AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systems

by   Sibendu Paul, et al.

Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine - they can be distorted due to lighting issues, sensor noise, compression etc. Such distortions not only deteriorate visual quality, they impact the accuracy of deep learning applications that process such video streams. In this work, we introduce AQuA, to protect application accuracy against such distorted frames by scoring the level of distortion in the frames. It takes into account the analytical quality of frames, not the visual quality, by learning a novel metric, classifier opinion score, and uses a lightweight, CNN-based, object-independent feature extractor. AQuA accurately scores distortion levels of frames and generalizes to multiple different deep learning applications. When used for filtering poor quality frames at edge, it reduces high-confidence errors for analytics applications by 17 filtering, and due to its low overhead (14ms), AQuA can also reduce computation time and average bandwidth usage by 25


page 2

page 3

page 4


Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics

Video analytics are often performed as cloud services in edge settings, ...

AccDecoder: Accelerated Decoding for Neural-enhanced Video Analytics

The quality of the video stream is key to neural network-based video ana...

Why is the video analytics accuracy fluctuating, and what can we do about it?

It is a common practice to think of a video as a sequence of images (fra...

Scaling Video Analytics on Constrained Edge Nodes

As video camera deployments continue to grow, the need to process large ...

Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications

Images and video frames captured by cameras placed throughout smart citi...

End-Edge Coordinated Joint Encoding and Neural Enhancement for Low-Light Video Analytics

In this paper, we investigate video analytics in low-light environments,...

Video Quality Enhancement Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients in MPEG I-frames

Recent works have successfully applied some types of Convolutional Neura...

Please sign up or login with your details

Forgot password? Click here to reset