GithubHelp home page GithubHelp logo

afeichina / extended_lidar_camera_calib Goto Github PK

View Code? Open in Web Editor NEW
85.0 2.0 21.0 16.01 MB

This repo is an extended version of livox_camera_calib(hku-mars/livox_camera_calib), which is suitable for spinning LiDAR。

CMake 1.80% C++ 98.20%
lidar camera calibration spinning

extended_lidar_camera_calib's Introduction

extended_lidar_camera_calib

This work is an extended version of livox_camera_calib, which is suitable for spinning LiDAR。

In order to apply this algorithm on spinning LIDAR(e.g:VLP16), I add the preprocess process(FLOAM) to make the point cloud of the spinning LiDAR denser.

Data Prepare

When you calibrate the spinning lidar and camera, record the data by holding the device(lidar and camera) stationary for a period of time and then slowly and repeatedly move the entire device in this direction to accumulate the point cloud.

Dependency

ceres-slover == 1.14.0
pcl==1.8.0

Build

cd ~/catkin_ws/src
git clone https://github.com/AFEICHINA/extended_lidar_camera_calib.git
cd ..
catkin_make
source ~/catkin_ws/devel/setup.bash

Run

step1: doing slam to accumulate dense pointcloud.

roslaunch floam floam_XXX.launch

step2: lidar camera calibration

roslaunch livox_camera_calib calib_XXX.launch

My Result

In my test, I get better results in indoor enviroment.

LIDAR : Robosense RS-Bpearl
Camera: MindVision MV-SUA133GC-T

slam result:

map result:

calib result:

Acknowledgements

Thanks for livox_camera_calib and FLOAM.

extended_lidar_camera_calib's People

Contributors

afeichina avatar shliang0603 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

extended_lidar_camera_calib's Issues

Problem in running code

Hello,

I collected a rosbag with my camera and lidar. I move both sensors with constant relative position to each other for several second to collect data. Then I save rosbag and close sensors.

  1. I call floam with this line: roslaunch floam floam_velodyne1.launch
    Before calling it, I modified rosbag path in the launch file.

When Rviz pop up, it show no point on the rviz. However, when I open save map with pcl viewer, it seems ok and proper.

  1. For calibration I call roslaunch livox_camera_calib calib_indoor_velodyne16.launch

Before, calling it, I changed my rosbag file path and camera and lidar topic names in these two config files: '/config/camera_velodyne16.yaml' '/config/config_indoor_velodyne16.yaml '
I recieve an Error: process has died.

How can I solve the problem about "LZ4_streamDecode_t"?

Hello! When I run the command of "catkin_make", there is a problem about "LZ4_streamDecode_t". The detailed information is followed.
error: conflicting declaration ‘typedef struct LZ4_streamDecode_t LZ4_streamDecode_t’
edef struct { unsigned long long table[LZ4_STREAMDECODESIZE_U64]; } LZ4_streamDecode_t;
^~~~~~~~~~~~~~~~~~

关于数据准备问题

你好,我想请问一下,准备数据的时候是各个角度和方向的移动都要有吗?比如传感器在小车上可能只有x,y和yaw方向的移动,这样可以吗?再就是有无实验数据提供一下呢?谢谢!

Bpearl support

Hi!Thanks for your great work!
I'm using RS-Bpearl as you do.But here is the problem:I launch the floam_rsbpearl32.launch and play my bag.But nothing happened,it seems like the algorithm doesn't get my data.Is anything needed to modify?
Your prompt reply will be appreciate!

Data collecting

Hi,
Can you explain how to collect data?

I should collect data for both camera and Lidar when moving?
If I need to just take a picture, where to put it? and how can I do it?
Which direction should I move?

Thank you,

which launch file should i roslaunch?

i roslanch floam_rslidar32.launch,but i can't found corresponding launch file. i only found calib_indoor_rsbpearl32.launch. is it same that roslaunch this file?

我在进行第二步是出现问题, process has died

我已经阅读了所有的issue,但是没找到我的问题所在。我的雷达是速腾32线,在录制好相机/Daheng_image和雷达/velodyne_points的rosbag之后,修改floam_rslidar32.launch,成功运行了第一步,但是在显示过程中/map的点云无法显示,得到了一个map_.pcd;
我看issue中有人遇到了同样的问题,但是好像得到的map_.pcd是正确的,我也就没在意。在修改了两个yaml文件后,我运行calib_indoor_velodyne16.launch(也已经修改了bag和map_.pcd的位置)但是直接报错了

速腾32线

你好,我使用速腾32线激光雷达,相机为USB免驱,使用rosbag录制了/points_raw和/usb_cam/image_raw两个主题的包,
修改了floam_rsbpearl32.launch和laserProcessingNode.cpp文件,如图所示
1
:
2
执行:roslaunch floam floam_rsbpearl32.launch,如图所示:
3
请问我错过了什么?谢谢!期待你的回复!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.