Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds

TL;DR

This paper investigates the challenges of 3D object detection in compressed point clouds for teleoperated driving, analyzing how data compression impacts detection accuracy, latency, and network performance in V2X communications.

Contribution

It introduces an expanded synthetic dataset with ground-truth annotations and evaluates the effects of various compression algorithms on detection performance and network metrics for teleoperated driving.

Findings

Compression affects detection accuracy and inference time.

Certain algorithms optimize data rate and latency.

Detection performance varies with compression methods.

Abstract

In recent years, the development of interconnected devices has expanded in many fields, from infotainment to education and industrial applications. This trend has been accelerated by the increased number of sensors and accessibility to powerful hardware and software. One area that significantly benefits from these advancements is Teleoperated Driving (TD). In this scenario, a controller drives safely a vehicle from remote leveraging sensors data generated onboard the vehicle, and exchanged via Vehicle-to-Everything (V2X) communications. In this work, we tackle the problem of detecting the presence of cars and pedestrians from point cloud data to enable safe TD operations. More specifically, we exploit the SELMA dataset, a multimodal, open-source, synthetic dataset for autonomous driving, that we expanded by including the ground-truth bounding boxes of 3D objects to support object detection. We analyze the performance of state-of-the-art compression algorithms and object detectors under several metrics, including compression efficiency, (de)compression and inference time, and detection accuracy. Moreover, we measure the impact of compression and detection on the V2X network in terms of data rate and latency with respect to 3GPP requirements for TD applications.