3D-SeqMOS: A Novel Sequential 3D Moving Object Segmentation in Autonomous Driving

by   Qipeng Li, et al.
Wuhan University
Florida Atlantic University
The Ohio State University
NetEase, Inc

For the SLAM system in robotics and autonomous driving, the accuracy of front-end odometry and back-end loop-closure detection determine the whole intelligent system performance. But the LiDAR-SLAM could be disturbed by current scene moving objects, resulting in drift errors and even loop-closure failure. Thus, the ability to detect and segment moving objects is essential for high-precision positioning and building a consistent map. In this paper, we address the problem of moving object segmentation from 3D LiDAR scans to improve the odometry and loop-closure accuracy of SLAM. We propose a novel 3D Sequential Moving-Object-Segmentation (3D-SeqMOS) method that can accurately segment the scene into moving and static objects, such as moving and static cars. Different from the existing projected-image method, we process the raw 3D point cloud and build a 3D convolution neural network for MOS task. In addition, to make full use of the spatio-temporal information of point cloud, we propose a point cloud residual mechanism using the spatial features of current scan and the temporal features of previous residual scans. Besides, we build a complete SLAM framework to verify the effectiveness and accuracy of 3D-SeqMOS. Experiments on SemanticKITTI dataset show that our proposed 3D-SeqMOS method can effectively detect moving objects and improve the accuracy of LiDAR odometry and loop-closure detection. The test results show our 3D-SeqMOS outperforms the state-of-the-art method by 12.4 proposed method to the SemanticKITTI: Moving Object Segmentation competition and achieve the 2nd in the leaderboard, showing its effectiveness.


page 1

page 2

page 4

page 8

page 9

page 10

page 11

page 14


Optimized SC-F-LOAM: Optimized Fast LiDAR Odometry and Mapping Using Scan Context

LiDAR odometry can achieve accurate vehicle pose estimation for short dr...

Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation

Accurate moving object segmentation is an essential task for autonomous ...

CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure

Multi-beam LiDAR sensors are increasingly used in robotics, particularly...

IMLS-SLAM: scan-to-model matching based on 3D data

The Simultaneous Localization And Mapping (SLAM) problem has been well s...

Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation

Mobile robots that navigate in unknown environments need to be constantl...

Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions

A key challenge for autonomous vehicles is to navigate in unseen dynamic...

A fast, complete, point cloud based loop closure for LiDAR odometry and mapping

This paper presents a loop closure method to correct the long-term drift...

Please sign up or login with your details

Forgot password? Click here to reset