Master Level Course Projects

From AIRWiki
Revision as of 11:27, 17 October 2008 by DavideMigliore (Talk | contribs) (Computer Vision and Image Analysis)

Jump to: navigation, search

Here you can find a list of project proposals for the courses of "Laboratorio di Intelligenza Artificiale e Robotica" (5 CFU for each student) and "Soft Computing" (1 CFU for each student)

Affective Computing


Title: Affective VideoGames
AffectiveGaming.jpg
Description: The goal of this activity is to develop an interactive video game (Car game, Shoot them up, Strategic game ..) able to adapt its behaviour in order to maximize your enjoyment. The game will measure your excitement by analizing your biological signals, which mirror your emotional state. The system will be able to adjust some parameters (i.e difficulty of car game circuits, opponets strength ...) in order to keep you egnagemet constant: "In your flow zone!".

Project phases:

  • Design and implementation of the game (it is possible to start form avaliable open source game)
  • Design of experimental protocol used to stimulate particolar emotions.
  • Data acquisition by usign biological sensors during the playing experience.
  • Off-line classification of data with avaliable tools.
  • Desing and develop of on-line classifier sistem for emotion recognition
  • Closed loop control: the game reacts to the user emotional state changing its behaviour.

These projects allow to experiment with biological-data acquisition tools and videogames design.

Each project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)

Tutor: Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 3
CFU: 2.5 to 20





Title: Affective recognition in multimedia contexts
MultimediaAffective.jpg
Description: The goal of this activity is to develop an interactive multimedia application (advertisement, e-learning, reccomenadation system) able to capture your emotional state (interests, excitement, anger, joy) while whatching to images, sounds etc. The application will measure your excitement by analizing your biological signals, which mirror your emotional state. The system could be used to give feedback on the quality of multimedia content (i.e goodness of the advertisement, enjoyment of the movie ...)

Project phases:

  • Design and implementation of the multimedia application.
  • Design of experimental protocol used to stimulate particolar emotions.
  • Data acquisition by usign biological sensors during the multimedia experience.
  • Off-line classification of data with avaliable tools.
  • Desing and develop of on-line classifier sistem for emotion recognition
  • Closed loop control: the multimedia application will provide contents according to your enjoyment .

These projects allow to experiment with biological-data acquisition tools and multimedia application design.

The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)

Tutor: Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 3
CFU: 2.5 to 20




Title: Affective robotics
SimoAffective.jpg
Description: The goal of this activity is to develop an rehabilitation robotic game able to capture your emotional state (interests, excitement, anger, joy, stress) while intereacting with the robot. The application will measure your excitement by analizing your biological signals, which mirror your emotional state. The system could be used to adapt the therapy (executed by the game) according to the patien's needs. We believe the quality of the theraphy is related to the subject's emotional state. The long term goal is to keep the user into a specific emotional state in order to maximize the theraphy efficacy.

Project phases:

  • Design and implementation of the robotic game on the avaliable robot.
  • Design of experimental protocol used to stimulate particolar emotions.
  • Data acquisition by usign biological sensors during the interaction with the robot.
  • Off-line classification of data with avaliable tools.
  • Desing and develop of on-line classifier sistem for emotion recognition
  • Closed loop control: the thrapy will be adapted to the patient's needs.

These projects allow to experiment with biological-data acquisition tools, robots and videogame design.

The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)

Tutor: Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 3
CFU: 2.5 to 20




Title: Driving companions
CarAffective.jpg
Description: The goal of this activity is to develop an application that is able to capture your emotional state (stress, attention level .. ) while driving standard cars. The application will measure the driver's stress level by analizing his biological signals, which mirror the phisiological state, and could be used to give feedbacks to the driver in dangerous situations.

Project phases:

  • Design of experimental protocol used to stimulate particolar emotions.
  • Data acquisition by usign biological sensors while driving in different conditions (city, highway, country ..)
  • Off-line classification of data with avaliable tools.
  • Desing and develop of on-line classifier sistem for emotion recognition
  • Closed loop control: the car will give audio/visual feedbacks to the user letting him know its phisiological state

These projects allow to experiment with biological-data acquisition tools, robots and videogame design.

The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)

Tutor: Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 3
CFU: 2.5 to 20




Title: Emotion from interaction
AffectiveGaming.jpg
Description: The goal of this activity is to detect emotional states, such as stress or boreness from the interaction with the computer via mouse and keyboard (Emotion from Interaction). A library getting data from these devices has been already developed. Data have to be acquired in different situations and analyzed by neural networks or other classification tools already implemented.
Tutor: Andrea Bonarini (bonarini-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 2
CFU: 5 to 12.5



BioSignal Analysis


Title: Human-computer interaction via voice recognition system
LURCH wheelchair.jpg
Description: We want develop a system to allow a voice interaction between the user and the wheelchair.

This project consists in develop one of the solutions proposed in literature and extended the LURCH software to include this kind of interface.

  • C/C++ and OpenCV library
  • Matlab (optionally)
  • Linux

References:

  • Phinx project [1]
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 1-2
CFU: 2.5-10


Brain-Computer Interface


Title: Development of an existing genetic algorithm for ERP-based BCIs
Ga-scheme.png
Description: Different event-related potentials (ERPs) are used in BCIs, e.g., P300 and error potentials.

A genetic algorithm (GA) for ERP feature extraction has been developed at the Airlab. The GA has been proved to work, but there different ways that can explored to further develop this algorithm and expand its application field.

Tools and instruments
C++, Matlab
Good programming skill required
Bibliography
B. Dal Seno, M. Matteucci, L. Mainardi. A Genetic Algorithm for Automatic Feature Extraction in P300 Detection [2]
Tutor: Matteo Matteucci (email), Bernardo Dal Seno (email)
Start: Anytime
Number of students: 1
CFU: 5-20



Title: Driving an autonomous wheelchair with a P300-based BCI
LURCH wheelchair.jpg
Description: This project pulls together different Airlab projects with the aim to drive an autonomous wheelchair (LURCH) with a BCI, through the development of key software modules. Depending on the effort the student is willing to put into it, the project can grow to a full experimental thesis.
Tools and instruments
C++, C, BCI2000
Linux
Bibliography
R. Blatt et al. Brain Control of a Smart Wheelchair [3]
Tutor: Matteo Matteucci, Bernardo Dal Seno
Start: November 2008
Number of students: 1
CFU: 5-20



Title: Online automatic tuning of the number of repetitions in a P300-based BCI
B p300 speller.jpg
Description: In a P300-based BCI, (visual) stimuli are presented to the user, and the intention of the user is recognized when a P300 potential is recognized in response of the desired stimulus. In order to improve accuracy, many stimulation rounds are usually performed before making a decision. The exact number of repetitions depends on the user and the goodness of the classifier, but it is usually fixed a-priori. The aim of this project is to adapt the number of repetitions to changing conditions, so as to achieve the maximum accuracy with the minimum time.

Depending on the effort the student is willing to put into it, the project can grow to a full experimental thesis.

Tools and instruments
C++, BCI2000
Bibliography
E. Donchin, K.M. Spencer, R. Wijesinghe. The Mental Prosthesis: Assessing the Speed of a P300-Based Brain-Computer Interface [4]
Tutor: Matteo Matteucci, Bernardo Dal Seno
Start: Anytime
Number of students: 1
CFU: 5-20



Title: Reproduction of an algorithm for the recognition of error potentials
Bci arch.png
Description: Error potentials (ErrPs) are event-related potentials present in the EEG (electroencephalogram) when a subject makes a mistake or when the machine a subject is interacting with works in an expected way. They could be used in the BCI field to improve the performance of a BCI by automatically detecting classification errors.

The project aims at reproducing algorithms for ErrP detection from the literature.

Tools and instruments
Matlab
Bibliography
P.W. Ferrez, J. Millán. You Are Wrong! Automatic Detection of Interaction Errors from Brain Waves [5]
G. Schalk et al. EEG-based communication: presence of an error potential [6]
Tutor: Matteo Matteucci, Bernardo Dal Seno
Start: Anytime
Number of students: 1
CFU: 5-15


Computer Vision and Image Analysis


Title: Environment Monitoring
Danch4.png
Description: The goal of this project is to develop a video surveillance system to track in 3D vehicles or people.

The idea is to use one or more calibrated camera to estimate the position and the trajectories of the moving objects in the scene. The skills required for this project are:

  • C/C++ and OpenCV library
  • Linux o.s.
  • Geometry/Image processing
  • Probabilistic robotics/IMAD

The project can be turned into a thesis extending the algorithm for a generic outdoor environment.

Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 2-3
CFU: 10-15




Title: Visual Merchandising
VisualM.jpg
Description: The goal of this project is to develop algorithms to count the number of products on the shelves of a market.

The idea is to use a calibrated camera to recognize the shelves, estimate the scale and improve the image quality. The skills required for this project are:

  • C/C++ and OpenCV library
  • Matlab (optionally)
  • Linux
  • Geometry/Image processing
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: As soon as possible
Number of students: 2-3
CFU: 2.5-15



Title: Analysis of patch recognition algorithms
Object.jpg
Description: Extract distinctive features from images is very important in computer vision application.

It can be used in algorithms for tasks like matching different views of an object or scene (e.g. for stereo vision) and object recognition. The aim of this work is to integrate in an existent framework the existing solution proposed in literature.

Skills

  • C/C++ and OpenCV library
  • Matlab (optionally)
  • Linux
  • Geometry/Image processing

References:

  • Oxford website [7]
  • Hess website [8]
  • Feature FAST [9]
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 2-3
CFU: 2.5-15




Title: Catadioptric MonoSLAM
Photo.jpg
Description: The goal of this work is to investigate a SLAM solutions based on catadioptric camera, integrating the solution presented in literature into an existing frameword.

Improvements could be the basis for a tesi.

Skills

  • C/C++ and OpenCV library
  • Matlab (optionally)
  • Linux
  • Geometry/Image processing

References:

  • Visual SLAM by Single Catadioptric Stereo [10]
  • Catadioptric reconstruction [11]
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 2-3
CFU: 2.5-15




Title: Trinocular Vision System (SUGR)
Trinoex.jpg
Description: A Trinocular Vision System is a device composed by three cameras that allows to measure 3D data (in this case segments) directly from images.

The aim of this tesina/project is to implement a trinocular algorithm based on SUGR, a library for Uncertain Projective Geometry.


Skills

  • C/C++ and OpenCV library
  • Matlab (optionally)
  • Linux
  • Geometry/Image processing
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: As soon as possible
Number of students: 2-3
CFU: 2.5-15




Title: GIFT and features extraction and description
Palla GIFT.jpg
Description: The idea is to improve and optimize the solution proposed by Campari et al. in their paper, who propose to estimate invariant descriptor using geodesic features descriptor based on color information.

Skills

  • C/C++ and OpenCV library
  • Matlab (optionally)
  • Linux
  • Geometry/Image processing
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 1-3
CFU: 10-20



Machine Learning


Title: Reinforcement Learning Competition
Keepaway.gif
Description: This project has the goal of participating to (and possibly winning ;)) the 2009 Reinforcement Learning competition. To have an idea of what participate to such a competition means you can have a look at the website of the 2008 RL competition.

The problems that will be proposed are still unknown. As soon as the domains will be published, the work will start by analyzing their main characteristics and, then we will identify which RL algorithms are most suited for solving such problems. After an implementation phase, the project will required a long experimental period to tune the parameters of the learning algorithms in order to improve the performance as much as possible.

Tutor: Marcello Restelli (restelli-AT-elet-DOT-polimi-DOT-it)
Start: January, 2009
Number of students: 2-4
CFU: 10-20



Title: Learning API for TORCS
TORCS.jpg
Description: TORCS is a state-of-the-art open source racing simulator that represents an ideal bechmark for machine learning techniques. We already organized two successfull competitions based on TORCS where competitors have been asked to develop a controller using their preferred machine learning techniques. The goal of this project is to extend the existing C++ API (available here) to simplify the development of controller using a learning framework.

Such an extension can be partially developed by porting an existing Java API for TORCS that already provides a lot of functionalities for machine learning approaches.

Tutor: Daniele Loiacono (loiacono-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 2
CFU: 5 to 12.5



Title: EyeBot
TORCS2.jpg
Description: TORCS is a state-of-the-art open source racing simulator that represents an ideal bechmark for machine learning techniques. We already organized two successfull competitions based on TORCS where competitors have been asked to develop a controller using their preferred machine learning techniques. So far, the controller developed for TORCS used as input only information extracted directly from the state of the game. The goal of this project is to extend the existing controller API (see here) to use the visual information (e.g. the screenshots of the game) as input to the controllers. A successfull project will include both the development of the API and some basic imaga preprocessing to extract information from the images.
Tutor: Daniele Loiacono (loiacono-AT-elet-DOT-polimi-DOT-it), Alessandro Giusti (giusti-AT-elet-DOT-polimi-DOT-it), and Pierluigi Taddei (taddei-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 2
CFU: 5 to 20



Title: SmarTrack
TORCS3.jpg
Description: The generation of customized game content for each player is an attractive direction to improve the game experience in the next-generation computer games. In this scenario, Machine Learning could play an important role to provide automatically such customized game content.

The goal of this project is to apply machine learning techniques for the generation of customized tracks in TORCS, a state-of-the-art open source racing simulator. The project include different activities: the automatic generation of tracks, the section of relevant features to characterize a track and the analysis of an interest measure.

Tutor: Daniele Loiacono (loiacono-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1 to 2
CFU: 5 to 20




Title: TORCS competition
TORCS.jpg
Description: TORCS is a state-of-the-art open source racing simulator that represents an ideal bechmark for machine learning techniques. We already organized two successfull competitions based on TORCS where competitors have been asked to develop a controller using their preferred machine learning techniques.

The goal of this project is to apply any machine learning technique to develop a successfull controller following the competition rules (available here)

Tutor: Daniele Loiacono (loiacono-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1
CFU: 5


Robotics


Title: Robot games
Robowii robot.jpg
Description: The goal of this activity is to develop an interactive game with robots using commercial devices such as the WII Mote (see the Robogames page)

Projects are available in different areas:

  • Design and implementation of the game on one of the available robots
  • Design of the game and a new suitable robot
  • Implementation/setting of a suitable robot
  • Evaluation of the game with users (in collaboration with Franca Garzotto)

These projects allow to experiment with real mobile robots and real interaction devices.

The project can be turned into a thesis by producing a new game and robot.

Tutor: Andrea Bonarini (bonarini-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1-2
CFU: 5-12.5



Title: Robocup: soccer robots
RIeRO.jpg
Description: The goal of this activity is to finalize the team of robots that will participate to the robocup world championship in Graz next summer (see the Robocup page and the MRT Team page)

Projects are available in different areas:

  • Implementation of mechanical and electronical parts of the robots for the management of the ball and kicking
  • Design of robot behaviors (fuzzy systems)
  • Coordination of robots
  • New sensors

These projects allow to experiment with real mobile robots. Participation to the championships is a unique experience (2000 people, with 800 robots playing all sort of games...)

The project can be turned into a thesis by facing different problems in depth.

Tutor: Andrea Bonarini (bonarini-AT-elet-DOT-polimi-DOT-it), Marcello Restelli (restelli-AT-elet-DOT-polimi-DOT-it)
Start: Anytime
Number of students: 1-2
CFU: 5-12.5




Title: Calibration of IMU-camera system
Imu cam big sphere.gif
Description: This work is about the problem to calibrate a system composed by an XSense

Inertial Measurement Unit and a Fire-i Camera. The pro ject will be focus on the problem to estimate both unknown rotation between the two devices and the extrinsic/intrinsic parameters of the camera. This algorithm allows to use the system for SLAM or robotics applications, like a wereable device for autonomous navigation or augmented reality.

Tools and instruments
Matlab/C++
Links
Matlab Toolbox for mutual calibration [12]
List of pubblications[13]
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 1
CFU: 5-20




Title: MonoSLAM system implementation
KC jc third.jpg
Description: The aim of this proposal is to investigate the different monocamera SLAM solution proposed in literature.

After a deepen bibliography research, the work will be focused on developing one of these algorithms into an existing framework and, only for tesi option, investigate possible improvements.

The algorithms interested are based on [14]:

  • Extended Kalman Filter [15]
  • Unscented Kalman Filter [16]
  • FastSLAM [17]
  • GraphSLAM [18]


Tools and instruments
Matlab/C++
Tutor: Matteo Matteucci (email), Davide Migliore (email)
Start: Anytime
Number of students: 1-2
CFU: 5-20