Action in Mind: A Neural Network Approach to Action Recognition and Segmentation

Research output: ThesisDoctoral Thesis (compilation)


Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry.
This thesis presents a novel computational approach for human action recognition through different implementations of multi-layer architectures based on artificial neural networks. Each system level development is designed to solve different aspects of the action recognition problem including online real-time processing, action segmentation and the involvement of objects. The analysis of the experimental
results are illustrated and described in six articles.
The proposed action recognition architecture of this thesis is composed of several processing layers including a preprocessing layer, an ordered vector representation layer and three layers of neural networks.
It utilizes self-organizing neural networks such as Kohonen feature maps and growing grids as the main neural network layers. Thus the architecture presents a biological plausible approach with certain features such as topographic organization of the neurons, lateral interactions, semi-supervised learning and the ability to represent high dimensional input space in lower dimensional maps.
For each level of development the system is trained with the input data consisting of consecutive 3D body postures and tested with generalized input data that the system has never met before. The experimental results of different system level developments show that the system performs well with quite high accuracy for recognizing human actions.


  • Zahra Gharaee
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Computer Science
  • Human Computer Interaction
  • Computer Vision and Robotics (Autonomous Systems)


  • Action recognition, motion perception, cognitive robotics, hierarchical models, self-organizing neural networks, growing grids, attention
Original languageEnglish
Supervisors/Assistant supervisor
Place of PublicationLund
  • Lund University Cognitive Science
Print ISBNs978-91-88473-73-8
Electronic ISBNs978-91-88473-74-5
Publication statusPublished - 2018 Mar 15
Publication categoryResearch

Bibliographic note

Defence details Date: 2018-04-27 Time: 10:00 Place: C121, LUX, Helgonavägen 3, Lund External reviewer(s) Name: Cangelosi, Angelo Title: professor Affiliation: Plymouth University, England ---

Total downloads

No data available

Related research output

Zahra Gharaee, 2018.

Research output: Contribution to conferenceAbstract

Zahra Gharaee, Peter Gärdenfors & Magnus Johnsson, 2017 Jun 4, In: Applied Soft Computing. 59, p. 574-585

Research output: Contribution to journalArticle

Zahra Gharaee, Peter Gärdenfors & Magnus Johnsson, 2017, Proceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017). SciTePress, p. 583-590 8 p.

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding

View all (5)

Related projects

Magnus Johnsson, Peter Gärdenfors & Zahra Gharaee


Project: Research

Birger Johansson, Christian Balkenius, Magnus Johnsson, Rasmus Bååth, Stefan Winberg, Zahra Gharaee & Trond Arild Tjöstheim


Project: Research

View all (2)