Processing

Please wait...

Settings

Settings

Goto Application

1. WO2007092905 - INTRA-MODE REGION-OF-INTEREST VIDEO OBJECT SEGMENTATION

Publication Number WO/2007/092905
Publication Date 16.08.2007
International Application No. PCT/US2007/061803
International Filing Date 07.02.2007
IPC
H04N 7/26 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
7Television systems
24Systems for the transmission of television signals using pulse code modulation
26using bandwidth reduction
G06K 9/00 2006.01
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 9/32 2006.01
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
20Image acquisition
32Aligning or centering of the image pick-up or image-field
CPC
G06K 9/00234
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
00221Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
00228Detection; Localisation; Normalisation
00234using pixel segmentation or colour matching
G06K 9/00248
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
00221Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
00228Detection; Localisation; Normalisation
00248using facial parts and geometric relationships
G06K 9/00261
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
00221Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
00228Detection; Localisation; Normalisation
00261using comparisons between temporally consecutive images
G06K 9/00604
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
00597Acquiring or recognising eyes, e.g. iris verification
00604Acquisition
H04N 19/17
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
10using adaptive coding
169characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
17the unit being an image region, e.g. an object
Applicants
  • QUALCOMM INCORPORATED [US]/[US] (AllExceptUS)
  • WANG, Haohong [CN]/[US] (UsOnly)
  • EL-MALEH, Khaled, Helmi [CA]/[US] (UsOnly)
Inventors
  • WANG, Haohong
  • EL-MALEH, Khaled, Helmi
Agents
  • OGROD, Gregory, D.
Priority Data
11/350,37607.02.2006US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) INTRA-MODE REGION-OF-INTEREST VIDEO OBJECT SEGMENTATION
(FR) SEGMENTATION D'OBJET VIDÉO D'UNE RÉGION D'INTÉRÊT INTRA-MODE
Abstract
(EN)
The disclosure is directed to techniques for automatic segmentation of a region-of-interest (ROI) video object from a video sequence. ROI object segmentation enables selected ROI or 'foreground' objects of a video sequence that may be of interest to a viewer to be extracted from non-ROI or 'background' areas of the video sequence. Examples of a ROI object are a human face or a head and shoulder area of a human body. The disclosed techniques include a hybrid technique that combines ROI feature detection, region segmentation, and background subtraction. In this way, the disclosed techniques may provide accurate foreground object generation and low-complexity extraction of the foreground object from the video sequence. A ROI object segmentation system may implement the techniques described herein. In addition, ROI object segmentation may be useful in a wide range of multimedia applications that utilize video sequences, such as video telephony applications and video surveillance applications.
(FR)
La présente invention se rapporte à des techniques de segmentation automatique d'un objet vidéo d'une région d'intérêt (ROI) à partir d'une séquence vidéo. La segmentation d'objet d'une région d'intérêt permet à des objets ROI ou 'de premier plan' sélectionnés d'une séquence vidéo pouvant présenter un intérêt pour un utilisateur d'être extraits de zones non ROI ou 'd'arrière plan' de la séquence vidéo. Les objets ROI peuvent par exemple être un visage humain ou une zone tête et épaules d'un corps humain. Les techniques de cette invention comprennent une technique hybride qui combine la détection de caractéristiques ROI, la segmentation de région et la soustraction d'arrière plan. Ainsi, les techniques de cette invention peuvent assurer une génération d'objet de premier plan précise et une extraction de faible complexité de l'objet de premier plan à partir de la séquence vidéo. Un système de segmentation d'objet ROI peut mettre en oeuvre les techniques de cette invention. En outre, la segmentation d'objet ROI peut être utilisée dans une vaste gamme d'applications multimédias qui utilisent des séquences vidéo, telles que des applications de visiophonie et des applications de vidéosurveillance.
Latest bibliographic data on file with the International Bureau