CAR-CNN: A Deep Residual Convolutional Neural Network for Compression Artifact Removal in Video Surveillance Systems

Miloud Aqqa, Shishir K. Shah

2020

Abstract

Video compression algorithms are pervasively applied at the camera level prior to video transmission due to bandwidth constraints, thereby reducing the quality of video available for video analytics. These artifacts may lead to decreased performance of some core applications in video surveillance systems such as object detection. To remove such distortions during video decoding, it is required to recover original video frames from distorted ones. To this end, we present a fully convolutional residual network for compression artifact removal (CAR-CNN) without prior knowledge on the noise distribution trained using a novel, differentiable loss function. To provide a baseline, we also trained our model by optimizing the Structural Similarity (SSIM) and Mean Squared Error (MSE). We test CAR-CNN on self-collected data, and we show that it can be applied as a pre-processing step for the object detection task in practical, non-idealized applications where quality distortions may be present.

Paper Citation

in Harvard Style

Aqqa M. and Shah S. (2020). CAR-CNN: A Deep Residual Convolutional Neural Network for Compression Artifact Removal in Video Surveillance Systems. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 569-575. DOI: 10.5220/0009184405690575

in Bibtex Style

@conference{visapp20,
author={Miloud Aqqa and Shishir K. Shah},
title={CAR-CNN: A Deep Residual Convolutional Neural Network for Compression Artifact Removal in Video Surveillance Systems},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={569-575},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009184405690575},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - CAR-CNN: A Deep Residual Convolutional Neural Network for Compression Artifact Removal in Video Surveillance Systems
SN - 978-989-758-402-2
AU - Aqqa M.
AU - Shah S.
PY - 2020
SP - 569
EP - 575
DO - 10.5220/0009184405690575
PB - SciTePress