VideoChef: Efficient Approximation for Streaming Video Processing Pipelines

Authors: 

Ran Xu, Jinkyu Koo, Rakesh Kumar, and Peter Bai, Purdue University; Subrata Mitra, Adobe Research; Sasa Misailovic, University of Illinois Urbana-Champaign; Saurabh Bagchi, Purdue University

Abstract: 

Many video streaming applications require low-latency processing on resource-constrained devices. To meet the latency and resource constraints, developers must often approximate filter computations. A key challenge to successfully tuning approximations is finding the optimal configuration suited for content characteristics, which are changing across and within the input videos. Searching through the entire search space for every frame in the video stream is infeasible, while tuning the pipeline off-line, on a set of training videos, yields suboptimal results.

We present VideoChef, a system for approximate optimization of video pipelines. VideoChef finds the optimal configurations of approximate filters at runtime, by leveraging the previously proposed concept canary inputs (using small inputs to tune the accuracy of the computations and transferring the approximate configurations to full inputs). VideoChef is the first system to show that canary inputs can be used for complex streaming applications. The two key innovations of VideoChef are (1) an accurate error mapping from the approximate processing with downsampled inputs to that with full inputs and (2) a directed search that balances the cost of each search step with the estimated reduction in the run time.

We evaluate our approach on 106 videos obtained from YouTube, on a set of 9 video processing pipelines (in total having 10 distinct filters). Our results show significant performance improvement over the baseline and the previous approach that uses canary inputs. We also perform a user study that shows that the videos produced by VideoChef are often acceptable to human subjects.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {216067,
author = {Ran Xu and Jinkyu Koo and Rakesh Kumar and Peter Bai and Subrata Mitra and Sasa Misailovic and Saurabh Bagchi},
title = {VideoChef: Efficient Approximation for Streaming Video Processing Pipelines},
booktitle = {2018 {USENIX} Annual Technical Conference ({USENIX} {ATC} 18)},
year = {2018},
isbn = {978-1-931971-44-7},
address = {Boston, MA},
pages = {43--56},
url = {https://www.usenix.org/conference/atc18/presentation/xu-ran},
publisher = {{USENIX} Association},
}