Authors:
Miloud Aqqa
and
Shishir K. Shah
Affiliation:
Quantitative Imaging Laboratory, Department of Computer Science, University of Houston, U.S.A.
Keyword(s):
Compression Artifacts, Video Quality Enhancement, Deep Learning, Visual Surveillance.
Abstract:
Video compression algorithms result in a degradation of frame quality due to their lossy approach to decrease the required bandwidth, thereby reducing the quality of video available for automatic video analysis. These artifacts may introduce undesired noise and complex structures, which remove textures and high-frequency details in video frames. Moreover, they may lead to decreased performance of some core applications in video surveillance systems such as object detectors. To remedy these quality distortions, it is required to restore high-quality videos from their low-quality counterparts without any changes to the existing compression pipelines through a complicated nonlinear 2D transformation. To this end, we devise a fully convolutional residual network for compression artifact removal (CAR-DCGAN) optimized in a patch-based generative adversarial approach (GAN). We show that our model is capable of restoring frames corrupted with complex and unknown distortions with more realist
ic details than existing methods. Furthermore, we show that CAR-DCGAN can be applied as a pre-processing step for the object detection task in video surveillance systems.
(More)