Git Product home page Git Product logo

spygrt's Introduction

SpyGRT

SpyGRT, or Surface Guided Radiotherapy Toolkit in Python is a toolkit that allows fast development of novel surface guidance applications for radiotherapy.

SpyGRT allows easy:

  • Operation of the depth camera (current model is Intel Realsense D415)
  • Calibration of multiple cameras into the same external frame of reference
  • Tracking of motion using an ICP workflow

Getting Started

Installing SpyGRT using pip

The preferred method for installing SpyGRT is to use pip. This will download all the required packages, however a list of prerequisites and where to find them are listed in the next section in case you prefer to build them from source.

Steps to installing SpyGRT with pip

  1. Clone the SpyGRT GitHub repo
  2. Open a command prompt
  3. Navigate to the SpyGRT folder (not the embedded spygrt folder)
  4. Enter the following pip command
pip install -e . 
  1. You should now be able to run SpyGRT

Prerequesites

1. Intel RealSense SDK2.0

If you want to build from source, installation instructions available here. The code has currently only been tested up to release version 2.5.0 but should work with more recent releases.

2. Open3D library v.0.15.0 or later

If you want to build it from source, full release available here and instructions to compile it yourself are available here.

3. OpenCV

Full release available here, if you prefer to build it from source.

4. Numpy

More Information available here

Working Examples

The example folder contain three examples that illustrate how to use the basic functions of SpyGRT. More instructions are located in that folder.

Depth Sensor

SpyGRT is currently built to use Intel RealSense D415 stereo depth sensors for capturing depth data. However, it should be possible to modify the stream module to work with any commercial depth sensors that have a python API.

Intel RealSense Viewer

While SpyGRT contains the required code for real-time SGRT and analysis of prior recordings, it cannot currently be used to create new recordings. We suggest installing the free realsense-viewer app available here if you want to create your own recordings.

Calibrations Boards

Default SpyGRT Calibration Board

SpyGRT uses a checkerboard to calibrate multiple cameras. By default, it assumes that the checkboard has 5 rows, 8 columns, and that the length of the sides of each square is 4.3 centimeters. If you want to print the default checkerboard, you can find it in a powerpoint file located in the SampleData folder. This file should be printed on an A3 paper to get the accurate dimensions.

Custom Calibration Board

Any checkerboard can be use to calibrate cameras with SpyGRT. If you want to use a custom checkerboard, you will need to change the following default variables in calibration.py

  1. DEFAULT_ROW: Number of rows in the custom calibration board.
  2. DEFAULT_COLUMN: Number of columns in the custom calibration board
  3. DEFAULT_SQUARE_SIZE: Length in meters of the sides of a square in the custom calibration board

Tracking with SpyGRT

Calibration files are necessary to use the SpyGRT for tracking. By default, SpyGRT will look for calibration files ../Calibrations/. If you want to change this path, you must change the following constant in tracker.py

  • CALIBRATION_FOLDER

Author

Youssef Ben Bouchta

Email: [email protected]

spygrt's People

Contributors

ybbouchta avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

spygrt's Issues

add python versions to setup

Installation with python3.11 fails.
This is because pyrealsense2 only supports python3.9 or less.
You should add supported python distributions to your setup.py file (google will tell you how)

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.