Litcius/Paper detail

PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization

Wei Wang, Bing Wang, Peijun Zhao, Changhao Chen, Ronald Clark, Bo Yang, Andrew Markham, Niki Trigoni

2021IEEE Sensors Journal54 citationsDOIOpen Access PDF

Abstract

In this paper, we present a novel end-to-end learning-based LiDAR sensor relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input. Compared to visual sensor-based relocalization, LiDAR sensors can provide rich and robust geometric information about a scene. However, point clouds of LiDAR sensors are unordered and unstructured making it difficult to apply traditional deep learning regression models for this task. We address this issue by proposing a novel PointNet-style architecture with self-attention to efficiently estimate 6-DoF poses from 360° LiDAR sensor frames. Extensive experiments on recently released challenging Oxford Radar RobotCar dataset and real-world robot experiments demonstrate that the proposed method can achieve accurate relocalization performance.

Topics & Concepts

LidarPoint cloudComputer scienceArtificial intelligenceComputer visionDeep learningPoint (geometry)RobotTask (project management)Cloud computingRemote sensingGeographyEngineeringSystems engineeringMathematicsGeometryOperating systemRobotics and Sensor-Based Localization3D Shape Modeling and AnalysisHuman Pose and Action Recognition