Git Product home page Git Product logo

orb-slam2-based-ar-on-android's Introduction

ORB-SLAM2-based-AR-on-Android

Introduction

This is a Android Augmented Reality APP based on ORB-SLAM2 and OpenGL. The demo video can be found in the links below.

demo videos

ORB-SLAM2   ORB-SLAM2   ORB-SLAM2

Dependencies & Installation & Usage

To run this APP you need to copy the ./SLAM folder into your mobile phones, which contains the vocabulary file(ORBvoc.bin) and camera Calibration file(mi6.yaml). Then you need to change the 20th row in the ./app/src/main/cpp/native-lib.cpp to configure the correct path in your phone. You may also need to calibrate your phone's camera for better performance. More details of camera calibration can be found on google.

ORB_SLAM2::System SLAM("/storage/emulated/0/SLAM/VOC/ORBvoc.bin","/storage/emulated/0/SLAM/Calibration/mi6.yaml",ORB_SLAM2::System::MONOCULAR,false);

Due to the project is based on ORB-SLAM2, OpenCV4Androi is needed. Other third part dependence like g2o, Eigen, DBoW2 are all included in the project. As for the IDE, Android studio 2.5 or higher version is recommended.

To compile the project you may need to edit some configurations in the CMakeLists.txt file, which is in the path /app/CMakeLists.txt

Due to the diversity of Android system version, I am not sure weather my configuration can work well on other Android devices. So you may also need to change some configurarions in the AndroidManifest.xml to make sure that the app have the authority to use the camera and file system.

Framework & Results

The system is consisted of two parts, the ORB-SLAM2 part is ported from FireStoneYS' profile, which is used to get the camera's pose matrix. The other part is the OpenGL Rendering module, which use the pose matrix to render the 3D object(the earth in this project).

The ORB-SLAM2 system requires lots of computing resources, So this APP can only achieve nearly 10 fps on the MI6 with a snapdragon 835 CPU.

orb-slam2-based-ar-on-android's People

Contributors

muziyongshixin avatar

Watchers

 avatar  avatar

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.