Video-based Concurrent Activity Recognition for Trauma Resuscitation

Yanyi Zhang, Yue Gu, Ivan Marsic, Yinan Zheng, Randall S. Burd

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

Abstract

We introduce a video-based system for concurrent activity recognition during teamwork in a clinical setting. During system development, we preserved patient and provider privacy by pre-computing spatio-Temporal features. We extended the inflated 3D ConvNet (i3D) model for concurrent activity recognition. For the model training, we tuned the weights of the final stages of i3D using back-propagated loss from the fully-connected layer. We applied filtering on the model predictions to remove noisy predictions. We evaluated the system on five activities performed during trauma resuscitation, the initial management of injured patients in the emergency department. Our system achieved an average value of 74% average precision (AP) for these five activities and outperformed previous systems designed for the same domain. We visualized feature maps from the model, showing that the system learned to focus on regions relevant to performance of each activity.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Healthcare Informatics, ICHI 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728153827
DOIs
StatePublished - Nov 2020
Event8th IEEE International Conference on Healthcare Informatics, ICHI 2020 - Virtual, Oldenburg, Germany
Duration: Nov 30 2020Dec 3 2020

Publication series

Name2020 IEEE International Conference on Healthcare Informatics, ICHI 2020

Conference

Conference8th IEEE International Conference on Healthcare Informatics, ICHI 2020
Country/TerritoryGermany
CityVirtual, Oldenburg
Period11/30/2012/3/20

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Decision Sciences (miscellaneous)
  • Modeling and Simulation
  • Medicine (miscellaneous)
  • Health Informatics
  • Health(social science)

Keywords

  • clinical teamwork
  • concurrent activity recognition
  • video understanding

Fingerprint

Dive into the research topics of 'Video-based Concurrent Activity Recognition for Trauma Resuscitation'. Together they form a unique fingerprint.

Cite this