Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Classification of Point Clouds with Neural Networks and Continuum-Type Memories. / Reitmann, Stefan; Kudryashova, Elena V.; Jung, Bernhard; Reitmann, Volker.
Artificial Intelligence Applications and Innovations - 17th IFIP WG 12.5 International Conference, AIAI 2021, Proceedings. ред. / Ilias Maglogiannis; John Macintyre; Lazaros Iliadis. Springer Nature, 2021. стр. 505-517 (IFIP Advances in Information and Communication Technology; Том 627).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Classification of Point Clouds with Neural Networks and Continuum-Type Memories
AU - Reitmann, Stefan
AU - Kudryashova, Elena V.
AU - Jung, Bernhard
AU - Reitmann, Volker
N1 - Publisher Copyright: © 2021, IFIP International Federation for Information Processing.
PY - 2021
Y1 - 2021
N2 - This paper deals with the issue of evaluating and analyzing geometric point sets in three-dimensional space. Point sets or point clouds are often the product of 3D scanners and depth sensors, which are used in the field of autonomous movement for robots and vehicles. Therefore, for the classification of point sets within an active motion, not fully generated point clouds can be used, but knowledge can be extracted from the raw impulses of the respective time points. Attractors consisting of a continuum of stationary states and hysteretic memories can be used to couple multiple inputs over time given non-independent output quantities of a classifier and applied to suitable neural networks. In this paper, we show a way to assign input point clouds to sets of classes using hysteretic memories, which are transferable to neural networks.
AB - This paper deals with the issue of evaluating and analyzing geometric point sets in three-dimensional space. Point sets or point clouds are often the product of 3D scanners and depth sensors, which are used in the field of autonomous movement for robots and vehicles. Therefore, for the classification of point sets within an active motion, not fully generated point clouds can be used, but knowledge can be extracted from the raw impulses of the respective time points. Attractors consisting of a continuum of stationary states and hysteretic memories can be used to couple multiple inputs over time given non-independent output quantities of a classifier and applied to suitable neural networks. In this paper, we show a way to assign input point clouds to sets of classes using hysteretic memories, which are transferable to neural networks.
KW - Classification
KW - Hysteretic memory
KW - Neural network
KW - Point clouds
UR - http://www.scopus.com/inward/record.url?scp=85111869141&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/6d644e4a-b906-3685-a18e-cb87c4df0f08/
U2 - 10.1007/978-3-030-79150-6_40
DO - 10.1007/978-3-030-79150-6_40
M3 - Conference contribution
AN - SCOPUS:85111869141
SN - 9783030791490
T3 - IFIP Advances in Information and Communication Technology
SP - 505
EP - 517
BT - Artificial Intelligence Applications and Innovations - 17th IFIP WG 12.5 International Conference, AIAI 2021, Proceedings
A2 - Maglogiannis, Ilias
A2 - Macintyre, John
A2 - Iliadis, Lazaros
PB - Springer Nature
T2 - 17th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2021
Y2 - 25 June 2021 through 27 June 2021
ER -
ID: 86422203