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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bragato, Filippo, Neri, Michael, Testolina, Paolo, Giordani, Marco, Battisti, Federica
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908407277027328
author Bragato, Filippo
Neri, Michael
Testolina, Paolo
Giordani, Marco
Battisti, Federica
author_facet Bragato, Filippo
Neri, Michael
Testolina, Paolo
Giordani, Marco
Battisti, Federica
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11804
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds
Bragato, Filippo
Neri, Michael
Testolina, Paolo
Giordani, Marco
Battisti, Federica
Computer Vision and Pattern Recognition
Networking and Internet Architecture
Image and Video Processing
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.
title Teleoperated Driving: a New Challenge for 3D Object Detection in Compressed Point Clouds
topic Computer Vision and Pattern Recognition
Networking and Internet Architecture
Image and Video Processing
url https://arxiv.org/abs/2506.11804