Kinect and Episodic Reasoning for Human Action Recognition

Ruben Cantarero; Maria J. Santofimia; David Villa; Roberto Requena; Maria Campos; Francisco Florez-Revuelta; Jean-Christophe Nebel; Jesus Martinez del Rincon; Juan C. Lopez

doi:10.1007/978-3-319-40162-1_16

Kinect and Episodic Reasoning for Human Action Recognition

Ruben Cantarero, Maria J. Santofimia, David Villa, Roberto Requena, Maria Campos, Francisco Florez-Revuelta, Jean-Christophe Nebel, Jesus Martinez del Rincon, Juan C. Lopez

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

2 Citations (Scopus)

591 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	Distributed Computing and Artificial Intelligence, 13th International Conference
Pages	147-154
Number of pages	8
ISBN (Electronic)	978-3-319-40162-1
DOIs	https://doi.org/10.1007/978-3-319-40162-1_16
Publication status	Published - Jun 2016
Event	13th International Conference on Distributed Computing and Artificial Intelligence (DCAI)) - Seville, Spain Duration: 01 Jun 2016 → 03 Jun 2016

Publication series

Name	Advances in Intelligent Systems and Computing
Publisher	Springer International Publishing
Volume	474
ISSN (Print)	2194-5357

Conference

Conference	13th International Conference on Distributed Computing and Artificial Intelligence (DCAI))
Country/Territory	Spain
City	Seville
Period	01/06/2016 → 03/06/2016

Access to Document

10.1007/978-3-319-40162-1_16Licence: Unspecified

Kinect and Episodic Reasoning for Human Action Recognition
© 2016 Springer International Publishing
Accepted author manuscript, 284 KBLicence: Unspecified

Cite this

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 (pp. 147-154). (Advances in Intelligent Systems and Computing; Vol. 474). https://doi.org/10.1007/978-3-319-40162-1_16

@inbook{5c7849221c2e43f9827d6820a59fe79d,

title = "Kinect and Episodic Reasoning for Human Action Recognition",

abstract = "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. ",

author = "Ruben Cantarero and Santofimia, \{Maria J.\} and David Villa and Roberto Requena and Maria Campos and Francisco Florez-Revuelta and Jean-Christophe Nebel and \{Martinez del Rincon\}, Jesus and Lopez, \{Juan C.\}",

year = "2016",

month = jun,

doi = "10.1007/978-3-319-40162-1\_16",

language = "English",

isbn = "978-3-319-40161-4",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer International Publishing",

pages = "147--154",

booktitle = "Distributed Computing and Artificial Intelligence, 13th International Conference",

note = "13th International Conference on Distributed Computing and Artificial Intelligence (DCAI)) ; Conference date: 01-06-2016 Through 03-06-2016",

}

Cantarero, R, Santofimia, MJ, Villa, D, Requena, R, Campos, M, Florez-Revuelta, F, Nebel, J-C, Martinez del Rincon, J & Lopez, JC 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, 01/06/2016. https://doi.org/10.1007/978-3-319-40162-1_16

Kinect and Episodic Reasoning for Human Action Recognition. / Cantarero, Ruben; Santofimia, Maria J.; Villa, David et al.
Distributed Computing and Artificial Intelligence, 13th International Conference. 2016. p. 147-154 (Advances in Intelligent Systems and Computing; Vol. 474).

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

TY - CHAP

T1 - Kinect and Episodic Reasoning for Human Action Recognition

AU - Cantarero, Ruben

AU - Santofimia, Maria J.

AU - Villa, David

AU - Requena, Roberto

AU - Campos, Maria

AU - Florez-Revuelta, Francisco

AU - Nebel, Jean-Christophe

AU - Martinez del Rincon, Jesus

AU - Lopez, Juan C.

PY - 2016/6

Y1 - 2016/6

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-319-40162-1_16

DO - 10.1007/978-3-319-40162-1_16

M3 - Chapter (peer-reviewed)

SN - 978-3-319-40161-4

T3 - Advances in Intelligent Systems and Computing

SP - 147

EP - 154

BT - Distributed Computing and Artificial Intelligence, 13th International Conference

T2 - 13th International Conference on Distributed Computing and Artificial Intelligence (DCAI))

Y2 - 1 June 2016 through 3 June 2016

ER -

Kinect and Episodic Reasoning for Human Action Recognition

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this