Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments

Daniel Roggen; Alberto Calatroni; Mirco Rossi; Thomas Holleczek; Kilian Förster; Gerhard Tröster; Paul Lukowicz; David Bannach; Gerald Pirkl; Florian Wagner; Alois Ferscha; Jakob Doppler; Clemens Holzmann; Marc Kurz; Gerald Holl; Ricardo Chavarriaga; Marco Creatura; Jose Millan

Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments

Daniel Roggen, Alberto Calatroni, Mirco Rossi, Thomas Holleczek, Kilian Förster, Gerhard Tröster, Paul Lukowicz, David Bannach, Gerald Pirkl, Florian Wagner, Alois Ferscha, Jakob Doppler, Clemens Holzmann, Marc Kurz, Gerald Holl, Ricardo Chavarriaga, Marco Creatura, Jose Millan

Institute of Pervasive Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

We aim at activity and context recognition in opportunistic sensor setups. The system ought to make use of sensor modalities that just happen to be available, rather than to rely on specific sensor deployment. In order to assess opportunistic activity recognition methods, we collected a large-scale dataset of complex activities in a highly sensor rich environment, with 72 sensors of 10 modalities in the environment, in objects and on-body. The dataset contains composite and atomic activities in large numbers (>28000 hand interactions). We present the activity scenario and the sensor setup. We show the user's activities and the corresponding sensor signals side by side. We argue that such a visualization may be an efficient form of dataset documentation, especially when such a dataset is shared, as it gives an insight into the complexity of the activities and richness of the sensor setup.

Original language	English
Title of host publication	Eighth International Conference on Pervasive Computing
Number of pages	4
Publication status	Published - May 2010

Fields of science

102 Computer Sciences
102009 Computer simulation
102013 Human-computer interaction
102019 Machine learning
102020 Medical informatics
102021 Pervasive computing
102022 Software development
102025 Distributed systems
202017 Embedded systems
211902 Assistive technologies
211912 Product design

Opportunity - Activity and Context Recognition with Opportunistic Sensor Configurations
Balazs, C. (Researcher), Doppler, J. (Researcher), Holzmann, C. (Researcher), Kurz, M. (Researcher) & Ferscha, A. (PI)
01.02.2009 → 31.01.2012
Project: Funded research › EU - European Union

Cite this

Roggen, D., Calatroni, A., Rossi, M., Holleczek, T., Förster, K., Tröster, G., Lukowicz, P., Bannach, D., Pirkl, G., Wagner, F., Ferscha, A., Doppler, J., Holzmann, C., Kurz, M., Holl, G., Chavarriaga, R., Creatura, M., & Millan, J. (2010). Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments. In Eighth International Conference on Pervasive Computing

@inproceedings{49e8fbddbc2948dead95fd1c1fafb4b2,

title = "Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments",

abstract = "We aim at activity and context recognition in opportunistic sensor setups. The system ought to make use of sensor modalities that just happen to be available, rather than to rely on specific sensor deployment. In order to assess opportunistic activity recognition methods, we collected a large-scale dataset of complex activities in a highly sensor rich environment, with 72 sensors of 10 modalities in the environment, in objects and on-body. The dataset contains composite and atomic activities in large numbers (>28000 hand interactions). We present the activity scenario and the sensor setup. We show the user's activities and the corresponding sensor signals side by side. We argue that such a visualization may be an efficient form of dataset documentation, especially when such a dataset is shared, as it gives an insight into the complexity of the activities and richness of the sensor setup.",

author = "Daniel Roggen and Alberto Calatroni and Mirco Rossi and Thomas Holleczek and Kilian F{\"o}rster and Gerhard Tr{\"o}ster and Paul Lukowicz and David Bannach and Gerald Pirkl and Florian Wagner and Alois Ferscha and Jakob Doppler and Clemens Holzmann and Marc Kurz and Gerald Holl and Ricardo Chavarriaga and Marco Creatura and Jose Millan",

year = "2010",

month = may,

language = "English",

booktitle = "Eighth International Conference on Pervasive Computing",

}

Roggen, D, Calatroni, A, Rossi, M, Holleczek, T, Förster, K, Tröster, G, Lukowicz, P, Bannach, D, Pirkl, G, Wagner, F, Ferscha, A, Doppler, J, Holzmann, C, Kurz, M, Holl, G, Chavarriaga, R, Creatura, M & Millan, J 2010, Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments. in Eighth International Conference on Pervasive Computing.

TY - GEN

T1 - Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments

AU - Roggen, Daniel

AU - Calatroni, Alberto

AU - Rossi, Mirco

AU - Holleczek, Thomas

AU - Förster, Kilian

AU - Tröster, Gerhard

AU - Lukowicz, Paul

AU - Bannach, David

AU - Pirkl, Gerald

AU - Wagner, Florian

AU - Ferscha, Alois

AU - Doppler, Jakob

AU - Holzmann, Clemens

AU - Kurz, Marc

AU - Holl, Gerald

AU - Chavarriaga, Ricardo

AU - Creatura, Marco

AU - Millan, Jose

PY - 2010/5

Y1 - 2010/5

N2 - We aim at activity and context recognition in opportunistic sensor setups. The system ought to make use of sensor modalities that just happen to be available, rather than to rely on specific sensor deployment. In order to assess opportunistic activity recognition methods, we collected a large-scale dataset of complex activities in a highly sensor rich environment, with 72 sensors of 10 modalities in the environment, in objects and on-body. The dataset contains composite and atomic activities in large numbers (>28000 hand interactions). We present the activity scenario and the sensor setup. We show the user's activities and the corresponding sensor signals side by side. We argue that such a visualization may be an efficient form of dataset documentation, especially when such a dataset is shared, as it gives an insight into the complexity of the activities and richness of the sensor setup.

AB - We aim at activity and context recognition in opportunistic sensor setups. The system ought to make use of sensor modalities that just happen to be available, rather than to rely on specific sensor deployment. In order to assess opportunistic activity recognition methods, we collected a large-scale dataset of complex activities in a highly sensor rich environment, with 72 sensors of 10 modalities in the environment, in objects and on-body. The dataset contains composite and atomic activities in large numbers (>28000 hand interactions). We present the activity scenario and the sensor setup. We show the user's activities and the corresponding sensor signals side by side. We argue that such a visualization may be an efficient form of dataset documentation, especially when such a dataset is shared, as it gives an insight into the complexity of the activities and richness of the sensor setup.

M3 - Conference proceedings

BT - Eighth International Conference on Pervasive Computing

ER -

Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments

Abstract

Fields of science

Projects

Opportunity - Activity and Context Recognition with Opportunistic Sensor Configurations

Cite this