Online Feature Extraction and Event Generation for Computer-Animal Interaction

Leon Bonde Larsen*, Mathias Mikkel Neerup

*Corresponding author for this work

Research output: Contribution to conference without publisher/journalConference abstract for conferenceResearch

Abstract

This talk will present an architecture developed to investigate the interaction with and between animals. The architecture allows online processing of multimedia streams and the generation, storing and visualizing of events using feature extraction. It allows biologists to analyze the events by monitoring live or by replaying streams through a web interface Docker swarm is the central component of the architecture and serves as infrastructure for stream processing, event generation, event processing and visualization. The main entry point for users is a web interface that spins up one container per user and allows independent replay of streams. This talk will focus on the architecture and on technical details concerning its implementation as well as how docker is utilized to process, store and visualize events. Some time will be spent explaining details about custom made docker solutions. Speaker: Mathias Mikkel Neerup, Scientific Assistant, University of Southern Denmark
Original languageEnglish
Publication date30. Apr 2019
Publication statusPublished - 30. Apr 2019
EventDockerCon19 - San Francisco, United States
Duration: 29. Apr 201910. May 2019
https://www.docker.com/dockercon/

Conference

ConferenceDockerCon19
Country/TerritoryUnited States
CitySan Francisco
Period29/04/201910/05/2019
Internet address

Keywords

  • docker
  • event-stream processing
  • events
  • biology methods

Fingerprint

Dive into the research topics of 'Online Feature Extraction and Event Generation for Computer-Animal Interaction'. Together they form a unique fingerprint.

Cite this