Giter VIP home page Giter VIP logo

lvi-sam-modified's Introduction

LVI-SAM-MODIFIED

This repository is a modified version of LVI-SAM.

Modification

  • Add function to get extrinsic parameters.The original code assumes there are no translation between the sensors and their parameters are written in the code. But now both our datasets and LVI-SAM official datasets are working well.
  • Add "lidar to imu extrinsics" in params_camera.yaml.
  • Using MahonyAHRS to caculate quaternion.So you don't need to prepare a 9-axis IMU.
  • Add lidar ring calculation method,whether your lidar provides "ring" information or not,it works.
  • Make some changes to the code for sensor alignment.
  • Fix depth association between camera and lidar (Default lidar orientation is x--->front,y--->left,z--->up).

Notes

  • Most of the changes are marked by "# modified".
  • If you are using VSCode and "#include xxx" prompt error,please ctrl+shit+p and enter C/C++ Edit Configurations(UI), add the following paths in Include path. /opt/ros/melodic/include/** /usr/include/**
  • Please make sure you have the same version of dependencies as LVI-SAM.If you have problems installing or importing multiple version of dependencies,you can refer to this blog.
  • You need to download and compile yaml-cpp.
  • You can use kalibr to get cam_to_imu,and calibration_camera_lidar to get cam_to_lidar,lidar_to_imu = cam_to_lidar.transpose * cam_to_imu
  • If you are looking up for Chinese annotation, please click this link LVI-SAM_detailed_comments.
  • You can see the difference between Fix depth association or not in the following pictures.Feature points are not easily go through wall, more reasonable.

Results 1.1.0

image image image

Results 2.0.0 fix depth association (Indoor)

image image image

Results 2.0.0 fix depth association (Outdoor)

image image image

Acknowledgement

lvi-sam-modified's People

Contributors

skyrim835 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.