FIND is now 100% open-source.
Note for past users, the codebase has been completely rewritten in Golang so things are ~100x faster, smarter, and more secure. The Python3 version will stay available, but it is no longer supported. Development will now be focused on this version.
Keywords: indoor GPS, WiFi positioning, indoor mapping, indoor navigation, indoor positioning
The Framework for Internal Navigation and Discovery (FIND) allows you to use your (Android) smartphone or WiFi-enabled computer (laptop or Raspberry Pi or etc.) to determine your position within your home or office. You can easily use this system in place of motion sensors as its resolution will allow your phone to distinguish whether you are in the living room, the kitchen or the bedroom, etc. The position information can then be used in a variety of ways including home automation, way-finding, or tracking!
Simply put, FIND will allow you to replace tons of motion sensors with a single smartphone!
The system is built on two main components - a server and a fingerprinting device. The fingerprinting device (computer program or android app) sends the specified data to the machine learning server which stores the fingerprints and analyzes them. It then returns the result to the device and stores the result on the server for accessing via a web browser or triggering via hooks.
FAQ (abbreviated):
- How does it work? It uses already available WiFi information to classify locations.
- Doesn't this already exist? Yes, kinda.
- Can I use an iPhone? Sorry, no.
- Does it work on a Raspberry Pi? Yes.
- What's the point? This short piece of code can do home automation and replace motion sensors and more.
- Can I help? Yes, please.
- How do I try it? It's easy. Just download and run.
More questions? See the unabbreviated FAQ.
- SSL support
- Compression to keep DBs small
- Fast (20-200x faster than the previous Python version)
- Mixes two machine learning algorithms for best classifications
- Bug free (yeah, um...probably not. Please submit an issue when you find one).
To use this system you need to have the following:
- (Optional) Server: A computer (OS X/Windows/Linux) to run the server. If you don't have this, use ours.
- Client(s): device (laptop/Raspberry Pi/Android smartphone) that has access to WiFi
The tools are prebuilt, so you can skip to the Usage section if you just want to try it out.
First install Go if you haven't already. FIND is tested on Go version 1.5+.
$ git clone https://github.com/schollz/find.git
$ cd find
$ go get ./...
$ go build
Then to run,
$ ./find
-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----
_________ _____
/ __/ _/ |/ / _ \ ______ _____ _____ ____
/ _/_/ // / // / (_-< -_) __/ |/ / -_) __/
/_/ /___/_/|_/____/ /___|__/_/ |___/\__/_/
(version 2.X) is up and running on http://192.168.1.2:8003
-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----
The client gathers WiFi fingerprints and sends them to the server. There are two clients - one for an Android smartphone, and one for a WiFi-enabled computer. Check out the individual repos to get started on either/both:
To get started using FIND you will need one of the client programs. The client programs gather WiFi fingerprints and locations and sends them to a server. There is a client for Android smartphones, and one for WiFi enabled computers.
Sorry iPhone users but the Apple store prevents apps that access WiFi information, so I will be unable to release a iPhone version.
To get started using FIND on a smartphone, download the latest app or build it yourself.
When you start up the app you will be asked for a username (enter whatever you want) and you'll be assigned a unique group name. Then you'll see the following:
Simply click "Learn" and you'll be prompted for a location name. After you enter a location, the app will connect to the server and then submit fingerprints. After you've learned some locations, just hit "Track" and you'll see your calculated location.
To see more detailed information, go to the server and login with your group name
Supports Linux, Windows, Raspberry Pi, and OS X!
To get started, download the program here or build it yourself. To start learning locations simply use
./fingerprint -eand then to track your location use
./fingerprintThere are other options, you can learn more by typing ./fingerprint --help. When you start learning/tracking, you can see more detailed information by logging into the server and login with your group name.
The server analyzes and helps you decipher the fingerprint data, if you are interested in that. Once you got your client you can see statistics about your fingerprints by logging on to the server and signing in with your group name. If you are using our server, login to ml.internalpositioning.com with your Group name. Otherwise, use your local version of the server.
You can see fingerprints of individual places by clicking on them, and then you can click on mac addresses to see there statistics across rooms.
Please, do! Checkout the latest issues to see what needs being done, or add your own cool thing.
If you find a bug or need help with something, feel free to contact:
- Email: [email protected]
- Twitter: @zack_118
- Gitter: Join room
- Github Issues: Open an issue
Thanks to tscholl2, sjsafranek, and jschools for their help in guiding the development of FIND and creating the early versions of FIND with me!
Thanks to Rishabh Rajgarhia and CanvasJS for help implementing a nice graph.
Thanks arafsheikh for adding interface selection, Pugio and ScottSWu for adding OS X/Windows support for the fingerprint program. Thanks Thom-x for the Dockerfile. Thanks certifiedloud for implementing the change to DELETE requests and implementing sockets for unix. Thanks bebus77 for making a awesome generic struct for OS support on the fingerprinting program!
Thanks to patorjk and asciiworld for the ASCII art. Thanks to Imgur for hosting images.
Like this? Help me keep it alive by donating $5 to pay for server costs.
FIND is a Framework for Internal Navigation and Discovery.
Copyright (C) 2015-2016 Zack Scholl
This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License along with this program. If not, see GNU Affero General Public License here.
FIND uses CanvasJS. Note that you will have to buy the appropriate CanvasJS License if you use this software for commercial purposes. CanvasJS has the following Dual Licensing Model:
Commercial use of CanvasJS requires you to purchase a license. Without a commercial license you can use it for evaluation purposes only. Please refer to the following link for further details: http://canvasjs.com/.
For non-commercial purposes you can use the software for free under Creative Commons Attribution-NonCommercial 3.0 License.
A credit Link is added to the bottom right of the chart which should be preserved. Refer to the following link for further details on the same: http://creativecommons.org/licenses/by-nc/3.0/deed.en_US.