ML Anthology

Active Object Recognition Integrating Attention and Viewpoint Control

Sven J. Dickinson, Henrik I. Christensen, John K. Tsotsos, Göran Olofsson
ECCV 1994 pp. 3-14
doi:10.1007/BFB0028330 /eccv/1994/dickinson1994eccv-active/

Abstract

We present an active object recognition strategy which combines the use of an attention mechanism for focusing the search for a 3-D object in a 2-D image, with a viewpoint control strategy for disambiguating recovered object features. The attention mechanism consists of a probabilistic search through a hierarchy of predicted feature observations, taking objects into a set of regions classified according to the shapes of their bounding contours. If the features recovered during the attention phase do not provide a unique mapping to the 3-D object being searched, the probabilistic feature hierarchy can be used to guide the camera to a new viewpoint from where the object can be disambiguated.

PDF ECCV Semantic Scholar

Cite

Text

Dickinson et al. "Active Object Recognition Integrating Attention and Viewpoint Control." European Conference on Computer Vision, 1994. doi:10.1007/BFB0028330

Markdown

[Dickinson et al. "Active Object Recognition Integrating Attention and Viewpoint Control." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/dickinson1994eccv-active/) doi:10.1007/BFB0028330

BibTeX

@inproceedings{dickinson1994eccv-active,
  title     = {{Active Object Recognition Integrating Attention and Viewpoint Control}},
  author    = {Dickinson, Sven J. and Christensen, Henrik I. and Tsotsos, John K. and Olofsson, Göran},
  booktitle = {European Conference on Computer Vision},
  year      = {1994},
  pages     = {3-14},
  doi       = {10.1007/BFB0028330},
  url       = {https://mlanthology.org/eccv/1994/dickinson1994eccv-active/}
}