Time-space domain motion segmentation and motion estimation method based on three-dimensional video
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.
Active Publication Date: 2012-06-27
ZHEJIANG UNIV
View PDF3 Cites 13 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] like 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 real...
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 estimation method based on a three-dimensional video. Implementing steps of the method comprises the following steps: (1) acquiring a three-dimensional video comprising a motion object and a background area through a three-dimensional video acquisition system; (2) establishing a two-dimensional motion field parameter model based on a background three-dimensional motion characteristic; (3) defining a segmentation curved surface, and embedding the two-dimensional motion field parameter model and the segmentation curved surface into a movable contour model to obtain an object function based on a time-space domain; (4) carrying out minimizing solution on the object function to obtain a motion parameter of the three-dimensional video acquisition system, a motion parameter of the motion object and an object curved surface. The method has the advantages of accurate and reliable motion analysis, high robustness, no camera motion prior dependence, suitability for complex motion and a wide application scope.
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 IPC IPC(8): G06T7/20G06T7/00H04N13/00
Inventor 于慧敏王诗言
Owner ZHEJIANG UNIV