No More Potentially Dynamic Objects: Static Point Cloud Map Generation based on 3D Object Detection and Ground Projection

TL;DR

This paper introduces a method to generate static point cloud maps by detecting and removing dynamic objects using 3D object detection and ground projection, improving map quality and localization accuracy.

Contribution

The paper presents a novel pipeline that effectively filters out dynamic objects from LiDAR point clouds to produce static maps, enhancing localization performance.

Findings

Successfully removes dynamic objects from point clouds

Creates accurate static maps for better localization

Validated on KITTI and proprietary datasets

Abstract

In this paper, we propose an algorithm to generate a static point cloud map based on LiDAR point cloud data. Our proposed pipeline detects dynamic objects using 3D object detectors and projects points of dynamic objects onto the ground. Typically, point cloud data acquired in real-time serves as a snapshot of the surrounding areas containing both static objects and dynamic objects. The static objects include buildings and trees, otherwise, the dynamic objects contain objects such as parked cars that change their position over time. Removing dynamic objects from the point cloud map is crucial as they can degrade the quality and localization accuracy of the map. To address this issue, in this paper, we propose an algorithm that creates a map only consisting of static objects. We apply a 3D object detection algorithm to the point cloud data which are obtained from LiDAR to implement our pipeline. We then stack the points to create the map after performing ground segmentation and projection. As a result, not only we can eliminate currently dynamic objects at the time of map generation but also potentially dynamic objects such as parked vehicles. We validate the performance of our method using two kinds of datasets collected on real roads: KITTI and our dataset. The result demonstrates the capability of our proposal to create an accurate static map excluding dynamic objects from input point clouds. Also, we verified the improved performance of localization using a generated map based on our method.