Privacy-Preserving Human Activity Recognition for Healthcare using Large Vision-Language Models

This project will develop privacy-preserving human activity recognition algorithms for healthcare, especially senior care and remote patient monitoring. We will develop algorithms in three areas: 1) Video-based high-performance and fast pose estimation algorithms running in the sensor. 2) Advanced stick-figure-based action recognition methods that run in the cloud. 3) Stick-figure-based large vision and language model (VLM) methods in the cloud. The developed algorithms will be implemented into the industry partner’s product, which will benefit seniors and patients in Canada and around the world.

Faculty Supervisor:

Zhenman Fang;Xiaoxiao Li;Zhenman Fang

Student:

Partner:

Altumview Systems Inc

Discipline:

Life Sciences

Sector:

Information and cultural industries; Manufacturing; Professional, scientific and technical services

University:

Simon Fraser University; The University of British Columbia

Program:

Elevate

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects