Neural Coding Strategies for Event-Based Vision Data

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

3 Downloads (Pure)

Abstract

Neural coding schemes are powerful tools used within neuroscience. This paper introduces three different neural coding scheme formations for event-based vision data which are designed to emulate the neural behaviour exhibited by neurons under stimuli. Presented are phase-of-firing and two sparse neural coding schemes. It is determined that machine learning approaches, i.e. Convolutional Neural Network combined with a Stacked Autoencoder network, produce powerful descriptors of the patterns within events. These coding schemes are deployed in an existing action recognition template and evaluated using two popular event-based data sets.
Original languageEnglish
Title of host publicationICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Number of pages5
ISBN (Electronic)978-1-5090-6631-5
Publication statusPublished - 4 May 2020
Event2020 IEEE International Conference on Acoustics, Speech and Signal Processing - Barcelona, Spain
Duration: 4 May 20208 May 2020
https://2020.ieeeicassp.org

Conference

Conference2020 IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated titleICASSP
CountrySpain
CityBarcelona
Period4/05/208/05/20
Internet address

Keywords

  • event-based vision
  • Convolutional Neural Network (CNN)
  • encoding scheme
  • Feature Extraction
  • Object recognition

Fingerprint Dive into the research topics of 'Neural Coding Strategies for Event-Based Vision Data'. Together they form a unique fingerprint.

  • Cite this

    Harrigan, S., Coleman, S., Kerr, D., Pratheepan, Y., Fang, Z., & Wu, C. (2020). Neural Coding Strategies for Event-Based Vision Data. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)