CN106022257A - Building shadow automatic recognition and model covering method - Google Patents

Building shadow automatic recognition and model covering method Download PDF

Info

Publication number
CN106022257A
CN106022257A CN201610330303.9A CN201610330303A CN106022257A CN 106022257 A CN106022257 A CN 106022257A CN 201610330303 A CN201610330303 A CN 201610330303A CN 106022257 A CN106022257 A CN 106022257A
Authority
CN
China
Prior art keywords
building
shadow
shade
height
covering method
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
Application number
CN201610330303.9A
Other languages
Chinese (zh)
Other versions
CN106022257B (en
Inventor
龙永生
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Shenzhoulong Information Service Co Ltd
Original Assignee
Shenzhen Shenzhoulong Information Service Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Shenzhoulong Information Service Co Ltd filed Critical Shenzhen Shenzhoulong Information Service Co Ltd
Priority to CN201610330303.9A priority Critical patent/CN106022257B/en
Publication of CN106022257A publication Critical patent/CN106022257A/en
Application granted granted Critical
Publication of CN106022257B publication Critical patent/CN106022257B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention discloses a building shadow automatic recognition and model covering method, and the method comprises the steps: the extraction and optimization of shadow and other parameters, the calculation and statistic analysis of a building height, the verification of the precision of a height extraction result, and the matching obtaining from a database. The method is high in calculation precision, can reach the precision: less than 2m (the height of one floor), and especially play a big role in actual prevention and reduction of natural disasters.

Description

Architectural shadow identifies and model covering method automatically
Technical field
The present invention relates to a kind of architectural shadow automatically identify and model covering method.
Background technology
Computer, by extracting the base map of Google satellite map, then identifies its shadow region, founding mathematical models, so Calculate volume and the height of building afterwards according to shade size, and from data base, get phase therewith according to building coordinate information The 3D model of coupling.
Conventionally, as the shade of building identifies automatically, the experiment of covering method is measured for little scope Measure, on a large scale, when the building of big quantity extracts height, still can not the most quickly obtain higher precision.
Drawbacks described above, is worth solving.
Summary of the invention
In order to overcome the deficiency of existing technology, the present invention provides a kind of architectural shadow automatically to identify and model covering side Method.
Technical solution of the present invention is as described below:
Architectural shadow identifies and model covering method automatically, it is characterised in that comprise the following steps:
The isoparametric extraction of S1: shade and optimization；
The calculating of S2: depth of building and statistical analysis；
S3: height extracts the precision test of result；
S4: obtain coupling from data base.
Further, described step S1 specifically includes:
S11: according to the feature of image zones of different and the rectangular histogram of correspondence and several groups of threshold values selecting optimum, use each threshold Value is respectively divided image, extracts dash area, and the shade that comprehensive each threshold value is extracted generates original echo；
S12: generate mask by the result drawn, processes the original echo generated in step S11, generates the shade optimized Figure；
S13: the echo for optimizing utilizes area features, the bound threshold value of setting area size, area is more than setting The dash area determining upper limit threshold is deleted, and area is deleted less than the dash area setting lower threshold；
S14: remove the water body being mingled in shade further with morphological characteristic.
Further, in described step S11, threshold value includes 2-4 group.
Further, described step S2, particularly as follows: the echo binaryzation that will finally obtain, utilizes institute in following formula calculating figure Hypographous length:
S u = n × r cosφ s
The shadow length retrieving shade and building border be recorded on the building of correspondence, utilize following formula to calculate each The depth of building that shadow length is corresponding:
ht=Su tanθu。
Wherein, SuFor daylight shade and the range difference of building effects, htFor the height of building,θuFor sunlight with Ground angle.
Further, described step S3 particularly as follows:
The effective percentage R that depth of building extracts is defined as:
R = C T × 100 %
Wherein C is the building number extracted in the drawings, and T is the number of actual measurement building,
Utilize following formula to calculate each statistics height value and relatively survey mean square error MSF of height value, and then determine extraction height The precision of degree:
M S E = 1 n Σ i = 1 n ( x i - H i ) 2 .
Further, described step S4 particularly as follows:
Carry out the Data Matching of data base, according to shadow extraction, calculate corresponding depth of building and get therewith Relevant coordinate information, carries out the coupling of data base, thus gets the 3D model matched.
According to the present invention of such scheme, it has the beneficial effects that, computational accuracy of the present invention is high, it is possible to reaches precision and is less than 2m (first floor height), especially at actual aspect of preventing and reducing natural disasters, plays the biggest effect.
Accompanying drawing explanation
Fig. 1 is the relation schematic diagram of the sun, satellite and building in the present invention；
Fig. 2 is building and the plane graph of shade in the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings and the present invention is conducted further description by embodiment:
As shown in Figure 1-2, a kind of architectural shadow identifies and model covering method automatically, comprises the following steps:
1, the isoparametric extraction of shade and optimization
1.1 according to the feature of image zones of different and the rectangular histogram of correspondence and select several groups of optimum threshold values, generally 2-4 Group threshold value.Use each threshold value to be respectively divided image, extract dash area, the shade that comprehensive each threshold value is extracted, generate original the moon Shadow figure.
1.2 generate mask by the result drawn, process the original echo generated in step 1, generate the echo optimized. This part mainly deletes the parts influential on shade such as vegetation, building, and road.
1.3 utilize area features for the echo optimized, the bound threshold value of setting area size, and area is more than setting The dash area of upper limit threshold is deleted, and area is deleted less than the dash area setting lower threshold.
1.4 remove, further with morphological characteristic, the water body being mingled in shade.
2, the calculating of depth of building and statistical analysis
The echo binaryzation that will finally obtain, utilizes programmingCalculate hypographous length in figure, this reality Execute example only to be recorded by the shadow length retrieving shade and building border on the building of correspondence.Utilize formula ht=Su tan θuCalculate the depth of building that each shadow length is corresponding.
In FIG, θe: satellite transducing signal and ground angle；θu、Day ground angle；Se: satellite-signal covers distance； Su: shadow distance is poor；St: daylight shadow distance；Ht: depth of building.
3, height extracts the precision test of result
The effective percentage (effectiverate) (R) that depth of building extracts is defined as:Wherein C be The building number extracted in figure；T is the number of actual measurement building.So Tanggu area building extracts effective percentage it is 96.8%.Calculate each statistics height value relatively to survey the mean square error (MSF) of height value and determine the precision extracting height.
MSE = 1 n Σ i = 1 n ( x i - H i ) 2
4, coupling is obtained from data base
Finally carry out the Data Matching of data base, according to shadow extraction, calculate corresponding depth of building and get Associated coordinate information, carries out the coupling of data base.Thus get the 3D model matched.
It should be appreciated that for those of ordinary skills, can be improved according to the above description or be converted, And all these modifications and variations all should belong to the protection domain of claims of the present invention.
Above in conjunction with accompanying drawing, patent of the present invention is carried out exemplary description, it is clear that the realization of patent of the present invention is not subject to The restriction of aforesaid way, if the various improvement that the method design that have employed patent of the present invention is carried out with technical scheme, or without Improve and design and the technical scheme of patent of the present invention are directly applied to other occasion, the most within the scope of the present invention.

Claims (5)

1. architectural shadow identifies and model covering method automatically, it is characterised in that comprise the following steps:
The isoparametric extraction of S1: shade and optimization；
The calculating of S2: depth of building and statistical analysis；
S3: height extracts the precision test of result；
S4: obtain coupling from data base.
Architectural shadow the most according to claim 1 identifies and model covering method automatically, it is characterised in that described step S1 Specifically include:
S11: according to the feature of image zones of different and the rectangular histogram of correspondence and the some threshold values selecting optimum, use each threshold value to divide Do not divide image, extract dash area, the shade that comprehensive each threshold value is extracted, generate original echo；
S12: generate mask by the result drawn, processes the original echo generated in step S11, generates the echo optimized；
S13: the echo for optimizing utilizes area features, the bound threshold value of setting area size, area is more than in setting The dash area of limit threshold value is deleted, and area is deleted less than the dash area setting lower threshold；
S14: remove the water body being mingled in shade further with morphological characteristic.
Architectural shadow the most according to claim 1 identifies and model covering method automatically, it is characterised in that described step S2 Particularly as follows: the echo binaryzation that will finally obtain, utilize hypographous length in following formula calculating figure:
S u = n × r cosφ s
The shadow length retrieving shade and building border be recorded on the building of correspondence, utilize following formula to calculate each shade The depth of building that length is corresponding:
ht=Su tanθu
Wherein, SuFor daylight shade and the range difference of building effects, htFor the height of building,θuFor sunlight and ground Angle.
Architectural shadow the most according to claim 1 identifies and model covering method automatically, it is characterised in that described step S3 Particularly as follows:
The effective percentage R that depth of building extracts is defined as:
R = C T × 100 %
Wherein C is the building number extracted in the drawings, and T is the number of actual measurement building,
Utilize following formula to calculate each statistics height value and relatively survey mean square error MSF of height value, and then determine extraction height Precision:
M S E = 1 n Σ i = 1 n ( x i - H i ) 2 .
Architectural shadow the most according to claim 1 identifies and model covering method automatically, it is characterised in that described step S4 Particularly as follows:
Carry out the Data Matching of data base, according to shadow extraction, calculate corresponding depth of building associated to get Coordinate information, carry out the coupling of data base, thus get the 3D model matched.
CN201610330303.9A 2016-05-18 2016-05-18 Automatic identification and model coverage method for building shadows Active CN106022257B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610330303.9A CN106022257B (en) 2016-05-18 2016-05-18 Automatic identification and model coverage method for building shadows

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610330303.9A CN106022257B (en) 2016-05-18 2016-05-18 Automatic identification and model coverage method for building shadows

Publications (2)

Publication Number Publication Date
CN106022257A true CN106022257A (en) 2016-10-12
CN106022257B CN106022257B (en) 2023-05-26

Family

ID=57097713

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610330303.9A Active CN106022257B (en) 2016-05-18 2016-05-18 Automatic identification and model coverage method for building shadows

Country Status (1)

Country Link
CN (1) CN106022257B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108765488A (en) * 2018-03-29 2018-11-06 武汉大学 A kind of high-resolution remote sensing image depth of building estimating and measuring method based on shade

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10269347A (en) * 1997-01-27 1998-10-09 N T T Data Tsushin Kk Method for eliminating shade shadow element on geographic image, geographic image processor and recording medium
US20070115284A1 (en) * 2005-11-24 2007-05-24 Inha-Industry Partnership Institute Method of extracting 3D building information using shadow analysis
CN104463868A (en) * 2014-12-05 2015-03-25 北京师范大学 Rapid building height obtaining method based on parameter-free high-resolution image
CN105528596A (en) * 2016-02-03 2016-04-27 长江大学 High-resolution remote sensing image building automatic extraction method and system by using shadow

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10269347A (en) * 1997-01-27 1998-10-09 N T T Data Tsushin Kk Method for eliminating shade shadow element on geographic image, geographic image processor and recording medium
US20070115284A1 (en) * 2005-11-24 2007-05-24 Inha-Industry Partnership Institute Method of extracting 3D building information using shadow analysis
CN104463868A (en) * 2014-12-05 2015-03-25 北京师范大学 Rapid building height obtaining method based on parameter-free high-resolution image
CN105528596A (en) * 2016-02-03 2016-04-27 长江大学 High-resolution remote sensing image building automatic extraction method and system by using shadow

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108765488A (en) * 2018-03-29 2018-11-06 武汉大学 A kind of high-resolution remote sensing image depth of building estimating and measuring method based on shade
CN108765488B (en) * 2018-03-29 2022-03-04 武汉大学 A shadow-based high-resolution remote sensing image building height estimation method

Also Published As

Publication number Publication date
CN106022257B (en) 2023-05-26

Similar Documents

Publication Publication Date Title
Wu et al. Automated delineation of karst sinkholes from LiDAR-derived digital elevation models
Choi et al. An automatic approach for tree species detection and profile estimation of urban street trees using deep learning and Google street view images
Rientjes et al. Changes in land cover, rainfall and stream flow in Upper Gilgel Abbay catchment, Blue Nile basin–Ethiopia
CN102819023B (en) Method and system of landslide recognition of complicated geological background area based on LiDAR
WO2019153746A1 (en) Geological linear body extraction method based on tensor voting coupled with hough transform
CN104361582B (en) Method of detecting flood disaster changes through object-level high-resolution SAR (synthetic aperture radar) images
CN101832769B (en) Method and system for estimating vegetation coverage degree in diggings based on close-up photography
CN103063311B (en) Nudity bed rock information extraction method based on soil index
CN103020649A (en) Forest type identification method based on texture information
Huang et al. Differentiating tower karst (fenglin) and cockpit karst (fengcong) using DEM contour, slope, and centroid
CN104299009A (en) Plate number character recognition method based on multi-feature fusion
CN105389799B (en) SAR image object detection method based on sketch map and low-rank decomposition
CN106251355A (en) A kind of detection method merging visible images and corresponding night vision infrared image
CN108898096B (en) A fast and accurate information extraction method for high-resolution images
CN107301512A (en) A kind of Rural Landscape sensitivity assessment analysis method based on 3S technologies
Mutayoba et al. Assessing the impacts of land use and land cover changes on hydrology of the Mbarali River Sub-Catchment. The Case of Upper Great Ruaha Sub-Basin, Tanzania
CN115344815A (en) Natural runoff change attribution analysis method and system considering vegetation space change
CN105913426A (en) ZY-3 image-based shallow lake seine zone extraction method
CN108648200B (en) An indirect urban high-resolution impervious surface extraction method
CN106022257A (en) Building shadow automatic recognition and model covering method
CN111861838B (en) Method and system for discriminating forest degradation cause in mountain area
CN116665070B (en) Terrace remote sensing identification method integrating jump network and Mask R-CNN model
CN112380994A (en) Artificial forest spatial pattern recognition method based on time sequence classification and spatial analysis
CN117115671A (en) Soil quality analysis method and device based on remote sensing and electronic equipment
CN108228920B (en) A screening method for abnormal uranium element in soil of sandstone-type uranium deposits

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: Room 602, Building 13, Shenzhen Software Park, Keji Middle 2nd Road, Nanshan District, Shenzhen City, Guangdong Province, 518000

Applicant after: Shenzhou Dragon Space Technology (Shenzhen) Co.,Ltd.

Address before: Room 602, Building 13, Shenzhen Software Park, Keji Middle 2nd Road, Nanshan District, Shenzhen City, Guangdong Province, 518000

Applicant before: SHENZHEN SHENZHOULONG INFORMATION SERVICES CO.,LTD.

GR01 Patent grant
GR01 Patent grant