Frank Wallhoff - Academia.edu (original) (raw)

Papers by Frank Wallhoff

Proc. 1st Intern. Workshop on Cognition for Technical Systems, Cotesys 2008, Munich, Germany, 2008

2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2016

In this paper we compare the performance of the Microsoft™ Kinect v2 with a high precision measur... more In this paper we compare the performance of the Microsoft™ Kinect v2 with a high precision measurement system for therapeutic purposes. A precise and low cost motion tracking system is of importance for the development of therapeutic assistance in everyday living environments. Upcoming therapeutic assistance systems have to be affordable and able to analyze the motion of the inhabitant. Therefore, an evaluation of the low cost Kinect v2 sensor is necessary to examine the usability of the sensor for joint angle measurements. We will show that a median deviation up to 8.4° in comparison with the high precision measurement may be achieved. We will conclude that the Kinect v2 sensor offers an adequate opportunity to analyze therapeutic exercises in living environments.

Gesundheit digital, 2018

Ausgehend davon, dass aufgrund der demographischen Entwicklung Betreuung und Pflege durch Mensche... more Ausgehend davon, dass aufgrund der demographischen Entwicklung Betreuung und Pflege durch Menschenhand nur sehr schwer gewahrleistet werden kann oder hilfebedurftige Personen technische Hilfsmittel bevorzugen, hat das Anwendungsfeld Assistenz- und Servicerobotik (ASR) im Zusammenhang mit der Digitalisierung in Milieus, in denen Menschen eine direkte Unterstutzung in ihren Lebensbereich benotigen, stark an Interesse gewonnen. Obwohl die Idee eines universell einsetzbaren Roboters in Karel Capeks Schauspiel „Rossums Universal-Roboter“ bereits fast 100 Jahre alt ist, erreichen die technischen Moglichkeiten im Zuge der Digitalisierung erst jetzt ausreichend Kapazitaten, um in komplexen Anwendungsszenarien wie beispielsweise im eigenen Haus dienlich zu sein. Aber konnen aktuelle Robotersysteme trotz des raschen Fortschritts die Bedarfe in komplexen Umfeldern wie der ambulanten Pflege, stationaren Pflegeeinrichtungen und Krankenhausern in der nahen Zukunft bedienen? Welche Engpasse mussen noch bewaltigt werden? Welches Verhalten und welchen Umgang erwarten potenzielle Nutzer von ihren Begleitern? Der vorliegende Beitrag soll Gedanken und Aspekte zu diesen Fragen aufzeigen.

Ambient Assisted Living, 2017

Speech input and output allow for a natural and intuitive means to communicate with a technical d... more Speech input and output allow for a natural and intuitive means to communicate with a technical device or system. This motivates the development of speech dialogue systems for convenient human-machine interaction. A speech dialogue system is particularly suitable in scenarios in which the user cannot use his or her hands for interaction, for example while driving a car. In kitchen environments, a speech dialogue system promises to be very useful as well. The application CooCo (Cooking Coach) aims at providing assistance under working conditions in a common kitchen. CooCo supports the user to choose recipes best matching the requests of the user and gives advice during the cooking processes. In this paper, the focus lies on the conceptual view on building up CooCo and the integration of a computer-based approach to adapt cooking recipes.

Sensors, 2021

The reproduction and simulation of workplaces, and the analysis of body postures during work proc... more The reproduction and simulation of workplaces, and the analysis of body postures during work processes, are parts of ergonomic risk assessments. A commercial virtual reality (VR) system offers the possibility to model complex work scenarios as virtual mock-ups and to evaluate their ergonomic designs by analyzing motion behavior while performing work processes. In this study a VR tracking sensor system (HTC Vive tracker) combined with an inverse kinematic model (Final IK) was compared with a marker-based optical motion capture system (Qualisys). Marker-based optical motion capture systems are considered the gold standard for motion analysis. Therefore, Qualisys was used as the ground truth in this study. The research question to be answered was how accurately the HTC Vive System combined with Final IK can measure joint angles used for ergonomic evaluation. Twenty-six subjects were observed simultaneously with both tracking systems while performing 20 defined movements. Sixteen joint ...

2018 IEEE Life Sciences Conference (LSC), 2018

One key task for motion recognition using machine learning algorithms is the preprocessing of the... more One key task for motion recognition using machine learning algorithms is the preprocessing of the input data. In this work 3D-skeleton-data is used to classify 19 motion exercises. Due to different body shapes and deviations in the movements from different subjects it becomes necessary to normalize the data. This work addresses the normalization of 3D-skeletoD-data by indicating body joint angles and normalization to an independent coordinate system. The recogntion is based on a Support Vector Machine (SVM) and is evaluated on a dataset containing examples from 21 subjects. The recognition accuracies using different normalized feature combinations are examined. The authors conclude that joint angles are best suitable for the recognition of motion exercises.

ECMS 2018 Proceedings edited by Lars Nolle, Alexandra Burger, Christoph Tholen, Jens Werner, Jens Wellhausen, 2018

The use of autonomous underwater vehicles requires stable and reliable algorithms within the cont... more The use of autonomous underwater vehicles requires stable and reliable algorithms within the control software. A misdirected vehicle can quickly lead to a costly damage or even loss of the vehicle. In this paper, an application is presented that allows an ongoing underwater mission to be tracked in real-time within a 3D simulation and, in the event of a problem, aborts it to set the vehicles into a safe state. It can communicate directionally with the control software of each vehicle, thus providing the basis of a simulation environment. Furthermore, first implementations for evaluating the control algorithms of autonomous vehicles within the simulation environment will be presented.

This work addresses the recognition of human motion exercises using 3D-skeleton-data and Neural N... more This work addresses the recognition of human motion exercises using 3D-skeleton-data and Neural Networks (NN). The examined dataset contains 16 gymnastic motion exercises (e.g. squats, lunges) executed from 21 subjects and captured with the second version of the MicrosoftTM Kinect sensor (Kinect v2). The NN was trained with eight datasets from eight subjects and tested with 13 unknown datasets. The investigation in this work focuses on the configuration of NNs for human motion recognition. The authors will conclude that a backpropagation NN consisting of 100 neurons, three hidden layers, and a learning rate of 0.001 reaches the best accuracy with 93.8% correct.

In this paper we present a system, which is capable of learning on-line dynamic gestures for a ga... more In this paper we present a system, which is capable of learning on-line dynamic gestures for a gaming scenario on a mobile robotic platform. The recognition of the gestures relies on a skeleton tracking based feature extraction method as well as a Graphical Model-based classification. The robotic platform deals as a research platform for Ambient Assisted Living environments, where the interaction between humans and robots should be improved by providing a more natural and intuitive kind of communication. The realized system is a first step heading into the direction of a more pleasant human-robot interaction, since the learning of the gestures is user-dependent.

Zusammenfassung: Bei der Ausübung von physiotherapeutischen Übungen ist besonders das Reflektiere... more Zusammenfassung: Bei der Ausübung von physiotherapeutischen Übungen ist besonders das Reflektieren der Bewegungsabläufe für ein erfolgreiches Training von Bedeutung. In einer Mensch-Mensch-Trainingsinteraktion kann eine Therapeutin oder ein Therapeut die trainierende Person unterstützen, Bewegungsabläufe korrigieren und motivieren. In diesem Beitrag wird ein Mensch-Roboter-Trainingssystem als Proof-of-Concept vorgestellt, welches Bewegungsübungen basierend auf physiotherapeutischen Wissen analysiert. Dabei fungiert ein humanoider Roboter als interaktiver Trainer und eine Tiefenbildkamera als Sensor für die Bewegungswahrnehmung. Zu Beginn einer Trainingsphase lernt das System den Bewegungsablauf durch Vormachen einer Übung kennen und adaptiert sich in der Analyse entsprechend des Trainingsstandes, der Körperstatur und der Bewegungseinschränkungen. Während des Trainings wird der möglichst optimale Zeitpunkt und situationsbezogene Inhalt einer unterstützenden, korrigierenden oder motiv...

2017 IEEE Life Sciences Conference (LSC), 2017

This work addresses the recognition of 19 gymnastic motion exercises for a training assistant. Th... more This work addresses the recognition of 19 gymnastic motion exercises for a training assistant. The system captures skeleton data in form of 3 dimensional body positions with the Microsoft™ Kinect v2. In the preprocessing phase, the 3 dimensional positions are transformed to joint angles. The recognition is based on a Support Vector Machine (SVM) with a polynomial kernel. Six subjects are used to train the models with 19 motion exercises. The models are tested with 15 different subjects afterwards. With the proposed method an accuracy of 81% correct classified motion sequences is achieved. From this work it can be concluded that autonomous systems for the recognition of motion exercises are a promising tool for rehabilitative purposes.

Sensors, 2020

Optimizing neurofeedback (NF) and brain–computer interface (BCI) implementations constitutes a ch... more Optimizing neurofeedback (NF) and brain–computer interface (BCI) implementations constitutes a challenge across many fields and has so far been addressed by, among others, advancing signal processing methods or predicting the user’s control ability from neurophysiological or psychological measures. In comparison, how context factors influence NF/BCI performance is largely unexplored. We here investigate whether a competitive multi-user condition leads to better NF/BCI performance than a single-user condition. We implemented a foot motor imagery (MI) NF with mobile electroencephalography (EEG). Twenty-five healthy, young participants steered a humanoid robot in a single-user condition and in a competitive multi-user race condition using a second humanoid robot and a pseudo competitor. NF was based on 8–30 Hz relative event-related desynchronization (ERD) over sensorimotor areas. There was no significant difference between the ERD during the competitive multi-user condition and the si...

How can robots effectively assist humans in the packaging industry, when it comes to handling lar... more How can robots effectively assist humans in the packaging industry, when it comes to handling large components, such as a LCD television? This is the question that scientists and industry partners of the research project ??CustomPacker?? [1] are seeking to answer. The aims of the project are to free the human worker of tedious, unchallenging work, whilst simultaneously reducing packaging costs. Area of Conference Topic: Robotics in Production / Industrial Robots Keywords: Safe human-robot cooperation / cooperating robots

2009 IEEE International Conference on Multimedia and Expo, 2009

In this paper, we motivate and introduce a novel vector quantization (VQ) scheme for distributing... more In this paper, we motivate and introduce a novel vector quantization (VQ) scheme for distributing the quantization error among the quantized features of a continuous feature vector in a predefined manner. This is done by defining ratios between the individual quantization errors of the features and shaping the Voronoi cells accordingly. In a series of experiments we show that the novel approach is capable of either distributing the quantization error equally among the dimensions or realize an arbitrary distribution.

2009 2nd Conference on Human System Interactions, 2009

Advanced Technologies and Societal Change, 2015

Within the AAL Joint Programme the MOBECS’ projectconsortium (MOBility and Emergency Call System)... more Within the AAL Joint Programme the MOBECS’ projectconsortium (MOBility and Emergency Call System), develops a novel mobile emergency call system which offers use and security for indoor and outdoor to increase mobility. A special feature in advantage to other emergency applications, is a base station at home which allows evaluating and controlling of sensordata (as example, to check the health of users) and actuators to control other electronic devices (for example to turn off the heater after leaving the house if it has been forgotten). For a continuous user integration from the outset focus groups interviews were conducted already in the conception phase in order to analyze the needs of potential users at an early stage. To accommodate the needs of end-users in the development phase, evaluations of the developed prototypes took place: this is a Smartphone application for the end user and on the other hand the interfaces for the home emergency call Centre staff. The implementation and the results of the evaluation are documented in a Bachelor thesis. It will also show up problems and proposed instructions.