A Human Action Descriptor Based on Motion Coordination

Pietro Falco; Matteo Saveriano; Eka Gibran Hasany; Nicholas H. Kirk; Dongheui Lee

doi:10.1109/LRA.2017.2652494

A Human Action Descriptor Based on Motion Coordination

Pietro Falco, Matteo Saveriano, Eka Gibran Hasany, Nicholas H. Kirk, Dongheui Lee

Computation, Information and Technology

Technical University of Munich

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

In this paper, we present a descriptor for human whole-body actions based on motion coordination. We exploit the principle, well known in neuromechanics, that humans move their joints in a coordinated fashion. Our coordination-based descriptor (CODE) is computed by two main steps. The first step is to identify the most informative joints which characterize the motion. The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints. In order to compute the distances between action descriptors, we propose a novel correlation-based similarity measure. The performance of CODE is tested on two public datasets, namely HDM05 and Berkeley MHAD, and compared with state-of-the-art approaches, showing recognition results.

Original language	English
Article number	7815304
Pages (from-to)	811-818
Number of pages	8
Journal	IEEE Robotics and Automation Letters
Volume	2
Issue number	2
DOIs	https://doi.org/10.1109/LRA.2017.2652494
State	Published - Apr 2017

Keywords

Gesture
human factors and human-in-the-loop
human-centered automation
posture and facial expressions

Access to Document

10.1109/LRA.2017.2652494

Cite this

@article{4eb946b06f314eab8a0e101b67abf23d,

title = "A Human Action Descriptor Based on Motion Coordination",

abstract = "In this paper, we present a descriptor for human whole-body actions based on motion coordination. We exploit the principle, well known in neuromechanics, that humans move their joints in a coordinated fashion. Our coordination-based descriptor (CODE) is computed by two main steps. The first step is to identify the most informative joints which characterize the motion. The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints. In order to compute the distances between action descriptors, we propose a novel correlation-based similarity measure. The performance of CODE is tested on two public datasets, namely HDM05 and Berkeley MHAD, and compared with state-of-the-art approaches, showing recognition results.",

keywords = "Gesture, human factors and human-in-the-loop, human-centered automation, posture and facial expressions",

author = "Pietro Falco and Matteo Saveriano and Hasany, {Eka Gibran} and Kirk, {Nicholas H.} and Dongheui Lee",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.",

year = "2017",

month = apr,

doi = "10.1109/LRA.2017.2652494",

language = "English",

volume = "2",

pages = "811--818",

journal = "IEEE Robotics and Automation Letters",

issn = "2377-3766",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - A Human Action Descriptor Based on Motion Coordination

AU - Falco, Pietro

AU - Saveriano, Matteo

AU - Hasany, Eka Gibran

AU - Kirk, Nicholas H.

AU - Lee, Dongheui

PY - 2017/4

Y1 - 2017/4

N2 - In this paper, we present a descriptor for human whole-body actions based on motion coordination. We exploit the principle, well known in neuromechanics, that humans move their joints in a coordinated fashion. Our coordination-based descriptor (CODE) is computed by two main steps. The first step is to identify the most informative joints which characterize the motion. The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints. In order to compute the distances between action descriptors, we propose a novel correlation-based similarity measure. The performance of CODE is tested on two public datasets, namely HDM05 and Berkeley MHAD, and compared with state-of-the-art approaches, showing recognition results.

AB - In this paper, we present a descriptor for human whole-body actions based on motion coordination. We exploit the principle, well known in neuromechanics, that humans move their joints in a coordinated fashion. Our coordination-based descriptor (CODE) is computed by two main steps. The first step is to identify the most informative joints which characterize the motion. The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints. In order to compute the distances between action descriptors, we propose a novel correlation-based similarity measure. The performance of CODE is tested on two public datasets, namely HDM05 and Berkeley MHAD, and compared with state-of-the-art approaches, showing recognition results.

KW - Gesture

KW - human factors and human-in-the-loop

KW - human-centered automation

KW - posture and facial expressions

UR - http://www.scopus.com/inward/record.url?scp=85052196831&partnerID=8YFLogxK

U2 - 10.1109/LRA.2017.2652494

DO - 10.1109/LRA.2017.2652494

M3 - Article

AN - SCOPUS:85052196831

SN - 2377-3766

VL - 2

SP - 811

EP - 818

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

IS - 2

M1 - 7815304

ER -

A Human Action Descriptor Based on Motion Coordination

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this