US 11,941,880 B2
System and method for image-based crop identification
Chen Du, Sunnyvale, CA (US); Jui-Hsin Lai, Santa Clara, CA (US); and Mei Han, Palo Alto, CA (US)
Assigned to PING AN TECHNOLOGY (SHENZHEN) CO., LTD., Shenzhen (CN)
Filed by PING AN TECHNOLOGY (SHENZHEN) CO., LTD., Shenzhen (CN)
Filed on Jun. 2, 2021, as Appl. No. 17/337,410.
Prior Publication US 2022/0391614 A1, Dec. 8, 2022
Int. Cl. G06V 20/10 (2022.01); G06F 16/58 (2019.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06F 18/40 (2023.01); G06N 20/00 (2019.01); G06V 20/68 (2022.01)
CPC G06V 20/188 (2022.01) [G06F 16/5866 (2019.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06F 18/40 (2023.01); G06N 20/00 (2019.01); G06V 20/68 (2022.01)] 20 Claims
OG exemplary drawing
 
1. An image-based crop identification system, comprising:
a database storing sample aerial data and annotated aerial data;
a communication module coupled to the database, the communication module configured to provide the sample aerial data to a user based on an ordering rule and receive the annotated aerial data from the user, wherein the ordering rule is determined based at least in part on a number indicative of annotation times of each piece of sample aerial data; and
a model library coupled to the database, the model library configured to obtain the annotated aerial data, train a crop classification model based on the annotated aerial data, and provide the trained crop classification model for subsequent crop identification,
wherein the annotated aerial data comprise determination of a type of a crop appearing in the sample aerial data.