COLLABORATIVE FEATURE EXTRACTION SYSTEM FOR THREE DIMENSIONAL DATASETS
First Claim
Patent Images
1. A collaborative feature extraction system, comprising:
- a knowledge base containing a first dataset, the first dataset comprising parameters that are associated with one or more assets;
a second dataset, the second dataset comprising three-dimensional data representing a geographic area and one or more candidate objects within the geographic area;
a processor in electronic communication with the knowledge base; and
a computer-readable medium containing programming instructions that, when executed, cause the processor to;
analyze the three-dimensional dataset to identify one of the candidate objects as a selected one of the assets by comparing the second set of data with one or more of the parameters in the first dataset;
output, to a user, a first image representing the identified candidate object and a user prompt;
in response to the user prompt, receive a user response indicating whether the selected asset matches the identified candidate object; and
update the knowledge base by adjusting one or more of the parameters associated with the selected asset based on the user response.
2 Assignments
0 Petitions
Accused Products
Abstract
A collaborative feature extraction system uses crowdsourced feedback to improve its ability to recognize objects in three-dimensional datasets. The system accesses a three-dimensional dataset and presents images showing possible objects to a group of users, along with potential identifiers for the objects. The users provide feedback as to the accuracy of the identifiers, and the system uses the feedback to adjust parameters for candidate identifiers to improve its recognition of three-dimensional assets in future iterations.
41 Citations
20 Claims
-
1. A collaborative feature extraction system, comprising:
-
a knowledge base containing a first dataset, the first dataset comprising parameters that are associated with one or more assets; a second dataset, the second dataset comprising three-dimensional data representing a geographic area and one or more candidate objects within the geographic area; a processor in electronic communication with the knowledge base; and a computer-readable medium containing programming instructions that, when executed, cause the processor to; analyze the three-dimensional dataset to identify one of the candidate objects as a selected one of the assets by comparing the second set of data with one or more of the parameters in the first dataset; output, to a user, a first image representing the identified candidate object and a user prompt; in response to the user prompt, receive a user response indicating whether the selected asset matches the identified candidate object; and update the knowledge base by adjusting one or more of the parameters associated with the selected asset based on the user response. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 17)
-
-
11. A method comprising, by a processor:
-
accessing a knowledge base containing a first dataset, the first dataset comprising parameters that are associated with one or more assets; accessing a second dataset comprising three-dimensional data representing a geographic area and one or more candidate objects within the geographic area; analyzing the three-dimensional dataset to identify one of the candidate objects as a selected one of the assets by comparing the second set of data with one or more of the parameters in the first dataset; outputting a first image representing the identified candidate object, a representation of selected asset and a user prompt; receiving a user response indicating whether the identified candidate objects matches the selected asset; and updating the knowledge base by adjusting one or more of the parameters associated with the selected asset based on the user response. - View Dependent Claims (12, 13, 14, 15, 16, 18)
-
-
19. A non-transitory computer-readable medium containing programming instructions for causing a processor to:
-
access a knowledge base containing a first dataset, the first dataset comprising parameters that are associated with one or more assets; access a second dataset comprising three-dimensional data representing a geographic area and one or more candidate objects within the geographic area; analyze the three-dimensional dataset to identify one of the candidate objects as a selected one of the assets by comparing the second set of data with one or more of the parameters in the first dataset; output a first image representing the identified candidate object and a user prompt; receiving a plurality of user responses indicating whether the identified candidate object matches the selected asset; and updating the knowledge base by adjusting one or more of the parameters associated with the selected asset based on the user responses so that either or both one of an intensity parameter and a color parameter is adjusted. - View Dependent Claims (20)
-
Specification