Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 29, Issue -, Pages 5612-5624Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2020.2984879
Keywords
Spatiotemporal phenomena; Quality assessment; Optical distortion; Feature extraction; Video recording; Distortion; Streaming media; Natural scene statistics of videos; spatiotemporal Gabor filters; human visual system (HVS); SVR and 3D-MSCN
Funding
- Visvesvaraya Ph.D. Scheme of the Media Asia Lab, Ministry of Electronics and Information Technology, Government of India
- Qualcomm Technologies through the Qualcomm Innovation Fellowship, India
Ask authors/readers for more resources
Robust spatiotemporal representations of natural videos have several applications including quality assessment, action recognition, object tracking etc. In this paper, we propose a video representation that is based on a parameterized statistical model for the spatiotemporal statistics of mean subtracted and contrast normalized (MSCN) coefficients of natural videos. Specifically, we propose an asymmetric generalized Gaussian distribution (AGGD) to model the statistics of MSCN coefficients of natural videos and their spatiotemporal Gabor bandpass filtered outputs. We then demonstrate that the AGGD model parameters serve as good representative features for distortion discrimination. Based on this observation, we propose a supervised learning approach using support vector regression (SVR) to address the no-reference video quality assessment (NRVQA) problem. The performance of the proposed algorithm is evaluated on publicly available video quality assessment (VQA) datasets with both traditional and in-capture/authentic distortions. We show that the proposed algorithm delivers competitive performance on traditional (synthetic) distortions and acceptable performance on authentic distortions. The code for our algorithm will be released at https://www.iith.ac.in/lfovia/downloads.html.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available