Thesis Code: 22010
Thesis Type: Master Thesis for Computer Engineering, ICT for Smart Societies, Telecommunication Engineering or related fields
Research Area: Connected Systems and Cybersecurity
Requirements
- Excellent software programming skills
- Strong experience with Python/bash scripting and Linux environment
- Strong experience with C/C++ programming languages
- Basic knowledge of machine learning
Motivation
Knowledge of the surrounding environment is crucial for connected and autonomous vehicles. These vehicles must rely on their own sensors to identify and keep track of other road users. Significant support can be provided from the roadside infrastructure. In critical places, fixed sensors can continuously sense the surrounding environment to identify vehicles, pedestrians, and obstacles and the infrastructure can communicate the gathered information to the connected vehicles. Visual cameras are typically used, but, nowadays, LiDARs are beginning to be employed as their cost is lowering. New detection and tracking approaches, that exploit LiDAR data, can be now introduced.
Objective
The aim of the thesis is to implement a framework for the automotive environment that provides object detection and tracking based on LiDAR data.
The first part of the thesis will be devoted to surveying the state-of-art solutions of object detection and tracking methods that exploit LiDAR data. The most promising approaches will be implemented in the second part of the thesis. The student will develop an object and detection tracking system exploiting data coming from real sensors installed on the field.
The student will have the possibility to work in an informal cutting-edge research laboratory using the latest available technologies of road sensors and exploiting a real-life testbed.
Contact: send a resume with attached the list of exams and related scores to daniele.brevi@linksfoundation.com specifying the thesis code and title.
