Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 27.07.2021 at 12:00 PM CEST
Settings

Settings

Goto Application

1. WO2020140223 - CONTINUOUS LEARNING FOR OBJECT TRACKING

Publication Number WO/2020/140223
Publication Date 09.07.2020
International Application No. PCT/CN2019/070174
International Filing Date 03.01.2019
IPC
G06K 9/00 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/66 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
64using simultaneous comparisons or correlations of the image signals with a plurality of references, e.g. resistor matrix
66references adjustable by an adaptive method, e.g. learning
G06T 7/20 2017.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
20Analysis of motion
CPC
G06K 9/00771
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
00771Recognising scenes under surveillance, e.g. with Markovian modelling of scene activity
G06K 9/6271
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
G06T 2207/10016
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
10Image acquisition modality
10016Video; Image sequence
G06T 2207/20081
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20081Training; Learning
G06T 2207/20084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
20Special algorithmic details
20084Artificial neural networks [ANN]
G06T 2207/30196
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
2207Indexing scheme for image analysis or image enhancement
30Subject of image; Context of image processing
30196Human being; Person
Applicants
  • INTEL CORPORATION [US]/[US]
  • ZHANG, Lidan [CN]/[CN] (BZ)
  • GUO, Ping [CN]/[CN] (BZ)
  • REN, Haibing [CN]/[CN] (BZ)
  • ZHANG, Yimin [CN]/[CN] (BZ)
Inventors
  • ZHANG, Lidan
  • GUO, Ping
  • REN, Haibing
  • ZHANG, Yimin
Agents
  • SHANGHAI PATENT & TRADEMARK LAW OFFICE, LLC
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) CONTINUOUS LEARNING FOR OBJECT TRACKING
(FR) APPRENTISSAGE CONTINU POUR SUIVI D'OBJET
Abstract
(EN)
A long-term object tracker employs a continuous learning framework to overcome drift in the tracking position of a tracked object. The continuous learning framework consists of a continuous learning module that accumulates samples of the tracked object to improve the accuracy of object tracking over extended periods of time. The continuous learning module can include a sample pre-processor to refine a location of a candidate object found during object tracking, and a cropper to crop a portion of a frame containing a tracked object as a sample and to insert the sample into a continuous learning database to support future tracking.
(FR)
Selon l'invention, un suiveur d'objet à long terme emploie un cadre d'apprentissage continu pour remédier à la dérive de la position de suivi d'un objet suivi. Le cadre d'apprentissage continu est constitué d'un module d'apprentissage continu qui accumule des échantillons de l'objet suivi pour améliorer la précision de suivi d'objet pendant de longues périodes. Le module d'apprentissage continu peut contenir un préprocesseur d'échantillon servant à affiner un emplacement d'un objet candidat trouvé pendant le suivi d'objet, et un recadreur servant à recadrer une partie d'une trame contenant un objet suivi en tant qu'échantillon et pour insérer l'échantillon dans une base de données d'apprentissage continu pour prendre en charge un suivi futur.
Latest bibliographic data on file with the International Bureau