I
Irina Mocanu
Researcher at Politehnica University of Bucharest
Publications - 71
Citations - 319
Irina Mocanu is an academic researcher from Politehnica University of Bucharest. The author has contributed to research in topics: Convolutional neural network & Activity recognition. The author has an hindex of 8, co-authored 59 publications receiving 225 citations. Previous affiliations of Irina Mocanu include University of Bucharest.
Papers
More filters
Journal ArticleDOI
A Comprehensive Survey of Indoor Localization Methods Based on Computer Vision.
Anca Morar,Alin Moldoveanu,Irina Mocanu,Florica Moldoveanu,Ion Emilian Radoi,Victor Asavei,Alexandru Gradinaru,Alexandru Butean +7 more
TL;DR: An overview of the computer vision based indoor localization domain is offered, presenting application areas, commercial tools, existing benchmarks, and other reviews, and proposing a new classification based on the configuration stage (use of known environment data), sensing devices, type of detected elements, and localization method.
Journal ArticleDOI
Digital camera connectivity solutions using the picture transfer protocol (PTP)
TL;DR: With a suitable application layer software, digital photographs can be sent directly from the camera to a desired target: disk storage, printer, Web site, as an e-mail message or Web print, using a single, purpose-designed, communication protocol: the picture transfer protocol, PTP.
Proceedings Article
AmIHomCare: a complex ambient intelligent system for home medical assistance
TL;DR: AmIHomCare not only monitors the vital signs of the patient or elderly people in attempt to identify a potential dangerous situation but it is also designed to ensure a personalized environment for the user.
Proceedings ArticleDOI
Human Activity Recognition in Smart Environments
TL;DR: By using background subtraction and skeletisation as image processing techniques, combined with Artificial Neural Networks for human posture classification and Hidden Markov Models for activity interpretation, basic human actions such as walking, rotating, sitting and bending up/down, lying and falling are recognized.
Proceedings ArticleDOI
A Kinect based adaptive exergame
TL;DR: The preliminary evaluations with ten people have shown that the system can be an effective tool that engages users into physical activity that stimulate for a long time physically activity.