Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Technical Advances in Body-Worn Camera Video Understanding

Back to the PSCR 2020 Portal

Technical Advances in Body-Worn Camera Video Understanding_On-Demand Session.mp4
Technical Advances in Body-Worn Camera Video Understanding_On-Demand Session.mp4
Our project is focusing on developing a new level of analytical capability in body-worn cameras for public safety. BOCA analyzes human activity from body-worn cameras with minimum human effort for data annotation by leveraging available regularity in the data as well as preexisting labeled data from third-person fixed-camera-view scenarios; it adapts ideas from transfer learning and multi-task clustering to overcome the following key challenges to realizing state-of-the-art body-worn camera analytics in public safety. This talk will present our recent finding on transfer learning for activity understanding in body-worn cameras, it will discuss mechanisms for leveraging attention in understanding body-worn cameras and it will discuss the challenge of scene understanding from body-worn cameras.


  • Jason Corso, University of Michigan
  • Chenliang Xo, University of Michigan
  • Tom Yan, University of Michigan
  • Kyle Min, University of Michigan

Related Content

Created May 19, 2020, Updated October 28, 2020