IP Library › Granted Patent US 12705911
Granted Patent B2
US 12705911 · App. 18/219,334 · Granted Aug 11, 2026

Systems and methods for geohash-based image scoring and labeling

Inventor: Christian Sidak (Golden Oak, FL)
Assignee: Palantir Technologies Inc.
G06V20/70G06V10/764G06V20/68G06V2201/10
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 12705911
App. No.
18/219,334
Granted
Aug 11, 2026
Kind
B2
Abstract

Systems and methods for image scoring are disclosed. For example, the method includes: receiving a plurality of images, each image of the plurality of images associated with a geographic metadata, the plurality of images associated with one or more geographic metadata; selecting a first set of images from the plurality of images, each image in the first set of images being associated with a first geographic metadata that is one of the one or more geographic metadata; obtaining one or more first labels indicating one or more object classes respectively for each image in the first set of images; and determining one or more first scores for the one or more object classes for the first geographic metadata based at least in part on the one or more first labels.

Claims (67)

1 . A method for image scoring, the method comprising:

receiving a plurality of images associated with a plurality of geographic metadata;

selecting a set of images from the plurality of images, each image in the set of images being associated with one of the plurality of geographic metadata;

obtaining one or more labels indicating one or more object classes respectively for each image in the set of images;

determining a plurality of scores for two or more geographic metadata of the plurality of geographic metadata with respect to one object class of the one or more object classes based at least in part on the one or more labels; and

determining a ranking among the two or more geographic metadata with respect to the one object class based at least in part on the plurality of scores;

wherein the method is performed using one or more processors.

2 . The method of claim 1 , wherein each geographic metadata of the plurality of geographic metadata includes a geohash.

3 . A method for image scoring, the method comprising:

receiving a plurality of images, each image of the plurality of images associated with a geographic metadata, the plurality of images associated with one or more geographic metadata;

selecting a first set of images and a second set of images from the plurality of images, each image in the first set of images being associated with a first geographic metadata that is one of the one or more geographic metadata, each image in the second set of images being associated with a second geographic metadata that is one of the one or more geographic metadata;

obtaining one or more first labels indicating one or more object classes respectively for each image in the first set of images and one or more second labels indicating the one or more object classes respectively for each image in the second set of images;

determining one or more first scores for the one or more object classes for the first geographic metadata based at least in part on the one or more first labels and one or more second scores for the one or more object classes for the second geographic metadata based at least in part on the one or more second labels; and

determining a ranking for one object class of the one or more object classes between the first geographic metadata and the second geographic metadata based at least in part on a first score of the one or more first scores corresponding to the one object class of the one or more object classes and a second score of the one or more second scores corresponding to the one object class of the one or more object classes;

wherein the method is performed using one or more processors.

4 . A method for image scoring, the method comprising:

receiving a plurality of images, each image of the plurality of images associated with a geographic metadata, the plurality of images associated with one or more geographic metadata;

selecting a first set of images and a second set of images from the plurality of images, each image in the first set of images being associated with a first geographic metadata that is one of the one or more geographic metadata, each image in the second set of images being associated with a second geographic metadata that is one of the one or more geographic metadata;

obtaining one or more first labels indicating one or more object classes respectively for each image in the first set of images and one or more second labels indicating the one or more object classes respectively for each image in the second set of images;

determining one or more first scores for the one or more object classes for the first geographic metadata based at least in part on the one or more first labels and one or more second scores for the one or more object classes for the second geographic metadata based at least in part on the one or more second labels;

receiving a plurality of unlabeled images and a request including an indication of an object class of interest; and

determining a plurality of geographic metadata associated with the plurality of unlabeled images, the plurality of geographic metadata including the first geographic metadata and the second geographic metadata;

wherein the method is performed using one or more processors.

5 . The method of claim 4 , further comprising:

selecting one or more selected geographic metadata from the plurality of geographic metadata based at least in part on the one or more first scores and the one or more second scores.

6 . The method of claim 5 , wherein the selecting one or more selected geographic metadata from the plurality of geographic metadata comprises:

selecting the first geographic metadata if a first object score corresponding to the object class of interest is higher than a first threshold, wherein the first object score is one of the one or more first scores.

7 . The method of claim 6 , wherein the selecting one or more selected geographic metadata from the plurality of geographic metadata further comprises:

selecting the first geographic metadata if a second object score corresponding to an uninterested object class is lower than a second threshold, wherein the second object score is one of the one or more first scores.

8 . The method of claim 4 , further comprising:

selecting a set of unlabeled images from the plurality of unlabeled images based at least in part on the one or more selected geographic metadata; and

transmitting an indication of the selected set of unlabeled images to an image labeling system.

9 . A system for image scoring, the system comprising:

one or more memories storing instructions thereon; and

one or more processors configured to execute the instructions and perform operations comprising:

receiving a plurality of images associated with a plurality of geographic metadata;

selecting a set of images from the plurality of images, each image in the set of images being associated with one of the plurality of geographic metadata;

obtaining one or more labels indicating one or more object classes respectively for each image in the set of images;

determining a plurality of scores for two or more geographic metadata of the plurality of geographic metadata with respect to one object class of based at least in part on the one or more labels; and

determining a ranking among the two or more geographic metadata with respect to the one object class based at least in part on the plurality of scores.

10 . The system of claim 9 , wherein each geographic metadata of the plurality of geographic metadata includes a geohash.

11 . A system for image scoring, the system comprising:

one or more memories storing instructions thereon; and

one or more processors configured to execute the instructions and perform operations comprising:

receiving a plurality of images, each image of the plurality of images associated with a geographic metadata, the plurality of images associated with one or more geographic metadata;

selecting a first set of images and a second set of images from the plurality of images, each image in the first set of images being associated with a first geographic metadata that is one of the one or more geographic metadata, each image in the second set of images being associated with a second geographic metadata that is one of the one or more geographic metadata;

obtaining one or more first labels indicating one or more object classes respectively for each image in the first set of images and one or more second labels indicating the one or more object classes respectively for each image in the second set of images;

determining one or more first scores for the one or more object classes for the first geographic metadata based at least in part on the one or more first labels and one or more second scores for the one or more object classes for the second geographic metadata based at least in part on the one or more second labels; and

determining a ranking for one object class of the one or more object classes between the first geographic metadata and the second geographic metadata based at least in part on a first score of the one or more first scores corresponding to the one object class of the one or more object classes and a second score of the one or more second scores corresponding to the one object class of the one or more object classes.

12 . A system for image scoring, the system comprising:

one or more memories storing instructions thereon; and

one or more processors configured to execute the instructions and perform operations comprising:

receiving a plurality of images, each image of the plurality of images associated with a geographic metadata, the plurality of images associated with one or more geographic metadata;

selecting a first set of images and a second set of images from the plurality of images, each image in the first set of images being associated with a first geographic metadata that is one of the one or more geographic metadata, each image in the second set of images being associated with a second geographic metadata that is one of the one or more geographic metadata;

obtaining one or more first labels indicating one or more object classes respectively for each image in the first set of images and one or more second labels indicating the one or more object classes respectively for each image in the second set of images;

determining one or more first scores for the one or more object classes for the first geographic metadata based at least in part on the one or more first labels and one or more second scores for the one or more object classes for the second geographic metadata based at least in part on the one or more second labels;

receiving a plurality of unlabeled images and a request including an indication of an object class of interest; and

determining a plurality of geographic metadata associated with the plurality of unlabeled images, the plurality of geographic metadata including the first geographic metadata and the second geographic metadata.

13 . The system of claim 12 , the operations further comprising:

selecting one or more selected geographic metadata from the plurality of geographic metadata based at least in part on the one or more first scores and the one or more second scores.

14 . The system of claim 13 , wherein the selecting one or more selected geographic metadata from the plurality of geographic metadata comprises:

selecting the first geographic metadata if a first object score corresponding to the object class of interest is higher than a first threshold, wherein the first object score is one of the one or more first scores.

15 . The system of claim 14 , wherein the selecting one or more selected geographic metadata from the plurality of geographic metadata further comprises:

selecting the first geographic metadata if a second object score corresponding to an uninterested object class is lower than a second threshold, wherein the second object score is one of the one or more first scores.

16 . The system of claim 12 , the operations further comprising:

selecting a set of unlabeled images from the plurality of unlabeled images based at least in part on the one or more selected geographic metadata; and

transmitting an indication of the selected set of unlabeled images to an image labeling system.