Neuromorphic Event-based Action Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

41 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 languageEnglish
Title of host publicationIrish Machine Vision and Image Processing Conference
PublisherIrish Pattern Recognition and Classification Society
Pages218 - 221
Number of pages3
ISBN (Print)978-0-9934207-4-0
Publication statusPublished - 28 Aug 2019

Keywords

  • action detection
  • neuromorphic processing
  • space-time
  • RoShambo.

Fingerprint Dive into the research topics of 'Neuromorphic Event-based Action Recognition'. Together they form a unique fingerprint.

  • Cite this

    Harrigan, S., Coleman, S., Kerr, D., Pratheepan, Y., Zheng, F., & Wu, C. (2019). Neuromorphic Event-based Action Recognition. In Irish Machine Vision and Image Processing Conference (pp. 218 - 221). Irish Pattern Recognition and Classification Society. http://www.imvip.ie/2019%20IMVIP%20Proceedings.pdf