MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations

Mike Wong, Murali Ramanujam, Guha Balakrishnan, Ravi Netravali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Camera orientations (i.e., rotation and zoom) govern the content that a camera captures in a given scene, which in turn heavily influences the accuracy of live video analytics pipelines. However, existing analytics approaches leave this crucial adaptation knob untouched, instead opting to only alter the way that captured images from fixed orientations are encoded, streamed, and analyzed. We present MadEye, a camera-server system that automatically and continually adapts orientations to maximize accuracy for the workload and resource constraints at hand. To realize this using commodity pan-tilt-zoom (PTZ) cameras, MadEye embeds (1) a search algorithm that rapidly explores the massive space of orientations to identify a fruitful subset at each time, and (2) a novel knowledge distillation strategy to efficiently (with only camera resources) select the ones that maximize workload accuracy. Experiments on diverse workloads show that MadEye boosts accuracy by 2.9-25.7% for the same resource usage, or achieves the same accuracy with 2-3.7× lower resource costs.

Original languageEnglish (US)
Title of host publicationProceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024
PublisherUSENIX Association
Pages549-568
Number of pages20
ISBN (Electronic)9781939133397
StatePublished - 2024
Event21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024 - Santa Clara, United States
Duration: Apr 16 2024Apr 18 2024

Publication series

NameProceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024

Conference

Conference21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024
Country/TerritoryUnited States
CitySanta Clara
Period4/16/244/18/24

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations'. Together they form a unique fingerprint.

Cite this