Granted Patent B2

US 10,176,194 · App. 15/077,886 · Granted Jan 8, 2019

Abstract

Claims (32)

1. A crowdsourced search and locate platform, comprising:

an application server comprising at least a processor, a memory, and a plurality of programming instructions stored in the memory and operating on the processor, wherein the programming instructions, when operating on the processor, cause the processor to

select an orthomosaic image of a portion of the Earth's surface corresponding to a particular geographic location;

automatically select a plurality of smaller images each drawn from a portion of the orthomosaic image, at least a portion of the plurality of images being selected such that, when combined, they cover a particular area of interest;

transmit, over a network, at least a portion of the plurality of smaller images to each of at least two user devices;

receive, over the network, tagging data from at least one of the user devices, the tagging data corresponding to a plurality of objects and locations identified by the user of the device; and

a crowdrank server comprising at least a processor, a memory, and a plurality of programming instructions stored in the memory and operating on the processor, wherein the programming instructions, when operating on the processor, cause the processor to:

receive tagging data corresponding to a plurality of objects and locations from an application server;

compute agreement and disagreement values for at least a portion of the tagging data;

perform at least an expectation-maximization analysis process based at least in part on the computed values, taking into account any available accuracy reliability rankings that each participant may accrue during any of a plurality of crowdsourcing campaigns;

determine specific geospatial images that are shown to a next crowdsourcing participant based upon the identification confidence levels of the objects within those images and a calculated reliability score accrued by that crowdsourcing participant; and

provides resulting output values corresponding to geolocations of objects of a plurality of types and an identification confidence level for each reported object in a pre-determined output format.

2. The system of claim 1 , wherein an identified object is tagged by a single point on the image.

3. The system of claim 1 , wherein an identified object is tagged by being circumscribed with a polygon on the image.

4. The system of claim 1 , wherein at least one new crowdsource participant is given geospatial images where the features to be identified are well known for both location and type to determine the reliability parameters of the participant to be used later in the current crowdsourcing campaign and in future crowd sourcing campaigns.

5. The system of claim 1 where a plurality one crowdsource participant of known high reliability will be shown geospatial images where features low confidence concerning their exact location, existence or identification type are present to improve study confidence.

6. The system of claim 1 , wherein the at least one crowdsourcing participant may be tasked to identify objects in images known devoid of objects so as to establish a reliability score to be used later in the current crowdsourcing campaign and in future crowdsourcing campaigns.

7. The system of claim 1 where a plurality one crowdsource participant of known high reliability will be shown geospatial images where features low confidence concerning their exact location, existence or identification type are present to improve study confidence.

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

(a) receiving, at an application server, connections from a plurality of crowdsourcing participants;

(b) navigating a first crowdsourcing participant to a particular geographic location possibly based upon the identification confidence level of objects previously tagged within the geospatial location and the user reliability score of the first crowdsourcing participant as calculated by a crowdrank server stored and operating on a network-attached computer;

(c) selecting an orthomosaic image of a portion of the Earth's surface corresponding to the particular geographic location;

(d) automatically selecting a plurality of smaller images each drawn from a portion of the orthomosaic image, at least a portion of the plurality of images being selected such that, when combined, they cover a particular area of interest;

(e) transmitting, over a network, at least a portion of the plurality of smaller images to each of at least two user devices;

(f) receiving tagging data from the first crowdsourcing participant, the tagging data corresponding to a plurality of objects and locations identified by the first crowdsourcing participant;

(g) retrieving, at the crowdrank server, a plurality of tags made by participating users by repeated carrying out of steps (a) through (d);

(h) computing agreement and disagreement values for each of the plurality of retrieved tags taking into account the accrued accuracy scores of each of the crowdsourcing participants;

(i) performing an expectation-maximization or expectation-minimization process iteratively until a configured maximum number of iterations is performed or until an indicia of rate of change between iterations falls below a configured threshold; and

(j) providing resulting output values corresponding to geolocations of objects of a plurality of types, with computed identification confidence scores for those objects in a pre-determined format.

9. The method of claim 8 , wherein an identified object is tagged by a single point on the image.

10. The method of claim 8 , wherein an identified object is tagged by being circumscribed with a polygon on the image.

11. The method of claim 8 , wherein at least one new crowdsource participant is given geospatial images where the features to be identified are well known for both location and type to determine the reliability parameters of the participant.

Assignments (21)