1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Robust trifocal tensor constraints for structure from motion estimation
作者 Hor, Maw-Kae
何瑁鎧
Chan, Kai-Hsuan
Tang, C.-Y.
Wu, Y.-L.
詹凱軒
貢獻者 資科系
關鍵詞 Accurate estimation; Camera parameter; Estimation errors; Global optimization problems; Ground truth data; Multi-view stereo; Optimization solution; Orthogonal array; Reprojection error; Structure from motion; Trifocal tensor; Cameras; Errors; Estimation; Motion estimation; Particle swarm optimization (PSO); Pixels; Tensors; Parameter estimation
日期 2013
上傳時間 21-五月-2015 17:25:31 (UTC+8)
摘要 It is important to estimate accurate camera parameters in multi-view stereo. In this paper, we use three-view relations, the trifocal tensor, to improve the Bundler, a popular structure from motion (SfM) system, for estimating accurate camera parameters. We propose a novel method: the Robust Orthogonal Particle Swarm Optimization (ROPSO) to estimate a robust and accurate trifocal tensor. In ROPSO, we formulate the trifocal tensor estimation as a global optimization problem and use the particle swarm optimization (PSO) for parameter searching. The orthogonal array is used to select the representative initial particles in PSO for more stable results. In the experiments, we use simulated and real ground truth data for statistical analysis. The experimental results show that the proposed ROPSO can achieve more accurate estimation of the trifocal tensor than the traditional methods and has higher probability to find the optimization solution than the traditional methods. Based on the trifocal tensor estimated by the proposed method, the SfM estimation errors can effectively be reduced. The average reprojection errors are reduced from 21.5 pixels to less than 1 pixel. © 2013 Elsevier B.V. All rights reserved.
關聯 Pattern Recognition Letters, 34(6), 627-636
資料類型 article
DOI http://dx.doi.org/10.1016/j.patrec.2012.12.023
dc.contributor 資科系-
dc.creator (作者) Hor, Maw-Kae-
dc.creator (作者) 何瑁鎧zh_TW
dc.creator (作者) Chan, Kai-Hsuanen_US
dc.creator (作者) Tang, C.-Y.en_US
dc.creator (作者) Wu, Y.-L.en_US
dc.creator (作者) 詹凱軒zh_TW
dc.date (日期) 2013-
dc.date.accessioned 21-五月-2015 17:25:31 (UTC+8)-
dc.date.available 21-五月-2015 17:25:31 (UTC+8)-
dc.date.issued (上傳時間) 21-五月-2015 17:25:31 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/75279-
dc.description.abstract (摘要) It is important to estimate accurate camera parameters in multi-view stereo. In this paper, we use three-view relations, the trifocal tensor, to improve the Bundler, a popular structure from motion (SfM) system, for estimating accurate camera parameters. We propose a novel method: the Robust Orthogonal Particle Swarm Optimization (ROPSO) to estimate a robust and accurate trifocal tensor. In ROPSO, we formulate the trifocal tensor estimation as a global optimization problem and use the particle swarm optimization (PSO) for parameter searching. The orthogonal array is used to select the representative initial particles in PSO for more stable results. In the experiments, we use simulated and real ground truth data for statistical analysis. The experimental results show that the proposed ROPSO can achieve more accurate estimation of the trifocal tensor than the traditional methods and has higher probability to find the optimization solution than the traditional methods. Based on the trifocal tensor estimated by the proposed method, the SfM estimation errors can effectively be reduced. The average reprojection errors are reduced from 21.5 pixels to less than 1 pixel. © 2013 Elsevier B.V. All rights reserved.-
dc.format.extent 1667087 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Pattern Recognition Letters, 34(6), 627-636-
dc.subject (關鍵詞) Accurate estimation; Camera parameter; Estimation errors; Global optimization problems; Ground truth data; Multi-view stereo; Optimization solution; Orthogonal array; Reprojection error; Structure from motion; Trifocal tensor; Cameras; Errors; Estimation; Motion estimation; Particle swarm optimization (PSO); Pixels; Tensors; Parameter estimation-
dc.title (題名) Robust trifocal tensor constraints for structure from motion estimation-
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1016/j.patrec.2012.12.023-
dc.doi.uri (DOI) http://dx.doi.org/10.1016/j.patrec.2012.12.023-