Kinect and Episodic Reasoning for Human Action Recognition
| Data(s) |
01/06/2016
|
|---|---|
| Identificador | |
| Idioma(s) |
eng |
| Direitos |
info:eu-repo/semantics/openAccess |
| Fonte |
Cantarero , R , Santofimia , M J , Villa , D , Requena , R , Campos , M , Florez-Revuelta , F , Nebel , J-C , Martinez del Rincon , J & Lopez , J C 2016 , Kinect and Episodic Reasoning for Human Action Recognition . in Distributed Computing and Artificial Intelligence, 13th International Conference . Advances in Intelligent Systems and Computing , vol. 474 , pp. 147-154 , 13th International Conference on Distributed Computing and Artificial Intelligence (DCAI)) , Seville , Spain , 1-3 June . DOI: 10.1007/978-3-319-40162-1_16 |
| Tipo |
contributionToPeriodical |
| Resumo |
This paper presents a method for rational behaviour recognition that combines vision-based pose estimation with knowledge modeling and reasoning. The proposed method consists of two stages. First, RGB-D images are used in the estimation of the body postures. Then, estimated actions are evaluated to verify that they make sense. This method requires rational behaviour to be exhibited. To comply with this requirement, this work proposes a rational RGB-D dataset with two types of sequences, some for training and some for testing. Preliminary results show the addition of knowledge modeling and reasoning leads to a significant increase of recognition accuracy when compared to a system based only on computer vision. |
| Formato |
application/pdf |
