Template-based Recognition of Static Sitting Postures

Abstract

In this paper we introduce a generalization of FisherRao's discriminant analysis and its application in a human-computer interaction scenario: a sensing chair. Our algorithm shows to be able to successfully estimate the underlying distributions of the pressure maps data of the sensing chair. Other linear discriminant techniques, such as LDA, had been found to be inadequate for the job; typically yielding inferior results than PCA. We compare our approach to several template-based approaches and show that the new discriminant function is comparable to the best approach classifier. This is important because generally each application tends to prefer a different algorithm. Fortunately, our new algorithm is usually the top one (or comparable to the top one). In this paper we will however restrict our study tothe classification of sitting postures.

Smart Chair for Monitoring of Sitting Behavior

“…Tan [4] used principal component analysis to solve the problem of sitting posture classification. Zhu [5] investigated the classification algorithms and found that Fisher-Rao's discriminant analysis can be applied for the application of sitting posture classification. Mutlu [6] proposed a lowcost solution with reduced sensors to detect sitting postures by a near optimal sensor placement strategy with a classifier based on logistic regression.…”

“…Research studies have been conducted using the pressure distribution measurement sheets placed on the seat pan and backrest to provide high resolution pressure data for posture recognition [4,5]. Tan [4] used principal component analysis to solve the problem of sitting posture classification.…”

Robust, low-cost, non-intrusive sensing and recognition of seated postures

“…We evaluate the performance of our system with a set of empirical evaluations including several cross-validation experiments using a large data set provided by the authors of [41,40,44], a physical deployment of our system to evaluate real-world performance, and a cross-validation experiment using data collected from 20 naive subjects on our deployed system. The next section provides a summary of related work.…”

“…In this paper, we present an approach to the seated posture recognition problem that provides a robust, inexpensive system with near-real-time prediction of seated postures. Our methodology involves iterative design, where we (1) iteratively improve the design of our system through a series of experiments (using data produced by previous work [41,40,44]) that inform our design decisions, and (2) prototype and evaluate our system design (with data collected from naive human subjects). Our final design displays accurate near-real-time classification performance on unfamiliar subjects by using a set of carefully designed, subjectinvariant signal features.…”

Human Sit Down Position Detection Using Data Classification and Dimensionality Reduction

“…For instance, in [6], after performing several experiments, it is determined that there are 10 typic poses. Another study [5] considers 5 poses to develop the detection system.…”