WO2022146343A1 - A system used for identifying geo-assets - Google Patents

A system used for identifying geo-assets Download PDF

Info

Publication number
WO2022146343A1
WO2022146343A1 PCT/TR2021/051409 TR2021051409W WO2022146343A1 WO 2022146343 A1 WO2022146343 A1 WO 2022146343A1 TR 2021051409 W TR2021051409 W TR 2021051409W WO 2022146343 A1 WO2022146343 A1 WO 2022146343A1
Authority
WO
WIPO (PCT)
Prior art keywords
server
electronic device
image
data
plans
Prior art date
Application number
PCT/TR2021/051409
Other languages
French (fr)
Inventor
Agit OKTAY
Erkut GENCER
Serkan GAZEL
Original Assignee
Netcad Yazilim Anonim Sirketi
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 Netcad Yazilim Anonim Sirketi filed Critical Netcad Yazilim Anonim Sirketi
Publication of WO2022146343A1 publication Critical patent/WO2022146343A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/56—Information retrieval; Database structures therefor; File system structures therefor of still image data having vectorial format

Definitions

  • the present invention relates to a system which enables to vectorize zoning plans and/or cadastral plans that are converted into raster format and to present these as data comprising coordinate, particularly in land surveying and planning fields.
  • the said invention provides a map vectorization sample enhancement method and system based on a generative adversarial network and it comprises the following steps: SI, preprocessing an image map; s2, constructing a generative adversarial network and training a sample generation model; s3, calibrating a self-sample; s4, generating a sample substrate; and s5, carrying out sample combination enhancement.
  • SI preprocessing an image map
  • s2 constructing a generative adversarial network and training a sample generation model
  • s3, calibrating a self-sample s4, generating a sample substrate
  • s5 carrying out sample combination enhancement.
  • the lightweight sample set of the self data of the image map is manufactured; the space of the effective sample set is greatly expanded by constructing a deep learning model of the generative adversarial network, so that the space can meet the data volume requirement of a deep learning training image vectorization model.
  • the method provided by the invention compared with the traditional process of realizing vectorization of the image map manually/semi-automatically, the method provided by the invention only needs to plot a small amount of initial samples manually and subsequently generates massive training samples meeting requirements in a full-automatic manner, thereby it provides powerful technical support for research and application of vectorization of the image map.
  • An objective of the present invention is to realize a system which enables to vectorize zoning plans and/or cadastral plans, that are converted from paper into raster format, by means of deep learning methods automatically and to present these as coordinated data.
  • Another objective of the present invention is to realize a system which enables to train symbology, types of line, fonts of cadastral and plan assets and geo- definitions specific to zoning plans, and to perform vectorization thereof automatically.
  • Another objective of the present invention is to realize a system which enables to use sheets and plans generated by means of graphic methods, as a base upon scanning.
  • Another objective of the present invention is to realize a system which enables to make images, that are difficult to be comprehended by citizens due to their symbology, understandable.
  • Another objective of the present invention is to realize a system which enables to subject scanned plans wherein wear, tear and deformation occurred, to image filtering transactions prior to a digitization transaction and to eliminate the noises in an image.
  • Another objective of the present invention is to realize a system which enables to provide speed, labour savings and to eliminate human-induced errors.
  • Figure 1 is a schematic view of the inventive system used for identifying geo-assets.
  • the inventive system (1) for vectorizing zoning plans and/or cadastral plans, in land surveying and planning fields comprises:
  • At least one electronic device (2) which is configured to receive scanned plans, that are aimed to be vectorised, and to run at least one application on it;
  • At least one database (3) which is configured to keep record of deep learning models that are geo-asset identifiers to be used for processing the images received by means of the electronic device (2);
  • At least one server (4) which is configured to be in communication with the electronic device (2) and the database (3), to receive the image that is aimed to be vectorized over the electronic device (2) via this communication established, to subject the received image to a noise removal transaction at first, to make asset definitions on the image by processing the processed image by means of deep learning models, to carry out vectorization transaction of the image and to ensure that the vectorized data is shared with the user over the electronic device (2).
  • the electronic device (2) is a device such as smartphone, tablet computer, desktop computer, laptop configured to run at least one application on it and to receive the data to be subjected to a vectorization transaction from the user.
  • the electronic device (2) is configured to be in communication with the server (4) and to share the plans to be processed that it receives over an application, a web service, a web application or a desktop module with the server (4) via this communication established.
  • the database (3) is configured to be in communication with the server (4) and to present the deep learning models to be used for processing the plans received by means of the electronic device (2), to the server (4) via this communication established.
  • the database (3) is configured to comprise a training service in order to classify and diversify geo-asset identifiers in the event that the plans to be processed in the server (4) vary.
  • the server (4) can carry out vectorization transaction by processing the plan according to symbology and plan/cadastral data of each country.
  • the server (4) is configured to use cloud technology, to communicate with the electronic device (2) by using any remote communication protocol included in the state of the art and to receive the data input over the electronic device (2) via this communication established.
  • the server (4) is configured to ensure that transactions of data control and admission, image pre-processing, data storage transactions and user management are carried out on the data received over the electronic device (2); images are vectorized by means of deep learning; and geo-asset statistics are produced.
  • the server (4) is configured to perform Raster-Bitmap conversion over the scanned image it receives over the electronic device (2) and to eliminate the noise in the image.
  • the server (4) is configured to use smoothing filters in order to eliminate the noise in an image, to clear small spots and meaningless elements.
  • the server (4) is also configured to use filter in order to clear grey-tone pixels by sharpening linear elements and to make the image black and white.
  • the server (4) is configured to use Canny edge detection algorithm in order to determine edges of closed spaces and to convert areal elements into a linear form.
  • the server (4) is configured to use Moore Neighbour Tracing algorithm in order to extract contour information of pixel groups on an image that include black pixel groups having white background.
  • the server (4) is configured to complete vectorization transaction by calculating the environment and space information of a given pixel group according to the contour information obtained.
  • the server (4) is also configured to share the vectorized data with its coordinate data.
  • the server (4) is configured to ensure that definitions are made on a plan over assets and symbologies to be detected in a modelling transaction according to generation of CNN (Convolutional Neural Networkt) engine and type of symbology.
  • the server (4) is configured to ensure that an identifier convolutional vector is obtained for an asset to be learned by using a different number of convolutional layers.
  • a CNN (Convolutional Neural Networkt) model is developed for an asset included in each plan.
  • the server (4) is configured to be in communication with a spatial data platform in order to carry out many identification and classification transactions for ensuring that a plurality of assets are identified, and to realize data exchange over this communication established.
  • the server (4) is configured to ensure that plans are served over a spatial data platform wherein kubemetes is used.
  • the inventive system (1) it is ensured to train cadastral and planning assets by using deep learning techniques and their vectorization is provided automatically.
  • the system (1) can be used by surveying, planning offices, local administrations, related government offices and citizens.
  • the inventive system (1) also turns land registry and cadastre data into a digital base upon transferring these to a digital media and scanning sheets and plans that are generated by means of graphical methods.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The present invention relates to a system (1) which enables to vectorize zoning plans and/or cadastral plans that are converted into raster format and to present these as data comprising coordinate, particularly in land surveying and planning fields.

Description

A SYSTEM USED FOR IDENTIFYING GEO-ASSETS
Technical Field
The present invention relates to a system which enables to vectorize zoning plans and/or cadastral plans that are converted into raster format and to present these as data comprising coordinate, particularly in land surveying and planning fields.
Background of the Invention
Plans and map bases are one of the most important components of smart cities. However, digitization of non-numeric data is one of the major obstacles for smart cities. Today, semi-automatic algorithms with manual or pixel tracking are used in order to digitize paper sheets or plans. Vectorization of data -such as usually zoning plan, cadastral plan- which are provided on paper or converted into raster format upon being scanned, manually or semi-automatically is a transaction requiring time and labour. At the same time, vectorization transaction is a quite error-prone process. Data which are processed by means of semi-automatic methods comprise only point, line, field information apart from plan or cadastral field information and then definitions of these interim outputs such as block, plot, residential area are carried out by operators. In addition, the precision of human eye to distinguish is 0,2 mm. And this leads to the fact that it takes about two days to make a plan manually by a human and it causes defects in the precision of a plan based on the fact that the person carrying out the plan gets tired as well. Therefore, today there is need for a solution which enables to perform transaction of digitizing zoning plans and/or cadastral plans -that are converted into raster format- automatically independently of human, in land surveying and planning fields. The Chinese patent document no. CN111626947A, an application in the state of the art, discloses a system and method for vectorising map contents in an image format on a network, semi-automatically by using deep learning. The said invention provides a map vectorization sample enhancement method and system based on a generative adversarial network and it comprises the following steps: SI, preprocessing an image map; s2, constructing a generative adversarial network and training a sample generation model; s3, calibrating a self-sample; s4, generating a sample substrate; and s5, carrying out sample combination enhancement. According to the invention, the lightweight sample set of the self data of the image map is manufactured; the space of the effective sample set is greatly expanded by constructing a deep learning model of the generative adversarial network, so that the space can meet the data volume requirement of a deep learning training image vectorization model. In the disclosed invention, compared with the traditional process of realizing vectorization of the image map manually/semi-automatically, the method provided by the invention only needs to plot a small amount of initial samples manually and subsequently generates massive training samples meeting requirements in a full-automatic manner, thereby it provides powerful technical support for research and application of vectorization of the image map.
Summary of the Invention
An objective of the present invention is to realize a system which enables to vectorize zoning plans and/or cadastral plans, that are converted from paper into raster format, by means of deep learning methods automatically and to present these as coordinated data.
Another objective of the present invention is to realize a system which enables to train symbology, types of line, fonts of cadastral and plan assets and geo- definitions specific to zoning plans, and to perform vectorization thereof automatically.
Another objective of the present invention is to realize a system which enables to use sheets and plans generated by means of graphic methods, as a base upon scanning.
Another objective of the present invention is to realize a system which enables to make images, that are difficult to be comprehended by citizens due to their symbology, understandable.
Another objective of the present invention is to realize a system which enables to subject scanned plans wherein wear, tear and deformation occurred, to image filtering transactions prior to a digitization transaction and to eliminate the noises in an image.
Another objective of the present invention is to realize a system which enables to provide speed, labour savings and to eliminate human-induced errors.
Detailed Description of the Invention
“A System Used for Identifying Geo- Assets” realized to fulfil the objectives of the present invention is shown in the figure attached, in which:
Figure 1 is a schematic view of the inventive system used for identifying geo-assets.
The components illustrated in the figure are individually numbered, where the numbers refer to the following: 1. System
2. Electronic device
3. Database
4. Server
The inventive system (1) for vectorizing zoning plans and/or cadastral plans, in land surveying and planning fields comprises:
- at least one electronic device (2) which is configured to receive scanned plans, that are aimed to be vectorised, and to run at least one application on it;
- at least one database (3) which is configured to keep record of deep learning models that are geo-asset identifiers to be used for processing the images received by means of the electronic device (2); and
- at least one server (4) which is configured to be in communication with the electronic device (2) and the database (3), to receive the image that is aimed to be vectorized over the electronic device (2) via this communication established, to subject the received image to a noise removal transaction at first, to make asset definitions on the image by processing the processed image by means of deep learning models, to carry out vectorization transaction of the image and to ensure that the vectorized data is shared with the user over the electronic device (2).
In the inventive system (1), the electronic device (2) is a device such as smartphone, tablet computer, desktop computer, laptop configured to run at least one application on it and to receive the data to be subjected to a vectorization transaction from the user. The electronic device (2) is configured to be in communication with the server (4) and to share the plans to be processed that it receives over an application, a web service, a web application or a desktop module with the server (4) via this communication established. In the inventive system (1), the database (3) is configured to be in communication with the server (4) and to present the deep learning models to be used for processing the plans received by means of the electronic device (2), to the server (4) via this communication established. The database (3) is configured to comprise a training service in order to classify and diversify geo-asset identifiers in the event that the plans to be processed in the server (4) vary. Thus, the server (4) can carry out vectorization transaction by processing the plan according to symbology and plan/cadastral data of each country.
In the inventive system (1), the server (4) is configured to use cloud technology, to communicate with the electronic device (2) by using any remote communication protocol included in the state of the art and to receive the data input over the electronic device (2) via this communication established. The server (4) is configured to ensure that transactions of data control and admission, image pre-processing, data storage transactions and user management are carried out on the data received over the electronic device (2); images are vectorized by means of deep learning; and geo-asset statistics are produced. The server (4) is configured to perform Raster-Bitmap conversion over the scanned image it receives over the electronic device (2) and to eliminate the noise in the image. The server (4) is configured to use smoothing filters in order to eliminate the noise in an image, to clear small spots and meaningless elements. The server (4) is also configured to use filter in order to clear grey-tone pixels by sharpening linear elements and to make the image black and white. The server (4) is configured to use Canny edge detection algorithm in order to determine edges of closed spaces and to convert areal elements into a linear form. The server (4) is configured to use Moore Neighbour Tracing algorithm in order to extract contour information of pixel groups on an image that include black pixel groups having white background. The server (4) is configured to complete vectorization transaction by calculating the environment and space information of a given pixel group according to the contour information obtained. The server (4) is also configured to share the vectorized data with its coordinate data.
In the inventive system (1), the server (4) is configured to ensure that definitions are made on a plan over assets and symbologies to be detected in a modelling transaction according to generation of CNN (Convolutional Neural Networkt) engine and type of symbology. The server (4) is configured to ensure that an identifier convolutional vector is obtained for an asset to be learned by using a different number of convolutional layers. In the inventive system (1), a CNN (Convolutional Neural Networkt) model is developed for an asset included in each plan.
In the inventive system (1), the server (4) is configured to be in communication with a spatial data platform in order to carry out many identification and classification transactions for ensuring that a plurality of assets are identified, and to realize data exchange over this communication established. In a preferred embodiment, the server (4) is configured to ensure that plans are served over a spatial data platform wherein kubemetes is used.
With the inventive system (1), it is ensured to train cadastral and planning assets by using deep learning techniques and their vectorization is provided automatically. The system (1) can be used by surveying, planning offices, local administrations, related government offices and citizens. The inventive system (1) also turns land registry and cadastre data into a digital base upon transferring these to a digital media and scanning sheets and plans that are generated by means of graphical methods.
Within these basic concepts; it is possible to develop various embodiments of the inventive “System Used for Identifying Geo-Assets (1)”; the invention cannot be limited to examples disclosed herein and it is essentially according to claims.

Claims

1. A system (1) for vectorizing zoning plans and/or cadastral plans, in land surveying and planning fields; characterized by
- at least one electronic device (2) which is configured to receive scanned plans, that are aimed to be vectorised, and to run at least one application on it;
- at least one database (3) which is configured to keep record of deep learning models that are geo-asset identifiers to be used for processing the images received by means of the electronic device (2); and
- at least one server (4) which is configured to be in communication with the electronic device (2) and the database (3), to receive the image that is aimed to be vectorized over the electronic device (2) via this communication established, to subject the received image to a noise removal transaction at first, to make asset definitions on the image by processing the processed image by means of deep learning models, to carry out vectorization transaction of the image and to ensure that the vectorized data is shared with the user over the electronic device (2).
2. A system (1) according to Claim 1; characterized by the electronic device (2) which is a device such as smartphone, tablet computer, desktop computer, laptop configured to run at least one application on it and to receive the data to be subjected to a vectorization transaction from the user.
3. A system (1) according to Claim 1 or 2; characterized by the electronic device (2) which is configured to be in communication with the server (4) and to share the plans to be processed that it receives over an application, a web service, a web application or a desktop module, with the server (4) via this communication established.
7
4. A system (1) according to any of the preceding claims; characterized by the database (3) which is configured to be in communication with the server (4) and to present the deep learning models to be used for processing the plans received by means of the electronic device (2), to the server (4) via this communication established.
5. A system (1) according to any of the preceding claims; characterized by the database (3) which is configured to comprise a training service in order to classify and diversify geo-asset identifiers in the event that the plans to be processed in the server (4) vary.
6. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to use cloud technology, to communicate with the electronic device (2) by using any remote communication protocol included in the state of the art and to receive the data input over the electronic device (2) via this communication established.
7. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to ensure that transactions of data control and admission, image pre-processing, data storage transactions and user management are carried out on the data received over the electronic device (2); images are vectorized by means of deep learning; and geo-asset statistics are produced.
8. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to perform Raster-Bitmap conversion over the scanned image it receives over the electronic device (2) and to eliminate the noise in the image.
8
9. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to use smoothing filters in order to eliminate the noise in an image, to clear small spots and meaningless elements.
10. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to use filter in order to clear grey-tone pixels by sharpening linear elements and to make the image black and white.
11. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to use Canny edge detection algorithm in order to determine edges of closed spaces and to convert areal elements into a linear form.
12. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to use Moore Neighbour Tracing algorithm in order to extract contour information of pixel groups on an image that include black pixel groups having white background.
13. A system (1) according to Claim 12; characterized by the server (4) which is configured to complete vectorization transaction by calculating the environment and space information of a given pixel group according to the contour information obtained.
14. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to share the vectorized data with its coordinate data.
15. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to ensure that definitions are made on a plan over assets and symbologies to be detected in a modelling transaction according to
9 generation of CNN (Convolutional Neural Network!) engine and type of symbology.
16. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to ensure that an identifier convolutional vector is obtained for an asset to be learned by using a different number of convolutional layers.
17. A system (1) according to any of the preceding claims; characterized by the server (4) which is configured to be in communication with a spatial data platform in order to carry out many identification and classification transactions for ensuring that a plurality of assets are identified, and to realize data exchange over this communication established.
10
PCT/TR2021/051409 2020-12-31 2021-12-14 A system used for identifying geo-assets WO2022146343A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2020/22658A TR202022658A1 (en) 2020-12-31 2020-12-31 A SYSTEM USED TO RECOGNIZE GROUND ASSETS
TR2020/22658 2020-12-31

Publications (1)

Publication Number Publication Date
WO2022146343A1 true WO2022146343A1 (en) 2022-07-07

Family

ID=82261005

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2021/051409 WO2022146343A1 (en) 2020-12-31 2021-12-14 A system used for identifying geo-assets

Country Status (2)

Country Link
TR (1) TR202022658A1 (en)
WO (1) WO2022146343A1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030040893A1 (en) * 2001-03-13 2003-02-27 Lascar Popovici Method and system of vectorial cartography
CN111626947A (en) * 2020-04-27 2020-09-04 国家电网有限公司 Map vectorization sample enhancement method and system based on generation of countermeasure network

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030040893A1 (en) * 2001-03-13 2003-02-27 Lascar Popovici Method and system of vectorial cartography
CN111626947A (en) * 2020-04-27 2020-09-04 国家电网有限公司 Map vectorization sample enhancement method and system based on generation of countermeasure network

Also Published As

Publication number Publication date
TR202022658A1 (en) 2022-07-21

Similar Documents

Publication Publication Date Title
Crommelinck et al. Review of automatic feature extraction from high-resolution optical sensor data for UAV-based cadastral mapping
Heipke et al. Deep learning for geometric and semantic tasks in photogrammetry and remote sensing
Basavaprasad et al. A study on the importance of image processing and its applications
CN111931664A (en) Mixed note image processing method and device, computer equipment and storage medium
Roeder et al. A computational image analysis glossary for biologists
DE112016004535T5 (en) Universal Compliance Network
Türkyılmaz et al. License plate recognition system using artificial neural networks
CN112529015A (en) Three-dimensional point cloud processing method, device and equipment based on geometric unwrapping
CN110210503B (en) Seal identification method, device and equipment
CN113011144B (en) Form information acquisition method, device and server
CN111046774A (en) Chinese signature handwriting identification method based on convolutional neural network
CN110781890A (en) Identification card identification method and device, electronic equipment and readable storage medium
CN109784171A (en) Car damage identification method for screening images, device, readable storage medium storing program for executing and server
CN108256520B (en) Method for identifying coin year, terminal equipment and computer readable storage medium
CN110135218A (en) The method, apparatus, equipment and computer storage medium of image for identification
Li et al. Sketch-to-photo face generation based on semantic consistency preserving and similar connected component refinement
Bilan et al. Image processing and pattern recognition based on parallel shift technology
Duque-Domingo et al. Deciphering egyptian hieroglyphs: Towards a new strategy for navigation in museums
CN105741171A (en) Character feature image processing method for credit reference systems and credit reference system
CN109886320B (en) Human femoral X-ray intelligent recognition method and system
WO2022146343A1 (en) A system used for identifying geo-assets
CN111414889A (en) Financial statement identification method and device based on character identification
CN110598702A (en) Preparation method, system, equipment and medium of ship target detection data set
WO2022156652A1 (en) Vehicle motion state evaluation method and apparatus, device, and medium
US11854185B2 (en) Individual identification apparatus

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21916025

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21916025

Country of ref document: EP

Kind code of ref document: A1