Human Daily Activities Indexing in Videos from Wearable Cameras for Monitoring of Patients with Dementia Diseases

TL;DR

This paper presents a method for indexing daily human activities in videos from wearable cameras to monitor dementia patients, using a Hidden Markov Model with novel features for activity recognition.

Contribution

It introduces a structural model based on Hidden Markov Models with new spatio-temporal, color, and localization features for activity recognition in noisy, high-dimensional data.

Findings

Initial activity recognition results are promising.

New features improve modeling of human activities.

Effective monitoring of dementia patients through wearable camera data.

Abstract

Our research focuses on analysing human activities according to a known behaviorist scenario, in case of noisy and high dimensional collected data. The data come from the monitoring of patients with dementia diseases by wearable cameras. We define a structural model of video recordings based on a Hidden Markov Model. New spatio-temporal features, color features and localization features are proposed as observations. First results in recognition of activities are promising.