DocumentCode :
3448801
Title :
Action classification of 3D human models using dynamic ANNs for mobile robot surveillance
Author :
Theodoridis, Theodoros ; Hu, Huosheng
Author_Institution :
Dept. of Comput. Sci., Univ. of Essex, Colchester
fYear :
2007
fDate :
15-18 Dec. 2007
Firstpage :
371
Lastpage :
376
Abstract :
This paper presents an alternative approach on physical human action classification implemented by mobile robots. In contrast with other action recognition methods, this research indicates the best configuration topology of a number of dynamic neural networks to be used in 3D time series classification by showing several comparison performances. In this action recognition investigation we demonstrate high level network granularity on dynamic classification and class discrimination of normal and aggressive action recognition. An interconnection between an ubiquitous 3D sensory tracker system and a mobile robot is set to create a perception to action architecture capable to perceive, process, and classify physical human actions. The robot is used as a process-to-action unit to process the 3D data taken by the tracker and to eventually generate surveillance assessment reports pointing towards action-class matchings as well as generating evaluation statistics which signify the quality of the actions recognized.
Keywords :
humanoid robots; mobile robots; neural nets; pattern classification; robot dynamics; surveillance; time series; ubiquitous computing; action recognition methods; dynamic ANN; dynamic neural networks; high level network granularity; human models; mobile robot surveillance; physical human action classification; surveillance assessment; time series classification; ubiquitous 3D sensory tracker system; Cameras; Computer architecture; Feature extraction; Hidden Markov models; Humans; Matching pursuit algorithms; Mathematical model; Mobile robots; Neural networks; Surveillance; Ubiquitous robotics; dynamic NN classifiers; kinematic models; time domain feature extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Biomimetics, 2007. ROBIO 2007. IEEE International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-1761-2
Electronic_ISBN :
978-1-4244-1758-2
Type :
conf
DOI :
10.1109/ROBIO.2007.4522190
Filename :
4522190
Link To Document :
بازگشت