Autonomous Motion Conference Paper 2013

Hypothesis Testing Framework for Active Object Detection

Featureextraction

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 view-points, 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 experiments with real scenes captured by a kinect sensor. The results suggest a significant improvement over static object detection.

Author(s): Sankaran, B. and Atanasov, N. and Le Ny, J. and Koletschka, T. and Pappas, G. and Daniilidis, K.
Book Title: IEEE International Conference on Robotics and Automation (ICRA)
Year: 2013
Month: May
Bibtex Type: Conference Paper (inproceedings)
Event Place: Karlsruhe, Germany
State: Published
Cross Ref: p10544
Digital: True
Electronic Archiving: grant_archive
Note: clmc
Attachments:

BibTex

@inproceedings{Sankaran_ICRA_2013,
  title = {Hypothesis Testing Framework for Active Object Detection},
  booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
  abstract = {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 view-points, 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 experiments with real scenes captured by a kinect sensor. The results suggest a significant improvement over static object detection.
  },
  month = may,
  year = {2013},
  note = {clmc},
  slug = {sankaran_icra_2013},
  author = {Sankaran, B. and Atanasov, N. and Le Ny, J. and Koletschka, T. and Pappas, G. and Daniilidis, K.},
  crossref = {p10544},
  month_numeric = {5}
}