Chasing feet in the wild: A proposed egocentric motion-aware gait assessment tool

Nouredanesh, Mina, Li, Aaron, Godfrey, Alan, Hoey, Jesse and Tung, James (2019) Chasing feet in the wild: A proposed egocentric motion-aware gait assessment tool. In: Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings. Lecture Notes in Computer Science, 1 (11134). Springer, pp. 176-192. ISBN 9783030012458

[img] Text (Chapter text)
Nouredanesh et al - Chasing feet in the wild AAM.pdf - Accepted Version
Restricted to Repository staff only until 23 January 2020.

Download (5MB)
Official URL: https://link.springer.com/chapter/10.1007%2F978-3-...

Abstract

Despite advances in gait analysis tools, including optical motion capture and wireless electrophysiology, our understanding of human mobility is largely limited to controlled conditions in a clinic and/or laboratory. In order to examine human mobility under natural conditions, or the 'wild', this paper presents a novel markerless model to obtain gait patterns by localizing feet in the egocentric video data. Based on a belt-mounted camera feed, the proposed hybrid FootChaser model consists of: 1) the FootRegionProposer, a ConvNet that proposes regions with high probability of containing feet in RGB frames (global appearance of feet), and 2) LocomoNet, which is sensitive to the periodic gait patterns, and further examines the temporal content in the stacks of optical low corresponding to the proposed region. The LocomoNet signicantly boosted the overall model's result by ltering out the false positives proposed by the FootRegionProposer. This work advances our long-term objective to develop novel markerless models to extract spatiotemporal gait parameters, particularly step width, to complement existing inertial measurement unit (IMU) based methods.

Item Type: Book Section
Uncontrolled Keywords: Ambulatory gait analysis, Wearable sensors, Deep convolutional neural networks, Egocentric vision, Optical flow
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: Becky Skoyles
Date Deposited: 18 Sep 2018 08:14
Last Modified: 12 Oct 2019 11:33
URI: http://nrl.northumbria.ac.uk/id/eprint/35755

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence