Time-space domain motion segmentation and motion evaluation method based on three-dimensional (3D) videos
A technology of motion segmentation and motion estimation, applied in the field of 3D video motion analysis, can solve the problems of lack of depth information, 2D flow field cannot truly reflect 3D spatial motion changes, etc.
Inactive Publication Date: 2012-07-04
ZHEJIANG UNIV
View PDF2 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the severe nonlinearity caused by the lack of depth information, the two-dimensional flow field itself cannot truly reflect the motion changes in the three-dimensional space, making motion estimation an ill-conditioned problem.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] Such as figure 1 As shown, the implementation steps of the temporal and spatial domain motion segmentation and motion estimation method based on 3D video in this embodiment are as follows:
[0049] 1) Obtain a 3D video comprising a moving target and a background area through a 3D video acquisition system;
[0050] 2) Establish a two-dimensional sports field parameter model based on the three-dimensional motion characteristics of the background;
[0051] 3) Define the segmentation surface, and embed the two-dimensional sports field parameter model and the segmentation surface into the active contour model to obtain the objective function based on the space-time domain;
[0052] 4) The objective function is minimized to obtain the motion parameters of the 3D video acquisition system, the motion parameters of the moving target and the target surface.
[0053] The 3D video acquisition system refers to an acquisition system capable of acquiring 2D video plus depth map in r...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a time-space domain motion segmentation and motion evaluation method based on three-dimensional (3D) videos, which includes implementation steps of: 1) obtaining 3D videos including motion targets and background areas through a 3D video obtaining system; 2) building a two-dimensional sports ground parameter model based on background three-dimensional motion characteristics; 3) defining a segmentation curve, and embedding the two-dimensional sports ground parameter model and the segmentation curve into an active contour model to obtain a target function based on a time-space domain; and 4) performing minimized solving on the target function to obtain motion parameters of the 3D video obtaining system, motion parameters of the motion target and a target curve. The time-space domain motion segmentation and motion evaluation method based on 3D videos has the advantages of being accurate and reliable in motion analysis, high in robustness, free of camera motion prior dependence, applicable to complex motions and wide in application range.
Description
technical field [0001] The invention relates to the field of three-dimensional video motion analysis, in particular to a time-space domain motion segmentation and motion estimation method based on 3D video in complex situations such as camera motion. Background technique [0002] Three-dimensional video refers to the two-dimensional image acquired in real time by the 3D video acquisition system plus depth information, that is, grayscale image and depth image. Motion analysis based on 3D video, especially in the case of camera system motion, is an important and challenging research direction of computer vision, and its application fields include 3DTV, machine vision, video compression (MPEG-4 ), automatic navigation, etc. Motion analysis includes two aspects of motion segmentation and motion estimation. In fact, these are two closely related and complementary topics. On the one hand, accurate motion segmentation can alleviate the uncertainty of motion estimation, especially...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/20G06T7/00
Inventor 于慧敏王诗言
Owner ZHEJIANG UNIV