发明名称 Method and apparatus for reconstructing three dimensional model
摘要 A method and an apparatus for reconstructing a three dimensional model of an object are provided. The method includes the following steps. A plurality of first depth images of an object are obtained. According to a linking information of the object, the first depth images are divided into a plurality of depth image groups. The linking information records location information corresponding to a plurality of substructures of the object. Each depth image group includes a plurality of second depth images, and the substructures correspond to the second depth images. According to the second depth image and the location information corresponding to each substructure, a local module of each substructure is built. According to the linking information, the local models corresponding to the substructures are merged, and the three-dimensional model of the object is built.
申请公布号 US9262862(B2) 申请公布日期 2016.02.16
申请号 US201213686927 申请日期 2012.11.28
申请人 Industrial Technology Research Institute 发明人 Tsai Yao-Yang;Tenn Hian-Kun;Huang Jay
分类号 G06T17/00;G06T7/00 主分类号 G06T17/00
代理机构 Jianq Chyun IP Office 代理人 Jianq Chyun IP Office
主权项 1. A method for reconstructing a three-dimensional model, adapted to build a three-dimensional model of an object, comprising: obtaining a plurality of first depth images of the object, wherein the object is a human body; dividing the first depth images of the object into a plurality of depth image groups according to linking information of the object, wherein the linking information records location information corresponding to a plurality of substructures of the object, each of the depth image groups comprises a plurality of second depth images, and each of the substructures corresponds to the second depth images of each of the depth image groups; building a local model corresponding to each of the substructures according to the second depth images and the location information corresponding to each of the substructures; and merging the local models corresponding to the substructures according to the linking information of the object, so as to build the three-dimensional model of the object, adjusting the local models according to the features of the surface of the object, wherein the step of merging the local models corresponding to the substructures according to the linking information of the object to build the three-dimensional model of the object further comprises: in a plurality of pixels in each of the second depth images corresponding to each of the substructures, when three neighboring pixels are connected to another pixel, determining whether a first figure formed by the three neighboring pixels is overlapped with a second figure formed by two of the three neighboring pixels and the other pixel;when the first figure is overlapped with the second figure, determining a connection relationship between the three neighboring pixels and the other pixel to be incorrect; andwhen the first figure is not overlapped with the second figure, maintaining the connection between the three neighboring pixels and the other pixel.
地址 Hsinchu TW