GithubHelp home page GithubHelp logo

victor-dp / rs_buildings_extraction Goto Github PK

View Code? Open in Web Editor NEW

This project forked from geocompass/rs_buildings_extraction

0.0 1.0 0.0 3.36 MB

Extract geojson of buildings outline from Remote Sensing images which complies with the WMTS standard.

License: GNU General Public License v3.0

Python 60.23% JavaScript 3.03% HTML 1.77% Vue 34.96%

rs_buildings_extraction's Introduction

基于遥感影像的建筑物轮廓提取框架

从符合 WMTS 标注的遥感影像中,使用基于深度学习的 RoboSat.geoc 库,提供可视化的 Web 页面,方便的进行训练和预测。并提供服务 RESTful 标准的建筑物提取接口,可以用于工程实践生产环境中。

基于 RoboSat.geoc 的建筑物轮廓提取框架

主要功能:

  • Web 地图方式浏览已有的建筑物轮廓训练样本标注数据,支持显示与隐藏控制
  • 一键拉框选取待训练的区域,开始自动化训练
  • 一键拉框选取待预测区域,预测结果自动加载到 Web 地图中
  • 支持切换天地图(CGCS2000 坐标系)或谷歌(WGS84 坐标系)的遥感影像底图
  • 支持查看当前训练日志
  • 提供符合 WMTS 的天地图和谷歌地图服务的 XYZ 代理
  • 提供符合 RESTful 标准的训练和预测接口,可以用于工程生产环境

如何安装:

  • 下载项目:git clone https://github.com/geocompass/rs_buildings_extraction.git
  • 进入目录:cd rs_buildings_extraction
  • 安装依赖:
    • python install -r requirements.txt (若使用 Anaconda 需要注意 python 路径,后同)
    • RoboSat_geoc 安装为系统Package,供本项目调用,安装方法见 如何作为Packages
  • 项目参数配置:
    • 设置 PostgreSQL 数据库连接: app/config/secure.py 中的 SQLALCHEMY_DATABASE_URI
    • 设置已有建筑物数据表名称:app/config/setting.py 中的 BUILDINGS_TABLE
    • 配置文件或训练结果数据路径:app/config/setting.py 中的 ROBOSAT_DATA_PATH
    • 自动生成的待训练或预测的临时数据集路径:app/config/setting.py 中的 ROBOSAT_DATASET_PATH
  • 运行项目:
    • 前台运行:python main.py
    • 后台运行:python main.py &

如何开发

技术栈

  • 前端:Vue.js+MapboxGL.js
  • 后台:Python+Flask
  • 数据库:PostgreSQL+PostGIS
  • 遥感影像提取:Robosat_geoc

文件目录

  • app:Flask 服务
    • api :对Flask外提供的接口
    • config:各类项目运行配置文件
  • webmap:前端地图页面开发库
    • dist:对外发布的前端页面
      • config.js:前端连接后台配置文件
    • public:vue.js开发时所需的静态配置文件
    • src:vue.js 开发文件

项目依赖

  • RoboSat_geoc ,并将其安装到系统 Packages
  • PostgreSQL + PostGIS
  • Python 3.6 以上

Key words:

IoU: Intersection of Union, main index for evaluation on the precision of model. Mathmetically expressed as: Area of I / Area of U, indicating the coefficiency of sample boundary and prediction boundary. This index is appalied to many cases of deep learning, being irrelevant to the process of model and optimal reflection on the model.

本项目作者:

rs_buildings_extraction's People

Contributors

liii18 avatar wucangeo avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.