Juan-Manuel Ahuactzin Larios

Nobody can be a prophet in his own land, but he/she can give an splendid conference !

Juan-Manuel Ahuactzin — 2010-03-29T23:33:00Z

I started my conference by telling "Nobody can be a prophet in his own land, however it is an honor to be here today". Last March 16th, I was invited by the Pyrotechnical University of Tlaxcala (UPT), Mexico to give a conference. Actually I was born in Tlaxcala city and lived in Santa Ana (close to Tlaxcala) until I was 19 years old. For me it was a big honor to give a "magisterial" conference at the Convention Center of Tlaxcala city. I gave conferences in many places inside and outside Mexico (including the state of Tlaxcala) but never in the city were I was born. That is why, I know that somehow this conference will be toughest than giving a conference outside Mexico.

I had a very nice time at the International Congress on Engineering and Software of UPT. An unexpected exchange with the audience was waiting for me... I really feel at home. Many participants started a very pleasant dialog with their lecturer, suddenly I remembered when I was at the other side of the audience.

Two days later I received an e-mail with few words:

"Dear Dr. Ahuactzin,

Thanks for your conference, it was really interesting, maybe nobody can be a prophet in his own land, but he/she can give a splendid conference ! ..."

That was a very nice present from my audience and my city...thanks a lot !

New publication: Bayesian reasoning for Laban Movement Analysis used in human-machine interaction

Juan-Manuel Ahuactzin — 2010-03-17T04:28:17Z

Jorg Rett, Jorge Dias [1] and Juan-Manuel Ahuactzin [2]

Paper link

We present the implementation of computational Laban Movement Analysis (LMA) for human-machine interaction using Bayesian reasoning. The research field of computational human movement analysis is lacking a general underlying modelling language, i.e., how to map the features into symbols. With such a semantic descriptor, the recognition problem can be posed as a problem to recognise a sequence of symbols taken from an alphabet consisting of motion-entities. LMA has been proven successful in areas where humans are observing other humans' movements. LMA provides a model for observation and description and a notational system (Labanotation). To implement LMA in a computer, we have chosen a Bayesian approach. The framework allows us to model the process, learn the dependencies between features and symbols and to perform online classification using LMA-labels. We have chosen the application 'social robots' to demonstrate the feasibility of our solution.

[1] Institute of Systems and Robotics, University of Coimbra, Polo II, 3030-290 Coimbra, Portugal

[2] Probayes SAS 345, rue Lavoisier, Inovallee, 38330 Montbonnot, France

SSIR: Summer School on Image & Robotics.

Juan-Manuel Ahuactzin — 2009-04-08T20:03:00Z

The main academic event where I'm involved is the the Summer School on Image & Robotics. This school is part of the activities organized under the framework of the French-Mexican Laboratory in Computer Sciences (LAFMI).

The principal objective of the Summer School on Image & Robotics is to introduce the state of the art in computer vision and robotics to final year engineering students, master and PhD students.

Until now, 9 editions of the Summer School on Image and Robotics have taken place in different locations in France and Mexico. The participation in the school has been around 60 students on average for each edition. So far, more than 536 students have participated. They come from about 50 institutions, mainly from Europe (France, Greece, Holland, Italy, Portugal, Spain, Sweden and Switzerland) and Latin America (Mexico, Brazil, Colombia, and Venezuela). A total of approx. 89 professors have participated in the previous editions of this school. Many of the attending students have continued graduate studies in topics related to computer vision and robotics in different institutions and countries.

SSIR 2000 INRIA Rhône-Alpes, France
SSIR 2001 ITESM Cuernavaca Morelos, Mexico
SSIR 2002 LAAS Toulouse, France
SSIR 2003 UDLAP, Cholula Puebla, Mexico
SSIR 2004 INRIA Sophia-Antipolis, France
SSIR 2005 FIMME, Guanajuato, Mexico
SSIR 2006 LIRMM, Montpellier, France
SSIR 2007 CIC, Mexico City, Mexico
SSIR 2008 LASMEA/IFMA, Clermont-Ferrand, France.

This year SSIR 2009 will be held at the National Institute of Astrophysics, Optics and Electronics (INAOE), Puebla, Mexico. INAOE is a national research center with a strong department of computer science, with 20 full-time researchers, and approx. 80 graduate students. The department has robotics and vision laboratories, and several researchers that work in computer vision, pattern recognition and robotics.

The new dates for the School on Image & Robotics: December 7th to December 18th. Dates were changed due to the influenza pandemic alert on last May.

Joerg Rett's thesis presentation at the University of Coimbra

Juan-Manuel Ahuactzin — 2009-04-06T23:46:46Z

Last January, I was on the jury of Joerg Rett's PhD. thesis defense. The place: the University of Coimbra in Portugal. Joerg's presentation was very professional, interesting and ceremonious. The room where the presentation took place was really magnificent: the "Sala Grande dos Actos or Sala dos Capelos". I'm sure that the ceremony was an unforgettable experience both for Joerg and the Jury. Here I re-write my evaluation of the thesis document, that I find very interesting.

From left to right: Joerg Rett, Professor Pierre Bessière and myself (Juan-Manuel Ahuactzin).

REPORT ON THE THESIS OF MR. JÖRG RETT: ROBOT-HUMAN INTERFACE USING LABAN MOVEMENT ANALYSIS INSIDE A BAYESIAN FRAMEWORK. BY JUAN-MANUEL AHUACTZIN. SEPTEMBER 2008.

Bayesian gesture recognition is a key issue on information technology. Humans and machines will increase their communication when our gesture languages will be recognized in real time and independently of the actor. The Bayesian paradigm and the Laban movement analysis are two fields that have proven to be very promising for the development of gesture recognition systems. The combination of the two fields is a response to the lacking ability to analyze, represent and recognize human movements. This is demonstrated by Mr. Joerg Rett's thesis that goes from the analysis of the human movements to a real implementation: a gesture recognition system controlling a mobile robot by a body language.

Mr. Rett's thesis starts by presenting an introduction to the different fields involved on his thesis: notation for describing human movements, human-robot interaction, social robots, computational human movement analysis and an examination about the use of Laban Movement Analysis for social robots. The introduction ends by a discussion on the contributions of the thesis.

The main body of the thesis is composed of four chapters: i) human movement analysis, ii) human movement tracking and description, iii) Bayesian models and iv) recognition system.

In Chapter 2 Mr. Rett introduces the Laban movement analysis (LMA): a method for observing, describing, notating and interpreting human movements. LMA includes two kinds of components: kinematics (Body and Space) and non-kinematics (Effort and Shape). On this work, Space and Effort are selected for describing body human gestures. Space concerns the location of the body parts, and Effort refers to the dynamic of the movements and their energy. A tagged database was created with different gestures examples capturing the Space and Effort properties. The database is an important contribution for the scientific community. Indeed, to the best of my knowledge it is the first gesture database including LMA.

Mr. Rett chose to describe Space and Effort components using low-level features: measurable entities obtained from sensing the body parts either in 2D and 3D. Chapter 3 contains a technical review of the sensing and tracking methods and the geometric problems involved on the task. Four low-level features are introduced: direction, velocity, acceleration and curvature. The pertinence of the low-level features for describing Effort and Space is evaluated. The frequencies “signatures” of the features given a particular kind of movement are analyzed for a single actor as well as for multiple actors. The problem of segmentation is also discussed. An original three-phase model segmentation has been adopted in order to improve the robustness of the gesture recognition task. This chapter is a pertinent demonstration of how it is difficult to represent a particular gesture without taking into account the uncertainty. Pure symbolic language cannot describe what is happening in the real world. The execution of a movement is not strict; low-level features can have important variations when executing the same gesture while the human observer or actor could or could not observe this variation.

On Chapter 4, Mr. Rett presents a global model for gesture recognition based on three levels of abstraction: concept space, Laban space and physical space. These levels associate the concepts presented in the previous chapters: (i) the movement and frame number, (ii) the components of the LMA and (iii) the low-level features. A sensor fusion like approach is used as the global model. Each of the LMA components is analogous to a virtual and independent sensor. The Space, Effort and Shape sub-models are developed in detail. Additional temporal model is introduced in order to deal with the speed and the length of a gesture description. The identification of the parametrical forms on the sub-models is also presented. This concerns the learning of the distributions of the low-level features knowing the gesture (movement) and the effort qualities knowing the gesture. The developed models are pertinent and easy to understand. In addition to the contribution of the gesture model, Mr. Rett contributes with a proposal for measuring the quality of anticipation. The interpretation is possible thanks to three entropy-based measures: speed, confidence and stability. From my point of view, the three entropy-based measures are an important contribution that is validated by experimentation.

Chapter 5 presents the results obtained by the gesture recognition model. This includes the analysis, the experimentation and a final application where a real robot follows human gesture instructions in a natural environment. This chapter is clear, convincing and complete in what we could expect of a strict validation. The robustness of the approach is experimented under different situations showing the fundamental importance of both the LMA and the Bayesian approach.

The last chapter of the thesis presents a resume of the content of the document as well as the future work.

From my point of view, Mr. Rett thesis is a complete work: it includes a deep reflection about the problem, an exceptional evaluation of the use of the LMA for solving this task, an original integrated model, and a pertinent experimentation. Key subjects of Artificial Intelligence are dealt all around the thesis, for example: symbolic languages, automatic analysis, probabilistic modeling, learning, classification, and robotics.

Gesture recognition will be adopted, in very short time, by numerous applications and devices. A diversity of gesture languages will be developed to be the main mean of communication between humans and computers. Mr. Rett's thesis makes important contributions on this direction.

In summary, I think that Mr. Rett's thesis makes important contributions on the subject of gesture recognition using Laban movement analysis. Let me unequivocally state my strong recommendation for proceeding to his final defense.

Juan Manuel Ahuactzin Research Director Probayes SAS

David Pogue in Mexico

Juan-Manuel Ahuactzin — 2009-03-04T23:39:52Z

South of the Border, Down Mexico Way

A few months ago, I received a most unusual request: to come and speak at a technical conference in Monterrey, Mexico—a conference run entirely, and I mean entirely, by students.

- Events / conference, Mexico, USA

New publication: Brain, Vision and AI

Juan-Manuel Ahuactzin — 2008-12-22T21:06:44Z

The aim of this book is to provide new ideas, original results and practical experiences regarding service robotics. This book provides only a small example of this research activity, but it covers a great deal of what has been done in the field recently. Furthermore, it works as a valuable resource for researchers interested in this field.

The book is published by IN-TECH who provide free online access to high quality, up-to-date scientific content covering fields of Artificial Intelligence, Robotics, Manufacturing and Operations Research. For a PDF copy of this book please click here

In this book Joerg Rett, Jorge Dias and Juan-Manuel Ahuactzin (myself) contribute with the book chapter:

Laban Movement Analysis using a Bayesian Model and Perspective Projections

Human movement is essentially the process of moving one or more body parts to a specific location along a certain trajectory. A person observing the movement might be able to recognize it through the spatial pathway alone. Kendon (Kendon, 2004) holds the view that willingly or not, humans, when in co-presence, continuously inform one another about their intentions, interests, feelings and ideas by means of visible bodily action. Analysis of face-toface interaction has shown that bodily action can play a crucial role in the process of interaction and communication. Kendon states that expressive actions like greeting, threat and submission often play a central role in social interaction. In order to access the expressive content of movements theoretically, a notational system is needed. Rudolf Laban, (1879-1958) was a notable central European dance artist and theorist, whose work laid the foundations for Laban Movement Analysis (LMA). Used as a tool by dancers, athletes, physical and occupational therapists, it is one of the most widely used systems of human movement analysis. Robotics has already acknowledged the evidence that human movements could be an important cue for Human-Robot Interaction. Sato et al. (Sato et al., 1996), while defining the requirements for 'human symbiosis robotics' state that those robots should be able to use non-verbal media to communicate with humans and exchange information. As input modalities on a higher abstraction level they define channels on language, gesture and unconscious behavior. This skill could enable the robot to actively perceive human behavior, whether conscious and unconscious. Human intention could be understood, simply by observation, allowing the system to achieve a certain level of friendliness, hospitality and reliance. Fong, Nourbakhsh and Dautenhahn (Fong et al., 2003) state in their survey on 'socially interactive robots' that the design of sociable robots needs input from research concerning social learning and imitation, gesture and natural language communication, emotion and recognition of interaction patterns. Otero et al. suggest (Otero et al., 2006) that the interpretation of a person's motion within its environment can enhance Human-Robot Interaction in several ways. They point out, that a recognized action can help the robot to plan its future tasks and goals, that the information flow during interaction can be extended and additional cues, like speech recognition, can be supported. Otero et al. state that body motion and context provide in many situations enough information to derive the person's current activity.

Second European-Mexican IT Workshop

Juan-Manuel Ahuactzin — 2008-12-01T19:34:00Z

The LAEMI organized the Second European-Mexican Information Technology (IT) Workshop. The event took place at the Sassegane castle near Grenoble, France on November 28-29, 2008.

Participants from Mexico, France, Spain, and Germany presented a large variety of research subjects, educational programs and R&D projects on Information Technologies. The goal was to identify and consolidate the opportunities of collaboration between Europe and Mexico on IT. Indeed, the European commission and Conacyt Mexico are creating attractive partnership opportunities not only for the educational and research institutions but also for the industry. This partnership includes research projects, educational programs and transfer of technology.

About 60 participants were hosted by INRIA Rhône-Alpes who was the main local organizer. If you are interested in the material and results obtained on this Workshop please see the list of presentations and conclusions at the event web page.

One of the presentations that kept my attention was that of Professor James L. Crowley from the Institut National Polytechnique de Grenoble (INPG) who presented the Master of Science in Informatics at Grenoble. This program is a real opportunity for all Mexican students for joining the the framework of cooperation between Europe and Mexico. As it was told by Professor James L. Crowley different laboratories in Grenoble, France have a large experience in receiving Mexican students who are always welcome to the capital of the Alps. For more information about this program please take a look to the video below.

International Congress on Information Technology and Electronics

Juan-Manuel Ahuactzin — 2008-10-01T20:38:43Z

This September I was an invited speaker at the Digit congress at the Instituto Tecnológico y de Estudios Superiores de Monterrey (ITESM) campus Puebla, in Mexico. The event, organized by the students, included top subjects on Information Technology and Electronics. This congress had a magnificent organization, high quality speakers, and a very dynamic audience. Despite the diversity and complexity of the subjects there were always very pertinent remarks and questions from the students audience.

During this event I have the opportunity to listen professor Philippe Jorrand's talk on Quantum Computation. Definitively, this is a subject that is opening the future of Information Technology. Personally, I was very happy to listen to the talks and to have some in live chat with professor Jorrand and doctor David Sol from ITESM Puebla. In 1990, when I started my graduate studies in France, professor Jorrand was the director of my hosting laboratory LIFIA, and doctor Sol was a classmate at the Polytechnic Institute of Grenoble !

THANKS a lot to the organizers and congratulations to all participants, I was showered with attention and had a very god time.

Computation and Systems January-March / 2008: Editorial

Juan-Manuel Ahuactzin — 2008-07-07T18:59:48Z

EDITORIAL Vol. 11 No.3

In this number of Computation and Systems, members of our scientific community present six articles about methodologies and algorithms for the design of programs, the interaction among programmers, the search of information, resource optimization, and robotics.

In the next paragraphs our readers will find the context in which each reported work is located. Each of these works is broadly motivated by the needs of our modern society that each time better understands the utility of computation and imagines new applications. Society claims for immediate and correct answers. It is required that programs are implemented and executed quickly not also in parallel but under a collaborative environment that allows to better exploit material and intellectual resources.

First we have parallelism, where design is not obvious and much less automatic. Each program's version has a different behavior. Performance depends on the design. How to evaluate among different alternatives of a program? Definitely, implementing each one of them is impossible. Jorge Ortega proposes using UML State Diagrams to estimate average execution time of a parallel program. This work makes possible to evaluate alternatives, explore the most promising ones and obtain good approximations.

Parallelism allows us to distribute tasks that are not only reserved to processors. This concerns programmers too. In this sense, Moran et al. propose and evaluate a system for programming in pairs. Who has not programmed next to the other? Who has not had a distance meeting through one of the teleconference systems or through a chat system? Moran et al. describe the architecture of a collaborative editor which allows programmers to work in the design of distributed systems in a distributed way.

When handling great volumes of data, information recovery becomes a complex problem where it turns out prohibitive to cross a database completely. The indexation method or that one that allow measuring the degree of similarity between two structures greatly influences quality of the results. In this number of Computation and Systems two papers approach the subject of information recovery. The first one by Felipe-Riveron et al. uses time series for color matching, a method very easy to understanding, proposed, implemented and experimented by its authors. The second work by Ledo Mezquita et al. proposes a new method that allows finding the correct sense of words composing the description of the searched information. This method takes advantage of content to improve quality of the results.

The applications of the works presented in Computation and Systems are varied, Romero et al. shows it with a real case by representing the dynamic behavior of a water distribution system. Efficient use of water depends on the design and configuration of their distribution networks. Romero et al. propose using evolving optimization methods to multiple objectives.

Finally, Gorrostieta and Vargas Soto contribute a work in the area of robotics and fuzzy logic. Their work proposes a set of necessary algorithms for the displacement of a spider robot: stability, control and locomotion. These algorithms are evaluated through two simulators.

Contents of this number show that today computation is everywhere and none of the modern professions can avoid it. The research lines have an ample perspective where it is required of an interdisciplinary work.

The editors of Computation and Systems trust that it will find each time more readers and enthusiastic authors. We thank the reviewers for their magnificent work carried out and invested time, the authors for their patience and quality of work and the readers for their opinions. Each of these roles makes possible the existence of Computation and Systems.

Juan Manuel Ahuactzin Associate Editor

New publications: Probabilistic Reasoning and Decision Making in Sensory-Motor Systems

Juan-Manuel Ahuactzin — 2008-05-05T17:48:42Z

In this book Miriam Amavizca, Christian Laugier, Emmanuel Mazer, Francois Leitner and my self contribute with the book chapter entitled:

3D human hip volume reconstruction with incomplete multimodal medical images

This work is within the context of Computer-assisted Orthopaedic Surgery (CAOS), in particular Total Hip Replacement (THR) surgery.

In conventional medical imagery, the patient's anatomy is obtained from multiple two-dimensional (2D) medical images. In contrast to conventional medical imagery, image processing allows a three-dimensional (3D) visualization of the patient from a numerical model. The 3D representation adds visibility to the organs and makes them more perceptible. Surgical systems intervene to obtain the 3D representation of the organs and to use the model in the different stages of the patient's medical treatment: preoperative (planning), operative (control) and post-operative (validation). In this way, the aim of CAS is to obtain more precise post-operative results according to the preoperative planning than can be achieved with conventional techniques.

We propose a methodology for obtaining a 3D patient's hip model from 2D data and partial 3D data. The 2D data are obtained from one anteroposterior radiographic image, and the partial 3D data are obtained from echographic images. All procedures are non-invasive, low cost and fast. The patient's personalized model is obtained by a “deformation” of a generic hip mesh. Control points are obtained from radiographic and echographic data.

"The book Probabilistic Reasoning and Decision Making in Sensory-Motor Systems by Pierre Bessiere, Christian Laugier and Roland Siegwart provides a unique collection of a sizable segment of the cognitive systems research community in Europe. It reports on contributions from leading academic institutions brought together within the European projects Bayesian Inspired Brain and Artifact (BIBA) and Bayesian Approach to Cognitive Systems (BACS). This fourteen-chapter volume covers important research along two main lines: new probabilistic models and algorithms for perception and action, new probabilistic methodology and techniques for artefact conception and development. The work addresses key issues concerned with Bayesian programming, navigation, filtering, modelling and mapping, with applications in a number of different contexts."