Work

Logan: Loss-tolerant Live Video Analytics System

Year: 2024

Type: conference-paper

Abstract: Cloud-based live video analytics with tight latency bound is gaining importance to support emerging applications such as UAVs and augmented reality. However, existing systems often struggle to meet stringent latency constraints under fluctuating network conditions with packet losses and late-arriving packets. We propose a loss-tolerant live video analytics system called Logan, which effectively accepts packet losses while maintaining high accuracy by utilizing the inherent resilience in DNNs. We design i) Codec-aware Inpainting, which accurately recovers the frame error from packet losses ii) Fast-Forward Recovery that prevents the remaining un-recovered error from propagating over future frames indefinitely. Our results show a 3× improvement (33.2%→99.9%) in SLO satisfaction rate compared to the reliable transmission scheme with <1% accuracy drop under a 5% packet loss rate.

Source: Proceedings of the 28th Annual International Conference on Mobile Computing And Networking

DOI: 10.1145/3636534.3690695

Authors: Kichang Yang, Minkyung Jeong, Juheon Yi, Jingyu Lee, KyoungSoo Park, Youngki Lee

Institutions: Seoul National University, Nokia (United Kingdom)

Language: English

Topic: Image and Video Quality Assessment

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Research Foundation of Korea

Award: G2717443326