Multimodal Sleeping Posture Classification

Abstract

Sleeping posture reveals important information for eldercare and patient care, especially for bed ridden patients. Traditionally, some works address the problem from either pressure sensor or video image. This paper presents a multimodal approach to sleeping posture classification. Features from pressure sensor map and video image have been proposed in order to characterize the posture patterns. The spatiotemporal registration of the two modalities has been considered in the design, and the joint feature extraction and data fusion is presented. Using multi-class SVM, experiment results demonstrate that the multimodal approach achieves better performance than the approaches using single modal sensing.

Sleep Pose Recognition in an ICU Using Multimodal Data and Environmental Feedback

“…Greater order moments increased estimation errors as reported in [8] and did not improve classification. The implementation of [9] to classify poses achieved an accuracy of 100 % in scenarios with bright and medium illumination. The performance increase (the authors reported a 94 % accuracy) is likely due to tunning parameters, higher resolution and complete bed coverage of the Tekscan mat.…”

“…4. Confusion matrices of implemented method from [9] with 16 % and our proposed method with 70 % accuracies for dark and occluded scenarios. The confusion matrices show how the indexes of the estimated labelsl (x-axis) match the actual labels l * (y-axis).…”

“…Performance contrast of the system in various scenes is shown in Table 1. The table includes classification accuracies of the trusted multimodal system, a MajorityVote-Learner (MaVL), and an in-house implementation of the method from [9]. Table 2.…”

“…Our work is most similar to [9], where standard RGB images and a lowresolution pressure array were used to classify sleep poses from static images. Their method used normalized geometric and load distribution features that depended on a clear view of the scene and the actor.…”

Deep Eye-CU (DECU): Summarization of Patient Motion in the ICU

“…Healthcare applications of pose monitoring include the detection and classification of sleep poses in controlled environments [14]. Static pose classification in a range of simulated healthcare environments is addressed in [15], where the authors use modality trust and RGB, Depth, and Pressure data.…”