315
Views
10
CrossRef citations to date
0
Altmetric
Research Paper

Development and evaluation of a hand tracker using depth images captured from an overhead perspective

&
Pages 150-157 | Received 26 Nov 2014, Accepted 05 Mar 2015, Published online: 27 Mar 2015
 

Abstract

Purpose: We present the development and evaluation of a robust hand tracker based on single overhead depth images for use in the COACH, an assistive technology for people with dementia. The new hand tracker was designed to overcome limitations experienced by the COACH in previous clinical trials. Methods: We train a random decision forest classifier using ∼5000 manually labeled, unbalanced, training images. Hand positions from the classifier are translated into task actions based on proximity to environmental objects. Tracker performance is evaluated using a large set of ∼24 000 manually labeled images captured from 41 participants in a fully-functional washroom, and compared to the system’s previous colour-based hand tracker. Results: Precision and recall were 0.994 and 0.938 for the depth tracker compared to 0.981 and 0.822 for the colour tracker with the current data, and 0.989 and 0.466 in the previous study. Conclusions: The improved tracking performance supports integration of the depth-based tracker into the COACH toward unsupervised, real-world trials.

    Implications for Rehabilitation

  • The COACH is an intelligent assistive technology that can enable people with cognitive disabilities to stay at home longer, supporting the concept of aging-in-place.

  • Automated prompting systems, a type of intelligent assistive technology, can help to support the independent completion of activities of daily living, increasing the independence of people with cognitive disabilities while reducing the burden of care experienced by caregivers.

  • Robust motion tracking using depth imaging supports the development of intelligent assistive technologies like the COACH.

  • Robust motion tracking also has application to other forms of assistive technologies including gaming, human–computer interaction and automated assessments.

Declaration of interest

The study was funded by grants from the Alzheimer Association (ETAC), Canadian Institute of Health Research (Operating Grant) and the NSERC CREATE CARE program.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.