US 12,087,052 B2
Method and system for crop loss estimation
Jayantrao Mohite, Thane (IN); Suryakant Ashok Sawant, Thane (IN); and Srinivasu Pappula, Hyderabad (IN)
Assigned to TATA CONSULTANCY SERVICES LIMITED, Mumbai (IN)
Appl. No. 17/756,073
Filed by Tata Consultancy Services Limited, Mumbai (IN)
PCT Filed Mar. 22, 2021, PCT No. PCT/IB2021/052360
§ 371(c)(1), (2) Date May 16, 2022,
PCT Pub. No. WO2021/191772, PCT Pub. Date Sep. 30, 2021.
Claims priority of application No. 202021013244 (IN), filed on Mar. 26, 2020.
Prior Publication US 2023/0005259 A1, Jan. 5, 2023
Int. Cl. G06K 9/00 (2022.01); G06V 10/25 (2022.01); G06V 10/75 (2022.01); G06V 20/10 (2022.01); G06V 20/13 (2022.01)
CPC G06V 20/188 (2022.01) [G06V 10/25 (2022.01); G06V 10/751 (2022.01); G06V 20/13 (2022.01)] 9 Claims
OG exemplary drawing
 
1. A processor implemented method (200) for crop loss estimation, comprising:
for each Region on Interest (ROI):
collecting (202) real-time information on one or more weather parameters, and one or more remote sensing indicators, via one or more hardware processors;
determining (204) by processing the real-time information on the one or more weather parameters and the one or more remote sensing indicators, one or more critical time windows in at least one later time instance, wherein in each of the one or more critical time windows one or more crops in the ROI suffers a crop loss;
classifying (206) the crop loss in each of the one or more critical time windows as one of a repairable damage and a permanent damage, via the one or more hardware processors; and
quantifying (208) crop loss in each of the critical time windows, comprising:
collecting (502) remote sensing time series data of at least one image of at least one hotspot in the critical time window for which crop loss is to be quantified;
estimating (504) a time series estimator for each pixel in the at least one image, wherein the time-series estimator for a pixel is estimated using comparison of a pre-defined time-series of the pixel with a current time series of the pixel;
estimating (506) a temporal estimator for each pixel in the at least one image, wherein the temporal estimator for a pixel is estimated based on a long-term temporal average of a crop at a target pixel with a temporal data of the crop at the current pixel;
estimating (508) a spatial estimator for each pixel in the at least one image, wherein the spatial estimator for a pixel is estimated based on condition of the pixel in comparison with one or more other pixels in the image of the hotspot; and
quantifying (510) a total crop loss at a hotspot as equal to weighted average of the time-series estimator, the temporal estimator, and the spatial estimator.