LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation

TL;DR

This paper introduces a real-time LiDAR motion segmentation method using Bird's Eye View data, achieving low latency and addressing class imbalance with a novel augmentation technique, crucial for autonomous driving tasks.

Contribution

It presents the first direct LiDAR BEV space motion segmentation architecture with a new data augmentation method for class imbalance.

Findings

Achieves 8 ms latency on Nvidia Jetson Xavier

Performs well on SemanticKITTI dataset

First to directly segment motion in LiDAR BEV space

Abstract

Moving object detection and segmentation is an essential task in the Autonomous Driving pipeline. Detecting and isolating static and moving components of a vehicle's surroundings are particularly crucial in path planning and localization tasks. This paper proposes a novel real-time architecture for motion segmentation of Light Detection and Ranging (LiDAR) data. We use three successive scans of LiDAR data in 2D Bird's Eye View (BEV) representation to perform pixel-wise classification as static or moving. Furthermore, we propose a novel data augmentation technique to reduce the significant class imbalance between static and moving objects. We achieve this by artificially synthesizing moving objects by cutting and pasting static vehicles. We demonstrate a low latency of 8 ms on a commonly used automotive embedded platform, namely Nvidia Jetson Xavier. To the best of our knowledge, this is the first work directly performing motion segmentation in LiDAR BEV space. We provide quantitative results on the challenging SemanticKITTI dataset, and qualitative results are provided in https://youtu.be/2aJ-cL8b0LI.