Collaborative tracking

• US 8,243,989 B2
• Filed: 12/12/2008
• Issued: 08/14/2012
• Est. Priority Date: 12/20/2007
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Vendrig, Jeroen
• Primary Examiner(s): Bhatnagar, Anand
• Application Number:
  US12/334,129
• Publication Number:
  US 20090169053A1
• Time in Patent Office: 1,341 Days
• Field of Search: 382/100, 382/103, 382/106, 382/107, 348/135, 348/154, 348/155, 348/156, 348/157, 348169-172, 342/89, 342/90
• US Class Current: 382/103
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image

Abstract

Disclosed is a system (200) and method (101) for collaborative tracking of an object, the method comprising updating (105) the track with an object measurement using a camera tracking module (230), determining (110) a track quality measure for the updated track, based on the track quality measure, determining (120) whether a second tracking module (260), remotely located from the camera, should be applied, if the second tracking module (260) is to be applied, selecting (130) data describing the track and the object, transmitting (140) the selected data to the second tracking module over a network (240) that imposes constraints of bandwidth and/or latency, and applying (150) the second tracking module (260) to determine the next position of the object in the track.

Claims

1. A method of predicting the next position of an object in a track, said method comprising the steps of:

(a) determining an object track comprising at least a history of object position;

(b) determining, using a processing module on an image capture device, (i) a first prediction for a next position for the object track, based on the history of object positions, and (ii) a confidence score for the prediction; and

(c) based on the confidence score transmitting, over a network, at least the object track to a second processing module on a device remote from the image capture device.

2. A method according to claim 1, wherein the network imposes constraints of at least one of bandwidth and latency.

3. A method of determining the next position of an object in a track, said method comprising the steps of:

(a) updating a track using a first tracking module;

(b) determining a track quality measure for the updated track;

(c) based on the track quality measure, determining whether a second tracking module, remotely located from the first tracking module, should be applied;

(d) if the second tracking module is to be applied;

(i) selecting data describing the track and the object;

(ii) transmitting the selected data to the second tracking module over a network; and

(iii) applying the second tracking module to determine the next position of the object in the track.

4. A method according to claim 3, comprising the further steps of:

(a) transmitting the next position to the first tracking module; and

(b) updating the track maintained by the first tracking module with the position determined by the second tracking module.

5. A method according to claim 3, where the track quality measure is determined based on the difference between measurements and predictions.

6. A method according to claim 3, comprising the further step of:

based on the track quality measure, determining whether a signature of the tracked object should be stored.

7. A method, in a system comprising an image capture device and a remote device able to communicate with the image capture device over a network, for allocating object tracking resources on the remote device, said method comprising the steps of:

(a) receiving, from a tracking module in the image capture device, a track quality measure value and data describing the corresponding track and corresponding object; and

(b) based on the track quality measure, allocating an object tracking resource on the remote device to determine the track of the object using the track and object data.

8. A method according to claim 7, comprising the further step of:

deallocating the object tracking resource used for an object track with a higher track quality measure value.

9. A system for determining the next position of an object in a track, said system comprising:

a plurality of memory modules for storing a corresponding plurality of program modules; and

a plurality of processors for executing the program modules, wherein the plurality of memory modules and the associated plurality of processors can communicate over a network, the program modules comprising;

(a) code for updating a track with an object measurement using a first tracking module;

(b) code for determining a track quality measure for the updated track;

(c) code for, based on the track quality measure, determining whether a second tracking module, remotely located from the first tracking module, should be applied;

(d) code for, if the second tracking module is to be applied;

(i) selecting data describing the track and the object;

(ii) transmitting the selected data to the second tracking module over a network that imposes constraints of at least one of bandwidth and latency; and

(iii) code for applying the second tracking module to determine the next position of the object in the track.

10. A non-transitory computer readable storage medium having recorded thereon a computer program for directing a processor to execute a method for determining the next position of an object in a track, the computer program comprising:

(a) code for updating a track with an object measurement using a first tracking module;

(b) code for determining a track quality measure for the updated track;

(c) code for, based on the track quality measure, determining whether a second tracking module, remotely located from the first tracking module, should be applied;

(d) code for, if the second tracking module is to be applied;

(i) selecting data describing the track and the object;

(ii) transmitting the selected data to the second tracking module over a network; and

(iii) code for applying the second tracking module to determine the next position of the object in the track.