Semantics-Guided Moving Object Segmentation with 3D LiDAR

05/06/2022
by   Shuo Gu, et al.
0

Moving object segmentation (MOS) is a task to distinguish moving objects, e.g., moving vehicles and pedestrians, from the surrounding static environment. The segmentation accuracy of MOS can have an influence on odometry, map construction, and planning tasks. In this paper, we propose a semantics-guided convolutional neural network for moving object segmentation. The network takes sequential LiDAR range images as inputs. Instead of segmenting the moving objects directly, the network conducts single-scan-based semantic segmentation and multiple-scan-based moving object segmentation in turn. The semantic segmentation module provides semantic priors for the MOS module, where we propose an adjacent scan association (ASA) module to convert the semantic features of adjacent scans into the same coordinate system to fully exploit the cross-scan semantic features. Finally, by analyzing the difference between the transformed features, reliable MOS result can be obtained quickly. Experimental results on the SemanticKITTI MOS dataset proves the effectiveness of our work.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 7

research
05/24/2021

SuMa++: Efficient LiDAR-based Semantic SLAM

Reliable and accurate localization and mapping are key components of mos...
research
03/07/2023

InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data

Identifying moving objects is a crucial capability for autonomous naviga...
research
05/10/2021

PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data

Semantic understanding of the surrounding environment is essential for a...
research
07/17/2023

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

Mobile robots that navigate in unknown environments need to be constantl...
research
06/08/2022

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

A key challenge for autonomous vehicles is to navigate in unseen dynamic...
research
03/29/2022

Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice

Semantic segmentation is a core ability required by autonomous agents, a...
research
05/12/2023

MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features

Identifying moving objects is an essential capability for autonomous sys...

Please sign up or login with your details

Forgot password? Click here to reset