The first video shows a pixel-based image differencing approach followed by and unsupervised classification within ArcGIS.
In the second video we move over to eCognition and take an object-based approach to change detection.
|Students and community members working with Open Street Map in the Aiken Center, UVM|
Port Loko, Sierra Leone before and after OSM’s recent activation
Freetown, Sierra Leone, before and after OSM’s recent updates
Here are some great resources/tutorials if you would like to join the effort:
If you have questions or would like to join future OSM mapathons please contact Noah - email@example.comThank you Alysia from Trader Joe’s, Leonardo’s Pizza and Jim from Brennan’s for supporting this event. Also, thank you Bill Morris for all his help.
|LiDAR point cloud. Each point is colored by its absolute elevation. Blue represents the low elevations and red the highest elevations.|
|LiDAR point cloud symbolized by class. Green is ground, magenta is overlap, cyan is water, and red is unclassified. Black areas are water that contain no LiDAR points as water absorbs the LiDAR signal.|
|LiDAR point cloud symbolized by return number. Red indicates a single return, green - two returns, cyan - three returns, and blue - four returns.|
|Normalized Digital Surface Model (nDSM).|
|Normalized Digital Terrain Model (nDTM).|
|nDTM subtracted from the nDSM.|
|Tree canopy extracted using an object-based approach overlaid on a hillshade layer derived from the nDSM.|