IP Library › Granted Patent US 12,743,863
Granted Patent B2
US 12,743,863 · App. 18/437,477 · Granted Sep 22, 2026

Platform for distributed landcover feature data review

Inventors: Yuanming Shu (Toronto, CA); Shuo Tan (Campbell, CA); Tuan Zhao (Toronto, CA); Huansheng Mo (Guilin, CN)
Assignee: ECOPIA TECH CORPORATION
G06V10/44G06T7/11G06T7/50G06T7/62G06V20/10G06V20/13G06V20/17G06T2207/20081G06T2207/30181G06T2207/30188G06V20/176G06V20/182G06V20/188
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,743,863
App. No.
18/437,477
Granted
Sep 22, 2026
Kind
B2
Abstract

Methods and systems for extracting and reviewing landcover feature data are provided. An example method involves accessing geospatial imagery covering a geographic area and landcover feature data extracted from the geospatial imagery, subdividing the geospatial imagery into a grid of image tiles, assigning landcover feature data review technicians to review the image tiles and associated landcover feature data through a landcover feature data review platform, and receiving revised landcover feature data that modifies the landcover feature data.

Claims (38)

1 . A method comprising:

accessing geospatial imagery covering a geographic area;

extracting landcover feature data from the geospatial imagery that represents one or more landcover features in the geographic area;

accessing confidence data associated with the landcover feature data that indicates a degree of confidence that the landcover feature data accurately represents the landcover features;

subdividing the geospatial imagery into a grid of image tiles, each image tile covering a subset of the geographic area, and, for each image tile, associating the image tile with a subset of the landcover feature data that represents the landcover features covered by the image tile;

determining a set of image tiles to be assigned for data review, the determination, for each image tile, based on an evaluation of the confidence data associated with the landcover feature data for the image tile;

for each image tile to be assigned for data review, assigning a landcover feature data review technician to review the landcover feature data with reference to the associated geospatial imagery through a landcover feature data review platform; and

receiving revised landcover feature data from the landcover feature data review platform that modifies the landcover feature data corresponding to one or more landcover features.

2 . The method of claim 1 , wherein the revised landcover feature data modifies one or more of a shape and size of a landcover feature.

3 . The method of claim 1 , further comprising:

substituting a portion of the landcover feature data that was extracted from the geospatial imagery with the revised landcover feature data that was obtained from the landcover feature data review platform.

4 . The method of claim 1 , wherein:

the landcover feature data is extracted from the geospatial imagery by a machine learning model; and

the method further comprises, following receiving revised landcover feature data, training the machine learning model with the revised landcover feature data.

5 . The method of claim 1 , wherein the landcover feature data review technicians are assigned to review landcover feature data, at least in part, in accordance with a predetermined sequence.

6 . The method of claim 5 , wherein the predetermined sequence is determined by a priority value assigned to each image tile, wherein the priority value for each image tile is non-consecutive with each adjacent image tile.

7 . The method of claim 1 , wherein each image tile comprises a working area and a surrounding buffer area, wherein the working area contains the geospatial imagery and associated landcover feature data that is to be reviewed by the assigned landcover feature data review technician.

8 . The method of claim 7 , wherein, for at least one image tile, the buffer area contains the landcover feature data associated with an adjacent image tile that has previously been reviewed by another landcover feature data review technician.

9 . The method of claim 8 , further comprising:

receiving, through the landcover feature data review platform, a notification generated by a first landcover feature data review technician assigned to a first image tile regarding landcover feature data contained in the buffer area of the first image tile that is associated with a second image tile adjacent to the first image tile that has previously been reviewed by a second landcover feature data review technician.

10 . The method of claim 9 , further comprising:

generating a ticket for a supervising landcover feature data review technician to address the notification.

11 . The method of claim 8 , further comprising:

receiving, through the landcover feature data review platform, revised landcover feature data generated by a first landcover feature data review technician assigned to a first image tile that modifies landcover feature data contained in the buffer area of the first image tile that is associated with a second image tile adjacent to the first image tile that has previously been reviewed by a second landcover feature data review technician.

12 . The method of claim 11 , further comprising:

generating a ticket for a supervising landcover feature data review technician to address the revised landcover feature data.

13 . The method of claim 1 , wherein the set of image tiles comprises a first image tile and a second image tile, and the revised landcover feature data modifies landcover feature data that represents a landcover feature that crosses a buffer area between the first image tile and the second image tile.

14 . The method of claim 1 , wherein the landcover feature data comprises vector data.

15 . The method of claim 14 , wherein the vector data includes at least one polygon that indicates a shape and size of a landcover feature.

16 . A method comprising:

accessing a landcover feature data review platform;

receiving, through the landcover feature data review platform, an assignment for a landcover feature data review technician to review landcover feature data associated with an image tile, and receiving access to the landcover feature data and geospatial imagery associated with the image tile, wherein the landcover feature data was extracted from the geospatial imagery to represent one or more landcover features depicted in the geospatial imagery; and

generating, through the landcover feature data review platform, with reference to the landcover feature data and associated geospatial imagery, one or more modifications to, or notifications regarding, the landcover feature data.

17 . The method of claim 16 , wherein:

the assignment for the landcover feature data review technician to review the landcover feature data is made at least in part in accordance with a predetermined sequence of assignments determined by a priority value assigned to each image tile in a grid of image tiles including the image tile assigned to the landcover feature data review technician, wherein the priority value for each image tile is non-consecutive with each adjacent image tile.

18 . The method of claim 16 , wherein the image tile comprises a working area and a surrounding buffer area, wherein the working area contains the landcover feature data associated with the image tile that is to be reviewed.

19 . The method of claim 18 , wherein the surrounding buffer area contains landcover feature data associated with an adjacent image tile, and wherein the one or more modifications or notifications are regarding landcover feature data that is contained in the buffer area of the image tile and that is associated with an adjacent image tile.

20 . The method of claim 19 , wherein the one or more modifications or notifications comprise revised landcover feature data that modifies landcover feature data that represents a landcover feature that crosses the surrounding buffer area between the image tile and the adjacent image tile.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 29, 2024
From: SHU, YUANMING; TAN, SHUO; ZHAO, TUAN; MO, HUANSHENG
To: ECOPIA TECH CORPORATION
Reel/Frame 066595/0800 →
Continuity (3)
Provisional Application 63598396 · Nov 13, 2023
Provisional Application 63515671 · Jul 26, 2023
Related Publication 20250037412A1 · Jan 30, 2025
References Cited (24)
US 8488845B1 · Tang et al. · 2013 [cited by applicant]
US 11126855B2 · Kim · 2021 [cited by examiner]
US 11170264B2 · Sallee · 2021 [cited by applicant]
US 11372687B1 · Hollosi et al. · 2022 [cited by applicant]
US 11830246B2 · Fleisig et al. · 2023 [cited by applicant]
US 12518510B2 · Shu · 2026 [cited by examiner]
US 20130046829A1 · Coch · 2013 [cited by applicant]
US 20150071528A1 · Marchisio · 2015 [cited by examiner]
US 20160005147A1 · Kirmse · 2016 [cited by examiner]
US 20170124490A1 · Crabtree · 2017 [cited by examiner]
US 20170249514A1 · Folens et al. · 2017 [cited by applicant]
US 20210042530A1 · Kim · 2021 [cited by applicant]
US 20210342586A1 · Fleisig et al. · 2021 [cited by applicant]
US 20220051017A1 · Choi · 2022 [cited by applicant]
US 20240233086A1 · Shu · 2024 [cited by examiner]
US 20240362898A1 · Brumby · 2024 [cited by applicant]
US 20250005858A1 · Shu · 2025 [cited by examiner]
Scott et al., “Training Deep Convolutional Neural Networks for Land-Cover Classification of 1-47 High-Resolution Imagery”, IEEE Geoscience and Remote Sensing Letters, Feb. 17, 2017 (Feb. 17, 2017), vol. vol. 14, Issue: … [cited by applicant]
Kim et al. “Cooperative scheduling schemes for explainable DNN acceleration in satellite image analysis and retraining.” IEEE Transactions on Parallel and Distributed Systems 33.7 (2021): 1605-1618. (Year: 2021). [cited by applicant]
Paris et al. “An interactive strategy for the training set definition based on active self-paced learning implemented on a cloud-computing platform.” IEEE Geoscience and Remote Sensing Letters 19 (2021): 1-5. (Year: 202… [cited by applicant]
Plazas et al. “Ensemble-based approach for semisupervised learning in remote sensing.” Journal of Applied Remote Sensing 15.3 (2021): 034509-034509. (Year: 2021). [cited by applicant]
Robinson et al. “Human-machine collaboration for fast land cover mapping.” Proceedings of the AAAI Conference on Artificial Intelligence. vol. 34. No. 03. 2020. (Year: 2020). [cited by applicant]
International Search Report and Written Opinion, PCT/IB2024/052277, dated May 9, 2024. [cited by applicant]
Notice of Allowance, U.S. Appl. No. 19/176,112, dated May 21, 2025. [cited by applicant]