The Community for Technology Leaders
2014 International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2014)
Seoul, South Korea
Aug. 26, 2014 to Aug. 29, 2014
ISBN: 978-1-4799-4871-0
pp: 142-147
Luc Brun , GREYC UMR CNRS 6072 ENSICAEN - Université de Caen Basse-Normandie 14050 Caen, France
Gennaro Percannella , Dept. of Information Eng. and Electrical Eng. and Applied Mathematics University of Salerno Via Giovanni Paolo II, 132, Fisciano (SA), Italy
Alessia Saggese , Dept. of Information Eng. and Electrical Eng. and Applied Mathematics University of Salerno Via Giovanni Paolo II, 132, Fisciano (SA), Italy
Mario Vento , Dept. of Information Eng. and Electrical Eng. and Applied Mathematics University of Salerno Via Giovanni Paolo II, 132, Fisciano (SA), Italy
ABSTRACT
In this paper we propose HAcK, a novel method for recognizing Human Actions by string Kernel; the main idea is to represent each action through a sequence of visual characters, namely a string, able to model the temporal evolution of the events. Visual characters are extracted by analyzing global descriptors of the scene and by taking advantage on the depth information provided by a Kinect sensor. The similarity between actions is evaluated with a fast global alignment kernel, which allows to deal with actions of different length as well as with the noise introduced during the features extraction step. HAcK has been evaluated over two standard datasets and the obtained results, compared with state of the art approaches, confirm its effectiveness and its applicability in real environments.
INDEX TERMS
Kernel, Visualization, Vectors, Feature extraction, Training, Computer hacking, Protocols
CITATION

L. Brun, G. Percannella, A. Saggese and M. Vento, "HAck: A system for the recognition of human actions by kernels of visual strings," 2014 International Conference on Advanced Video and Signal Based Surveillance (AVSS), Seoul, South Korea, 2014, pp. 142-147.
doi:10.1109/AVSS.2014.6918658
97 ms
(Ver 3.3 (11022016))