Work Package 2: Video Monitoring
Lead Academic: Professor Majid Mirmehdi (University of Bristol)
With: Dr Dima Damen, Dr Neill Campbell (University of Bristol)
The main objectives of WP2 consist of developing an efficient, real-time multi-camera system for activity monitoring in the home environment. The system will be based on low cost cameras and depth sensors to estimate client’s position and to analyse their movements to extract features for use for action understanding and activity recognition.
The Work Package will be built upon the implementation of a real time multi-camera system comprised of a combination of low-cost RGB-D cameras (Microsoft Kinect, Asus Xtion, Prime Sense) and wide angle traditional monocular low-cost colour cameras (such as Genius WideCam 1050). We anticipate that each SPHERE home will be equipped with a minimum of 5 such devices, with the RGB-D cameras being stationed advantageously such that specific actions such as sitting to standing (in front of the television) and ascending the stairs might best be observed.
The vision team are developing a video based action recognition and multi-user tracking system for the house environment. This solution will allow the system to estimate the activity/inactivity level of the user during their daily life. The platform has been tested in SPHERE’s house and integrated with the other sensor systems; providing a unique multisensory system for data collection. On-going video work includes a collaboration with respiratory physicians in Bristol developing and validating video-based systems for monitoring breathing.
Online quality assessment of human movements from skeleton data
The objective of this project is to evaluate the quality of human movements from visual information. This has use in a broad range of applications, such as diagnosis and rehabilitation.
Depth Scaling Kernelised Correlation Filters DS-KCF
The objective of this project is to develop a efficient Real-time tracker based on RGB-D data provided by the Video Sensors of the SPHERE platform. The most recent version of DS-KCF (including C++ code and shape module) can be found here. First version of the DS-KCF presented at BMVC 2015 can be found here.
A Comparative Home Activity Monitoring Study using Visual and Inertial Sensors
The objective of this project is to present a comparative study towards activity monitoring using these visual and accelerometer sensors in daily living scenarios.
Calorie Counter: RGB-Depth Visual Estimation of Energy Expenditure at Home
This project presents a new framework for vision-based estimation of calorific expenditure from RGB-D data in daily living scenarios.