2014 IEEE International Conference on Image Processing (ICIP)

Optimizing feature pooling and prediction models of VQA algorithms

K. Zhu, M. Barkowsky, M. Shen, P. Callet, D. Saupe

Material

Abstract

In this paper, we propose a strategy to optimize feature pooling and prediction models of video quality assessment (VQA) algorithms with a much smaller number of parameters than methods based on machine learning, such as neural networks. Based on optimization, the proposed mapping strategy is composed of a global linear model for pooling extracted features, a simple linear model for local alignment in which local factors depend on source videos, and a non-linear model for quality calibration. Also, a reduced-reference VQA algorithm is proposed to predict the local factors from the source video. In the IRCCyN/IVC video database of content influence and the LIVE mobile video database, the performance of VQA algorithms is improved significantly by local alignment. The proposed mapping strategy with prediction of local factors outperforms one no-reference VQA metric and is comparable to one full-reference VQA metric. Thus predicting the local factors in local alignment based on video content will be a promising new approach for VQA.

BibTeX

@inproceedings{Zhu2014Optimizingfeaturepooling,
  author    = {K. Zhu, M. Barkowsky, M. Shen, P. Callet, D. Saupe},
  booktitle = {2014 IEEE International Conference on Image Processing (ICIP)},
  doi       = {10.1109/ICIP.2014.7025108},
  issn      = {1522-4880},
  keywords  = {feature extraction;learning (artificial intelligence);optimisation;video signal processing;IRCCyN-IVC video database;LIVE mobile video database;content influence;feature pooling;full-reference VQA metric;global linear model;local alignment;local factors;machine learning;neural networks;no-reference VQA metric;prediction models;quality calibration;reduced-reference VQA algorithm;source videos;video content;video quality assessment algorithms;Databases;Distortion measurement;Entropy;Feature extraction;Prediction algorithms;Quality assessment;Video recording;Video quality assessment;feature pooling;local alignment;non-linear mapping;reduce reference},
  month     = {oct},
  pages     = {541--545},
  title     = {Optimizing feature pooling and prediction models of VQA algorithms},
  url       = {http://graphics.uni-konstanz.de/publikationen/Zhu2014Optimizingfeaturepooling},
  year      = {2014}
}