Kamrad Khoshhal Homepage


  • Increase font size
  • Default font size
  • Decrease font size


E-mail Print PDF

    Researcher for the AMS-HMI12 Project- 





The LMA-based Human Movement, Action and Interaction analysis Matlab codes were written by Kamrad Khoshhal Roudposhti. 

Needed steps to run:

2.Install BNT code on current Path : for more information about BNT ( https://code.google.com/p/bnt/ )

1.Open xsens-XML parser codes zip file which provided by ISR-MRL UC group to the current path. Find from : http://mrl.isr.uc.pt/experimentaldata/public/uc-3d/#supportsoftware

This version was last updated on 1/1/2013.

To download the latest version, and to get documentation, please go to


PhD thesis research Founded by FCT (Foundation of Science and Technology)  (2011 - 2014). 


Probabilistic LMA-based Human Behaviour Understanding by Conjugation of Frequency and Spatial Domains
Project Type: PhD Project
Sponsors: Portuguese Foundation for Science and Technology (FCT) - SFRH/BD/70640/2010

This application addresses one plan for research on computational systems for human behaviour analysis (HBA) in scenes with single or multi-persons. The objective is to develop algorithms and techniques that automatically describe the interaction between persons or the interaction of persons with objects. The impact of the results will be important for applications of automatic surveillance of infra-structures or automatic support for home care such as abnormal behaviour detection or supporting elderly and disabled people. This thesis will direct our work to representation based on Laban movement analysis (LMA) for human´s movement, action and behaviour understanding. We intend to define the best solution for our problems in terms of using 3D-based data by a multi-sensing framework with cameras, microphone and laser. The frequency and spatial-based techniques will be defined to detect features used for Bayesian-based classifiers to obtain LMA-based human motion features.


 Researcher for the PROMETHEUS European Project  (May 2008 - Dec. 2010)


PROMETHEUS - Prediction and interpretation of human behaviour based on probabilistic structures and heterogeneous sensors
Project Type: General Research Project
Sponsors: European Comission
The project intends to establish a link between fundamental sensing tasks and automated cognition processes that concern the understanding a short-term prediction of human behaviour as well as complex human interaction. The analysis of human behaviour is unrestricted environments, including localization and tracking of multiple people and recognition of their activities, currently constitutes a topic of intensive research in the signal processing and computer vision communities. This research is driven by different important applications, including unattended surveillance and intelligent space monitoring.

Last Updated on Wednesday, 22 July 2015 10:43