Thesis Code: 19018
Thesis Type: M.Sc. thesis in Machine Learning, Data Science, Computer Science, Mathematics, or equivalent

Research Area: Data Science for Industrial and Societal Application

Requirements:

  • Knowledge of Python
  • Software development skills
  • Basic concepts on data science, concerning data analysis, processing and machine learning
  • Basic concepts on image processing

Description:
Monitoring and recognizing pedestrians’ actions is important, especially in areas where there is a risk of terrorist attacks or that are normally poorly guarded, in order to guarantee the safety of the citizens. It is therefore necessary to support the police or other surveillance agencies with intelligent systems. These systems must recognize and track an individual, in order to analyse displacements and actions taken by the target in a series of video sequence.
The objective of this thesis consists in the study and implementation of machine learning algorithms useful for recognizing and tracing a pedestrian in non-contiguous video scenes (re-identification). The proposed algorithms will be trained using a synthetic dataset. This is created with the help of dedicated tools for extracting information from the Grand Theft Auto V graphic engine. The candidate will have both the task of creating the dataset and studying and evaluating the best algorithms to apply for the case of study. The candidate is required to implement machine learning algorithms, with the exploratory possibility of deep learning algorithms using popular framework (TensorFlow, PyTorch, Keras, etc..).

Contact: send a resume with attached the list of exams to mirko.zaffaroni@linksfoundation.com specifying the thesis code and title.