Vision-based human-computer interaction in the operating theatre


L. Gallo and M. Frucci, Invited Talk at the 13th International Conference on Pattern Recognition and Information Processing (PRIP 2016)

October 3-5, 2016, Minsk, Republic of Belarus

Web page

Touchless Interaction in Surgery: the Medical Imaging Toolkit experience


Keynote speech at the 2nd International Conference on Augmented and Virtual Reality (SalentoAVR 2015)

1st September 2015, Lecce, Italy

During the last few years, we have been witnessing a widespread interest on touchless technologies in the context of surgical procedures. The main reason is that surgeons often need to visualize medical images in operating rooms, but checking a computer through keyboard or mouse would result in a bacterial contamination. Touchless interfaces, which exploits sensor technologies and machine learning techniques for tracking and analyzing body movements, are advantageous in that they can preserve sterility around the patient.

Comparative evaluation of methods for filtering Kinect depth data


Essmaeel, K., Gallo, L., Damiani, E., De Pietro, G., & Dipanda, A. (2015). Comparative evaluation of methods for filtering Kinect depth data. Multimedia Tools and Applications, 74(17), 7331-7354. doi:10.1007/s11042-014-1982-6

In this work, we discuss the results of a study in which we have compared the most commonly used filtering approaches for Kinect depth data, in both static and dynamic contexts, by using novel metrics. The experimental results show that each approach can be profitably used to enhance the precision and/or accuracy of Kinect depth data in a specific context, whereas the temporal filtering approach is able to reduce noise in different experimental conditions.