Morphological neural networks for localization and mapping

I. Villaverde; M. Graña; A. D'Anjou

doi:10.1109/CIMSA.2006.250739

Morphological neural networks for localization and mapping

I. Villaverde^*
, M. Graña
, A. D'Anjou

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

Morphological Associative Memories (MAM) have been proposed for image denosing and pattern recognition, We have shown that they can be applied to other domains, like image retrieval and hyperspectral image unsupervised segmentation. In both cases the key idea is that Morphological Autoassociative Memories (MAAM) selective sensitivity to erosive and dilative noise can be applied to detect the morphological independence between patterns. The convex coordinates obtained by linear unmixing based on the sets of morphological independent patterns define a feature extraction process. These features may be useful either for pattern classification. We present some results on the task of visual landmark recognition for a mobile robot self-localization task.

Original language	English
Title of host publication	Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006
Pages	9-14
Number of pages	6
DOIs	https://doi.org/10.1109/CIMSA.2006.250739
Publication status	Published - 2006
Externally published	Yes
Event	2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006 - La Coruna, Spain Duration: 12 Jul 2006 → 14 Jul 2006

Publication series

Name	Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006

Conference

Conference	2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006
Country/Territory	Spain
City	La Coruna
Period	12/07/06 → 14/07/06

Keywords

Morphological neural networks
Robot localization

Access to Document

10.1109/CIMSA.2006.250739

Cite this

Villaverde, I., Graña, M., & D'Anjou, A. (2006). Morphological neural networks for localization and mapping. In Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006 (pp. 9-14). Article 4016815 (Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006). https://doi.org/10.1109/CIMSA.2006.250739

Villaverde, I. ; Graña, M. ; D'Anjou, A. / Morphological neural networks for localization and mapping. Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006. 2006. pp. 9-14 (Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006).

@inproceedings{9ec3876ef2e14c2aa3742968ceddabef,

title = "Morphological neural networks for localization and mapping",

abstract = "Morphological Associative Memories (MAM) have been proposed for image denosing and pattern recognition, We have shown that they can be applied to other domains, like image retrieval and hyperspectral image unsupervised segmentation. In both cases the key idea is that Morphological Autoassociative Memories (MAAM) selective sensitivity to erosive and dilative noise can be applied to detect the morphological independence between patterns. The convex coordinates obtained by linear unmixing based on the sets of morphological independent patterns define a feature extraction process. These features may be useful either for pattern classification. We present some results on the task of visual landmark recognition for a mobile robot self-localization task.",

keywords = "Morphological neural networks, Robot localization",

author = "I. Villaverde and M. Gra{\~n}a and A. D'Anjou",

year = "2006",

doi = "10.1109/CIMSA.2006.250739",

language = "English",

isbn = "142440245X",

series = "Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006",

pages = "9--14",

booktitle = "Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006",

note = "2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006 ; Conference date: 12-07-2006 Through 14-07-2006",

}

Villaverde, I, Graña, M & D'Anjou, A 2006, Morphological neural networks for localization and mapping. in Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006., 4016815, Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006, pp. 9-14, 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006, La Coruna, Spain, 12/07/06. https://doi.org/10.1109/CIMSA.2006.250739

Morphological neural networks for localization and mapping. / Villaverde, I.; Graña, M.; D'Anjou, A.
Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006. 2006. p. 9-14 4016815 (Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Morphological neural networks for localization and mapping

AU - Villaverde, I.

AU - Graña, M.

AU - D'Anjou, A.

PY - 2006

Y1 - 2006

N2 - Morphological Associative Memories (MAM) have been proposed for image denosing and pattern recognition, We have shown that they can be applied to other domains, like image retrieval and hyperspectral image unsupervised segmentation. In both cases the key idea is that Morphological Autoassociative Memories (MAAM) selective sensitivity to erosive and dilative noise can be applied to detect the morphological independence between patterns. The convex coordinates obtained by linear unmixing based on the sets of morphological independent patterns define a feature extraction process. These features may be useful either for pattern classification. We present some results on the task of visual landmark recognition for a mobile robot self-localization task.

AB - Morphological Associative Memories (MAM) have been proposed for image denosing and pattern recognition, We have shown that they can be applied to other domains, like image retrieval and hyperspectral image unsupervised segmentation. In both cases the key idea is that Morphological Autoassociative Memories (MAAM) selective sensitivity to erosive and dilative noise can be applied to detect the morphological independence between patterns. The convex coordinates obtained by linear unmixing based on the sets of morphological independent patterns define a feature extraction process. These features may be useful either for pattern classification. We present some results on the task of visual landmark recognition for a mobile robot self-localization task.

KW - Morphological neural networks

KW - Robot localization

UR - https://www.scopus.com/pages/publications/33749853257

U2 - 10.1109/CIMSA.2006.250739

DO - 10.1109/CIMSA.2006.250739

M3 - Conference contribution

AN - SCOPUS:33749853257

SN - 142440245X

SN - 9781424402458

T3 - Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006

SP - 9

EP - 14

BT - Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006

T2 - 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006

Y2 - 12 July 2006 through 14 July 2006

ER -

Villaverde I, Graña M, D'Anjou A. Morphological neural networks for localization and mapping. In Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006. 2006. p. 9-14. 4016815. (Proceedings of 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2006). doi: 10.1109/CIMSA.2006.250739

Morphological neural networks for localization and mapping

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this