An Efficient Method for No-Reference Video Quality Assessment
| Autor: | Raimondo Schettini, Luigi Celona, Mirko Agarla |
|---|---|
| Přispěvatelé: | Agarla, M, Celona, L, Schettini, R |
| Rok vydání: | 2021 |
| Předmět: |
lightweight method
Computer science media_common.quotation_subject convolutional neural network support vector regressor 02 engineering and technology lcsh:Computer applications to medicine. Medical informatics Video quality computer.software_genre Convolutional neural network Article lcsh:QA75.5-76.95 Sampling (signal processing) 0202 electrical engineering electronic engineering information engineering Radiology Nuclear Medicine and imaging Quality (business) no-reference video quality assessment lcsh:Photography Electrical and Electronic Engineering Subjective video quality media_common 020206 networking & telecommunications efficient method lcsh:TR1-1050 Computer Graphics and Computer-Aided Design In-the-wild video Support vector machine in-the-wild videos Quality Score Benchmark (computing) lcsh:R858-859.7 020201 artificial intelligence & image processing lcsh:Electronic computers. Computer science Computer Vision and Pattern Recognition Data mining computer |
| Zdroj: | Journal of Imaging, Vol 7, Iss 55, p 55 (2021) Journal of Imaging Volume 7 Issue 3 |
| ISSN: | 2313-433X |
| DOI: | 10.3390/jimaging7030055 |
| Popis: | Methods for No-Reference Video Quality Assessment (NR-VQA) of consumer-produced video content are largely investigated due to the spread of databases containing videos affected by natural distortions. In this work, we design an effective and efficient method for NR-VQA. The proposed method exploits a novel sampling module capable of selecting a predetermined number of frames from the whole video sequence on which to base the quality assessment. It encodes both the quality attributes and semantic content of video frames using two lightweight Convolutional Neural Networks (CNNs). Then, it estimates the quality score of the entire video using a Support Vector Regressor (SVR). We compare the proposed method against several relevant state-of-the-art methods using four benchmark databases containing user generated videos (CVD2014, KoNViD-1k, LIVE-Qualcomm, and LIVE-VQC). The results show that the proposed method at a substantially lower computational cost predicts subjective video quality in line with the state of the art methods on individual databases and generalizes better than existing methods in cross-database setup. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|