Giter Site home page Giter Site logo

danesfield-app's Introduction

Deprecation Notice

The Danesfield-App web application has been superseded by https://github.com/girder/Danesfield. This repo is deprecated, see the original README below.

Danesfield App

The Danesfield App is a web application for running the Danesfield algorithms and visualizing results. Danesfield addresses the algorithmic challenges of the IARPA CORE3D program by reconstructing semantically meaningful 3D models of buildings and other man-made structures from satellite imagery.

Video demo

Screenshots

Server

Requirements

Setup

  1. Run conda/install.sh. This will create and active a new conda environment, as well as install the required packages.
  2. Pull the publicly available Danesfield image on Docker Hub
  3. Run pip install -e server to install girder and it's
  4. (Optional) To setup girder with some default settings, you can run python server/init_girder.py. A default admin user and password are included in that script. If you would like to configure this, you can export the GIRDER_ADMIN_USER and GIRDER_ADMIN_PASS environment varibales before running the above command.

Running dependent services/applicatons

Girder requires that MongoDB and RabbitMQ are running. If you've installed docker-compose, this can be done easily:

docker-compose up -d

You can stop these services by running docker-compose stop, and remove all associated data by runnning docker-compose down.

Running the application/services

Run the following commands separately on the machine you wish to host the application on (within the conda environment):

  1. girder serve --host 0.0.0.0
  2. python -m girder_worker -l info --concurrency 4

Girder should now be running.

Configuration

Models used:

  1. UNet Semantic Segmentation
  2. Building Segmentation
  3. Material Classification
  4. Roof Geon Extraction
  5. Run Metrics

Upload all models to the models folder within the core3d collection, creating it if it doesn't exist.

Client Setup

See here

danesfield-app's People

Contributors

aashish24 avatar dmjoy avatar jjnesbitt avatar matthewma7 avatar mleotta avatar msmolens avatar mvandenburgh avatar syncharny avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

danesfield-app's Issues

Workflow for Multiple Images

If I have multiple satellite images of a region, what is the general workflow for combining them using the Danesfield-App?

I have the app up and running, however there is no data or workflows shown. Judging from the readme, there must be a way to

  1. upload the models from here, then
  2. upload a set of images, and
  3. run a job workflow.

Is that the correct workflow? If so, how do you upload models and images?

how to test the effect?

I send the test_data 'D1_mls_building.txt' to collections, and comfirn the 'Start a pipeline ' ,and then waited too long with no result! so,how to test the effect? or What are the test data format requirements?

docker build failed, cannot pull p3d?

(girder_env) :~/workspace/3d_reconstruction/Danesfield-App/support/docker/p3d_gw$ sudo docker build -t gitlab.kitware.com:4567/core3d/danesfield-app/p3d_gw .
Step 1/3 : FROM p3d
pull access denied for p3d, repository does not exist or may require 'docker login'

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.