US8385658B2 — Detecting an object in an image using multiple te…

Claim 1

Independent Claim 169 words

A method for processing image data, comprising: obtaining an image of a live event, the image of the live event is captured by at least one camera and comprises a representation of an object in the live event; obtaining a first template comprising pixel data of the object from a prior image, taken prior to the image of the live event; obtaining a second template comprising a 3d model of the object; determining a first position of the representation of the object in the image of the live event, the first position is based on a correlation of the first template with the image of the live event; determining a second position of the representation of the object in the image of the live event, the second position is based on a correlation of the second template with the image of the live event; and determining a position of the representation of the object in the image of the live event which is between the first and second positions.

Claim 2

Independent Claim 169 words

A method for processing image data, comprising: obtaining an image of a live event, the image of the live event is captured by at least one camera and comprises a representation of an object in the live event; obtaining a first template comprising pixel data of the object from a prior image, taken prior to the image of the live event; obtaining a second template comprising a 3d model of the object; determining a first position of the representation of the object in the image of the live event, the first position is based on a correlation of the first template with the image of the live event; determining a second position of the representation of the object in the image of the live event, the second position is based on a correlation of the second template with the image of the live event; and determining a position of the representation of the object in the image of the live event which is between the first and second positions.

Claim 3

Dependent Claim 22 words

The method of claim 1 , wherein: the first template comprises at least one of monochrome data, chrominance data or luminance data.

Claim 4

Dependent Claim 23 words

The method of claim 1 , wherein: the 3d model mimics an appearance of the object including a paint scheme of the object.

Claim 5

Dependent Claim 19 words

The method of claim 1 , wherein: the 3d model is rendered based on an orientation of the object.

Claim 6

Dependent Claim 24 words

The method of claim 1 , wherein: the 3d model comprises a predetermined static texture which is based on an appearance of the object.

Claim 7

Dependent Claim 30 words

The method of claim 1 , wherein: the 3d model comprises a texture which is obtained during the live event from at least one prior image of the live event.

Claim 8

Dependent Claim 105 words

The method of claim 1 , wherein: the first template is correlated with different candidate representations of the object in a first search area of the image of the live event, the second template is correlated with different candidate representations of the object in a second search area of the image of the live event which is different than the first search area, and the second search area of the image of the live event is smaller than, and at least partially within, the first search area, and is defined based on a result of the first template being correlated in the first search area.

Claim 9

Dependent Claim 44 words

The method of claim 1 , wherein the position of the representation of the object in the image of the live event which is between the first and second positions is based on respective weights which are assigned to the first and second positions.

Claim 10

Dependent Claim 21 words

The method of claim 8 , wherein: the weights are assigned based on reliabilities associated with the first and second positions.

Claim 11

Dependent Claim 44 words

The method of claim 1 , further comprising: updating sensor and/or registration data of the at least one camera based on the position of the representation of the object in the image of the live event which is between the first and second positions.

Claim 12

Dependent Claim 46 words

The method of claim 1 , further comprising: determining an update to a location of the object in the live event based on the position of the representation of the object in the image of the live event which is between the first and second positions.

Claim 13

Dependent Claim 111 words

The method of claim 1 , further comprising: combining a graphic with the image of the live event, the graphic is located in the image of the live event based on the position of the representation of the object in the image of the live event which is between the first and second positions, the image of the live event is part of a video broadcast of the live event, the graphic is combined with the image of the live event substantially in real time, and the graphic is located in the image of the live event based on at least one of an orientation or a perspective of the object.

Claim 14

Independent Claim 182 words

A system for processing image data, comprising: at least one camera for capturing an image of a live event, the image of the live event comprises a representation of an object in the live event; and at least one processing facility which receives the image, the at least one processing facility: obtains a first template comprising pixel data of the object from a prior image, taken prior to the image of the live event, obtains a second template comprising a 3d model of the object, determines a first position of the representation of the object in the image of the live event, the first position is based on a correlation of the first template with the image of the live event, determines a second position of the representation of the object in the image of the live event, the second position is based on a correlation of the second template with the image of the live event, and determines a position of the representation of the object in the image of the live event which is between the first and second positions.

Claim 15

Independent Claim 182 words

A system for processing image data, comprising: at least one camera for capturing an image of a live event, the image of the live event comprises a representation of an object in the live event; and at least one processing facility which receives the image, the at least one processing facility: obtains a first template comprising pixel data of the object from a prior image, taken prior to the image of the live event, obtains a second template comprising a 3d model of the object, determines a first position of the representation of the object in the image of the live event, the first position is based on a correlation of the first template with the image of the live event, determines a second position of the representation of the object in the image of the live event, the second position is based on a correlation of the second template with the image of the live event, and determines a position of the representation of the object in the image of the live event which is between the first and second positions.

Claim 16

Independent Claim 121 words

A method for processing image data, comprising: obtaining an image of a live event which is captured by at least one camera, the live event including an object; detecting a position of a representation of the object in the image based on matching using a first template; detecting a set of positions of a representation of the object in the image based on matching using a second template, each position in the set of positions being characterized by an associated correlation with the second template and an associated distance from the position detected based on the matching using the first template; and selecting one of the positions in the set of positions based on the associated correlation and the associated distance.

Claim 17

Independent Claim 121 words

A method for processing image data, comprising: obtaining an image of a live event which is captured by at least one camera, the live event including an object; detecting a position of a representation of the object in the image based on matching using a first template; detecting a set of positions of a representation of the object in the image based on matching using a second template, each position in the set of positions being characterized by an associated correlation with the second template and an associated distance from the position detected based on the matching using the first template; and selecting one of the positions in the set of positions based on the associated correlation and the associated distance.

Claim 18

Dependent Claim 33 words

The method of claim 14 , wherein: the selecting comprises selecting one of the positions in the set of positions which has a satisfactorily high associated correlation and a satisfactorily low associated distance.

Claim 19

Dependent Claim 82 words

The method of claim 14 , wherein: the selecting comprises determining a value of a function, w 1 *correlation+w 2 *(1-dist/maxdist), for each of the positions in the set of positions, where w 1 and w 2 are weights, correlation is the associated correlation, dist is the associated distance, as a Euclidean distance, and maxdist is a maximum of the Euclidean distances, and selecting one of the positions in the set of positions for which the value of the function is highest.

Claim 20

Dependent Claim 25 words

The method of claim 14 , wherein: the first template comprises a video template, and the second template comprises an edge and morphology based template.

Claim 21

Dependent Claim 58 words

The method of claim 14 , further comprising: combining a graphic with the image, the graphic is located in the image based on the selected one of the positions in the set of positions, the image is part of a video broadcast of the live event, and the graphic is combined with the image substantially in real time.

Claim 22

Dependent Claim 32 words

The method of claim 14 , further comprising: updating sensor and/or registration data of the at least one camera based on the selected one of the positions in the set of positions.

Claim 23

Independent Claim 144 words

A system for processing image data, comprising: at least one camera for capturing an image of a live event, the image of the live event comprises a representation of an object in the live event; and at least one processing facility which receives the image, the at least one processing facility: detects a position of a representation of the object in the image based on matching using a first template, detects a set of positions of a representation of the object in the image based on matching using a second template, each position in the set of positions being characterized by an associated correlation with the second template and an associated distance from the position detected based on the matching using the first template, and selects one of the positions in the set of positions based on the associated correlation and the associated distance.

Claim 24

Independent Claim 144 words

A system for processing image data, comprising: at least one camera for capturing an image of a live event, the image of the live event comprises a representation of an object in the live event; and at least one processing facility which receives the image, the at least one processing facility: detects a position of a representation of the object in the image based on matching using a first template, detects a set of positions of a representation of the object in the image based on matching using a second template, each position in the set of positions being characterized by an associated correlation with the second template and an associated distance from the position detected based on the matching using the first template, and selects one of the positions in the set of positions based on the associated correlation and the associated distance.

Claim 25

Dependent Claim 35 words

The system of claim 20 , wherein: at least one processing facility selects one of the positions in the set of positions which has a satisfactorily high associated correlation and a satisfactorily low associated distance.

Claim 26

Dependent Claim 85 words

The system of claim 20 , wherein: at least one processing facility determines a value of a function, w 1 *correlation+w 2 * (1-dist/maxdist), for each of the positions in the set of positions, where w 1 and w 2 are weights, correlation is the associated correlation, dist is the associated distance, as a Euclidean distance, and maxdist is a maximum of the Euclidean distances, and selects one of the positions in the set of positions for which the value of the function is highest.

Claim 27

Dependent Claim 25 words

The system of claim 20 , wherein: the first template comprises a video template, and the second template comprises an edge and morphology based template.

Claim 28

Dependent Claim 23 words

The system of claim 13 , wherein: the 3d model mimics an appearance of the object including a paint scheme of the object.

Claim 29

Dependent Claim 42 words

The system of claim 13 , wherein: the position of the representation of the object in the image of the live event which is between the first and second positions is based on different weights assigned to the first and second positions.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2016-02-26	2016-08-27	2017-02-26	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2020-02-26	2020-08-27	2021-02-26	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2024-02-26	2024-08-27	2025-02-26	$7700.00	Window Closed / Lapsed

Detecting an object in an image using multiple templates

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag