ML Anthology

Learning Perceptual Organization with a Developmental Robot

Remi Driancourt
CVPR 2004 pp. 60
doi:10.1109/CVPR.2004.385 /cvpr/2004/driancourt2004cvpr-learning/

Abstract

This paper presents a biologically-inspired model of self-organization for robotic intermediary vision. Two mechanisms are under concern. First, the development of low-level local feature detectors adapted to the sensory input signal statistics in order to perform a piecewise categorization of the sensory signal. Second, the hierarchical grouping of these local features in a holistic perception. While the grouping mechanism is expressed as a classical agglomerative clustering, underlying similarity measures are not pre-given but developed from the signal statistics. Segmentation results are therefore adapted to the robot's experience. Based on information-theory, a stopping criterion that expresses a "good" abstraction level is proposed. Proposed mechanisms are illustrated with examples in both color and edge segmentation.

CVPR Semantic Scholar

Cite

Text

Driancourt. "Learning Perceptual Organization with a Developmental Robot." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.385

Markdown

[Driancourt. "Learning Perceptual Organization with a Developmental Robot." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/driancourt2004cvpr-learning/) doi:10.1109/CVPR.2004.385

BibTeX

@inproceedings{driancourt2004cvpr-learning,
  title     = {{Learning Perceptual Organization with a Developmental Robot}},
  author    = {Driancourt, Remi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {60},
  doi       = {10.1109/CVPR.2004.385},
  url       = {https://mlanthology.org/cvpr/2004/driancourt2004cvpr-learning/}
}