Action detection in in-classroom firefighter training: A 360-degree video analytics service
Tiwari, Aditi
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/124576
Description
Title
Action detection in in-classroom firefighter training: A 360-degree video analytics service
Author(s)
Tiwari, Aditi
Issue Date
2024-04-29
Director of Research (if dissertation) or Advisor (if thesis)
Nahrstedt, Klara
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
360-degree video, firefighting, action detection
Abstract
In hazardous situations like firefighting, split-second decisions can differentiate between success and failure, between life and death. Understanding the actions taken by firefighters in various scenarios can help inform decision-making processes, enabling responders to make more informed choices under pressure. Identifying actions provides valuable feedback for training programs. By reviewing and analyzing recorded firefighting actions, the instructors at the firefighter training facility can identify areas for improvement and tailor training sessions to address specific challenges or shortcomings. After a firefighting operation, analyzing the actions taken can provide insights into what worked well and what could be improved for future incidents. This post-incident analysis is essential for continuous learning and refinement of firefighting tactics and procedures, and to avoid any dangerous mistakes in the actions being performed on the field.
This research focuses on a system combining the advantage of 360-degree videos and deep learning to automatically detect important actions being performed on the field during training in the panoramic scene, assisting firefighting instructors in classroom teaching scenarios. Specifically, we summarize the salient actions and events relevant to firefighting through multiple interviews with experienced firefighting instructors. Using a unique dataset collected from a firefighting training institute, our approach successfully helps in identifying and detecting the important actions in firefighting like carrying a civilian, operating a hose, breaking a door or window, etc.
For a better reviewing experience for the user, we have integrated our system with a latency-aware Viewing and Query Service (VQS) that allows the user to choose which action they want to focus on in the video of their choice, and also at which time stamp they want to jump to save time.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
