3차원 쉐어렛 변환과 심층 잔류 신경망을 이용한 무참조 스포츠 비디오 화질 평가 = No-Reference Sports Video-Quality Assessment Using 3D Shearlet Transform and Deep Residual Neural Network

다국어 초록 (Multilingual Abstract)

In this paper, we propose a method for no-reference quality assessment of sports videos using 3D shearlet transform and deep residual neural networks. In the proposed method, 3D shearlet transform-based spatiotemporal features are extracted from the overlapped video blocks and applied to logistic regression concatenated with a deep residual neural network based on a conditional video block-wise constraint to learn the spatiotemporal correlation and predict the quality score. Our evaluation reveals that the proposed method predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

참고문헌 (Reference)

1 장원두, "웨이블릿 계수와 Dynamic Positional Warping을 통한 EOG기반의 사용자 독립적 시선인식" 한국멀티미디어학회 21 (21): 1119-1130, 2018

2 P. V. Vu, "ViS3 : An Algorithm for Video Quality Assessment via Analysis of Spatial and Spatiotemporal Slices" 23 (23): 013016-, 2014

3 T. R. Goodall, "Tasking on Natural Statistics of Infrared Images" 25 (25): 65-79, 2016

4 S. W. Fu, "Quality-Net : An End-to-end Nonintrusive Speech Quality Assessment Model Based on BLSTM" 1873-1877, 2018

5 K. Zhu, "Noreference Video Quality Assessment Based on Artifact Measurement and Statistical Analysis" 25 (25): 533-546, 2014

6 Y. Li, "No-reference Video Quality Assessment with 3D Shearlet Transform and Convolutional Neural Networks" 26 (26): 1044-1057, 2016

7 J. Søgaard, "No-reference Video Quality Assessment Using Codec Analysis" 25 (25): 1637-1650, 2015

8 K. Gu, "Hybrid No-reference Quality Metric for Singly and Multiply Distorted Images" 60 (60): 555-567, 2014

9 K. He, "Deep Residual Learning for Image Recognition" 770-778, 2016

10 Wang, "COME for No-reference Video Quality Assessment" 232-237, 2018