學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Nonrigid Motion Analysis: Articulated and Elastic Motion
作者 Liao, Wen-hung;Aggarwal, Jake K.;Cai, Quin;Sabata, Bikash
廖文宏
貢獻者 資科系
日期 1998
上傳時間 17-Jun-2015 16:52:52 (UTC+8)
摘要 Motion of physical objects in the world is, in general, nonrigid. In robotics and computer vision, the motion of nonrigid objects is of growing interest to researchers from a wide spectrum of disciplines. The nonrigid objects being studied may be generally categorized into three groups according to the degree of deformation of body parts: articulated, elastic, and fluid. In articulated motion, individual rigid parts of an object move independently of one another and the motion of the whole object is nonrigid in nature. Elastic motion is nonrigid motion that conforms to a certain degree of continuity or smoothness. Fluid motion violates even the continuity assumption and may involve topological variations and turbulent deformations. This paper presents an overview of existing work on articulated and elastic motion, motivated by problems relating to the motion of the human body and of an animal heart, respectively. We study various approaches for recovering the D structure and motion of objects through a sequence of images in a bottom-up fashion, a strategy widely employed by various investigators. These approaches are classified as (1) motion recovery without shape models, and (2) model-based analysis. In the discussion of each algorithm, we also include a description of the complexity of feature and motion constraints, which are highly related to each other.
關聯 Computer Vision and Image Understanding - CVIU , vol. 70, no. 2, pp. 142-156
資料類型 article
DOI http://dx.doi.org/10.1006/cviu.1997.0620
dc.contributor 資科系-
dc.creator (作者) Liao, Wen-hung;Aggarwal, Jake K.;Cai, Quin;Sabata, Bikash-
dc.creator (作者) 廖文宏-
dc.date (日期) 1998-
dc.date.accessioned 17-Jun-2015 16:52:52 (UTC+8)-
dc.date.available 17-Jun-2015 16:52:52 (UTC+8)-
dc.date.issued (上傳時間) 17-Jun-2015 16:52:52 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/75927-
dc.description.abstract (摘要) Motion of physical objects in the world is, in general, nonrigid. In robotics and computer vision, the motion of nonrigid objects is of growing interest to researchers from a wide spectrum of disciplines. The nonrigid objects being studied may be generally categorized into three groups according to the degree of deformation of body parts: articulated, elastic, and fluid. In articulated motion, individual rigid parts of an object move independently of one another and the motion of the whole object is nonrigid in nature. Elastic motion is nonrigid motion that conforms to a certain degree of continuity or smoothness. Fluid motion violates even the continuity assumption and may involve topological variations and turbulent deformations. This paper presents an overview of existing work on articulated and elastic motion, motivated by problems relating to the motion of the human body and of an animal heart, respectively. We study various approaches for recovering the D structure and motion of objects through a sequence of images in a bottom-up fashion, a strategy widely employed by various investigators. These approaches are classified as (1) motion recovery without shape models, and (2) model-based analysis. In the discussion of each algorithm, we also include a description of the complexity of feature and motion constraints, which are highly related to each other.-
dc.format.extent 262136 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Computer Vision and Image Understanding - CVIU , vol. 70, no. 2, pp. 142-156-
dc.title (題名) Nonrigid Motion Analysis: Articulated and Elastic Motion-
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1006/cviu.1997.0620-
dc.doi.uri (DOI) http://dx.doi.org/10.1006/cviu.1997.0620-