Towards Live Video Analytics with On-Drone Deeper-yet-Compatible Compression

TL;DR

This paper introduces DCC, a novel adaptive video compression technique for drones that significantly reduces data transmission while maintaining analytical accuracy, enabling real-time edge-assisted video analytics.

Contribution

DCC is the first to adaptively compress drone video streams based on content relevance, improving transmission efficiency without sacrificing detection accuracy.

Findings

Reduced transmission volume by 9.5 times compared to baseline

Outperformed state-of-the-art compression methods by 19-683%

Maintained comparable vehicle detection accuracy

Abstract

In this work, we present DCC(Deeper-yet-Compatible Compression), one enabling technique for real-time drone-sourced edge-assisted video analytics built on top of the existing codec. DCC tackles an important technical problem to compress streamed video from the drone to the edge without scarifying accuracy and timeliness of video analytical tasks performed at the edge. DCC is inspired by the fact that not every bit in streamed video is equally valuable to video analytics, which opens new compression room over the conventional analytics-oblivious video codec technology. We exploit drone-specific context and intermediate hints from object detection to pursue adaptive fidelity needed to retain analytical quality. We have prototyped DCC in one showcase application of vehicle detection and validated its efficiency in representative scenarios. DCC has reduced transmission volume by 9.5-fold over the baseline approach and 19-683% over the state-of-the-art with comparable detection accuracy.