Neuromorphic Event-based Action Recognition

Shane Harrigan; Sonya Coleman; Dermot Kerr; Y Pratheepan; Fang Zheng; Chengdong Wu

Neuromorphic Event-based Action Recognition

Shane Harrigan, Sonya Coleman, Dermot Kerr, Y Pratheepan, Fang Zheng, Chengdong Wu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

124 Downloads (Pure)

Abstract

An action can be viewed as spike trains or streams of events when observed and captured by neuromorphic imaging hardware such as the iniLabs DVS128. These streams are unique to each action enabling them to be used to form descriptors. This paper describes an approach for detecting specific actions based on space-time template matching by forming such descriptors and using them as comparative tools. The developed approach is used to detect symbols from the popular RoShambo (rock, paper and scissors) game. The results demonstrate that the developed approach can be used to correctly detect the motions involved in producing RoShambo symbols.

Original language	English
Title of host publication	Irish Machine Vision and Image Processing Conference
Publisher	Irish Pattern Recognition and Classification Society
Pages	218 - 221
Number of pages	3
ISBN (Print)	978-0-9934207-4-0
Publication status	Published (in print/issue) - 28 Aug 2019

Keywords

action detection
neuromorphic processing
space-time
RoShambo.

Access to Document

IMVIP_2019_short_paper_Camera_ReadyAuthor Accepted Manuscript, 4.04 MB

http://www.imvip.ie/2019%20IMVIP%20Proceedings.pdf

Cite this

@inproceedings{e8c5d4cd10154dfda205ac8713f04dc7,

title = "Neuromorphic Event-based Action Recognition",

abstract = "An action can be viewed as spike trains or streams of events when observed and captured by neuromorphic imaging hardware such as the iniLabs DVS128. These streams are unique to each action enabling them to be used to form descriptors. This paper describes an approach for detecting specific actions based on space-time template matching by forming such descriptors and using them as comparative tools. The developed approach is used to detect symbols from the popular RoShambo (rock, paper and scissors) game. The results demonstrate that the developed approach can be used to correctly detect the motions involved in producing RoShambo symbols.",

keywords = "action detection, neuromorphic processing, space-time, RoShambo.",

author = "Shane Harrigan and Sonya Coleman and Dermot Kerr and Y Pratheepan and Fang Zheng and Chengdong Wu",

year = "2019",

month = aug,

day = "28",

language = "English",

isbn = "978-0-9934207-4-0",

pages = "218 -- 221",

booktitle = "Irish Machine Vision and Image Processing Conference",

publisher = "Irish Pattern Recognition and Classification Society",

address = "Ireland",

}

TY - GEN

T1 - Neuromorphic Event-based Action Recognition

AU - Harrigan, Shane

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - Pratheepan, Y

AU - Zheng, Fang

AU - Wu, Chengdong

PY - 2019/8/28

Y1 - 2019/8/28

N2 - An action can be viewed as spike trains or streams of events when observed and captured by neuromorphic imaging hardware such as the iniLabs DVS128. These streams are unique to each action enabling them to be used to form descriptors. This paper describes an approach for detecting specific actions based on space-time template matching by forming such descriptors and using them as comparative tools. The developed approach is used to detect symbols from the popular RoShambo (rock, paper and scissors) game. The results demonstrate that the developed approach can be used to correctly detect the motions involved in producing RoShambo symbols.

AB - An action can be viewed as spike trains or streams of events when observed and captured by neuromorphic imaging hardware such as the iniLabs DVS128. These streams are unique to each action enabling them to be used to form descriptors. This paper describes an approach for detecting specific actions based on space-time template matching by forming such descriptors and using them as comparative tools. The developed approach is used to detect symbols from the popular RoShambo (rock, paper and scissors) game. The results demonstrate that the developed approach can be used to correctly detect the motions involved in producing RoShambo symbols.

KW - action detection

KW - neuromorphic processing

KW - space-time

KW - RoShambo.

M3 - Conference contribution

SN - 978-0-9934207-4-0

SP - 218

EP - 221

BT - Irish Machine Vision and Image Processing Conference

PB - Irish Pattern Recognition and Classification Society

ER -

Neuromorphic Event-based Action Recognition

Abstract

Keywords

Access to Document

Fingerprint

Cite this