Detecting an object in an image using camera registration data indexed to location or camera sensors

Claim 3

The method of claim 1 , further comprising: determining a search area in the additional image based on the estimate of the position; and detecting the representation of the object in the search area.

Claim 4

The method of claim 2 , further comprising: determining and storing an update to the updated registration data based on a position of the representation of the object in the search area.

Claim 5

The method of claim 1 , wherein: each entry indexes the updated registration data to the time-varying sensor data of the camera.

Claim 6

The method of claim 4 , wherein: the time-varying sensor data comprises at least one of time-varying tilt and zoom of the camera.

Claim 7

The method of claim 1 , wherein: the different locations and the location along the circuit during the subsequent traversal of the circuit, are determined using GPS data.

Claim 8

The method of claim 1 , wherein: the different locations and the location along the circuit during the subsequent traversal of the circuit, are determined using radio data by at least one of multi-angulation and multi-lateration.

Claim 9

The method of claim 1 , wherein: the different locations and the location along the circuit during the subsequent traversal of the circuit, are determined using at least one of a time and a distance since the object passed a known location in the live event.

Claim 10

The method of claim 1 , wherein: the different locations are designated locations around the circuit.

Claim 11

The method of claim 1 , further comprising: transforming, using the updated registration data for the additional image, a determined position of the representation of the object in the additional image to a location in the live event.

Claim 12

The method of claim 10 , further comprising: determining an inaccuracy between: a) a location of the object in the live event which is determined independently from the determined position and b) the location which is determined based on the transforming; and applying a correction to location data of the object based on the determined inaccuracy.

Claim 13

The method of claim 1 , wherein: the updated registration data comprises updates to registration parameters of the camera.

Claim 14

The method of claim 1 , wherein: the updated registration data comprises registration parameters of the camera.

Claim 15

The method of claim 1 , wherein: the determining the estimate comprises transforming location data of the object in the live event to a coordinate system of the image using the updated registration data for the additional image.

Claim 16

The method of claim 1 , further comprising: combining a graphic with the additional image, the graphic is located in the additional image based on a determined position of the representation of the object in the additional image.

Claim 17

The method of claim 1 , further comprising: combining a graphic with the additional image, the graphic is located in the additional image based on an orientation of the object.

Claim 18

The method of claim 1 , further comprising: combining a graphic with the additional image, the graphic is located in the additional image based on a perspective of the object.

Claim 19

The method of claim 1 , wherein: the object comprises a vehicle and the circuit is a race track.

Claim 20

The method of claim 1 , wherein: the updated registration data indicates tilt offset of the camera.

Claim 21

The method of claim 1 , wherein: the updated registration data indicates at least one of a zoom field of view map, a camera position, a lens distortion and a focus.

Claim 22

The method of claim 1 , wherein: the obtaining images is performed periodically, once per a time interval which is greater than a time interval at which images are captured by the camera.

Claim 25

The system of claim 22 , wherein: the movement of the camera comprises a pan of the camera to follow the object at the different locations along the circuit; and for each image obtained during the one traversal of the circuit, the time-varying sensor data of the camera comprises time-varying panning data based on the pan, and the updated camera registration data comprises an adjusted panning offset to the time-varying panning data.

Claim 26

A processor readable storage device comprising processor readable code embodied thereon for programming a processor to perform a method for processing image data of a live event in which an object repeatedly traverses a circuit, the method comprising: obtaining images of the live event when the object is at different locations along the circuit during one traversal of the circuit, the images are captured by panning a camera as the object moves to the different locations; for each image obtained during the one traversal of the circuit: (a) obtaining time-varying sensor data of the camera comprising time-varying panning data based on the panning, (b) determining a detected position of a representation of the object in the image, (c) determining a corresponding one of the different locations along the circuit using a location detection technique which is independent of the image, (d) determining an expected position of a representation of the object in the image based on the corresponding one of the different locations, (e) determining an inaccuracy between the detected position and the expected position, and (f) based on the inaccuracy, providing updated registration data of the camera comprising an adjusted panning offset to the time-varying panning data; for each location of the different locations during the one traversal of the circuit, storing an entry which indexes the updated registration data to the location; obtaining an additional image of the live event which is captured by the camera when the object is at a location along the circuit during a subsequent traversal of the circuit; determining one of the different locations during the one traversal of the circuit which is closest to the location along the circuit during the subsequent traversal of the circuit, by panning the camera to follow the object, the location of the object along the circuit during the subsequent traversal of the circuit is determined using a location detection technique which is independent of the additional image; retrieving the updated registration data from one of the entries which is indexed to the one of the different locations; and responsive to the retrieving, determining an estimate of a position of a representation of the object in the additional image.

Claim 27

A processor readable storage device comprising processor readable code embodied thereon for programming a processor to perform a method for processing image data of a live event in which an object repeatedly traverses a circuit, the method comprising: obtaining images of the live event when the object is at different locations along the circuit during one traversal of the circuit, the images are captured by panning a camera as the object moves to the different locations; for each image obtained during the one traversal of the circuit: (a) obtaining time-varying sensor data of the camera comprising time-varying panning data based on the panning, (b) determining a detected position of a representation of the object in the image, (c) determining a corresponding one of the different locations along the circuit using a location detection technique which is independent of the image, (d) determining an expected position of a representation of the object in the image based on the corresponding one of the different locations, (e) determining an inaccuracy between the detected position and the expected position, and (f) based on the inaccuracy, providing updated registration data of the camera comprising an adjusted panning offset to the time-varying panning data; for each location of the different locations during the one traversal of the circuit, storing an entry which indexes the updated registration data to the location; obtaining an additional image of the live event which is captured by the camera when the object is at a location along the circuit during a subsequent traversal of the circuit; determining one of the different locations during the one traversal of the circuit which is closest to the location along the circuit during the subsequent traversal of the circuit, by panning the camera to follow the object, the location of the object along the circuit during the subsequent traversal of the circuit is determined using a location detection technique which is independent of the additional image; retrieving the updated registration data from one of the entries which is indexed to the one of the different locations; and responsive to the retrieving, determining an estimate of a position of a representation of the object in the additional image.