Git Product home page Git Product logo

peterzs / slam-dunk-android Goto Github PK

View Code? Open in Web Editor NEW

This project forked from cvlab-unibo/slam-dunk-android

0.0 1.0 0.0 90.05 MB

Android implementation of "Fusion of inertial and visual measurements for rgb-d slam on mobile devices"

License: Apache License 2.0

Shell 0.14% Makefile 16.37% Java 7.68% CMake 1.94% C 8.53% C++ 44.10% Objective-C 0.35% Python 0.23% Visual Basic 0.01% DTrace 6.25% D 14.11% GLSL 0.01% TeX 0.25% Yacc 0.02% Lex 0.01%

slam-dunk-android's Introduction

Slam Dunk Android

Android implementation of "Fusion of inertial and visual measurements for rgb-d slam on mobile devices", if you use this code please refer to:

Brunetto, N., Salti, S., Fioraio, N., Cavallari, T., & Stefano, L. (2015). Fusion of inertial and visual measurements for rgb-d slam on mobile devices. In Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 1-9).


Instruction to set up the application

Android Device

Application tested on Samsung Galaxy Tab Pro 10.1 and Nexus 7 tablets.

REQUIREMENTS:

  • The device of choice has to support USB host mode in order to connect it to the RGB-D sensors and be able to recognize the components.
  • Rooting of the phone required in order to use the compatible RGB-D sensors.
  • Install the BusyBox application after the rooting procedure and specify the path "/system/xbin" for the binaries location. It is possible to use a different path. In this case it is only necessary to modify the value of the string "binariesPath" inside the class SuperUserProcess (package it.unibo.slam.runtime).
  • By now the native code is compatible with ARMv7 architecture with NEON instructions while the minimum Android version is 3.0.

OpenNI

Compiled binaries for Kinect (OpenNI 1.5):

  • SensorKinect/Platform/Android/libs/armeabi-v7a
  • OpenNI/Platform/Android/libs/armeabi-v7a

Compiled binaries for Xtion Pro Live (OpenNI 1.5):

  • Sensor-Unstable/Platform/Android/libs/armeabi-v7a
  • OpenNI-Unstable/Platform/Android/libs/armeabi-v7a

Compiled binaries for Structure (OpenNI 2):

  • OpenNI-2-Structure/Packaging/Final/OpenNI-android-2.2

The libraries (*.so files) found in the specified folders need to be placed on the tablet in the folder "/system/lib" (root required).At the moment only one possible OpenNI configuration at a time is supported. To change the supported sensor it is needed to place the required libraries in the "/system/lib" folder and change the file "jni/Android.mk" accordingly.

In case of the Structure sensor it is also needed to place in the "/system/lib" folder the files OpenNI.ini and PS1080.ini found in the same folder previously specified. For the Xtion sensor it is necessary to place the files OpenNI-Unstable/Data/SamplesConfig.xml, OpenNI-Unstable/Data/licenses.xml,OpenNI-Unstable/Data/modules.xml and Sensor-Unstable/Data/GlobalDefaults.ini in the folder "/data/ni" (create it if it doesn't exist) on the tablet. For the Kinect sensor similar files are available in the folders OpenNI/Data and SensorKinect/Data.

All the files copied inside the "/system/lib" folder need to have the permissions of read and write enabled for all categories of users.

Boost

Boost libraries (*.a files) are found in the folder "BoostAndroid/build/lib" and need to be placed in the "/system/lib" folder of the device, in the same way as specified for the OpenNI libraries. By now the Boost libraries used by the application are:

  • libboost_chrono
  • libboost_date_time
  • libboost_system
  • libboost_timer

G2O

Same as for OpenNI and Boost libraries, in this case the G2O libraries (*.so files) are found in the folder "g2o/lib". The used libraries are:

  • libg2o_core
  • libg2o_solver_pcg
  • libg2o_stuff
  • libg2o_types_slam3d

slam-dunk-android's People

Contributors

alessiotonioni avatar

Watchers

 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.