60 https://www.uni-bremen.de/en/csl/research/motion-recognition Gesture Recognition en University of Bremen Tue, 21 Apr 2026 08:38:15 +0200 Tue, 21 Apr 2026 08:38:15 +0200 University of Bremen content-17956 Wed, 04 Mar 2026 17:59:16 +0100 https://www.uni-bremen.de/en/csl/research/motion-recognition#c17956 <p>Various groups deal with using IMUs and EMG in the context of gesture recognition. A comparison between their results is often very hard, due to the multitude of different tasks and gesture sets. In addition, often the performance in session-, as well as person-independent recognition are not evaluated, both being of special importance for practical and usable interfaces.</p> <p>We publish the data corpus we collected during our experiments for gesture recognition using IMUs and EMG.</p> <h3><strong>mmGest</strong></h3> <p>Data corpus for gesture recognition using IMUs and EMG. We collected both IMU and EMG readings from 5 different subjects in 5 different session.</p> <p>If you want to use this data, please cite:</p> <p><a href="http://www.csl.uni-bremen.de/publications/bibtexbrowser.php?key=georgi2015recognizing&bib=publications%2Fcsl_all_publications.bib" target="_blank" title="Öffnet externen Link in neuem Fenster">Recognizing Hand and Finger Gestures with IMU based Motion and EMG based Muscle Activity Sensing</a> (Marcus Georgi, Christoph Amma, Tanja Schultz), <em>In International Conference on Bio-inspired Systems and Signal Processing</em>, 2015. (BIOSIGNALS 2015)</p> <p>The complete data can be found <a class="externalLink" href="http://www.csl.uni-bremen.de/CorpusData/download.php?crps=mmGest" target="_blank" title="Opens external link in new window">here</a>.</p> <h3><strong>CSL hdemg</strong></h3> <p>This is the csl-hdemg dataset containing high-density EMG recordings of finger motions. The dataset is described together with a baseline recognition system in the paper:</p> <p><a href="http://www.csl.uni-bremen.de/publications/bibtexbrowser.php?key=amma2015advancing&bib=publications%2Fcsl_all_publications.bib" target="_blank" title="Öffnet externen Link in neuem Fenster">Advancing Muscle-Computer Interfaces with High-Density Electromyography</a> (Christoph Amma, Thomas Krings, Jonas Böer, Tanja Schultz), <em>In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems</em>, ACM, 2015.</p> <p>Please cite this paper, if you publish any work based on this dataset. The data is contained in a zip file which is over 2GB in size. Within the archive, there is a readme.txt, that describes how the data is structured and how to access the data from Matlab or Python.</p> <p>You can download the dataset <a class="externalLink" href="http://www.csl.uni-bremen.de/CorpusData/download.php?crps=cslhdemg" target="_blank" title="Opens external link in new window">here</a>.</p> Content