The accuracy of video quality metrics (VQMs) is an important issue for several applications. In this work, first we observe that the accuracy of several video quality metrics (VQMs) is strongly related to the spatial complexity index (SI) of the source. In particular, our investigation suggests that the VQMs are more likely to inaccurately predict the subjective quality of the processed video sequences derived from sources characterized by low SI. To address such a situation, we propose a machine learning based improvement for each of the VQMs considered in this work and a video quality metric fusion index (VQMFI) that jointly exploits all the VQMs considered in the study as well as spatiotemporal features to produce a better estimation of the subjective quality. Computational results demonstrate the superiority of our proposals on several datasets.

Full Reference Video Quality Measures Improvement using Neural Networks / FOTIO TIOTSOP, Lohic; Servetti, Antonio; Masala, Enrico. - STAMPA. - (2020), pp. 2737-2741. (Intervento presentato al convegno IEEE 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP) tenutosi a Barcelona, Spain nel May 2020) [10.1109/ICASSP40776.2020.9053739].

Full Reference Video Quality Measures Improvement using Neural Networks

Lohic Fotio Tiotsop;Antonio Servetti;Enrico Masala
2020

Abstract

The accuracy of video quality metrics (VQMs) is an important issue for several applications. In this work, first we observe that the accuracy of several video quality metrics (VQMs) is strongly related to the spatial complexity index (SI) of the source. In particular, our investigation suggests that the VQMs are more likely to inaccurately predict the subjective quality of the processed video sequences derived from sources characterized by low SI. To address such a situation, we propose a machine learning based improvement for each of the VQMs considered in this work and a video quality metric fusion index (VQMFI) that jointly exploits all the VQMs considered in the study as well as spatiotemporal features to produce a better estimation of the subjective quality. Computational results demonstrate the superiority of our proposals on several datasets.
2020
9781509066315
File in questo prodotto:
File Dimensione Formato  
FINAL_IEEExplore_ICASSP2020__09053739.pdf

non disponibili

Descrizione: Versione editoriale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 715.54 kB
Formato Adobe PDF
715.54 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
ICASSP2020_versione_autori.pdf

accesso aperto

Descrizione: Versione autori, final draft post-refereeing
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 685.28 kB
Formato Adobe PDF
685.28 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2840345