FR3099270B1 - Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device - Google Patents

Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device Download PDF

Info

Publication number
FR3099270B1
FR3099270B1 FR1908289A FR1908289A FR3099270B1 FR 3099270 B1 FR3099270 B1 FR 3099270B1 FR 1908289 A FR1908289 A FR 1908289A FR 1908289 A FR1908289 A FR 1908289A FR 3099270 B1 FR3099270 B1 FR 3099270B1
Authority
FR
France
Prior art keywords
person
area
race segment
zone
identification
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
FR1908289A
Other languages
French (fr)
Other versions
FR3099270A1 (en
Inventor
Rémi Druihle
Cécile Boukamel-Donnou
Benoit Pelletier
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.)
Bull SA
Original Assignee
Bull 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 Bull SA filed Critical Bull SA
Priority to FR1908289A priority Critical patent/FR3099270B1/en
Publication of FR3099270A1 publication Critical patent/FR3099270A1/en
Application granted granted Critical
Publication of FR3099270B1 publication Critical patent/FR3099270B1/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
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/63—Scene text, e.g. street names
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/18—Extraction of features or characteristics of the image
    • G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
    • G06V30/18019—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections by matching or filtering
    • G06V30/18038—Biologically-inspired filters, e.g. difference of Gaussians [DoG], Gabor filters
    • G06V30/18048—Biologically-inspired filters, e.g. difference of Gaussians [DoG], Gabor filters with interaction between the responses of different filters, e.g. cortical complex cells
    • G06V30/18057—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]

Abstract

Ce procédé comporte : - pour chacune d’une pluralité d’images successives d’un flux vidéo d’une caméra, la recherche (306) d’au moins une personne présente dans l’image et la définition (306), dans l’image, pour chaque personne trouvée, d’une zone, dite zone de personne, entourant au moins en partie cette personne ; - la construction (308) d’au moins un segment de course regroupant plusieurs zones de personne issues d’images successives et entourant au moins en partie la même personne ; - pour chaque segment de course, l’identification de la personne de ce segment de course, par un numéro porté par cette personne, cette identification comportant : -- pour chaque zone de personne du segment de course, la recherche (310) d’au moins un numéro présent dans la zone de personne et la définition, dans la zone de personne, pour chaque numéro trouvé, d’une zone, dite zone de numéro, entourant ce numéro ; -- pour chaque zone de numéro du segment de course, la reconnaissance (312) du numéro présent dans la zone de numéro et, pour chaque numéro reconnu, l’évaluation d’une fiabilité de la reconnaissance ; -- la sélection (314) d’un des numéros reconnus à partir des fiabilités de ces numéros reconnus ; et -- la recherche (316) du numéro sélectionné parmi un ensemble de numéros d’identification prédéfinis identifiant des personnes respectives. Figure pour l’abrégé : Fig. 3This method comprises: - for each of a plurality of successive images of a video stream from a camera, the search (306) for at least one person present in the image and the definition (306), in the image, for each person found, of an area, called person area, at least partially surrounding this person; - the construction (308) of at least one race segment grouping together several person areas from successive images and surrounding at least in part the same person; - for each race segment, the identification of the person in this race segment, by a number carried by this person, this identification comprising: -- for each person zone in the race segment, the search (310) for at least one number present in the person area and the definition, in the person area, for each number found, of an area, called number area, surrounding this number; -- for each race segment number zone, recognizing (312) the number present in the number zone and, for each recognized number, evaluating a reliability of the recognition; -- selecting (314) one of the recognized numbers from the reliabilities of those recognized numbers; and -- searching (316) the selected number from a set of predefined identification numbers identifying respective persons. Figure for abstract: Fig. 3

FR1908289A 2019-07-22 2019-07-22 Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device Active FR3099270B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR1908289A FR3099270B1 (en) 2019-07-22 2019-07-22 Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1908289A FR3099270B1 (en) 2019-07-22 2019-07-22 Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device
FR1908289 2019-07-22

Publications (2)

Publication Number Publication Date
FR3099270A1 FR3099270A1 (en) 2021-01-29
FR3099270B1 true FR3099270B1 (en) 2021-10-29

Family

ID=69104527

Family Applications (1)

Application Number Title Priority Date Filing Date
FR1908289A Active FR3099270B1 (en) 2019-07-22 2019-07-22 Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device

Country Status (1)

Country Link
FR (1) FR3099270B1 (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6545705B1 (en) * 1998-04-10 2003-04-08 Lynx System Developers, Inc. Camera with object recognition/data output
US8442922B2 (en) 2008-12-24 2013-05-14 Strands, Inc. Sporting event image capture, processing and publication
JP6535196B2 (en) 2015-04-01 2019-06-26 キヤノンイメージングシステムズ株式会社 Image processing apparatus, image processing method and image processing system

Also Published As

Publication number Publication date
FR3099270A1 (en) 2021-01-29

Similar Documents

Publication Publication Date Title
US10949675B2 (en) Image summarization system and method
US10614314B2 (en) Image summarization system and method
CN109345522A (en) A kind of picture quality screening technique and device, equipment and storage medium
US20180144481A1 (en) Moving object tracking device, display device, and moving object tracking method
EP3686838A1 (en) Verification system
US8401254B2 (en) Image search device and image search method
Azhar et al. People tracking system using DeepSORT
Ivanova et al. Optimization of machine learning algorithm of emotion recognition in terms of human facial expressions
EP3623998A1 (en) Character recognition
US20150071529A1 (en) Learning image collection apparatus, learning apparatus, and target object detection apparatus
AU2014240669A1 (en) Object monitoring system, object monitoring method, and monitoring target extraction project
JP2015187759A (en) Image searching device and image searching method
Rota et al. Real time detection of social interactions in surveillance video
Shirodkar et al. Automated attendance management system using face recognition
FR3087033B1 (en) METHODS OF LEARNING PARAMETERS OF A CONVOLUTION NEURON NETWORK AND DETECTION OF ELEMENTS OF VISIBLE INTEREST IN AN IMAGE
FR3099270B1 (en) Method of identifying a person in a video, by a number carried by this person, corresponding computer program and device
FR3076377B1 (en) PREDICTION OF DISPLACEMENT AND TOPOLOGY FOR A NETWORK OF CAMERAS.
Thanikasalam et al. Target-specific siamese attention network for real-time object tracking
Fang et al. Design flow for real-time face mask detection using PYNQ system-on-chip platform
FR3099278B1 (en) Method for video surveillance of the crossing of a line by persons, corresponding computer program and device
El-Naggar et al. Ear detection in the wild using faster R-CNN deep learning
FR3099269B1 (en) Method for identifying a person in a video, by a visual signature of this person, corresponding computer program and device
EP2966592B1 (en) Face recognition apparatus and method for recognizing face
Hou et al. A multi-stream approach for seizure classification with knowledge distillation
CN107506747A (en) Face identification system and method based on video data characteristic point

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20210129

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

PLFP Fee payment

Year of fee payment: 5