Hybrid Point Cloud Semantic Compression for Automotive Sensors: A Performance Evaluation

TL;DR

This paper presents a real-time LiDAR point cloud compression pipeline for autonomous vehicles, combining semantic data reduction with efficient 3D compression to enable reliable, bandwidth-efficient communication in autonomous driving systems.

Contribution

It introduces a novel pipeline that integrates semantic point selection with Draco compression, achieving real-time performance for automotive LiDAR data transmission.

Findings

Achieves real-time compression and transmission of LiDAR data.

Reduces data volume by selecting semantically important points.

Demonstrates effectiveness on Semantic KITTI dataset.

Abstract

In a fully autonomous driving framework, where vehicles operate without human intervention, information sharing plays a fundamental role. In this context, new network solutions have to be designed to handle the large volumes of data generated by the rich sensor suite of the cars in a reliable and efficient way. Among all the possible sensors, Light Detection and Ranging (LiDAR) can produce an accurate 3D point cloud representation of the surrounding environment, which in turn generates high data rates. For this reason, efficient point cloud compression is paramount to alleviate the burden of data transmission over bandwidth-constrained channels and to facilitate real-time communications. In this paper, we propose a pipeline to efficiently compress LiDAR observations in an automotive scenario. First, we leverage the capabilities of RangeNet++, a Deep Neural Network (DNN) used to semantically infer point labels, to reduce the channel load by selecting the most valuable environmental data to be disseminated. Second, we compress the selected points using Draco, a 3D compression algorithm which is able to obtain compression up to the quantization error. Our experiments, validated on the Semantic KITTI dataset, demonstrate that it is possible to compress and send the information at the frame rate of the LiDAR, thus achieving real-time performance.