点云配准python代码_自动驾驶中激光雷达点云的论文

01

激光雷达点云的平面提取与路面分割

Fast Segmentation of 3D Point Clouds: A Paradigm on LiDAR Data for Autonomous Vehicle Applications 

code：https://github.com/VincentCheungM/Run_based_segmentation

Time-series LIDAR Data Superimposition for Autonomous Driving 

Fast segmentation of 3D point clouds for ground vehicles 

An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells

Segmentation of Dynamic Objects from Laser Data

A Fast Ground Segmentation Method for 3D Point Cloud 

Ground Estimation and Point Cloud Segmentation using SpatioTemporal Conditional Random Field

Real-Time Road Segmentation Using LiDAR Data Processing on an FPGA 

Efficient Online Segmentation for Sparse 3D Laser Scans 

该文章可查看公众号文章 实时稀疏点云分割

CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data 

A Comparative Study of Segmentation and Classification Methods for 3D Point Clouds

Fast Multi-pass 3D Point Segmentation Based on a Structured Mesh Graph for Ground Vehicles 

Circular Convolutional Neural Networks for Panoramic Images and Laser Data

Python bindings for Point Cloud Library 

code：https://github.com/strawlab/python-pcl

02

点云配准与定位

Point Clouds Registration with Probabilistic Data Association 

code：https://github.com/ethz-asl/robust_point_cloud_registration

Robust LIDAR Localization using Multiresolution Gaussian Mixture Maps for Autonomous Driving

Automatic Merging of Lidar Point-Clouds Using Data from Low-Cost GPS/IMU Systems 

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

Incremental Segment-Based Localization in 3D Point Clouds 

03

点云特征提取

Fast Feature Detection and Stochastic Parameter Estimation of Road Shape using Multiple LIDAR 

Finding Planes in LiDAR Point Clouds for Real-Time Registration 

Online detection of planes in 2D lidar

A Fast RANSAC–Based Registration Algorithm for Accurate Localization in Unknown Environments using LIDAR Measurements 

Hierarchical Plane Extraction (HPE): An Efficient Method For Extraction Of Planes From Large Pointcloud Datasets 

A Fast and Accurate Plane Detection Algorithm for Large Noisy Point Clouds Using Filtered Normals and Voxel Growing 

04

点云物体检测与跟踪

Learning a Real-Time 3D Point Cloud Obstacle Discriminator via Bootstrapping 

Terrain-Adaptive Obstacle Detection

3D Object Detection from Roadside Data Using Laser Scanners 

3D Multiobject Tracking for Autonomous Driving : Masters thesis A S Abdul Rahman

Motion-based Detection and Tracking in 3D LiDAR Scans 

Lidar-histogram for fast road and obstacle detection

End-to-end Learning of Multi-sensor 3D Tracking by Detection 

Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection

Deep tracking in the wild: End-to-end tracking using recurrent neural networks

Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection 

Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges 

Low resolution lidar-based multi-object tracking for driving applications 

05

点云分类与监督学习

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation 

website:http://stanford.edu/~rqi/pointnet2/

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

Improving LiDAR Point Cloud Classification using Intensities and Multiple Echoes 

DepthCN: Vehicle Detection Using 3D-LIDAR and ConvNet

3D Object Localisation with Convolutional Neural Networks 

SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud 

PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud 

Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks 

ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGA 

06

点云与各类地图

Hierarchies of Octrees for Efficient 3D Mapping Adaptive Resolution Grid Mapping using Nd-Tree

LIDAR-Data Accumulation Strategy To Generate High Definition Maps For Autonomous Vehicles 

Long-term 3D map maintenance in dynamic environments

Detection and Tracking of Moving Objects Using 2.5D Motion Grids 

3D Lidar-based Static and Moving Obstacle Detection in Driving Environments: an approach based on voxels and multi-region ground planes 

Spatio–Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments 

Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labeling 

Fast 3-D Urban Object Detection on Streaming Point Clouds

Mobile Laser Scanned Point-Clouds for Road Object Detection and Extraction: A Review 

Efficient Continuous-time SLAM for 3D Lidar-based Online Mapping 

DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map 

Recurrent-OctoMap: Learning State-based Map Refinement for Long-Term Semantic Mapping with 3D-Lidar Data 

HDNET: Exploiting HD Maps for 3D Object Detection

07

点云端到端学习

Monocular Fisheye Camera Depth Estimation Using Semi-supervised Sparse Velodyne Data 

Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net 

08

点云其他类相关论文

DBSCAN algorithm：A density-based algorithm for discovering clusters in large spatial databases with noise

Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection

STD: Sparse-to-Dense 3D Object Detector for Point Cloud

Fast semantic segmentation of 3d point clounds with strongly varying density 

The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

09

点云数据集与模拟器

nuScenes : public large-scale dataset for autonomous driving 

https://www.nuscenes.org/overview

Paris-Lille-3D: A Point Cloud Dataset for Urban Scene Segmentation and Classification 

http://npm3d.fr/paris-lille-3d

Ford Campus Vision and Lidar Data Set 

http://robots.engin.umich.edu/SoftwareData/Ford

Oxford RobotCar dataset 1 Year, 1000km: The Oxford RobotCar Dataset 

https://robotcar-dataset.robots.ox.ac.uk/

Udacity based simulator 

https://github.com/EvanWY/USelfDrivingSimulator

Tutorial on Gazebo to simulate raycasting from Velodyne lidar

http://gazebosim.org/tutorials?tut=guided_i1

Udacity Driving Dataset 

https://github.com/udacity/self-driving-car/tree/master/datasets

Virtual KITTI 

http://www.europe.naverlabs.com/Research/Computer-Vision/Proxy-Virtual-Worlds

KAIST Complex Urban Data Set Dataset 

http://irap.kaist.ac.kr/dataset/download_1.html

Semantic KITTI 

http://semantic-kitti.org/

希望有跑过以上开源代码的小伙伴能够积极评论与公众号取得联系，分享demo视频，并分享您的想法与更多志同道合的小伙伴一起交流和学习。

平台活动指南

公众号将会推送基于PCL库的点云处理，SLAM，三维视觉，高精地图相关的文章。公众号致力于理解三维世界相关内容的干货分享。不仅组织技术交流群，并且组建github组群，可自由分享。交流提问。

历史文章查看点云学习历史文章大汇总

1.一起学SLAM：第三期：一起来学SLAM

2.招募乐于分享的你：点云PCL运营招募啦

3.招募计算机视觉，SLAM，三维视觉，点云等相关领域博客博主，或者公司开设专栏,只要与平台主题相关，乐于分享，都可以与本平台合作经营，发布原创文章。并且可以加入微信，QQ交流群，认识更多志同道合的一起同行分享。

4，相机测评活动：图漾双目，小觅相机，奥比中光三款相机测评活动正在进行中,,,,,,

有意者均可联系邮箱：dianyunpcl@163.com，或者评论文章留言。

关于我们

 目前微信交流群不断壮大，由于人数太多，目前有两个群，为了鼓励大家分享，我们希望大家能在学习的同时积极分享，将您的问题或者小总结和分享投稿发到群主邮箱dianyunpcl@163.com。

     以上内容如有错误或者需要补充的，请留言！同时欢迎大家关注微信公众号,积极分享投稿，或者加入3D视觉微信群或QQ交流群。

  原创不易，转载请联系群主，注明出处

排版：particle

供稿：群主

点一下“在看”你会更好看耶