A Novel Coding Architecture for LiDAR Point Cloud Sequence

In this letter, we propose a novel coding architecture for LiDAR point cloud sequences based on clustering and prediction neural networks. LiDAR point clouds are structured, which provides an opportunity to convert the 3D data to a 2D array, represented as range images. Thus, we cast the LiDAR point clouds compression as a range images coding problem. Inspired by the high efficiency video coding (HEVC) algorithm, we design a novel coding architecture for the point cloud sequence. The scans are divided into two categories: intra-frames and inter-frames. For intra-frames, a cluster-based intra-prediction technique is utilized to remove the spatial redundancy. For inter-frames, we design a prediction network model using convolutional LSTM cells, which is capable of predicting future inter-frames according to the encoded intra-frames. Thus, the temporal redundancy can be removed. Experiments on the KITTI data set show that the proposed method achieves an impressive compression ratio, with 4.10% at millimeter precision. Compared with octree, Google Draco and MPEG TMC13 methods, our scheme also yields better performance in compression ratio.

I. Introduction

Advances in autonomous driving technology have widened the use of 3D data acquisition techniques. LiDAR is almost indispensable for outdoor mobile robots, and plays a fundamental role in many autonomous driving applications such as localization, path planning [1], and obstacle detection [2], etc. The enormous volume of LiDAR point cloud data could be an important bottleneck for transmission and storage. Therefore, it is highly desirable to develop an efficient coding algorithm to satisfy the requirement of autonomous driving.