2012年9月5日水曜日

3D-2D位置合わせ技術

3D-2D位置合わせ技術とは

ここでの「3D-2D位置合わせ技術」とは,モデルベーストラッキングやレンジデータへのテクスチャマッピングに限らず,画像と3次元空間の対応を得るという広い意味で,特に複数の画像を用いる技術に関してまとめた。具体的には以下のキーワードが該当するが、未完成であり、新しいものを発見次第追加していく。

  • Camera Calibration
  • Tracking
  • Structure-from-motion (SfM)
  • Multiple View Stereo (MVS)
  • Simultaneous Mapping and Localization (SLAM)

代表的な国際会議

  • International Journal of Computer Vision (ICCV)
  • Conference on Computer Vision and Pattern Recognition (CVPR)
  • International Conference on Pattern Recognition (ICPR)
  • International Symposium on Mixed and Augmented Reality (ISMAR)
  • British Machine Vision Conference (BMCV)
  • European Conference on Computer Vision (ECCV)
  • Asian Conference on Computer Vision (ACCV)

代表的な論文誌

  • International Journal of Computer Vision (IJCV)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)

サーベイ論文・教科書

  • Vincent Lepetit and Pascal Fua. 2005. Monocular model-based 3D tracking of rigid objects. Found. Trends. Comput. Graph. Vis. 1, 1 (January 2005), 1-89
  • R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge University Press, 2000.
  • Feng Zhou, Henry Been-Lirn Duh, and Mark Billinghurst. 2008. Trends in augmented reality tracking, interaction and display: A review of ten years of ISMAR. In Proceedings of the 7th IEEE/ACM International Symposium on Mixed and Augmented Reality (ISMAR '08)
  • Josep Aulinas, Yvan Petillot, Joaquim Salvi, and Xavier Llado. 2008. The SLAM problem: a survey. In Proceedings of the 2008 conference on Artificial Intelligence Research and Development: Proceedings of the 11th International Conference of the Catalan Association for Artificial Intelligence, 363-371.

特徴点抽出・記述

ロバスト推定 for 対応点探索

  • PROSAC: Progressive Sample Consensus
  • IRLS: Iteratively Re-weighted Least Square
  • GOODSAC: Good Sample Consensus
  • SURSAC: SUfficient Random SAmple Coverage
  • RANSAC: RANdom SAmple Consensus
  • LMedS: Least Median of Squares
  • M-estimator

C/C++ライブラリなど

評価サイト・評価用データ