METHOD FOR AUTOMATICALLY RECOGNIZING SCENES AND OBJECTS IN AN IMAGE Russian patent published in 2022 - IPC G06T5/50 G06K9/46 

Abstract RU 2778906 C1

FIELD: objects identifying.

SUBSTANCE: invention relates to the field of identifying objects in an image.

A method for automatically recognizing scenes and objects in an image, in which reference images are formed and stored, the stream of input images is processed to find an object of interest on them, using reference images, characterized in that key points and areas around them are selected on the reference image, after which search on the input image for the corresponding key points of the reference image. Next, descriptors of key points are created, after that, for each key point of the reference image, based on the maximum proximity of the descriptors, the corresponding key point on the current image is determined and, if the proximity size is less than a predetermined threshold, the corresponding key point on the current image is stored, and when the number of corresponding key points on the current image will exceed half of the key points on the reference image, the scene object in the image is considered recognized.

EFFECT: reducing the time and resources required to carry out image processing, as well as increasing the likelihood of detecting objects in the image.

1 cl, 20 dwg

Similar patents RU2778906C1

Title Year Author Number
METHOD AND APPARATUS FOR DETECTING LOCAL FEATURES ON IMAGE 2013
  • Marchuk Vladimir Ivanovich
  • Voronin Vjacheslav Vladimirovich
  • Morozova Tat'Jana Vladimirovna
  • Pis'Menskova Marina Mikhajlovna
RU2535184C2
DEVICE OF SEARCHING IMAGE DUPLICATES 2013
  • Marchuk Vladimir Ivanovich
  • Voronin Vjacheslav Vladimirovich
  • Pis'Menskova Marina Mikhajlovna
  • Morozova Tat'Jana Vladimirovna
RU2538319C1
METHOD AND SYSTEM OF ACCURATE LOCALIZATION OF VISUALLY IMPAIRED OR BLIND PERSON 2017
  • Bunyakov Vladimir Aleksandrovich
  • Zhukov Konstantin Andreevich
  • Kitaev Vitalij Aleksandrovich
RU2681346C2
METHOD OF IDENTIFYING REFERENCE POINTS ON SPACE IMAGES OF AREA IN ABSENCE OF GEOREFERENCING PARAMETERS 2021
  • Borisovskij Sergej Aleksandrovich
  • Orlov Sergej Alekseevich
  • Spirin Andrej Viktorovich
  • Tikhonov Dmitrij Vladimirovich
  • Shuklin Igor Igorevich
RU2768219C1
METHOD FOR AUTOMATIC RECOGNITION OF OBJECTS ON IMAGE 2013
  • Efremov Vladimir Anatol'Evich
  • Tupikov Vladimir Alekseevich
  • Moskovchenko Leonid Vasil'Evich
  • Pavlova Valerija Anatol'Evna
  • Kudrin Mikhail Ivanovich
  • Manannikov Vladimir Vasil'Evich
  • Sozinova Marija Vladimirovna
  • Krjukov Sergej Nikolaevich
RU2528140C1
METHOD OF IDENTIFICATION OF SUPPORTING POINTS ON SPACE IMAGES OF TERRAIN DURING TRANSFORMATION THEREOF 2018
  • Shuklin Igor Igorevich
  • Borisovskij Sergej Aleksandrovich
  • Borisovskij Igor Aleksandrovich
RU2683626C1
METHOD OF FINDING CORRESPONDING PARTICULAR POINTS OF DIGITAL IMAGES 2015
  • Medvedev Mikhail Viktorovich
  • Shlejmovich Mikhail Petrovich
  • Gomzin Aleksandr Vladislavovich
  • Saleev Arkadij Borisovich
RU2614494C2
METHOD FOR INTELLIGENT PROCESSING OF ARRAY OF NON-UNIFORM IMAGES 2021
  • Katin Vyacheslav Viktorovich
  • Charovskij Maksim Aleksandrovich
  • Lupanchuk Vladimir Yurevich
  • Skiba Valerij Aleksandrovich
  • Zajtsev Aleksandr Vladimirovich
  • Danilochev Dmitrij Valerevich
  • Shikhovtsev Aleksandr Leonidovich
  • Lazarev Viktor Mikhajlovich
  • Struchkov Ivan Evgenevich
  • Kulak Aleksandr Viktorovich
RU2767281C1
AUTOMATED METHODS AND SYSTEMS OF IDENTIFYING IMAGE FRAGMENTS IN DOCUMENT-CONTAINING IMAGES TO FACILITATE EXTRACTION OF INFORMATION FROM IDENTIFICATED DOCUMENT-CONTAINING IMAGE FRAGMENTS 2016
  • Zagaynov Ivan Germanovich
  • Borin Pavel Valerievich
RU2647670C1
METHOD OF RECOGNISING OBJECTS 2010
  • Vrazhnov Denis Aleksandrovich
  • Shapovalov Aleksandr Vasil'Evich
RU2438174C1

RU 2 778 906 C1

Authors

Tupikov Vladimir Alekseevich

Pavlova Valeriya Anatolevna

Kryukov Sergej Nikolaevich

Bondarenko Vladimir Aleksandrovich

Dates

2022-08-29Published

2021-03-23Filed