Online Recognition of Actions Involving Objects
(2017) In Biologically Inspired Cognitive Architectures 22. p.10-19- Abstract
- We present an online system for real time recognition of actions involving objects working in online mode. The system merges two streams of information pro- cessing running in parallel. One is carried out by a hierarchical self-organizing map (SOM) system that recognizes the performed actions by analysing the spa- tial trajectories of the agent’s movements. It consists of two layers of SOMs and a custom made supervised neural network. The activation sequences in the first layer SOM represent the sequences of significant postures of the agent during the performance of actions. These activation sequences are subsequently recoded and clustered in the second layer SOM, and then labeled by the ac- tivity in the third layer custom made... (More)
- We present an online system for real time recognition of actions involving objects working in online mode. The system merges two streams of information pro- cessing running in parallel. One is carried out by a hierarchical self-organizing map (SOM) system that recognizes the performed actions by analysing the spa- tial trajectories of the agent’s movements. It consists of two layers of SOMs and a custom made supervised neural network. The activation sequences in the first layer SOM represent the sequences of significant postures of the agent during the performance of actions. These activation sequences are subsequently recoded and clustered in the second layer SOM, and then labeled by the ac- tivity in the third layer custom made supervised neural network. The second information processing stream is carried out by a second system that determines which object among several in the agent’s vicinity the action is applied to. This is achieved by applying a proximity measure. The presented method combines the two information processing streams to determine what action the agent per- formed and on what object. The action recognition system has been tested with excellent performance. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/8567677
- author
- Gharaee, Zahra LU ; Gärdenfors, Peter LU and Johnsson, Magnus LU
- organization
- publishing date
- 2017-10-10
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Hierarchical models, Self-organizing maps, Action recognition, Object detection
- in
- Biologically Inspired Cognitive Architectures
- volume
- 22
- pages
- 10 - 19
- publisher
- Elsevier
- external identifiers
-
- scopus:85021179496
- wos:000418309200002
- ISSN
- 2212-6848
- DOI
- 10.1016/j.bica.2017.09.007
- project
- Ikaros: An infrastructure for system level modelling of the brain
- What you say is what you did (WYSIWYD)
- Thinking in Time: Cognition, Communication and Learning
- language
- English
- LU publication?
- yes
- id
- 6d1299b8-0bba-4f57-af20-fced586cf4d4 (old id 8567677)
- date added to LUP
- 2016-04-04 08:36:05
- date last changed
- 2022-02-20 21:56:13
@article{6d1299b8-0bba-4f57-af20-fced586cf4d4, abstract = {{We present an online system for real time recognition of actions involving objects working in online mode. The system merges two streams of information pro- cessing running in parallel. One is carried out by a hierarchical self-organizing map (SOM) system that recognizes the performed actions by analysing the spa- tial trajectories of the agent’s movements. It consists of two layers of SOMs and a custom made supervised neural network. The activation sequences in the first layer SOM represent the sequences of significant postures of the agent during the performance of actions. These activation sequences are subsequently recoded and clustered in the second layer SOM, and then labeled by the ac- tivity in the third layer custom made supervised neural network. The second information processing stream is carried out by a second system that determines which object among several in the agent’s vicinity the action is applied to. This is achieved by applying a proximity measure. The presented method combines the two information processing streams to determine what action the agent per- formed and on what object. The action recognition system has been tested with excellent performance.}}, author = {{Gharaee, Zahra and Gärdenfors, Peter and Johnsson, Magnus}}, issn = {{2212-6848}}, keywords = {{Hierarchical models; Self-organizing maps; Action recognition; Object detection}}, language = {{eng}}, month = {{10}}, pages = {{10--19}}, publisher = {{Elsevier}}, series = {{Biologically Inspired Cognitive Architectures}}, title = {{Online Recognition of Actions Involving Objects}}, url = {{http://dx.doi.org/10.1016/j.bica.2017.09.007}}, doi = {{10.1016/j.bica.2017.09.007}}, volume = {{22}}, year = {{2017}}, }