Template-based method for repairing holes in human point cloud
A point cloud and human body technology, applied in the field of 3D modeling, can solve problems such as low robustness of the algorithm, inability to fit the fitting results everywhere, damage to the accuracy of data in non-hole areas, etc.
Active Publication Date: 2019-01-04
ZHEJIANG UNIV
View PDF7 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these methods use a complete human body template to fit the overall point cloud instead of only the local area of the hole, which makes the algorithm less robust and easy to fall into a local optimal solution, resulting in the fitting result not being able to fit the input point cloud everywhere. It will destroy the accuracy of the data in the non-hole area; in addition, the amount of calculation for fitting the overall point cloud is relatively large, which makes the calculation efficiency of the algorithm low
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
[0075] The method provided by the present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0076] Such as figure 1 As shown, the implementation steps of the template-based human point cloud hole repair method provided in this embodiment are as follows:
[0077] Step (1): Segment the human body mesh model template according to the hole area in the point cloud, and mark some key corresponding feature points between the template and the human body point cloud.
[0078] In this embodiment, the typical hole regions in the human body point cloud obtained by the passive vision-based 3D human body reconstruction system are segmented, such as the top of the head, underarms, hands, crotch, and soles of the feet. And 7-12 groups of corresponding feature points are marked in each segmented area.
[0079] Step (2): From the original human point cloud, extract the body point cloud expansion boundary point set with confidence.
[0...
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 template-based method for repairing holes in a human body point cloud, which comprises the following steps: a human body mesh model template is segmented according to a holearea in a point cloud, and some key corresponding characteristic points in the point cloud are marked with the template; the Expanded Boundary Point Set of Human Body Point Cloud with Confidence Degree is extracted; the segmented template is rigidly registered with the human body point cloud locally; after rigid registration, the template is deformed to match the human body point cloud locally; vertices on the deformed template are extracted to form a template point cloud, and the part of the template point cloud overlapping with the original human body point cloud is removed; the de-overlapping template point cloud is resampled to the original human body point cloud density and smoothly fused to the original human body point cloud hole part. The human body point cloud hole repairing method provided by the invention can repair the point cloud hole encountered in the three-dimensional modeling of the human body and ensure that the hole repairing result accords with the prior knowledge of the human body shape, and has the advantages of smooth transition of the repairing hole area and high operation efficiency.
Description
technical field [0001] The invention relates to the field of real object-oriented three-dimensional modeling in computer graphics, in particular to a method for repairing holes in human body point clouds based on templates. Background technique [0002] Using 3D surface data acquisition equipment to model real-world objects has been widely used in various fields, which can save a lot of manual modeling operations and capture more model details. The use of three-dimensional surface data data acquisition equipment to model the human body has attracted people's attention because of its huge application value. Using a 3D data acquisition device, such as a 3D scanning instrument, the 3D surface data of an object collected is usually point cloud data, which is a collection of discrete 3D points. Usually, the original human body point cloud data acquired by the three-dimensional surface data acquisition equipment is affected by factors such as the viewing angle limitation of the a...
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): G06T17/00G06T5/50G06T7/33
CPCG06T5/50G06T7/33G06T17/00G06T2207/10028G06T2207/20221G06T2207/30196
Inventor 冯结青康鋆鹏
Owner ZHEJIANG UNIV