3D Pose Tracking Using a Recovered 3D Model

作者

Chen, Wei; Zhao, Yuelong; Chen, Shu; 更多内容

期刊:JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS ISSN:0218-1266 , 年:2018 . 卷:27 . 期:4

语种: English

原文链接:http://dx.doi.org/10.1142/S0218126618500615

摘要

Template warping is a widely used approach in the pose recovery field. Due to its flexibility, template warping is especially useful in monocular video motion tracking. Tracking accuracy is largely determined by the appearance of the 3D model. Moreover, the appearance of the 3D model plays a very important role in template warping. However, accurate tracking results are difficult to obtain because hand estimated 3D models are prone to inaccuracies (the appearance of 3D models is commonly initialized by the user based on the first frame of video footage; the result is a hand estimated 3D model). In order to overcome this problem, we propose an iterative optimization process that estimates the appearance of the 3D model during tracking. Our results show that our proposed 3D model estimation achieves better performance than the hand model initialization estimation.

更多>>>

关键词
Template warping; pose estimation; 3D appearance model

附加关键词:
IMAGE

作者信息

通讯作者:
     Chen, S , Xiangtan Univ, Sch Informat Engn, Xiangtan 411105, Peoples R China.
作者机构:
     [1] [ Chen, Wei; Zhao, Yuelong ] South China Univ Technol, Sch Comp Sci & Engn, Guangzhou 510006, Guangdong, Peoples R China.
     [2] [ Chen, Wei ] GuangDong Pharmaceut Univ, Coll Med Informat Engn, Guangzhou 510640, Guangdong, Peoples R China.
     [3] [ Chen, Shu; Ouyang, Jianquan ] Xiangtan Univ, Sch Informat Engn, Xiangtan 411105, Peoples R China.
作者邮箱:
     csu_cs@163.com