抄録
This paper describes a method to localize 3D objects, which is the extension of the segment-based object recognition method to use on a STL CAD model. Models for localization are automatically generated using contour generators, which are estimated by occluding contours of projected images of the CAD model from multiple viewing directions and depth images computed with a graphics accelerator. In addition, the model is dynamically updated in a recognition process according to the viewing direction. Localization process is based on multiple hypotheses verification using the model and 3D boundaries reconstructed from stereo images. Experimental results show the effectiveness of the proposed method.
元の言語 | English |
---|---|
ホスト出版物のタイトル | Proceedings - International Conference on Pattern Recognition |
出版物ステータス | Published - 2008 |
外部発表 | Yes |
イベント | 2008 19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL 継続期間: 2008 12 8 → 2008 12 11 |
Other
Other | 2008 19th International Conference on Pattern Recognition, ICPR 2008 |
---|---|
市 | Tampa, FL |
期間 | 08/12/8 → 08/12/11 |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
これを引用
3D object localization based on occluding contour using STL CAD model. / Maruyama, Kenichi; Kawai, Yoshihiro; Yoshimi, Takashi; Tomita, Fumiaki.
Proceedings - International Conference on Pattern Recognition. 2008. 4761593.研究成果: Conference contribution
}
TY - GEN
T1 - 3D object localization based on occluding contour using STL CAD model
AU - Maruyama, Kenichi
AU - Kawai, Yoshihiro
AU - Yoshimi, Takashi
AU - Tomita, Fumiaki
PY - 2008
Y1 - 2008
N2 - This paper describes a method to localize 3D objects, which is the extension of the segment-based object recognition method to use on a STL CAD model. Models for localization are automatically generated using contour generators, which are estimated by occluding contours of projected images of the CAD model from multiple viewing directions and depth images computed with a graphics accelerator. In addition, the model is dynamically updated in a recognition process according to the viewing direction. Localization process is based on multiple hypotheses verification using the model and 3D boundaries reconstructed from stereo images. Experimental results show the effectiveness of the proposed method.
AB - This paper describes a method to localize 3D objects, which is the extension of the segment-based object recognition method to use on a STL CAD model. Models for localization are automatically generated using contour generators, which are estimated by occluding contours of projected images of the CAD model from multiple viewing directions and depth images computed with a graphics accelerator. In addition, the model is dynamically updated in a recognition process according to the viewing direction. Localization process is based on multiple hypotheses verification using the model and 3D boundaries reconstructed from stereo images. Experimental results show the effectiveness of the proposed method.
UR - http://www.scopus.com/inward/record.url?scp=77957931686&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77957931686&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77957931686
SN - 9781424421756
BT - Proceedings - International Conference on Pattern Recognition
ER -