Please enable JavaScript.
Coggle requires JavaScript to display documents.
Binh Tan AI Illegal Construction Detection App - Coggle Diagram
Binh Tan AI
Illegal Construction Detection App
TARGETS
Find satellite imagery source with high resolution for the years before 2009
High accuracy build-up area classification algorithm
Develop an AI algorithm that allows government staff to generate build-up area maps
Develop an AI algorithm that detects potential illegal construction areas automatically
ISSUES
Low accuracy build-up area classification by ArcMap
Long update interval of satellite imagery
Depend on Google Earth source
Potential illegal construction areas detection is still manual
Depend on specialist to generate build-up area map
TECHNICAL SOLUTIONS
Adjust satellite images coordinates using ArcMap
Build-up area classification
Current solution
Use Maximum Likelihood Classification tool + signature file --> raster
Use Raster to Polygon tool in ArcMap --> Polygon Vectors
Collects training samples --> signature file
Future solution
Minimal data labelling cost
Can use a better algorithms that can detect more than 70% illegal constructions
More interactive web app
Can export data to CAD/GIS file formats
Reuse data label when changing to a new data source
Easy to change a new algorithm in the future
Imagery resolution
Best: 0.3 m
Acceptable: 3 m
Good: 1 m
Aerial imagery sources
Free
SPOT 5
Range: 2010
Resolution: 10 m
Google Earth/Maxar
Range: 2009-2022
Resolution: 0.3 m
LIDAR Projects
Range: 2012 & 2019
Resolution: 0.1 m
Fee
PlanetScope
Resolution: 3 m
$1.80/km2
Từ 2017
SPOT 6
Resolution: 1.5 m
Từ 2012
$4.75/km2
SPOT 7
Resolution: 1.5 m
Từ 2015
$4.75/km2
IKONOS
Resolution: 0.8 m
2000 – 2014
$10.00/km2
Quick Bird
Resolution: 0.6 - 0.72 m
2002 – 2013
$17.50/km2
Rapid Eye
Resolution: 5 m
2009 – 2019
$1.28/km2