Integration of Probabilistic Pose Estimates from Multiple Views

ERKENT Ö., Shukla D., Piater J.

14th European Conference on Computer Vision (ECCV), Amsterdam, Hollanda, 8 - 16 Ekim 2016, cilt.9911, ss.154-170 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 9911
  • Doi Numarası: 10.1007/978-3-319-46478-7_10
  • Basıldığı Şehir: Amsterdam
  • Basıldığı Ülke: Hollanda
  • Sayfa Sayıları: ss.154-170
  • Anahtar Kelimeler: Pose estimation, Object recognition, Multiple cameras, RECOGNITION
  • Hacettepe Üniversitesi Adresli: Hayır

Özet

We propose an approach to multi-view object detection and pose estimation that considers combinations of single-view estimates. It can be used with most existing single-view pose estimation systems, and can produce improved results even if the individual pose estimates are incoherent. The method is introduced in the context of an existing, probabilistic, view-based detection and pose estimation method (PAPE), which we here extend to incorporate diverse attributes of the scene. We tested the multiview approach with RGB-D cameras in different environments containing several cluttered test scenes and various textured and textureless objects. The results show that the accuracies of object detection and pose estimation increase significantly over single-view PAPE and over other multiple-view integration methods.