{"id":1257,"date":"2020-11-17T02:41:17","date_gmt":"2020-11-17T02:41:17","guid":{"rendered":"https:\/\/rossedwards.co.uk\/blog\/?p=1257"},"modified":"2020-11-17T18:31:50","modified_gmt":"2020-11-17T18:31:50","slug":"testing-nasa-ames-stereo-pipeline","status":"publish","type":"post","link":"https:\/\/rossedwards.co.uk\/blog\/2020\/11\/17\/testing-nasa-ames-stereo-pipeline\/","title":{"rendered":"Testing NASA AMES Stereo Pipeline"},"content":{"rendered":"\n

Whilst looking for the best available open source solution to generate terrain heightmaps from satellite stereo pairs, I stumbled upon the results of an international IARPA ‘Multiple view Stereo 3D Mapping challenge<\/a>‘. The entries that secured 2nd and 3rd place used variation’s of Ames Stereo Pipeine (ASP)<\/a> NASA’s automated, open-source pipeline for mass production of digital elevation models (DEMs) from very high-resolution commercial stereo satellite imagery. I couldn’t wait to dig deeper and review it’s capabilities. I started by setting up a QGIS project file which allowed me to load up my results from numerous test runs covering every key permutation available for the 2 most successful algorithms, this enabled quick comparison of sometimes subtle differences in results:<\/p>\n\n\n\n

SGM (Semi-Global Matching)<\/strong> – a proven stereo algorithm with widesread popularity.<\/p>\n\n\n\n

MGM (More Global Matching)<\/strong> – is a variation of SGM that can produce superior output at the cost of longer run-time and higher memory usage.<\/p>\n\n\n\n

I added a red background on every resulting raster to highlight area’s where the algorithm had not been able to process. Click below image to see animated testing:<\/p>\n\n\n\n