Semantics-Guided Moving Object Segmentation with 3D LiDAR

TL;DR

This paper introduces a semantics-guided CNN that leverages sequential LiDAR range images and cross-scan semantic features to improve moving object segmentation accuracy, benefiting autonomous navigation tasks.

Contribution

It proposes a novel network architecture combining semantic segmentation and cross-scan association to enhance moving object segmentation from LiDAR data.

Findings

Achieves improved segmentation accuracy on SemanticKITTI MOS dataset.

Effectively exploits cross-scan semantic features for reliable MOS.

Demonstrates fast and accurate moving object detection.

Abstract

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.