SpaceNetChallenge/RoadDetector

Stars
204
Rank 190,931 (Top 4 %)
Language
Python
License
Other
Created over 6 years ago
Updated about 1 year ago

SpaceNetChallenge/RoadDetector

SpaceNetChallenge

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Winning Solutions from SpaceNet Road Detection and Routing Challenge

SpaceNet Road Detection and Routing Challenge Solutions

For more information about the SpaceNet Challenge visit the SpaceNet Challenge Website

About the Dataset

The Average Path Length Similarity (APLS): Metric Part 1

The Average Path Length Similarity (APLS): Metric Part 2

Competition Specific information:

SpaceNet Challenges hosted on TopCoder

Topcoder Competition Page

Results:

Place	Entrant	Country	Average Score	Las Vegas	Paris	Shanghai	Khartoum
1	albu	Russia	0.6663	0.7977	0.604	0.6543	0.6093
2	cannab	Russia	0.6661	0.7804	0.6446	0.6398	0.5996
3	pfr	France	0.666	0.8009	0.6008	0.6646	0.5975
4	selim_sef	Germany	0.6567	0.7884	0.5991	0.6472	0.5922
5	fbastani	America	0.6284	0.771	0.5474	0.6326	0.5628
6	ipraznik	Germany	0.6215	0.7578	0.5668	0.6078	0.5537
7	tcghanareddy	India	0.6182	0.7591	0.571	0.6014	0.5415
8	hasan.asyari	Norway	0.6097	0.7407	0.5557	0.5952	0.5472
9	aveysov	Russia	0.5943	0.7426	0.5805	0.5751	0.4789

Top 5 Solutions:

utilities

Packages intended to assist in the preprocessing of SpaceNet satellite imagery data corpus to a format that is consumable by machine learning algorithms.

BuildingDetectors_Round2

Building detector algorithms from second SpaceNet Challenge

SpaceNet_Off_Nadir_Solutions

Winning algorithms for the SpaceNet 4: Off-Nadir Building Footprint Detection Challenge

BuildingDetectors

Winning building footprint detector implementations from the SpaceNet challenges.

SpaceNet8

Algorithmic baseline for SpaceNet 8 Challenge

SpaceNet_SAR_Buildings_Solutions

The winning solutions for the SpaceNet 6 Challenge

Jupyter Notebook

SpaceNet7_Multi-Temporal_Solutions

SpaceNet_Optimized_Routing_Solutions

SAR-RGB-DataFusion

A small codebase featuring a few elementary methods for SAR and Optical imagery data fusion

Jupyter Notebook

BuildingDetectorVisualizer

The purpose of the visualizer application is to let you view 3-band and 8-band images, view ground truth building footprints and your solution's building footprint as overlays on these images, compare truth to solution and calculate your solution's score.

stac-implementation

Tools for Implementation of STAC SPEC for SpaceNet dataset https://github.com/radiantearth/stac-spec/tree/dev

Jupyter Notebook

ml-export-tool