General repo for work with Berkeley Fire Lab https://pyro.turtlebasket.ml
 
 
 
 
 
 
Go to file
michael c689247975 add configurability 2022-10-06 17:42:39 -07:00
.DS_Store working ratio pyrometry 2022-10-06 16:30:55 -07:00
.gitignore initial commit 2022-10-06 00:13:40 -07:00
01-0001-cropped-transformed-ratio.png add configurability 2022-10-06 17:42:39 -07:00
01-0001-cropped.png add configurability 2022-10-06 17:42:39 -07:00
01-0001-transformed-grayscale.png working ratio pyrometry 2022-10-06 16:30:55 -07:00
01-0001.png initial commit 2022-10-06 00:13:40 -07:00
01-0002-cropped-transformed-ratio.png add configurability 2022-10-06 17:42:39 -07:00
01-0002-cropped.png add configurability 2022-10-06 17:42:39 -07:00
01-0002.png add configurability 2022-10-06 17:42:39 -07:00
01-0003-cropped-transformed-ratio.png add configurability 2022-10-06 17:42:39 -07:00
01-0003-cropped.png add configurability 2022-10-06 17:42:39 -07:00
01-0003.png add configurability 2022-10-06 17:42:39 -07:00
Pipfile initial commit 2022-10-06 00:13:40 -07:00
Pipfile.lock initial commit 2022-10-06 00:13:40 -07:00
README.md add configurability 2022-10-06 17:42:39 -07:00
grayscale_pyrometry.py working ratio pyrometry 2022-10-06 16:30:55 -07:00
ratio_pyrometry.py add configurability 2022-10-06 17:42:39 -07:00

README.md

Pyrometry image processing

Temperature maps

Grayscale pyrometry: currently basic; uses grayscale opencv import, then just applies a jet filter. Doesn't yet copy the full impl in the paper.

Ratio pyrometry: pretty damn close to what's in the paper but it's very broken atm

Test image:

Grayscale pyrometry result:

Ratio pyrometry result (with 2x2 convolutional smoothing):

According to general researcher consensus, ratio pyrometry is supposed to be more accurate.