Ricerca CERCA

Area Ingegneria

Unsupervised/Semi-Supervised Video classification

azienda Tesi esterna in azienda    


Riferimenti esterni Enrico Busto - ADDFOR

Gruppi di ricerca 15-Modellazione, simulazione e controllo di velivoli

Descrizione When there are hundreds or thousands of cameras producing video streams all day long it is very useful to have an algorithm that analyzes such streams instead of a human. Today such technology exists and is called convolutional neural networks for video classification [1]. The downside of such neural networks is that we have a fixed number of cases on which the net is trained which is ok for benchmarking our algorithm on a specific dataset but not for real life applications such as security cameras where we donít know specifically for which scene the algorithm should give an alert signal. So we need to produce an abstract representation of the video scene (embedding)[2] and to classify it in an unsupervised way [3].

[1] https://arxiv.org/pdf/1705.07750.pdf
[2] https://arxiv.org/pdf/1810.06951.pdf
[3] https://arxiv.org/pdf/1810.06951.pdf
[4] http://charuaggarwal.net/ICDE16_research_420.pdf

Planned Activities
The first part of this thesis will be research state of the art algorithms for video
classification and clustering.
The second part of the project will be devoted to the implementation of such
algorithms and testing on real datasets.
Addfor will provide data sets of real-time image sequences obtained in different
weather conditions and in non-optimal conditions (flickering and jittering) that
represent the common difficulties found on real computer vision tasks.
The final purpose of the thesis will be to define an algorithm which starting
from a video sequence will classify similar sequences as belonging to the same
cluster in order to give an alert signal when there is an anomalous [4] sequence
belonging to an unknown cluster.

Vedi anche  thesis 17e- unsupervised_semi-supervised video classification.pdf 

Conoscenze richieste Students that are about to get their master degree in: aerospace engineering, Mathematics, Physics of Complex Systems.
Skills: Python, advanced math, abstraction skills, exp. w. at least one among
TensorFlow / PyTorch.

Scadenza validita proposta 04/10/2020      PROPONI LA TUA CANDIDATURA

© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY