Human Segmentation with Dynamic LiDAR Data

TL;DR

This paper introduces a spatio-temporal neural network for human segmentation in dynamic LiDAR point clouds, leveraging motion cues from sequences to improve accuracy over static methods.

Contribution

It presents a novel two-branch neural network architecture that jointly learns spatial segmentation and temporal velocity estimation for dynamic 3D data.

Findings

Temporal features improve segmentation accuracy.

The method achieves high accuracy on a generated dynamic point cloud dataset.

Joint learning of spatial and temporal features is effective.

Abstract

Consecutive LiDAR scans compose dynamic 3D sequences, which contain more abundant information than a single frame. Similar to the development history of image and video perception, dynamic 3D sequence perception starts to come into sight after inspiring research on static 3D data perception. This work proposes a spatio-temporal neural network for human segmentation with the dynamic LiDAR point clouds. It takes a sequence of depth images as input. It has a two-branch structure, i.e., the spatial segmentation branch and the temporal velocity estimation branch. The velocity estimation branch is designed to capture motion cues from the input sequence and then propagates them to the other branch. So that the segmentation branch segments humans according to both spatial and temporal features. These two branches are jointly learned on a generated dynamic point cloud dataset for human recognition. Our works fill in the blank of dynamic point cloud perception with the spherical representation of point cloud and achieves high accuracy. The experiments indicate that the introduction of temporal feature benefits the segmentation of dynamic point cloud.