Partager à toutes et tous (enfin ceux que ça intéresse) ce que je note sur le net

Aller au contenu | Aller au menu | Aller à la recherche

RadarCat un des ancètres du Tricoder ?

Tricorder ?  Dans Star Trek, c'est le scanner portatif à tout faire.

Côté de ses "capacités" de reconnaissance à ce jour, je cite la vidéo:

26 materials (including complex composite objects),
next with 16 transparent materials (with different thickness and varying dyes)
and finally 10 body parts from 6 participants

On peut se demander quelles sont les 10 parties du corps qu'il a appris à reconnaitre... ;)
OK , je => []

Pour détecter/identifier les choses, ils utilisent le senseur Soli (atap.google.com/soli/), dont Nikopik parlait déjà en 2015. 
La papage du projet à Saint Andrew / UK.

Source: nikopik

RadarCat: Radar Categorization for Input & Interaction using Soli [UIST2016]

RadarCat.jpg

La vidéo:

Crédits:

6 oct. 2016

Official PR goes here: https://www.st-andrews.ac.uk/news/arc...
Project page: http://sachi.cs.st-andrews.ac.uk/rese...
In RadarCat we present a small, versatile radar-based system for material and object classification which enables new forms of everyday proximate interaction with digital devices. We demonstrate that we can train and classify different types of objects which we can then recognize in real time. Based on established research designs, we report on the results of three studies, first with 26 materials (including complex composite objects), next with 16 transparent materials (with different thickness and varying dyes) and finally 10 body parts from 6 participants. Both leave one-out and 10-fold cross-validation demonstrate that our approach of classification of radar signals using random forest classifier is robust and accurate. We further demonstrate four working examples including a physical object dictionary, painting and photo editing application, body shortcuts and automatic refill based on RadarCat. We conclude with a discussion of our results, limitations and outline future directions.