Component level three dimensional model building method of bayesian network constraint

Abstract

The present invention discloses a component level three dimensional model building method of bayesian network constraint. The method comprises the following steps of firstly, placing a target object on a turntable rotating slowly, using a Kinect to scan the target object to obtain a RGBD data sequence, and generating an initial three dimensional point cloud by combining a depth image fusion algorithm (KinectFusion); secondly, utilizing an interactive segmenting tool to modify the initial three dimensional point cloud to remove a noisy point and the redundant part; on the basis, utilizing a trained bayesian network to carry out the component segment on the three dimensional point cloud, automatically selecting a component model according with the requirement from a three dimensional model component base for each segmented component, registering a candidate three dimensional component to the model three dimensional point cloud by utilizing a non-rigid deformation algorithm, calculating the fitting degree of the candidate three dimensional component, and further selecting an optimal three dimensional component; finally, automatically splicing the optimal three dimensional component by utilizing a conformal deformation algorithm, and fitting to the model three dimensional point cloud in a deformation manner to obtain the three dimensional model possessing the component semantics finally.

Description

technical field [0001] The invention relates to the fields of clothing modeling and computer-aided design, in particular to a component-level three-dimensional model construction method constrained by a Bayesian network. Background technique [0002] Computer-aided design (Computer Aided Design, referred to as CAD) refers to the use of computers and graphics equipment to assist designers in design work. The traditional industrial design process needs to deal with a large number of design schemes, and there are generally situations where the design is difficult, the cycle is long and the waste of resources is serious. Utilizing the computer-aided design process can save design costs and free designers from tedious tasks. After the designer gives the design sketch, the computer can turn the design sketch into an engineering sample drawing, and visualize the result, which is convenient for the designer to make rapid iterative modifications. [0003] Virtual reality (Virtual R...

AI Technical Summary

Problems solved by technology

However, under the current circumstances, it is difficult to generate 3D models. Professionals are required to use professional 3D design software. The threshold is high, time-consuming, and heavy workload. It is even more difficult for ordinary users to generate 3D models of target objects and then realize 3D printing.

Images