Side Window Infotainment is a student project of the TU Berlin in cooperation with IAV as the industrial partner.
The goal is to build an infotainment system for car passengers which automatically captures points of interest in the field of view and displays relevant information on the side window.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
- Intel RealSense SR300
- Webcam
- GPS Module
- JDK 8
- .NET Framework 4.5 (should already be available on Win10)
- Intel RealSense SDK 2016 R2
Google APIs:
- Setup a project with the Google Cloud Console and create an API key
- On the dashboard, enable the following services:
- Cloud Vision API
- Places API
- Knowledge Graph Search API
- You can create API keys for each service or use one for all
- Insert your API keys in
src/main/resources/api-config.cfg
JavoNet:
- Request a license at JavoNet, you can also use the trial version for now
- Insert the email you have used for registration and the license key in
src/main/resources/api-config.cfg
There a additional steps needed to setup your development environment.
- Import the project as a Maven project to your IDE (e.g. Intellij IDEA)
- In order to make the GPS module work, you need to download the RXTX Windows x64 binaries from here
- Copy
RXTXcomm.jar
to<JAVA_HOME>\jre\lib\ext
- Copy
rxtxSerial.dll
to<JAVA_HOME>\jre\bin
- Copy
rxtxParallel.dll
to<JAVA_HOME>\jre\bin
-
The model graph and labels of the classifier are not bundled into the repository, you can download them using Maven:
mvn compile
-
Run
ApplicationViewImplementation.java
to start the app
Build and deploy the jar
using Maven
mvn package
- Maven - Dependency Management
- JavaFX - standard GUI libra ry for Java SE
- JavoNet - Java to .NET Bridge
- Tensorflow - Machine Learning Framework
- JavaCV - Java Interface to OpenCV
- Google API Client - API Client for Google Services
For the versions available, see the tags on this repository.
This project is licensed under the MIT License - see the LICENSE.md file for details