Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Saturday 31.10.2020 at 7:00 AM CET
Settings

Settings

Goto Application

1. WO2019041447 - 3D VIDEO FRAME FEATURE POINT EXTRACTION METHOD AND SYSTEM

Publication Number WO/2019/041447
Publication Date 07.03.2019
International Application No. PCT/CN2017/105475
International Filing Date 10.10.2017
IPC
G06K 9/46 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
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06T 7/00 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
CPC
G06K 9/00744
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
00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
00744Extracting features from the video content, e.g. video "fingerprints", or characteristics, e.g. by automatic extraction of representative shots or key frames
G06K 9/4647
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
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4642by performing operations within image blocks or by using histograms
4647summing image-intensity values; Projection and histogram analysis
G06K 9/6215
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
6201Matching; Proximity measures
6215Proximity measures, i.e. similarity or distance measures
Applicants
  • 深圳依偎控股有限公司 SHENZHEN IVVI HOLDING LIMITED [CN]/[CN]
Inventors
  • 王新宁 WANG, Xinning
  • 刘恩宝 LIU, Enbao
Agents
  • 广州嘉权专利商标事务所有限公司 JIAQUAN IP LAW FIRM
Priority Data
201710756592.329.08.2017CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) 3D VIDEO FRAME FEATURE POINT EXTRACTION METHOD AND SYSTEM
(FR) PROCÉDÉ ET SYSTÈME D'EXTRACTION DE POINTS CARACTÉRISTIQUES D'UNE TRAME DE VIDÉO 3D
(ZH) 一种3D视频帧特征点提取的方法及系统
Abstract
(EN)
Disclosed is a 3D video frame feature point extraction method, comprising the following steps: acquiring a frame of image from a video and segmenting the image along a centerline; respectively compiling statistics of gray-scale histograms of the left and right images and the upper and lower images after segmentation, and respectively carrying out gray-scale histogram matching calculation; comparing a matching calculation result to obtain the type of image; if the image is 3D, segmenting the image along the symmetric line thereof to obtain a first half image and a second half image; segmenting the first half image and the second half image into N equal parts respectively; and obtaining corresponding feature matching points in the second half image by means of solving feature points in each equally segmented image of the first half image. A 3D video frame feature point extraction system, comprising: a segmentation module, a calculation module, and a feature point solution module. By means of the solution, the problem that the conventional feature extraction and matching method has a large amount of calculation and poor accuracy can be solved. The method and system can be widely applied to the field of image processing.
(FR)
L'invention concerne un procédé d'extraction de points caractéristiques d'une trame de vidéo 3D, comprenant les étapes consistant : à acquérir une trame d'une image à partir d'une vidéo et à segmenter l'image sur une ligne centrale ; à compiler respectivement des statistiques d'histogrammes d'échelle de gris des images gauche et droite et des images supérieure et inférieure après la segmentation, et à exécuter respectivement un calcul de correspondance d'histogrammes d'échelle de gris ; à comparer un résultat de calcul de correspondance pour obtenir le type de l'image ; si l'image est en 3D, à segmenter l'image sur sa ligne symétrique pour obtenir une première et une seconde demi-image ; à segmenter chacune de la première et de la seconde demi-image en N parties égales ; et à obtenir des points de correspondance de caractéristiques en rapport dans la seconde demi-image au moyen de la résolution de points caractéristiques dans chaque image segmentée de manière égale de la première demi-image. L'invention a également trait à un système d'extraction de points caractéristiques d'une trame de vidéo 3D, comprenant : un module de segmentation, un module de calcul et un module de solution de points caractéristiques. Au moyen de la solution, le problème de la grande quantité de calculs et de la faible précision du procédé d'extraction et de correspondance de caractéristiques classique peut être résolu. Le procédé et le système peuvent être largement appliqués au domaine du traitement d'images.
(ZH)
本发明公开了一种3D视频帧特征点提取的方法,其包括以下步骤:从视频中获取一帧图像,并将所述图像沿着中线分割;分别统计分割后左、右图像以及上、下图像的灰度直方图,并分别进行灰度直方图匹配计算;比较匹配计算结果,得出图像的类型;若所述图像为3D,则将所述图像沿着其对称线进行分割,得到第一半图像和第二半图像;分别将第一半图像和第二半图像分为N等份;通过求解第一半图像的各等分图像内的特征点,进而可得第二半图像中相应的特征匹配点。一种3D视频帧特征点提取的系统,包括:分割模块、计算模块、特征点求解模块。采用该方案,改善了传统的特征提取和匹配计算量大、准确度不够的问题,广泛应用于图像处理领域。
Also published as
Latest bibliographic data on file with the International Bureau