FR3104759B1 - Location of electrical network elements in aerial images - Google Patents

Location of electrical network elements in aerial images Download PDF

Info

Publication number
FR3104759B1
FR3104759B1 FR1914221A FR1914221A FR3104759B1 FR 3104759 B1 FR3104759 B1 FR 3104759B1 FR 1914221 A FR1914221 A FR 1914221A FR 1914221 A FR1914221 A FR 1914221A FR 3104759 B1 FR3104759 B1 FR 3104759B1
Authority
FR
France
Prior art keywords
location
convolution kernel
training database
network elements
electrical network
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.)
Active
Application number
FR1914221A
Other languages
French (fr)
Other versions
FR3104759A1 (en
Inventor
Pierre Stephan
Joris Guerry
Quentin Bion
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.)
Electricite de France SA
Original Assignee
Electricite de France SA
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 Electricite de France SA filed Critical Electricite de France SA
Priority to FR1914221A priority Critical patent/FR3104759B1/en
Publication of FR3104759A1 publication Critical patent/FR3104759A1/en
Application granted granted Critical
Publication of FR3104759B1 publication Critical patent/FR3104759B1/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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Processing Or Creating Images (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé de remplissage d’une base de données d’entraînement destinée à permettre l’entraînement d’un algorithme de localisation d’un élément de réseau, comprenant les étapes suivantes :génération d’un noyau de convolution, le noyau de convolution étant formé d’une matrice ayant un nombre de lignes et un nombre de colonnes choisis aléatoirement, et enregistrement en mémoire du noyau de convolution,application, à une pluralité de pixels d’au moins une image de zone géographique, d’un filtre de floutage correspondant au noyau de convolution, résultant en une image floutée,ajout de l’image floutée à la base de données d’entraînement, pour obtenir une base de données d’entraînement complétée.La présente invention concerne également un procédé de localisation d’un élément de réseau au sein d’une zone géographique d’intérêt, à l’aide d’un algorithme de localisation préalablement entraîné selon un procédé d’apprentissage comprenant un procédé de remplissage de base de données d’entraînement tel que défini ci-avant. Figure pour l’abrégé : Fig. 2 FIGURESThe present invention relates to a method for filling a training database intended to allow training of an algorithm for locating a network element, comprising the following steps: generation of a convolution kernel, the convolution kernel being formed of a matrix having a number of rows and a number of columns chosen randomly, and recording in memory of the convolution kernel, application, to a plurality of pixels of at least one image of geographical area, of a blurring filter corresponding to the convolution kernel, resulting in a blurred image, adding the blurred image to the training database, to obtain a completed training database. The present invention also relates to a method of location of a network element within a geographical area of interest, using a location algorithm previously trained according to a learning method comprising a method of filling training database as defined above. Figure for the abstract: Fig. 2 FIGURES

FR1914221A 2019-12-12 2019-12-12 Location of electrical network elements in aerial images Active FR3104759B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR1914221A FR3104759B1 (en) 2019-12-12 2019-12-12 Location of electrical network elements in aerial images

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1914221 2019-12-12
FR1914221A FR3104759B1 (en) 2019-12-12 2019-12-12 Location of electrical network elements in aerial images

Publications (2)

Publication Number Publication Date
FR3104759A1 FR3104759A1 (en) 2021-06-18
FR3104759B1 true FR3104759B1 (en) 2021-12-10

Family

ID=70613900

Family Applications (1)

Application Number Title Priority Date Filing Date
FR1914221A Active FR3104759B1 (en) 2019-12-12 2019-12-12 Location of electrical network elements in aerial images

Country Status (1)

Country Link
FR (1) FR3104759B1 (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018038720A1 (en) * 2016-08-24 2018-03-01 Google Inc. Change detection based imagery acquisition tasking system
US10140544B1 (en) * 2018-04-02 2018-11-27 12 Sigma Technologies Enhanced convolutional neural network for image segmentation

Also Published As

Publication number Publication date
FR3104759A1 (en) 2021-06-18

Similar Documents

Publication Publication Date Title
CN109445457B (en) Method for determining distribution information, and method and device for controlling unmanned aerial vehicle
US11048948B2 (en) System and method for counting objects
US11532071B2 (en) Creating super-resolution images
Streit et al. Patchy delivery of functions undermines functional redundancy in a high diversity system
WO2017101690A1 (en) Advertisement detection method and device
US20190156501A1 (en) Three-dimensional reconstruction method using a plenoptic camera
JPWO2020191391A5 (en)
TW200735337A (en) Method and apparatus for setting black level in an imager using both optically black and tied pixels
FR2973162B1 (en) VERY HIGH DYNAMIC IMAGE SENSOR
Chamaillé-Jammes et al. Spatial distribution of a large herbivore community at waterholes: an assessment of its stability over years in Hwange National Park, Zimbabwe
Mackenzie et al. The Shoreline Video Assessment Method (S-VAM): Using dynamic hyperlapse image acquisition to evaluate shoreline mangrove forest structure, values, degradation and threats
MY162211A (en) Method and apparatus for manufacturing a security document comprising a lenticular array and blurred pixel tracks
CN101729778A (en) Image processing apparatus and method
CN103453881A (en) Distance measuring device and distance measuring method
JP2017010534A (en) High capacity 2d color barcode design and processing method for camera based applications
Elleouet et al. A trait‐based approach for assessing and mapping niche overlap between native and exotic species: the M editerranean coastal fish fauna as a case study
DE112010003748B4 (en) METHOD AND APPARATUS FOR IMAGE CORRECTION
Dubuc et al. Patterns of reef fish taxonomic and functional diversity in the Eastern Tropical Pacific
FR3104759B1 (en) Location of electrical network elements in aerial images
Humber et al. Placing Madagascar's marine turtle populations in a regional context using community-based monitoring
Sáenz et al. Value creation through marketing data analytics: The distinct contribution of data analytics assets and capabilities to unit and firm performance
Peng et al. MND-GAN: A research on image deblurring algorithm based on generative adversarial network
CN105989072A (en) Duplicate removal counting method and device
CN114154680A (en) Urban ground collapse prediction method and device and electronic equipment
CN114529483B (en) Data processing method, device, terminal and readable storage medium

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20210618

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

PLFP Fee payment

Year of fee payment: 5

PLFP Fee payment

Year of fee payment: 6