Clinical assessment of depth sensor based pose estimation algorithms for technology supervised rehabilitation applications. (January 2019)

• Record Type: Journal Article
• Authors: Sarsfield, Joe; Brown, David; Sherkat, Nasser; Langensiepen, Caroline; Lewis, James; Taheri, Mohammad; McCollin, Christopher; Barnett, Cleveland; Selwood, Louise; Standen, Penny; Logan, Pip; Simcox, Christopher; Killick, Catherine; Hughes, Emma
• Is Part Of: International journal of medical informatics. Volume 121(2019)
• Page Start: 30
• Page End: 38
• Publication Date: 2019-01
• Subjects: Stroke rehabilitation -- Home rehabilitation -- Clinical evaluation -- Depth sensors -- Pose estimation accuracy; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2018.11.001
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: Clinical analysis required to determine suitability of pose estimation algorithm. Joint rotation required for more in-depth and correct assessment. Exploit temporal information to ameliorate issues with occlusion. Constrain joint estimations to within the anatomical limits of the human body. Consult clinicians to select exercises that provide fewer challenges for algorithm. Abstract: Encouraging rehabilitation by the use of technology in the home can be a cost-effective strategy, particularly if consumer-level equipment can be used. We present a clinical qualitative and quantitative analysis of the pose estimation algorithms of a typical consumer unit (Xbox One Kinect), to assess its suitability for technology supervised rehabilitation and guide development of future pose estimation algorithms for rehabilitation applications. We focused the analysis on upper-body stroke rehabilitation as a challenging use case. We found that the algorithms require improved joint tracking, especially for the shoulder, elbow and wrist joints, and exploiting temporal information for tracking when there is full or partial occlusion in the depth data.