592314A (en) * | 2011-12-31 | 2012-07-18 | 中国神华能源股份有限公司 | Processing method and processing device of remote sensing image data |
| CN103136781A (en) * | 2011-11-30 | 2013-06-05 | 国际商业机器公司 | Method and system of generating three-dimensional virtual scene |
| CN103455709A (en) * | 2013-07-31 | 2013-12-18 | 华中科技大学 | Super-resolution method and system for digital elevation model |
| CN107635191A (en) * | 2017-09-26 | 2018-01-26 | 安徽美图信息科技有限公司 | The public security standard positioning service system that remote sensing image is combined with local police station's data |
| CN107862667A (en) * | 2017-11-23 | 2018-03-30 | 武汉大学 | A kind of city shadow Detection and minimizing technology based on high-resolution remote sensing image |
| CN107944503A (en) * | 2017-12-13 | 2018-04-20 | 北京数洋智慧科技有限公司 | A kind of Urban Data acquisition method and system based on image recognition |
| CN108038908A (en) * | 2017-11-21 | 2018-05-15 | 泰瑞数创科技(北京)有限公司 | Spatial object identification and modeling method and system based on artificial intelligence |
| CN108053474A (en) * | 2017-12-29 | 2018-05-18 | 湖南城市学院 | A kind of new city three-dimensional modeling control system and method |
| CN108693876A (en) * | 2017-04-06 | 2018-10-23 | 通用汽车环球科技运作有限责任公司 | Target following |
| CN109067822A (en) * | 2018-06-08 | 2018-12-21 | 珠海欧麦斯通信科技有限公司 | The real-time mixed reality urban service realization method and system of on-line off-line fusion |
| CN111723469A (en) * | 2020-05-25 | 2020-09-29 | 贵州华泰智远大数据服务有限公司 | Digital portrait modeling method and system based on twin data |
| WO2020228676A1 (en) * | 2019-05-16 | 2020-11-19 | 阿里巴巴集团控股有限公司 | Image generation method and device, image display method and device |
| CN113222918A (en) * | 2021-04-29 | 2021-08-06 | 桂林理工大学 | Method for detecting high-resolution orthographic image shadow by polygonal semantic matching |
| CN113989680A (en) * | 2021-12-27 | 2022-01-28 | 苏州工业园区测绘地理信息有限公司 | Automatic building three-dimensional scene construction method and system |
| WO2022105604A1 (en) * | 2020-11-18 | 2022-05-27 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for constructing a building block model |
-
2007
- 2007-08-07 CN CNB2007100756822A patent/CN100533486C/en not_active Expired - Fee Related
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102119402B (en) * | 2008-06-16 | 2013-12-25 | Eyefi私人有限公司 | Method for spatial predictive approximation and radial convolution and system implementing same |
| CN102119402A (en) * | 2008-06-16 | 2011-07-06 | Eyefi研发有限公司 | Spatial predictive approximation and radial convolution |
| CN101545775B (en) * | 2009-05-05 | 2011-06-08 | 东南大学 | Method for calculating orientation elements of photo and the height of building by utilizing digital map |
| WO2012012943A1 (en) * | 2010-07-28 | 2012-02-02 | Shenzhen Institute Of Advanced Technology Chinese Academy Of Sciences | Method for reconstruction of urban scenes |
| CN102254350A (en) * | 2011-07-05 | 2011-11-23 | 中国测绘科学研究院 | 3D (three-dimensional) model matching method |
| CN102393971A (en) * | 2011-07-07 | 2012-03-28 | 东北林业大学 | Seamless linkage method of highway three-dimensional model database and digital elevation model database |
| CN102521273B (en) * | 2011-11-23 | 2013-06-19 | 中国科学院地理科学与资源研究所 | High-resolution remote-sensing multifunctional urban land spatial information generation method |
| CN102521273A (en) * | 2011-11-23 | 2012-06-27 | 中国科学院地理科学与资源研究所 | High-resolution remote-sensing multifunctional urban land spatial information generation method |
| CN103136781A (en) * | 2011-11-30 | 2013-06-05 | 国际商业机器公司 | Method and system of generating three-dimensional virtual scene |
| CN103136781B (en) * | 2011-11-30 | 2016-06-08 | 国际商业机器公司 | For generating method and the system of three-dimensional virtual scene |
| US11574438B2 (en) | 2011-11-30 | 2023-02-07 | International Business Machines Corporation | Generating three-dimensional virtual scene |
| US11069130B2 (en) | 2011-11-30 | 2021-07-20 | International Business Machines Corporation | Generating three-dimensional virtual scene |
| CN102592314A (en) * | 2011-12-31 | 2012-07-18 | 中国神华能源股份有限公司 | Processing method and processing device of remote sensing image data |
| CN102592314B (en) * | 2011-12-31 | 2014-12-17 | 中国神华能源股份有限公司 | Processing method and processing device of remote sensing image data |
| CN103455709A (en) * | 2013-07-31 | 2013-12-18 | 华中科技大学 | Super-resolution method and system for digital elevation model |
| CN103455709B (en) * | 2013-07-31 | 2016-02-24 | 华中科技大学 | A kind of super-resolution method for digital elevation model and system thereof |
| CN108693876A (en) * | 2017-04-06 | 2018-10-23 | 通用汽车环球科技运作有限责任公司 | Target following |
| CN107635191A (en) * | 2017-09-26 | 2018-01-26 | 安徽美图信息科技有限公司 | The public security standard positioning service system that remote sensing image is combined with local police station's data |
| CN108038908A (en) * | 2017-11-21 | 2018-05-15 | 泰瑞数创科技(北京)有限公司 | Spatial object identification and modeling method and system based on artificial intelligence |
| CN107862667B (en) * | 2017-11-23 | 2019-12-24 | 武汉大学 | Urban shadow detection and removal method based on high-resolution remote sensing image |
| CN107862667A (en) * | 2017-11-23 | 2018-03-30 | 武汉大学 | A kind of city shadow Detection and minimizing technology based on high-resolution remote sensing image |
| CN107944503A (en) * | 2017-12-13 | 2018-04-20 | 北京数洋智慧科技有限公司 | A kind of Urban Data acquisition method and system based on image recognition |
| CN108053474A (en) * | 2017-12-29 | 2018-05-18 | 湖南城市学院 | A kind of new city three-dimensional modeling control system and method |
| CN109067822A (en) * | 2018-06-08 | 2018-12-21 | 珠海欧麦斯通信科技有限公司 | The real-time mixed reality urban service realization method and system of on-line off-line fusion |
| WO2020228676A1 (en) * | 2019-05-16 | 2020-11-19 | 阿里巴巴集团控股有限公司 | Image generation method and device, image display method and device |
| CN111723469A (en) * | 2020-05-25 | 2020-09-29 | 贵州华泰智远大数据服务有限公司 | Digital portrait modeling method and system based on twin data |
| WO2022105604A1 (en) * | 2020-11-18 | 2022-05-27 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for constructing a building block model |
| CN113222918A (en) * | 2021-04-29 | 2021-08-06 | 桂林理工大学 | Method for detecting high-resolution orthographic image shadow by polygonal semantic matching |
| CN113989680A (en) * | 2021-12-27 | 2022-01-28 | 苏州工业园区测绘地理信息有限公司 | Automatic building three-dimensional scene construction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100533486C (en) | 2009-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100533486C (en) | Digital city full-automatic generating method | |
| CN101149843B (en) | Succession type automatic generation and real time updating method for digital city | |
| CN112598796A (en) | Method for building and automatically updating three-dimensional building information model based on generalized point cloud | |
| CN108182724B (en) | High-precision urban heat island detection method and device and storage device | |
| Agugiaro et al. | A web-based interactive tool for multi-resolution 3D models of a Maya archaeological site | |
| Khayyal et al. | Creation and spatial analysis of 3D city modeling based on GIS data | |
| Tohidi et al. | A review of the machine learning in gis for megacities application | |
| CN102800120B (en) | Emergency disaster situation display system and method based on multiple intelligent bodies | |
| Taubenböck et al. | Remote sensing—An effective data source for urban monitoring | |
| Adreani et al. | Digital twin framework for smart city solutions | |
| Borisov et al. | An automated process of creating 3D city model for monitoring urban infrastructures | |
| CN101256576A (en) | Method and system for generating city digital platform | |
| Zhang et al. | An Approach to Map Visibility in the Built Environment From Airborne LiDAR Point Clouds | |
| Komadina et al. | Automated 3D urban landscapes visualization using open data sources on the example of the city of Zagreb | |
| WO2018196214A1 (en) | Statistics system and statistics method for geographical influence on vernacular architectural form | |
| Fissore et al. | DSM and DTM for extracting 3D building models: advantages and limitations | |
| CN115880427A (en) | Three-dimensional construction method and device of natural environment | |
| CN112907567B (en) | SAR image ordered artificial structure extraction method based on spatial reasoning method | |
| Xiong | Reconstructing and correcting 3d building models using roof topology graphs | |
| CN113313418A (en) | Urban building roof greening suitability evaluation grading method | |
| Nandi et al. | Geographical Information System (GIS) in water resources engineering | |
| Jazayeri | Trends in 3D land information collection and management | |
| Gruen et al. | Perspectives in the reality-based generation, n D modelling, and operation of buildings and building stocks | |
| Zhu et al. | Unified Representation of three dimensional city models | |
| Lee | Case study on emerging trends in geospatial technologies for study of urban form |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: SHENZHEN CAS INCUBATION TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: SHENZHEN ADVANCED TECHNOLOGY RESEARCH INST. Effective date: 20121128 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 518067 SHENZHEN, GUANGDONG PROVINCE TO: 518054 SHENZHEN, GUANGDONG PROVINCE |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20121128 Address after: 518054 building D, building 202E, No.1 building, six industrial road, Nanshan District, Guangdong, Shenzhen Patentee after: Shenzhen Zhongke Breeding Technology Co., Ltd. Address before: 518067, A, Nanshan Medical Instrument Industrial Park, No. 1019 Nanhai Road, Shekou, Guangdong, Shenzhen, Nanshan District Patentee before: Shenzhen Advanced Technology Research Inst. |
|
| ASS | Succession or assignment of patent right |
Owner name: GUANGDONG ZHONGKE ADVANCED CLOUD COMPUTING TECHNOL Free format text: FORMER OWNER: SHENZHEN CAS INCUBATION TECHNOLOGY CO., LTD. Effective date: 20130306 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 518054 SHENZHEN, GUANGDONG PROVINCE TO: 518022 SHENZHEN, GUANGDONG PROVINCE |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20130306 Address after: 518022 Shenzhen International Trust Building, 1010 Hongling Road, Shenzhen, Luohu District 1801, 1802, Guangdong Patentee after: Guangdong Zhongke advanced Cloud Computing Technology Co., Ltd. Address before: 518054 building D, building 202E, No.1 building, six industrial road, Nanshan District, Guangdong, Shenzhen Patentee before: Shenzhen Zhongke Breeding Technology Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090826 Termination date: 20140807 |
|
| EXPY | Termination of patent right or utility model |