Towards a mobility diagnostic tool: Tracking rollator users' leg pose with a monocular vision system

• Published in: 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 2009; pp. 1220 - 1225
• Main Authors: Ng, S., Fakih, A., Fourney, A., Poupart, P., Zelek, J.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01-01-2009
• Subjects: Activities of Daily Living; Bayes Theorem; Bayesian methods; Biomedical Engineering; Cameras; Cognition Disorders - physiopathology; Cognition Disorders - rehabilitation; Cognition Disorders - therapy; Diagnosis, Computer-Assisted; Humans; Image segmentation; Intelligent sensors; Leg; Legged locomotion; Machine vision; Mobility Limitation; Models, Biological; Motion estimation; Navigation; Stability; Walkers; Walking - physiology
• ISSN: 1094-687X; 1557-170X; 1558-4615
• DOI: 10.1109/IEMBS.2009.5333085

Cognitive assistance of a rollator (wheeled walker) user tends to reduce the attentional capacity of the user and may impact her stability. Hence, it is important to understand and track the pose of rollator users before augmenting a rollator with some form of cognitive assistance. While the majority of current markerless vision systems focus on estimating 2D and 3D walking motion in the sagittal plane, we wish to estimate the 3D pose of rollator users' lower limbs from observing image sequences in the coronal (frontal) plane. Our apparatus poses a unique set of challenges: a single monocular view of only the lower limbs and a frontal perspective of the rollator user. Since motion in the coronal plane is relatively subtle, we explore multiple cues within a Bayesian probabilistic framework to formulate a posterior estimate for a given subject's leg limbs. In this work, our focus is on evaluating the appearance model (the cues). Preliminary experiments indicate that texture and colour cues conditioned on the appearance of a rollator user outperform more general cues, at the cost of manually initializing the appearance offline.