Code Monkey home page Code Monkey logo

fusion2018's Introduction

Matlab code used for the paper: M. Brossard, S. Bonnabel and A. Barrau, Invariant Kalman Filtering for Visual Inertial SLAM, 21st International Conference on Information Fusion (FUSION), pp. 2021--2028, 2018. [IEEE paper, HAL paper]

EUROC datasets are available here.

The Matlab code is written in a clear manner, and since not in computationnaly optimized or implementable manner.

Please contact the corresponding author at [email protected]

Citation

If you use this code in your research, please cite:

@INPROCEEDINGS{2018_Brossard_Invariant,
  author = {Martin Brossard, Silvère Bonnabel, and Axel Barrau},
  booktitle={2018 21st International Conference on Information Fusion (FUSION)},
  title={Invariant Kalman Filtering for Visual Inertial SLAM},
  year={2018},
  pages={2021-2028},
  doi={10.23919/ICIF.2018.8455807},
  month={July},}

fusion2018's People

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

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

fusion2018's Issues

GPS Data

Hi Dear Martin,
At first, I want to thank you for sharing the code u have written for ur paper. I want to add GPS data to your code, and so fuse IMU, GPS and visual data. but I dont exactly know, how can I do that. would you please help me, that how can I do that?

Thanks in advance.

h and ObserveLandmarks functions

Dear Martin,

Thank you very much for sharing the code and the helping out also for the first Issue.

In function h which is widely used in all the Update functions. the syntax is following:
y_bar = z(1:2,:)./z(3,:);
but I was having the division issue. So I solved it in the following way
A1= z(1,:);A2= z(2,:);
B= z(3,:);
y = [A1./B;A2./B];

the size of y should be 2x25?.......well it works but I wanted to ask if that is correct.

The second issue I am facing is in ObserveLandmarks function.

The algorithm stopped with the following:
Error using randsample (line 131)
K must be less than or equal 0 for sampling without
replacement.

Error in ObserveLandmarks (line 45)
idx = randsample(find(validityMain == 1),1);

Error in mainExperiment (line 205)
ObserveLandmarks(trackerMain,trackerBis,dirImage,IdxImage,...

It means my values are greater than zero or complex. Could you please guide me how to solve this issue.

Thank you very much in anticipation and keep up the great work!!

What EuroC dataset did you use?

Hello! Thank you very much for sharing your code with the robotic community!
Just want to check what EuroC dataset did you use? I check on the website, they only have V2_02_medium and V2_01_easy. I can not find out the V2_01_medium.

Thanks

ORB_SLAM_INT database and ObserveLandmarks functions

Dear Dr. Martin Brossard,
Hello!
I am very interested in this research work. However I have some confusion about the program for the ORB_SLAM_INT database.

It is excellent that you provide some introduction for the ORB_SLAM_INT database. For example, orb_slam.trackerMain, orb_slam.trackerBis, orb_slam.myTracks and what their role is.

The second issue I am facing is in ObserveLandmarks function.
Object tracking is to create a tracking object, initialize and track. Track the corner points directly in the current image frame using trackerMain.step(line 14).
I did not find the creation and initialization of the object. Whether the creation and initialization of the object was completed in orb_slam.trackerMain or orb_slam.trackerBis.

Thanks!

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.