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

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 low-cost sensors and accessibility to powerful hardware and software. One area that significantly benefits from these advancements is Teleoperated Driving. In this scenario, a remote controller (human or software) safely drives a vehicle using sensor 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, pedestrians, and cyclists from point cloud data generated by LiDAR sensors to enable safe Teleoperated Driving operations. Specifically, we use 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. Finally, we measure the impact of compression and detection on a simulated V2X network in terms of data rate and latency with respect to the 3GPP requirements of Teleoperated Driving applications. Our results show that G-PCC outperforms its competitors in terms of both compression efficiency and accuracy, and consumes fewer channel resources for data transmissions. On the contrary, the two most conservative quantization modes of Draco, combined with SECOND or PointPillars for object detection, offer superior speed in both compression and decompression with comparable accuracy. Finally, we show that the choice of the detector depends on the class of objects to detect, specifically pedestrians or cyclists.