# Semantic search

PrjDescription | PrjResArea | PrjTutor | PrjStudMin | PrjStudMax | |
---|---|---|---|---|---|

AGW | Control system design of an electric wheelchair for autonomous drive with obstacle avoidance | Robotics | MatteoMatteucci Marcello Farina Luca Bascetta |
||

Accurate AR Marker Location | ARTags, QR codes, Data Matrix, are visual landmark used for augmented reality, but they could be used for robotics as well. A thesis has already been done on using data matrix for robot localization and mapping, but improvements are required in terms generality, accuracy and robustness of the solution. The goal is thuss to: *increase the number of markers supported by the system (ARTag + QR codes) *increase the accuracy of the detection and localization of the marker *test different algorithms for the solution of the perspective from n points problem '''Material:''' *papers on PnP algorithms, OpenCV, *Matlab code with three PnP algorithms implementations *C++ libraries for marker detection (to be found and evaluated) '''Expected outcome:''' *C++ library to the robust localization of artificial markers *a ROS node performing accurate ARTag localization *a comparison of Tags and algorithms in a real world scenario *The use of this library in a SLAM framework (Thesis) '''Required skills or skills to be acquired:''' *background on computer vision and image processing *C++ programming under Linux | Computer Vision and Image Analysis | MatteoMatteucci | 1 | 2 |

Ackerman vehicle autonomous drive | Development of an autonomous drive system for an Ackerman vehicle with the use of Move base ROS package | MatteoMatteucci | |||

Aperiodic visual stimulation in a VEP-based BCI | Visual-evoked potentials (VEPs) are a possible way to drive the a Brain-Computer Interface (BCI). This projects aims at maximizing the discrimination between different stimuli by using numerical codes derived from techniques of digital telecommunications. *J.R. Wolpaw et al. ''Brain-computer interfaces for communication and control'' (http://tinyurl.com/yhq27pq) *Erich E. Sutter. ''The brain response interface: communication through visually-induced electrical brain responses'' (http://tinyurl.com/yfqvwp6) | BioSignal Analysis | MatteoMatteucci | 1 | |

Automatic Differentiation Techniques for Real Time Kalman Filtering | In Gauss-Newton non linear optimization one of the most tedious part is computing Jacobians. At the AIRLab we have developed a framework for non linear Simultaneous Localization and Mapping suitable for different motion models and measurement equations, but any time you need to change something you need to recompute the required Jacobian. Automatic differentiation is a tool for the automatic differentiation of source code either at compiling time or at runtime; we are interested in testing these techniques in the software we have developed and compare their performance with respect to (cumbersome) optimized computation. '''Material''' *C++ modules for Extended Kalman Filtering *libraries for automatic differentiation (http://www.autodiff.org/) '''Expected outcome:''' New modules implementations based on automatic differentiation A comparison between the old stuff and new approach '''Required skills or skills to be acquired:''' *C++ programming under Linux | Robotics | MatteoMatteucci | 1 | 2 |

Automatic generation of domain ontologies | This thesis to be developed together with Noustat S.r.l. (see http://www.noustat.it), who are developing research activities directed toward the optimization of knowledge management services, in collaboration with another company operating in this field. This project is aimed at removing the ontology building bottleneck, long and expensive activity that usually requires the direct collaboration of a domain expert. The possibility of automatic building the ontology, starting from a set of textual documents related to a specific domain, is expected to improve the ability to provide the knowledge management service, both by reducing the time-to-application, and by increasing the number of domains that can be covered. For this project, unsupervised learning methods will be applied in sequence, exploiting the topological properties of the ultra-metric spaces that emerge from the taxonomic structure of the concepts present in the texts, and associative methods will extend the concept network to lateral, non-hierarchical relationships. | Machine Learning | MatteoMatteucci AndreaBonarini DavideEynard |
1 | 2 |

BCI & artifacts | BCI and artifacts | BioSignal Analysis | MatteoMatteucci | ||

BCI based on Motor Imagery | This project is aimed is to control an external device through the analysis of brain waves measured on the human scalp. | BioSignal Analysis | MatteoMatteucci RossellaBlatt BernardoDalSeno |
||

BCI on Sockets | Communication on TCP/IP between BCI Software modules | BioSignal Analysis | MatteoMatteucci | ||

Balancing Robot Development | Building a balancing robot starting from an existing hardware | MatteoMatteucci | |||

Behavior recognition from visual data | In the literature several approaches have been used to model observed behaviors and these date back to early approaches in animal behavior analysis (Baum and Eagon, 1967)(Colgan, 1978). Nowadays several techniques are used and they can be roughly classified as: State space models, Automata (e.g., Finite State Machines, Agents, etc.), Grammars (e.g., strings, T-Patterns, etc.), Bayeasian models (e.g., Hidden Markov Models), and Dynamic State Variables. The work will leverage on a huge corpus of techniques to devise the most suitable for behavior recognition from visual data. We exclude from the very beginning any deterministic approach being the phenomenon under observation complex and affected by noisy observations. The focus will be mainly of the use of dynamic graphical models (Ghahramani, 1998) and the application of bottom up learning techniques (Stolcke and Omohundro, 1993)(Stolcke and Omohundro, 1994) for model induction. *L. E. Baum and J. A. Eagon. An inequality with applications to statistical estimation for probabilistic functions of markov processes and to a model for ecology. Bull. Amer. Math. Soc, 73(73):360–363, 1967. *P. W. Colgan. Quantitative Ethology. John Wiley & Sons, New York, 1978. *A. Stolcke and S. M. Omohundro. Hidden markov model induction by bayesian model merging. In Stephen Jos é Hanson, Jack D. Cowan, and C. Lee Giles, editors, Advances in Neural Information Processing Systems, volume 5. Morgan Kaufmann, San Mateo, CA, 1993. *Zoubin Ghahramani. Learning dynamic bayesian networks. Lecture Notes in Computer Science, 1387:168, 1998. *A. Stolcke and S. M. Omohundro. Best-first model merging for hidden markov model induction. Technical Report TR-94-003, 1947 Center Street, Berkeley, CA, 1994. '''''Material:''''' *papers from major journals and conferences *kinet SDK for the extraction of body poses '''''Expected outcome:''''' *general framework for the recognition of behaviors from time series *toolkit for behavior segmentation and recognition from time series *running prototype based on data coming from the Microsoft kinect sensor '''''Required skills or skills to be acquired:''''' *understanding of techniques for behavior recognition *background on pattern recognition and stochastic models *basic understanding of computer vision *C++ programming under Linux or Matlab | Machine Learning | MatteoMatteucci AndreaBonarini |
1 | 2 |

Characterization of the NIA signal | The NIA system by OCZ provides a very cheap way to get a signal that includes EOG, EMG and EEG. Aim of this project is to characterize it and investigate how could it be used as a substitute of a clinical EEG for non-clinical applications, and as one more signal for affective computing. | BioSignal Analysis | MatteoMatteucci | ||

Combinatorial optimization based on stochastic relaxation | The project will focus on the study, implementation, comparison and analysis of different algorithms for the optimization of pseudo-Boolean functions, i.e., functions defined over binary variables with values in R. These functions have been studied a lot in the mathematical programming literature, and different algorithms have been proposed (1). More recently, the same problems have been faced in evolutionary computations, with the use of genetic algorithms, and in particular estimation of distribution algorithms (2,3). Estimation of distribution algorithms are a recent meta-heuristic, where classical crossover and mutation operators used in genetic algorithms are replaced with operators that come from statistics, such as sampling and estimation. The focus will be on the implementation of a new algorithm able to combine different approaches (estimation and sampling, from one side, and exploitation of prior knowledge about the structure of problem, on the other), together with the comparison of the results with existing techniques that historically appear in different (and often separated) communities. Good coding (C/C++) abilities are required. Since the approach will be based on statistical models, the student is supposed to be comfortable with notions that come from probability and statistics courses. The project could require some extra effort in order to build and consolidate some background in math, especially in Bayesian statistics and MCMC techniques, such as Gibbs and Metropolis samplers (4). The project can be extended to master thesis, according to interesting and novel directions of research that will emerge in the first part of the work. Possible ideas may concern the proposal of new algorithms able to learn existing dependencies among the variables in the function to be optimized, and exploit them in order to increase the probability to converge to the global optimum. Picture taken from http://www.ra.cs.uni-tuebingen.de/ Bibliography # Boros, Endre and Boros, Endre and Hammer, Peter L. (2002) Pseudo-boolean optimization. Discrete Applied Mathematics. # Pelikan, Martin; Goldberg, David; Lobo, Fernando (1999), A Survey of Optimization by Building and Using Probabilistic Models, Illinois: Illinois Genetic Algorithms Laboratory (IlliGAL), University of Illinois at Urbana-Champaign. # Larrañga, Pedro; & Lozano, Jose A. (Eds.). Estimation of distribution algorithms: A new tool for evolutionary computation. Kluwer Academic Publishers, Boston, 2002. # Image Analysis, Random Fields Markov Chain Monte Carlo Methods | Machine Learning | MatteoMatteucci LuigiMalago |
1 | 2 |

Combining Estimation of Distribution Algorithms and other Evolutionary techniques for combinatorial optimization | The project will focus on the study, implementation, comparison and analysis of different algorithms for combinatorial optimization using techniques and algorithms proposed in Evolutionary Computation. In particular we are interested in the study of Estimation of Distribution Algorithms (1,2,3,4), a recent meta-heuristic, often presented as an evolution of Genetic Algorithms, where classical crossover and mutation operators, used in genetic algorithms, are replaced with operators that come from statistics, such as sampling and estimation. The focus will be on the implementation of new hybrid algorithms able to combine estimation of distribution algorithms with different approaches available in the evolutionary computation literature, such as genetic algorithms and evolutionary strategies, together with other local search techniques. Good coding (C/C++) abilities are required. Some background in combinatorial optimization form the "Fondamenti di Ricerca Operativa" is desirable. The project could require some effort in order to build and consolidate some background in MCMC techniques, such as Gibbs and Metropolis samplers (4). The project could be extended to master thesis, according to interesting and novel directions of research that will emerge in the first part of the work. Computer vision provides a large number of optimization problems, such as new-view synthesis, image segmentation, panorama stitching and texture restoration, among the others, (6). One common approach in this context is based on the use of binary Markov Random Fields and on the formalization of the optimization problem as the minimum of an energy function expressed as a square-free polynomial, (5). We are interested in the proposal, comparison and evaluation of different Estimation of Distribution Algorithms for solving real world problems that appear in computer vision. Pictures taken from http://www.genetic-programming.org and (6) Bibliography # Pelikan, Martin; Goldberg, David; Lobo, Fernando (1999), A Survey of Optimization by Building and Using Probabilistic Models, Illinois: Illinois Genetic Algorithms Laboratory (IlliGAL), University of Illinois at Urbana-Champaign. # Larrañga, Pedro; & Lozano, Jose A. (Eds.). Estimation of distribution algorithms: A new tool for evolutionary computation. Kluwer Academic Publishers, Boston, 2002. # Lozano, J. A.; Larrañga, P.; Inza, I.; & Bengoetxea, E. (Eds.). Towards a new evolutionary computation. Advances in estimation of distribution algorithms. Springer, 2006. # Pelikan, Martin; Sastry, Kumara; & Cantu-Paz, Erick (Eds.). Scalable optimization via probabilistic modeling: From algorithms to applications. Springer, 2006. # Image Analysis, Random Fields Markov Chain Monte Carlo Methods # Carsten Rother, Vladimir Kolmogorov, Victor Lempitsky, Martin Szummer. Optimizing Binary MRFs via Extended Roof Duality, CVPR 2007 | Machine Learning | MatteoMatteucci LuigiMalago |
1 | 2 |

Comparison of State of the Art Visual Odometry Systems | Visual odometry is the estimation of camera(s) movement from a sequence of images. In case we deal with a single camera system we have Monocular Visual Odometry; in case we have more cameras we have a Stero Visual Odometry. The goal of the thesis is to review the state of the art on in visual odometry, classify existing approaches and compare their implementations (many of the algorithms have online source code available). '''Material''' *a huge corpus of literature on the topic *libraries on visual odometry (http://www.cvlibs.net/datasets/kitti/index.php) *C++ library for image processing and computer vision (OpenCV) '''Expected outcome:''' *a set of running algorithms performing visual odometry '''Required skills or skills to be acquired:''' *computer vision and 3D reconstruction *C++ programming under Linux | Computer Vision and Image Analysis | MatteoMatteucci | 1 | 2 |

Creation of new EEG training by introduction of noise | A Brain-Computer Interface (BCI) must be trained on the individual user in order to be effective. This training phase require recording data in long sessions, which is time consuming and boring for the user. The aim of this project is to develop algorithm to create new training EEG (electroencephalography) data from existing ones, so as to speed up the training phase. *J.R. Wolpaw et al. ''Brain-computer interfaces for communication and control'' (http://tinyurl.com/yhq27pq) | BioSignal Analysis | MatteoMatteucci | 1 | 2 |

Deep Learning on Event-Based Cameras | This project aims to study deep learning techniques on event-based cameras and develop algorithms to perform object recognition on those devices. | MatteoMatteucci | |||

DiffDrivePlanner | A Search-Based Trajectory Planner for differential drive vehicles in ROS Context | Robotics | MatteoMatteucci | ||

Driving an autonomous wheelchair with a P300-based BCI | 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. | BioSignal Analysis | MatteoMatteucci | 1 | |

Environment Monitoring | 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 | Computer Vision and Image Analysis | MatteoMatteucci DavideMigliore |
2 | 3 |