US 12,007,277 B2
Hyperspectral imager method and apparatus
Richard J. Murphy, Sydney (AU); Arman Melkumyan, Sydney (AU); Anna Chlingaryan, Sydney (AU); Dai Bang Nguyen, Sydney (AU); Stuart Wishart, Sydney (AU); Alex Lowe, Sydney (AU); and Steven Scheding, Sydney (AU)
Assigned to Technological Resources Pty. Limited, Melbourne (AU)
Filed by TECHNOLOGICAL RESOURCES PTY. LIMITED, Melbourne (AU)
Filed on Aug. 25, 2021, as Appl. No. 17/412,029.
Application 17/412,029 is a continuation of application No. 15/543,442, granted, now 11,125,619, previously published as PCT/AU2016/000004, filed on Jan. 14, 2016.
Claims priority of application No. 2015900094 (AU), filed on Jan. 14, 2015; and application No. 2015901769 (AU), filed on May 15, 2015.
Prior Publication US 2022/0034717 A1, Feb. 3, 2022
Int. Cl. G01J 3/28 (2006.01); G01J 3/02 (2006.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); H04N 23/11 (2023.01); H04N 23/51 (2023.01); H04N 23/71 (2023.01); H04N 23/73 (2023.01)
CPC G01J 3/2823 (2013.01) [G01J 3/0202 (2013.01); G01J 3/0208 (2013.01); G01J 3/0237 (2013.01); G01J 3/0264 (2013.01); G01J 3/0286 (2013.01); G01J 3/0291 (2013.01); G01J 3/28 (2013.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); H04N 23/11 (2023.01); H04N 23/51 (2023.01); H04N 23/71 (2023.01); H04N 23/73 (2023.01); G01J 2003/2826 (2013.01)] 8 Claims
OG exemplary drawing
 
1. A method of processing a series of hyperspectral images in order to classify its constituent parts, the method including the steps of:
(a) deriving a non-stationary observation angle dependent probabilistic model having a series of parameters for the series of hyperspectral images;
(b) training the series of probabilistic model parameters on mineral samples obtained from artificial light reflectance measurements; and
(c) utilising the probabilistic model on hyperspectral imagery acquired from sampling geographical conditions under natural lighting conditions, to classify constituent parts of the hyperspectral imagery.