paper-with-me

Papers

BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge

2023-12-25 · Lin Sun, Weijun Wang, Tingting Yuan, Liang Mi, Haipeng Dai, Yunxin Liu, XiaoMing Fu

High-definition (HD) cameras for surveillance and road traffic have experienced tremendous growth, demanding intensive computation resources for real-time analytics. Recently, offloading frames from the front-end device to the back-end edge server has shown great promise. In multi-stream competitive environments, efficient bandwidth management and proper scheduling are crucial to ensure both high inference accuracy and high throughput. To achieve this goal, we propose BiSwift, a bi-level framework that scales the concurrent real-time video analytics by a novel adaptive hybrid codec integrated with multi-level pipelines, and a global bandwidth controller for multiple video streams. The lower-level front-back-end collaborative mechanism (called adaptive hybrid codec) locally optimizes the accuracy and accelerates end-to-end video analytics for a single stream. The upper-level scheduler aims to accuracy fairness among multiple streams via the global bandwidth controller. The evaluation of BiSwift shows that BiSwift is able to real-time object detection on 9 streams with an edge device only equipped with an NVIDIA RTX3070 (8G) GPU. BiSwift improves 10%$\sim$21% accuracy and presents 1.2$\sim$9$\times$ throughput compared with the state-of-the-art video analytics pipelines.

📄 PDF Abstract BibTeX arXiv:2312.15740

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessGPUManagementobject-detectionObject DetectionReal-Time Object DetectionScheduling

Similar Papers 제목 키워드 기반

CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams

2026-06-22 · Xu Liu, Guikun Chen, Zihao Yan, Kanzhi Wu 외 arxiv

Long, continuous video streams are an increasingly critical driver of multimedia intelligence. Existing efforts often handle long videos with a sample-encode-reason approach using large models. However, they overlook a c…

DeformStream: Deformation-based Adaptive Volumetric Video Streaming

2024-09-25 · Boyan Li, YongTing Chen, Dayou Zhang, Fangxin Wang

Volumetric video streaming offers immersive 3D experiences but faces significant challenges due to high bandwidth requirements and latency issues in transmitting detailed content in real time. Traditional methods like po…

Neural Rendering

Enhancement or Super-Resolution: Learning-based Adaptive Video Streaming with Client-Side Video Processing

2022-01-20 · Junyan Yang, Yang Jiang, Shuoyao Wang

The rapid development of multimedia and communication technology has resulted in an urgent need for high-quality video streaming. However, robust video streaming under fluctuating network conditions and heterogeneous cli…

Deep Reinforcement LearningSuper-ResolutionVideo CompressionVideo Enhancement

Interactive $360^{\circ}$ Video Streaming Using FoV-Adaptive Coding with Temporal Prediction

2024-03-17 · Yixiang Mao, Liyang Sun, Yong liu, Yao Wang

For $360^{\circ}$ video streaming, FoV-adaptive coding that allocates more bits for the predicted user's field of view (FoV) is an effective way to maximize the rendered video quality under the limited bandwidth. We deve…

Prediction

A Log-Rectilinear Transformation for Foveated 360-degree Video Streaming

2021-03-22 · David Li, Ruofei Du, Adharsh Babu, Camelia Brumar 외

With the rapidly increasing resolutions of 360° cameras, head-mounted displays, and live-streaming services, streaming high-resolution panoramic videos over limited-bandwidth networks is becoming a critical challenge. Fo…