Semantic search

Title: Visual stabilization techniques for tracking with a moving camera
Description: Target tracking in video sequences can suffer poor performances if the camera is moving (e.g, wind, hand held device, aerial tracking system). The aim of the project is to investigate the state of the art in image stabilization and registration in non static or cluttered scenes. Possible ideas to be investigated include: homography tracking or smoothing, 3D camera motion estimation, image registration and mosicing. As a by product of the work, a tool for the performance evaluation of image stabilization algorithms should be designed.

Material

• a huge corpus of literature on the topic
• datasets to test the approach upon
• C++ library for image processing and computer vision (OpenCV)

Expected outcome:

• software for the stabilization of videos from a moving camera showing moving objects in cluttered environments
• a tool for the objective evaluation of image stabilization algorithms

Required skills or skills to be acquired:

• computer vision and 3D reconstruction
• C++ programming under Linux
  

Tutor: MatteoMatteucci
Additional Info: CFU 10 - 20 / Bachelor of Science, Master of Science / Thesis

Title: Wikipedia Page Social Network
Description: Goal of this project is to study the social network of Wikipedia pages, where two pages are connected if they share at least one main contributor. This social network can be studied to reveal interesting information; for example, it is possible to extract clusters of pages which apparently have nothing in common. A metric of distance between pages in the network can be defined, and compared with other metrics, such as the distance in the category tree or in the hyperlink graph.
Tutor: DavidLaniado, RiccardoTasso, MarcoColombetti
Additional Info: CFU 5 - 20 / Bachelor of Science, Master of Science / Course, Thesis

Title: Wikipedia Tripartite Graph
Description: When a user edits a Wikipedia page, we can establish a link among her, the page and the categories to which the page belongs. A model to represent this information is a tripartite graph. Aim of this project is to build a tripartite graph from Wikipedia users, pages and categories, and mine the outcome network to extract emergent semantics.
Tutor: DavidLaniado, RiccardoTasso, MarcoColombetti
Additional Info: CFU 20 - 20 / Master of Science / Thesis