Summarization of First Person Videos
The project aim to build visual intellingence algorithms able to get a video acquired with wearable cameras (e.g. Hololens) as input and produce a short video summary as output containing the main objects and context observed by the user. To this aim,modern Computer Vision and Machine Learning algorithms will be employed to detect and recognise automatically the observed objects and scenes.
Required Competences:
Image processing, computer vision, machine learning, python/matlab programming.
Tutor: prof. Giovanni Maria Farinella.
Study cycle:
post graduate
Languages skills required:
English B2
Length:
6 months
Period:
second semester
Summer traineeships:
no
Insurance:
Accident insurance during working hours only and Liability insurance
Benefits:
none
Traineeship type:
Erasmus traineeship