Sciweavers

Share
AROBOTS
2010

Track-based self-supervised classification of dynamic obstacles

8 years 8 months ago
Track-based self-supervised classification of dynamic obstacles
Abstract This work introduces a self-supervised architecture for robust classification of moving obstacles in urban environments. Our approach presents a hierarchical scheme that relies on the stability of a subset of features given by a sensor to perform an initial robust classification based on unsupervised techniques. The obtained results are used as labels to train a set of supervised classifiers. The outcomes obtained with the second sensor can be used for higher level tasks such as segmentation or to refine the within-clusters discrimination. The proposed architecture is evaluated for a particular realization based on range and visual information which produces track-based labeling that is then employed to train supervised modules that perform instantaneous classification. Experiments show that the system is able to achieve 95% classification accuracy and to maintain the performance through on-line retraining when working conditions change. Keywords Self-supervised learning
Roman Katz, Juan Nieto, Eduardo Mario Nebot, Bertr
Added 08 Dec 2010
Updated 08 Dec 2010
Type Journal
Year 2010
Where AROBOTS
Authors Roman Katz, Juan Nieto, Eduardo Mario Nebot, Bertrand Douillard
Comments (0)
books