Leveraging the Edge and Cloud for V2X-Based Real-Time Object Detection in Autonomous Driving

TL;DR

This paper explores offloading object detection in autonomous driving to edge and cloud platforms, balancing detection accuracy and latency through compression and network strategies, enabling real-time performance.

Contribution

It introduces a comprehensive evaluation of offloading strategies, including compression techniques, for real-time perception in autonomous vehicles, which was not extensively studied before.

Findings

Compressed models can achieve real-time detection on cloud platforms.

Offloading with compression outperforms local detection in accuracy and latency.

Trade-offs between compression quality and detection performance are quantified.

Abstract

Environmental perception is a key element of autonomous driving because the information received from the perception module influences core driving decisions. An outstanding challenge in real-time perception for autonomous driving lies in finding the best trade-off between detection quality and latency. Major constraints on both computation and power have to be taken into account for real-time perception in autonomous vehicles. Larger object detection models tend to produce the best results, but are also slower at runtime. Since the most accurate detectors cannot run in real-time locally, we investigate the possibility of offloading computation to edge and cloud platforms, which are less resource-constrained. We create a synthetic dataset to train object detection models and evaluate different offloading strategies. Using real hardware and network simulations, we compare different trade-offs between prediction quality and end-to-end delay. Since sending raw frames over the network implies additional transmission delays, we also explore the use of JPEG and H.265 compression at varying qualities and measure their impact on prediction metrics. We show that models with adequate compression can be run in real-time on the cloud while outperforming local detection performance.