CoChat

Kinect=IMU? Learning MIMO Signal Mappings to Automatically Translate Activity Recognition Systems across Sensor Modalities

Open access
Banos, Oresti, Calatroni, Alberto, Damas, Miguel, Pomares, Hector, Rojas, Ignacio, Sagha, Hesam, del R. Mill´n, Jose, Troster, Gerhard, Chavarriaga, Ricardo, Roggen, Daniel · 2012 · 2012 16th International Symposium on Wearable Computers
Cited by 33

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Abstract

We propose a method to automatically translate a preexisting activity recognition system, devised for a source sensor domain S, so that it can operate on a newly discovered target sensor domain T, possibly of different modality. First, we use MIMO system identification techniques to obtain a function that maps the signals of S to T. This mapping is then used to translate the recognition system across the sensor domains. We demonstrate the approach in a 5-class gesture recognition problem translating between a vision-based skeleton tracking system (Kinect), and inertial measurement units (IMUs). An adequate mapping can be learned in as few as a single gesture (3 seconds) in this scenario. The accuracy after Kinect → IMU or IMU → Kinect translation is 4% below the baseline for the same limb. Translating across modalities and also to an adjacent limb yields an accuracy 8% below baseline. We discuss the sources of errors and means for improvement. The approach is independent of the sensor modalities. It supports multimodal activity recognition and more flexible real-world activity recognition system deployments.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/iswc.2012.17

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 1 references

Research works printed but not linked: 22

  1. nelles, 2000, Nonlinear System Identification
  2. yazdizadeh, 2002, Adaptive time delay neural network structures for nonlinear system identification, Neurocomputing, 47, 207, 10.1016/S0925-2312(01)00589-6 · DOI
  3. 2009, XM-B Technical Documentation
  4. sjo?berg, 1995, Nonlinear black-box modeling in system identification: A unified overview, Automatica, 31, 1691, 10.1016/0005-1098(95)00120-8 · DOI · Paper page
  5. 10.1109/MPRV.2008.36 · DOI · Paper page
  6. 10.1016/j.procs.2011.09.003 · doi:10.1016/j.procs.2011.09.003
  7. 2010, Prime Sensor NITE 1 3 Algorithms Notes Version 1 0
  8. stone, 2011, Evaluation of an inexpensive depth camera for passive in-home fall risk assessment, 2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops PervasiveHealth, 71
  9. 10.1109/CVPR.2011.5995316 · DOI · Paper page
  10. 10.1109/MRA.2011.940992 · DOI · Paper page
  11. sung, 0, Human activity detection from rgbd images, AAAI Workshop Plan Activity and Intent Recognition 2011
  12. 10.1109/ISWC.2010.5665868 · DOI · Paper page
  13. chavarriaga, 2012, Unsupervised adaptation for acceleration-based activity recognition: Robustness to sensor displacement and rotation, Pers Ubiquit Comput
  14. 10.1109/13.485241 · doi:10.1109/13.485241
  15. lester, 0, A practical approach to recognizing physical activities, Proc of Pervasive Computing 2006, 1
  16. calatroni, 0, A methodology to use unknown new sensors for activity recognition by leveraging sporadic interactions with primitive sensors and behavioral assumptions, Proc of the Opportunistic Ubiquitous Systems Workshop Part of 12th ACM Int Conf on Ubiquitous Computing 2010
  17. van kasteren, 0, Transferring knowledge of activity recognition across sensor networks, Proc 8th Int Conf on Pervasive Computing 2010, 283
  18. kunze, 0, Where am i: Recognizing on-body positions of wearable sensors, LOCA'04 International Workshop on Location and Context-Awareness Jan 2005
  19. 10.1109/ISWC.2010.5665859 · DOI
  20. 10.1109/ISWC.2009.12 · DOI · Paper page
  21. calatroni, 0, Automatic transfer of activity recognition capabilities between body-worn motion sensors: Training newcomers to recognize locomotion, Proc 8th Int Conf on Networked Sensing Systems 2011
  22. 10.1109/ISWC.2009.33 · DOI

Cited by

Metadata

Authors
Banos, O., Calatroni, A., Damas, M., Pomares, H., Rojas, I., Sagha, H., del R. Mill´n, J., Troster, G., Chavarriaga, R., & Roggen, D.
Venue
2012 16th International Symposium on Wearable Computers
Publisher
IEEE
Published
2012-06
Pages
92-99
OpenAlex
W2167409460
Cited by
33
References
1
FWCI
2.96
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.