Reliable posture labels in hospital environments can augment research studies on neural correlates to natural behaviors and clinical applications that monitor patient activity. However, many existing pose estimation frameworks are not calibrated for these unpredictable settings. In this paper, we propose a semi-automated approach for improving upper-body pose estimation in noisy clinical environments, whereby we adapt and build around an existing joint tracking framework to improve its robustness to environmental uncertainties. The proposed framework uses subject-specific convolutional neural network models trained on a subset of a patient's RGB video recording chosen to maximize the feature variance of each joint. Furthermore, by compensating for scene lighting changes and by refining the predicted joint trajectories through a Kalman filter with fitted noise parameters, the extended system yields more consistent and accurate posture annotations when compared with the two state-of-the-art generalized pose tracking algorithms for three hospital patients recorded in two research clinics. 2018 IEEE.
|Original language||English (US)|
|Journal||IEEE Journal of Translational Engineering in Health and Medicine|
|State||Published - 2018|
Bibliographical noteFunding Information:
This work was supported in part by the Hellman Fellowship, in part by the UCSD ECE Department Medical Devices & Systems Initiative, in part by the UCSD Centers for Human Brain Activity Mapping (CHBAM) and Brain Activity Mapping (CBAM), in part by the UCSD Frontiers of Innovation Scholars Program, and in part by the Qualcomm Institute Calit2 Strategic Research Opportunities (CSRO) Program.
- Clinical environments
- Convolutional neural networks
- Kalman filter
- Patient monitoring
- Pose estimation