Nonmyopic View Planning for Active Object Classification and Pose Estimation

2014

Article

am


One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose. Most of the work in object detection has been based on single image processing and its performance is limited by occlusions and ambiguity in appearance and geometry. This paper proposes an active approach to object detection by controlling the point of view of a mobile depth camera. When an initial static detection phase identifies an object of interest, several hypotheses are made about its class and orientation. The sensor then plans a sequence of viewpoints, which balances the amount of energy used to move with the chance of identifying the correct hypothesis. We formulate an active M-ary hypothesis testing problem, which includes sensor mobility, and solve it using a point-based approximate POMDP algorithm. The validity of our approach is verified through simulation and real-world experiments with the PR2 robot. The results suggest a significant improvement over static object detection

Author(s): Atanasov, N. and Sankaran, B. and Le Ny, J. and Pappas, G. and Daniilidis, K.
Journal: IEEE Transactions on Robotics
Year: 2014
Month: May

Department(s): Autonomous Motion
Bibtex Type: Article (article)
Paper Type: Journal

Cross Ref: p10543
Digital: True
Note: clmc
State: Published
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6822578

Links: Web
Attachments: pdf

BibTex

@article{sankaran_tro_2014,
  title = {Nonmyopic View Planning for Active Object Classification and Pose Estimation},
  author = {Atanasov, N. and Sankaran, B. and Le Ny, J. and Pappas, G. and Daniilidis, K.},
  journal = {IEEE Transactions on Robotics},
  month = may,
  year = {2014},
  note = {clmc},
  crossref = {p10543},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6822578},
  month_numeric = {5}
}