Detection of collaborative activity with Kinect depth cameras

TL;DR

This paper presents a preliminary system using Kinect depth cameras to detect and analyze collaborative activities of elderly individuals in home environments, aiming for long-term health monitoring.

Contribution

It introduces a novel approach for detecting multiple subjects and classifying collaborative activities using depth cameras in a home setting.

Findings

Artifacts removal improves detection specificity and sensitivity.

Localization enables task classification in home environments.

Scenario validation demonstrates system feasibility.

Abstract

The health status of elderly subjects is highly correlated to their activities together with their social interactions. Thus, the long term monitoring in home of their health status, shall also address the analysis of collaborative activities. This paper proposes a preliminary approach of such a system which can detect the simultaneous presence of several subjects in a common area using Kinect depth cameras. Most areas in home being dedicated to specific tasks, the localization enables the classification of tasks, whether collaborative or not. A scenario of a 24 hours day shrunk into 24 minutes was used to validate our approach. It pointed out the need of artifacts removal to reach high specificity and good sensitivity.