US 12,444,189 B2
Methods and systems for classifying and benchmarking irrigation performance
Zitian Gao, Victoria (AU); Danlu Guo, Victoria (AU); Andrew William Western, Victoria (AU); Dongryeol Ryu, Victoria (AU); and David John Aughton, Victoria (AU)
Assigned to Rubicon Research Pty Ltd, Victoria (AU); and The University of Melbourne, Victoria (AU)
Appl. No. 18/719,543
Filed by Rubicon Research Pty Ltd, Victoria (AU); and The University of Melbourne, Victoria (AU)
PCT Filed Dec. 14, 2022, PCT No. PCT/AU2022/051505
§ 371(c)(1), (2) Date Jun. 13, 2024,
PCT Pub. No. WO2023/108213, PCT Pub. Date Jun. 22, 2023.
Claims priority of application No. 2021904049 (AU), filed on Dec. 14, 2021.
Prior Publication US 2025/0054298 A1, Feb. 13, 2025
Int. Cl. G06V 20/00 (2022.01); G06T 3/40 (2006.01); G06T 7/13 (2017.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 20/10 (2022.01)
CPC G06V 20/188 (2022.01) [G06T 3/40 (2013.01); G06T 7/13 (2017.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01)] 25 Claims
OG exemplary drawing
 
1. An automated method comprising:
identifying a plurality of field areas delineated by field boundaries within a geographical region;
processing seasonal normalised difference vegetation index (NDVI) time series data to generate a plurality of aggregate field NDVI feature values for each identified field area; and
classifying irrigation status of each identified field area by executing a decision tree classifier that is configured to determine a classification as either ‘irrigated’ or ‘non-irrigated’ based upon the corresponding plurality of aggregate field NDVI feature values.