Invisible Motion uncovered by Eulerian Video Magnification

Some weeks ago I read about a really interesting algorithm proposed by a team of scientists at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory. I found a really good description of how it works on this website. I simply copy and paste here the very good explanation they give about this amazing achievement 🙂

A 30-second video of a newborn baby shows the infant silently snoozing in its crib, his breathing barely perceptible. But when the video is run through an algorithm that can amplify both movement and color, the baby’s face blinks crimson with each tiny heartbeat. The amplification process is called Eulerian Video Magnification, and is the brainchild of a team of scientists at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory.

The team originally developed the program to monitor neonatal babies without making physical contact. But they quickly learned that the algorithm can be applied to other videos to reveal changes imperceptible to the naked eye. Prof. William T. Freeman, a leader on the team, imagines its use in search and rescue, so that rescuers could tell from a distance if someone trapped on a ledge, say, is still breathing. “Once we amplify these small motions, there’s like a whole new world you can look at”, he said.

The system works by homing in on specific pixels in a video over the course of time. Frame-by-frame, the program identifies minute changes in color and then amplifies them up to 100 times, turning, say, a subtle shift toward pink to a bright crimson. The scientists who developed it believe it could also have applications in industries like manufacturing and oil exploration. For example, a factory technician could film a machine to check for small movements in bolts that might indicate an impending breakdown. In one video presented by the scientists, a stationary crane sits on a construction site, so still it could be a photograph. But once run through the program, the crane appears to sway precariously in the wind, perhaps tipping workers off to a potential hazard. It is important to note that the crane does not actually move as much as the video seems to show. It is the process of motion amplification that gives the crane its movement.

The program originally gained attention last summer when the team presented it at the annual computer graphics conference known as Siggraph in Los Angeles. Since then, the M.I.T. team has improved the algorithm to achieve better quality results, with significant improvements in clarity and accuracy. Michael Rubinstein, a doctoral student and co-author on the project, said that after the presentation and subsequent media coverage, the team was inundated with e-mails inquiring about the availability of the program for uses ranging from health care to lie detection in law enforcement. Some people, says Mr. Rubinstein, inquired about how the program might be used in conjunction with Google’s glasses to see changes in a person’s face while gambling. “People wanted to be able to analyze their opponent during a poker game or blackjack and be able to know whether they’re cheating or not, just by the variation in their heart rate”, he said.

The team posted the code online and made it available to anyone who wanted to download it and run the program. But to do so required some technical expertise because the interface was not simple to use. Last week, Quanta Research Cambridge, a Taiwan-based manufacturer of laptop computers that helped finance the project, provided a way for people to upload video clips to their Web site and to see a video that is run through the program. The project is also financed by the National Science Foundation and Royal Dutch Shell, among others.

The team is also working toward making the program as an app for smartphones. “I want people to look around and see what’s out there in this world of tiny motions”, said Mr. Freeman.

European Robotics Week 2012

European Robotics Week: 26 November / 2 December 2012

The European Robotics Week offers one week of variousLogo euRobotics week robotics related activities across Europe for the general public, highlighting growing importance of robotics in a wide variety of application areas. The Week aims at inspiring technology education in students of all ages to pursue careers in STEM-related fields, i.e. science, technology, engineering and math.

There is a lot going on in Europe during the European Robotics Week: school visits with lectures on robotics, guided tours for pupils, public talks, open labs, workshops, exhibitions, challenges, robots in action on public squares
 The participating companies, universities and research centres come up with interesting programs to bring their robots and organisations to the attention of the public educating them on how robotics impacts society, both now and in the future.

The goal is to show the general public what robotics is all about and what important role robots nowadays play in Europe.

Events are organised locally (by scientists, labs, teachers, schools, robotics engineers, robot makers etc.), but centrally listed and co-promoted. EUnited Robotics -The European Robotics Association is acting as the central coordinator. They are supported through national coordinators who are promoting the idea among their national networks and communities.

source: EUnited Robotics

Peut-on extraire des donnĂ©es de votre cerveau ?

Pourrait-on vous amener Ă  divulguer votre code bancaire simplement en vous faisant penser Ă  lui ? L’activitĂ© Ă©lectrique de votre cerveau peut-elle trahir vos secrets ? C’est la dĂ©monstration qu’on accomplie des chercheurs lors de la rĂ©cente confĂ©rence sur la sĂ©curitĂ© informatique Usenix. Pour cela, ils ont utilisĂ© un simple casque EEG (type Emotiv, disponible dans le commerce pour 500 $), qui mesure l’activitĂ© Ă©lectrique du cerveau, une technologie qui n’avait jamais Ă©tĂ© Ă©tudiĂ©e sous l’angle de ses implications en matiĂšre de sĂ©curitĂ©, rapportent Extreme Tech etCnet.

un cobaye en situation de reconnaĂźtre des cartes de crĂ©ditsL’Ă©tude (.pdf) des chercheurs (prĂ©sentation en vidĂ©o) menĂ©s par Ivan Martinovic du dĂ©partement des sciences informatiques de l’universitĂ© d’Oxford, a consistĂ© Ă  crĂ©er un programme personnalisĂ© conçu dans le but de vous faire penser Ă  des donnĂ©es sensibles telles que l’emplacement de votre maison, le code secret de votre carte de crĂ©dit ou votre mois de naissance. Les chercheurs ont testĂ© leur programme sur 28 participants coopĂ©ratifs (mĂȘme s’ils ne connaissaient pas le but de l’expĂ©rience) et les rĂ©sultats ont montrĂ© que la fuite d’information provenant de l’utilisateur (la mesure de “l’entropie de l’information”) apportait une rĂ©ponse supĂ©rieure de 15 % Ă  40 % Ă  une mĂ©thode alĂ©atoire.

Les chercheurs se sont appuyĂ©s sur les ondes P300, un tracĂ© d’ondes trĂšs spĂ©cifique qui se produit lorsque vous reconnaissez quelque chose qui a un sens (visage d’une personne connue) ou quelque chose qui convient Ă  ce que vous ĂȘtes en train de faire (voir un marteau quand vous bricolez) et qui commence Ă  ĂȘtre pris en compte dans les dĂ©tecteurs de mensonges. L’exercice pour les cobayes consistait Ă  observer des sĂ©ries de photos dĂ©filant rapidement sur un ordinateur (des visages, des cartes gĂ©ographiques, des photos de cartes bancaires, la liste des mois de l’annĂ©e…) tout en leur posant des questions spĂ©cifiques et pour les chercheurs Ă  observer celles qui dĂ©clenchaient une rĂ©ponse du capteur.

Pour les chercheurs, des dĂ©veloppeurs malveillants pourraient utiliser cette technologie, utilisĂ©e dans de plus en plus de jeux, pour crĂ©er un “logiciel espion de cerveau”, une application incitant les joueurs Ă  rĂ©flĂ©chir Ă  des informations sensibles qu’ils pourraient donc voler. Bien sĂ»r, les rĂ©sultats obtenus sont encore trop bruyants. “Les dispositifs utilisĂ©s ne sont pas faits pour dĂ©tecter ce type de modĂšles”, a soulignĂ© Martinovic. Cependant, l’expĂ©rience a montrĂ© que les rĂ©sultats Ă©taient meilleurs qu’une supposition purement alĂ©atoire. En amĂ©liorant le camouflage de l’interrogatoire pour rendre l’utilisateur plus coopĂ©ratif et la qualitĂ© des appareils de mesure, le taux de rĂ©ussite pourrait certainement ĂȘtre amĂ©liorĂ©.

Les chercheurs ont notĂ© dans leurs conclusions qu’il Ă©tait possible de diminuer le taux de rĂ©ponse que votre cerveau donne malgrĂ© vous en se concentrant sur autre chose, par exemple en comptant les visages qui ne vous sont pas familiers… A l’inverse, ces techniques permettraient aussi de dĂ©velopper de nouvelles mĂ©thodes de sĂ©curitĂ©, vous permettant par exemple d’accĂ©der Ă  vos donnĂ©es simplement en prĂ©sentant sous vos yeux l’image d’un de vos amis.

source: Hubert Guillaud sur ce site

CrĂ©ation d’un plan robotique

Assises de l’industrie 2012 :

Arnaud Montebourg parie sur le

secteur de la robotique

En ouverture de la 3e Ă©dition des Assises de l’Industrie consacrĂ©e aux “nouvelles frontiĂšres de l’industrie”, le ministre du Redressement productif a indiquĂ© que ses Ă©quipes travaillaient sur un plan de soutien au secteur de la robotique, avec l’ambition d’en devenir un leader mondial.

Le ministre du redressement productif prononçait le matin du mercredi 17 octobre l’allocution d’ouverture des 3e Assises de l’industrie. A l’instar du plan de soutien au secteur automobile annoncĂ© en juillet dernier, Arnaud Montebourg a indiquĂ© que des dispositifs Ă©quivalents seront mis en place pour tous les secteurs, Ă  commencer par celui de la robotique.

“Nous prĂ©parons un plan robotique. La France dispose dans ce domaine de compĂ©tences remarquables comparables Ă  celles qui existent au Japon. Nous avons des inventeurs de gĂ©nie mais, avec une atomisation des entreprises, les autres puissances, les autres Etats, viennent piocher dans ce secteur “, a prĂ©cisĂ© le ministre. Il a mis en avant l’objectif de s’imposer comme un leader dans ce domaine Ă  l’Ă©chelle internationale.

Arnaud Montebourg n’a cependant pas prĂ©cisĂ© quand ce plan robotique serait mis en place. “Nos Ă©quipes y travaillent”, a-t-il simplement dĂ©clarĂ©. Quant Ă  sa force de frappe, il a indiqué “une puissance modeste mais avec des effets dĂ©cuplĂ©s”.

Le ministre a ensuite replacĂ© ce plan dans un programme plus large et rĂ©pĂ©tĂ© la volontĂ© du gouvernement de faire son “travail de redĂ©marrage, de mobilisation autour de l’industrie, en collaboration avec ses acteurs. C’est ce que j’appelle la politique du colbertisme participatif, on travaille ensemble pour reconstruire l’industrie en France”, a ajoutĂ© Arnaud Montebourg.

source: L’Usine Nouvelle

Virtual Water

A very interesting web page created to sensibilize people on the problem of water consumption!

Most of the water we use – 92 % of it – is used in food production. Most of this water is managed by the world’s farmers. With the help of science and technology they have performed greater and greater miracles in improving water productivity – in getting more  crops per drop.

CAN WE HELP ?

Of course yes… just click on the link below here (or on the image itself) to spend 3 minutes to learn something useful 😉

source: this website

new e-mail address

Hi everybody!

I’ve just started the second year of my PhD thesis at LIRMM Laboratory, in Montpellier. Apparently I’m going to spend about one year and a half in this awesome place. Since 3 e-mail addresses were not enough, I have a fourth one, ‘official’ from this new lab where I’m now.

I’ve updated the Contact section of this scientific blog with my two -let’s say- ‘scientific’ e-mail addresses, the one from TĂ©lĂ©com Bretagne and this brand new one from LIRMM. No more interest in showing the other two addresses, more ‘personal’ 🙂