SYSTEM AND METHOD FOR LARGE SCALE CROWDSOURCING OF MAP DATA CLEANUP AND CORRECTION

• US 20160004724A1
• Filed: 04/07/2015
• Published: 01/07/2016
• Est. Priority Date: 02/19/2013
• Status: Active Grant

• Current Assignee: Maxar Intelligence Incorporated (Galileo Parent, Inc.)
• Original Assignee: DigitalGlobe, Inc. (Galileo Parent, Inc.)
• Inventors: Har-Noy, Shay, Barrington, Luke, Ricklin, Nathan
• Granted Patent: US 10,083,186 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/587 using geographical or spatial information, e.g. location
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A system for large-scale crowd sourcing of map data cleanup and correction, comprising an application server that generates image data, sends image data to a user device, receives tagging data provided by the device user, and provides tags to a crowdsourced search and locate server based on tagging data from a user device, a crowdsourced search and locate server that receives tags from an application server, computes agreement and disagreement values and performs expectation-maximization analysis, and a map data server that stores and provides map data, and a method for estimating location and quality of a set of geolocation data.

Claims

1. A system for large-scale crowd sourcing of map data cleanup and correction, comprising:

an application server comprising a plurality of programming instructions stored in a memory operating on a network-connected computing device and adapted to receive at least a plurality of input data from a plurality of user devices, generate image data based at least in part on map data received from a map data server, send at least a portion of image data to a user device based at least in part on the generated image data, receive input from the user device comprising at least a plurality of tagging data provided by the device user, and provide at least a plurality of tags to a crowdsourced search and locate server, the tags being based at least in part on received tagging data from at least a user device;

a crowdsourced search and locate server comprising a plurality of programming instructions stored in a memory operating on a network-connected computing device and adapted to receive at least a plurality of tags from an application server, compute agreement and disagreement values for at least a portion of the plurality of tags, perform at least an expectation-maximization analysis process based at least in part on the computed values; and

a map data server comprising a plurality of programming instructions stored in a memory operating on a network-connected computing device and adapted to store and provide map data.

2. The system of claim 1, wherein the image portions contain at least a three-dimensional viewable images of said area, aiding crowdsourcing participants to better recognize difficult objects.

3. The system of claim 1, further comprising a client interface application comprising a plurality of programming instructions stored in a memory operating on a network-attached computer and adapted to display a plurality of interactive elements to a user, receive input from the user, and provide the results of the input to the application server.

4. The system of claim 3, wherein the crowdsourced search and locate server provides analysis results to the client interface application for display to a user.

5. A method for conducting crowdsourced search and locate operations, comprising the steps of:

receiving, at an application server, a plurality of communication connections from a plurality of user devices via a communication network;

navigating a to a specific geospatial location based at least in part on input received from a first user device;

sending an image corresponding to the geospatial location to the first user device; and

receiving tagging data from the first user device, the tagging data corresponding to a plurality of objects and locations identified by the user of the device.

6. A method for estimating location and quality of a set of geolocation data, comprising the steps of:

receiving, at a crowdsourced search and locate server, a plurality of tags;

computing agreement and disagreement values for at least a portion of the tags;

computing maximum likelihood values for at least a portion of the tags, the likelihood values being based at least in part on the computed agreements and disagreement values;

merging a plurality of vectors based at least in part on the computed likelihood values; and

producing final tag and vector values based at least in part on the results of analysis performed in previous steps.

7. The method of claim 6, further comprising the steps of:

iteratively performing analysis over a plurality of tags and values; and

when a threshold is reached, stopping iteration and producing final values.

8. The method of claim 7, wherein the threshold is based at least in part on the quantity of data remaining for analysis.

9. The method of claim 7, wherein the threshold is based at least in part on a value configured by a user.