Holger Junker

Gesture spotting with body-worn inertial sensors to detect user activities

We present a method for spotting sporadically occurring gestures in a continuous data stream from body-worn inertial sensors. Our method is based on a natural partitioning of continuous sensor signals and uses a two-stage approach for the spotting task. In a first stage, signal sections likely to contain specific motion events are preselected using a simple similarity search. Those preselected sections are then further classified in a second stage, exploiting the recognition capabilities of hidden Markov models. Based on two case studies, we discuss implementation details of our approach and show that it is a feasible strategy for the spotting of various types of motion events.

Recognizing Workshop Activity Using Body Worn Microphones and Accelerometers

The paper presents a technique to automatically track the progress of maintenance or assembly tasks using body worn sensors. The technique is based on a novel way of combining data from accelerometers with simple frequency matching sound classification. This includes the intensity analysis of signals from microphones at different body locations to correlate environmental sounds with user activity. To evaluate our method we apply it to activities in a wood shop. On a simulated assembly task our system can successfully segment and identify most shop activities in a continuous data stream with zero false positives and 84.4% accuracy.

Using multiple sensors for mobile sign language recognition

We build upon a constrained, lab-based Sign Languagerecognition system with the goal of making it a mobile assistivetechnology. We examine using multiple sensors for disambiguationof noisy data to improve recognition accuracy.Our experiment compares the results of training a smallgesture vocabulary using noisy vision data, accelerometerdata and both data sets combined.

Detection of eating and drinking arm gestures using inertial body-worn sensors

We propose a two-stage recognition system for detecting arm gestures related to human meal intake. Information retrieved from such a system can be used for automatic dietary monitoring in the domain of behavioural medicine. We demonstrate that arm gestures can be clustered and detected using inertial sensors. To validate our method, experimental results including 384 gestures from two subjects are presented. Using isolated discrimination based on HMMs an accuracy of 94% can be achieved. When spotting the gestures in continuous movement data, an accuracy of up to 87% is reached.

WearNET: A Distributed Multi-sensor System for Context Aware Wearables

This paper describes a distributed, multi-sensor system architecture designed to provide a wearable computer with a wide range of complex context information. Starting from an analysis of useful high level context information we present a top down design that focuses on the peculiarities of wearable applications. Thus, our design devotes particular attention to sensor placement, system partitioning as well as resource requirements given by the power consumption, computational intensity and communication overhead. We describe an implementation of our architecture and initial experimental results obtained with the system.

Where am i: recognizing on-body positions of wearable sensors

The paper describes a method that allows us to derive the location of an acceleration sensor placed on the users body solely based on the sensors signal. The approach described here constitutes a first step in our work towards the use of sensors integrated in standard appliances and accessories carried by the user for complex context recognition. It is also motivated by the fact that device location is an important context (e.g. glasses being worn vs. glasses in a jacket pocket). Our method uses a (sensor) location and orientation invariant algorithm to identify time periods where the user is walking and then leverages the specific characteristics of walking motion to determine the location of the body-worn sensor. In the paper we outline the relevance of sensor location recognition for appliance based context awareness and then describe the details of the method. Finally, we present the results of an experimental study with six subjects and 90 walking sections spread over several hours indicating that reliable recognition is feasible. The results are in the low nineties for frame by frame recognition and reach 100% for the more relevant event based case.

Wearable sensing to annotate meeting recordings

We propose to use wearable computers and sensor systems to generate personal contextual annotations in audio visual recordings of meetings. In this paper we argue that such annotations are essential and effective to allow retrieval of relevant information from large audio-visual databases. The paper proposes several useful annotations that can be derived from cheap and unobtrusive sensors. It also describes a hardware platform designed to implement this concept and presents first experimental results.

Sensing muscle activities with body-worn sensors

We demonstrate that simple, unobtrusive sensors attached to the lower arm can be used to capture muscle activations during specific hand and arm activities such as grasping. Specifically, we investigate the use of force sensitive resistors and fabric stretch sensors, that can both be easily integrated into clothing. We use the above sensors to detect the contractions of arm muscles. We present and compare the signals that both sensors produce for a set of typical hand actions. We finally argue that they can provide important information for activity recognition

PadNET: wearable physical activity detection network

This paper describes a low power, distributed platform that combines a wide range of different sensors in a wearable, hierarchical network. The architecture simplifies integration of the sensors into the user’s outfit by structuring the hierarchy according to the anatomy of the human body. To date, acceleration and magnetic field sensors were used with the platform for a series of context recognition experiments. Other devices including gyroscopes and force resistive sensors are now being integrated. All designs are available over the internet under GPL licence.

Continuous recognition of arm activities with body-worn inertial sensors

This paper presents a new method for recognizing nonperiodic, sporadic arm-related activities in a continuous signal stream from body-worn inertial sensors. The method utilizes a segmentation scheme based on a natural, dynamic signal partitioning.