IRTUM – Institutional Repository of the Technical University of Moldova

Human Motion Recognition Using Artificial Intelligence Techniques

Show simple item record

dc.contributor.author ENACHI, Andrei
dc.contributor.author TURCU, Cornel
dc.contributor.author CULEA, George
dc.contributor.author BANU, Ioan-Viorel
dc.contributor.author ANDRIOAIA, Dragos-Alexandru
dc.contributor.author PETRU, Puiu-Gabriel
dc.contributor.author POPA, Sorin-Eugen
dc.date.accessioned 2022-12-28T11:35:38Z
dc.date.available 2022-12-28T11:35:38Z
dc.date.issued 2022
dc.identifier.citation ENACHI, Andrei, TURCU, Cornel, CULEA, George et al. Human Motion Recognition Using Artificial Intelligence Techniques. In: Electronics, Communications and Computing (IC ECCO-2022): 12th intern. conf., 20-21 Oct. 2022, Chişinău, Republica Moldova: conf. proc., Chişinău, 2022, pp. 200-202. en_US
dc.identifier.uri https://doi.org/10.52326/ic-ecco.2022/CS.11
dc.identifier.uri http://repository.utm.md/handle/5014/21857
dc.description.abstract The goal of this paper's research is to develop learning methods that promote the automatic analysis and interpretation of human and mime-gestural movement from various perspectives and using various data sources images, video, depth, mocap data, audio, and inertial sensors, for example. Deep neural models are used as well as supervised classification and semi-supervised feature learning modeling temporal dependencies, and their effectiveness in a set of tasks that are fundamental, such as detection, classification, and parameter estimation, is demonstrated as well as user verification. A method for identifying and classifying human actions and gestures based on utilizing multi-dimensional and multi-modal deep learning from visual signals (for example, live stream, depth, and motion - based data). A training strategy that uses, first, individual modalities must be carefully initialized, followed by gradual fusion (called ModDrop) to learn correlations between modalities while preserving the uniqueness of each modality specific representation. In addition, the suggested ModDrop training approach assures that the classifier detect has weak inputs for one or maybe more channels, enabling these to make valid predictions from any amount of data points accessible modalities. In this paper, inertial sensors (such as accelerometers and gyroscopes) embedded in mobile devices collect data are also used. en_US
dc.language.iso en en_US
dc.publisher Technical University of Moldova en_US
dc.rights Attribution-NonCommercial-NoDerivs 3.0 United States *
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/3.0/us/ *
dc.subject deep learning en_US
dc.subject neural models en_US
dc.subject sensors en_US
dc.subject human movement en_US
dc.subject mime-gestural movement en_US
dc.subject automatic analysis en_US
dc.title Human Motion Recognition Using Artificial Intelligence Techniques en_US
dc.type Article en_US


Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

  • 2022
    Proceedings of the 12th IC|ECCO; October 20-21, 2022

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 United States Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 3.0 United States

Search DSpace


Browse

My Account