Please use this identifier to cite or link to this item:
http://elea.unisa.it/xmlui/handle/10556/6450
Title: | Multiple object tracking and face-based video retrieval: applications of deep learning to video analysis |
Authors: | Ciaparrone, Gioele Antonelli, Valerio Tagliaferri, Roberto |
Keywords: | Deep learning;Multiple object tracking;Video retrieval |
Issue Date: | 11-Oct-2021 |
Publisher: | Universita degli studi di Salerno |
Abstract: | In recent years, deep learning (DL) has obtained numerous successes in analyzing complex data, such as images or audio. A particularly recent area of application is the analysis of videos. This thesis focuses on the application of deep learning algorithm to two video analysis tasks: Multiple Object Tracking (MOT) and Face-based Video Retrieval (FBVR). The first main part of the thesis presents an in-depth survey of the state of the art of DL-based MOT algorithms. This is the first comprehensive survey specifically on the use of DL for MOT, focusing on 2D frames extracted from single-camera videos. I identify the four main steps of a MOT algorithm and describe the various DL techniques used in the literature in each of those four steps. I also collect and compare results obtained by existing algorithms on the most common MOT datasets and I analyze the most successful techniques employed. Finally, I present a discussion about the open issues of current MOT algorithms and the possible solutions and future directions of research. The second part of the thesis focuses instead on the task of FBVR. I present a novel pipeline for the retrieval of unconstrained multi-shot videos using faces, specifically in the context of television-like videos. Since no existing dataset in the literature is appropriate for an end-to-end evaluation of the proposed pipeline, I build a large-scale video dataset by adapting the VoxCeleb2 dataset to the task of FBVR. I compare and evaluate numerous DL-based approaches for the various steps in pipeline, such as shot detection, face detection and face recognition, and I describe the advantages and disadvantages of each employed technique. ... [edited by Author] |
Description: | 2019 - 2020 |
URI: | http://elea.unisa.it:8080/xmlui/handle/10556/6450 http://dx.doi.org/10.14273/unisa-4522 |
Appears in Collections: | Big Data Management |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
tesi di dottorato G.Ciaparrone.pdf | tesi di dottorato | 4,05 MB | Adobe PDF | View/Open |
abstract in italiano G.Ciaparrone.pdf | abstract in italiano a cura dell'Autore | 248,7 kB | Adobe PDF | View/Open |
abstract in inglese G.Ciaparrone.pdf | abstract in inglese a cura dell'Autore | 238,12 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.