METHOD AND DEVICE FOR DETERMINATION OF WEAR PART LOCATION ON WORKING TOOL IMAGE Russian patent published in 2020 - IPC G06T7/00 G06N3/02 G06N3/08 E21C35/00 E02F3/04 

Abstract RU 2713684 C2

FIELD: physics.

SUBSTANCE: group of inventions relates to image processing for determination of wear part location on working tool image. Device for location of wear part on working tool image includes image sensor for gripping at least one image of working tool during operation of heavy equipment, wherein the image comprises a plurality of pixels, each having a defined brightness value, a processing circuit configured to: select consecutive subsets of pixels from a plurality of pixels; processing each subset of pixels to determine whether pixel brightness values from a subset of pixels satisfy a matching criterion which indicates a probability that a subset of pixels corresponds to a wear part. Processing of each subset of pixels includes processing of each subset of pixels by means of the corresponding multiple input nodes of the neural network, each input unit has the weight assigned to it and is capable of creating weighted output signals in response to the received brightness value. A compliance criterion is based on processing of the marked plurality of training images during the training exercise prior to capturing at least one image of the working tool, wherein the training exercise enables to determine assigned weights for a plurality of input nodes.

EFFECT: technical result is faster installation in commissioning, high reliability of monitoring system wearing parts.

32 cl, 20 dwg

Similar patents RU2713684C2

Title Year Author Number
METHOD, APPARATUS AND SYSTEM FOR MONITORING THE WORKING CONDITION OF HEAVY MACHINERY SUCH AS A MINING EXCAVATOR 2018
  • Tafazoli Bilandi, Shakhram
  • Ramezani, Makhdi
  • Nuranian, Saman
  • Smit, Kennet
  • Gavidel, Saar
  • Sameti, Mokhammad
RU2772929C1
METHOD AND APPARATUS FOR IDENTIFYING PORTIONS OF FRAGMENTED MATERIAL WITHIN AN IMAGE 2016
  • Tafazoli Bilandi, Shakhram
  • Ramezani, Makhdi
  • Bell, Yan Lo
  • Sameti, Mokhammad
  • Abolmaesumi, Purang
  • Nuranian, Seman
RU2694021C1
DETECTING AND IDENTIFYING OBJECTS ON IMAGES 2020
  • Ivan Zagaynov
  • Andrew Zharkov
RU2726185C1
SYSTEM AND METHOD OF DETECTING WEAR AND LOSS OF EARTHMOVING EQUIPMENT 2021
  • Petrany, Peter Joseph
  • Ram, Shastri
RU2820623C1
NEURAL NETWORK FOR GENERATING SYNTHETIC MEDICAL IMAGES 2017
  • Han, Xiao
RU2698997C1
SYSTEM FOR IDENTIFYING FRESH PRODUCTS FOR A RETAIL TRADE CASH TERMINAL 2018
  • Herz Marcel
  • Sampson Christopher
RU2769888C2
METHOD OF GENERATING A COMMON LOSS FUNCTION FOR TRAINING A CONVOLUTIONAL NEURAL NETWORK FOR CONVERTING AN IMAGE INTO AN IMAGE WITH DRAWN PARTS AND A SYSTEM FOR CONVERTING AN IMAGE INTO AN IMAGE WITH DRAWN PARTS 2019
  • Shcherbinin Andrei Yurievich
  • Anisimovskiy Valery Valerievich
  • Biryulin Pavel Igorevich
RU2706891C1
AUTOMATIC DETERMINATION OF SET OF CATEGORIES FOR DOCUMENT CLASSIFICATION 2018
  • Nikita Orlov
  • Konstantin Anisimovich
RU2701995C2
METHOD OF PROCESSING MAGNETIC RESONANCE IMAGING IMAGES FOR GENERATING TRAINING DATA 2023
  • Danilov Aleksej Nikolaevich
  • Lavrikov Aleksandr Vladimirovich
RU2813480C1
RECONSTRUCTION OF THE DOCUMENT FROM DOCUMENT IMAGE SERIES 2017
  • Loginov Vasilij Vasilevich
  • Zagajnov Ivan Germanovich
  • Karatsapova Irina Aleksandrovna
RU2659745C1

RU 2 713 684 C2

Authors

Tafazoli Bilandi Shakhram

Ramezani Makhdi

Suzani Amin

Parnian Neda

Baumann Mettyu Aleksandr

Nuranian Saman

Khamtsej Nazanin

Sameti Mokhammad

Karimifard Said

Dates

2020-02-06Published

2016-05-13Filed