Identifying objects tracked in images using active device

• US 20060133648A1
• Filed: 12/17/2004
• Published: 06/22/2006
• Est. Priority Date: 12/17/2004
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Crowley, James L., Ferrer-Biosca, Alba, Roulland, Frederic, Meunier, Jean-Luc
• Granted Patent: US 7,505,607 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: H04B 10/1149 Arrangements for indoor wireless networking of information

Abstract

Methods are disclosed for augmenting the identification of objects tracked in a sequence of images using active devices. In one embodiment, encoded information transmitted from active devices, such as a PDA, is decoded from the sequence of images to provide identifying information to a tracked region of interest. In another embodiment, motion information transmitted from active devices is associated with regions of interest tracked between images in the sequence of images. In a further embodiment, these embodiments operate together to minimize possible signal interference.

Claims

1. A method for identifying objects in a sequence of images, comprising:

receiving the sequence of images recorded using a camera having a field of view;

detecting regions of interest in the sequence of images including at least some the objects;

locating in the detected regions of interest encoded transmissions from active devices positioned in the field of view of the camera;

outputting the sequence of images while identifying at least some of the regions of interest using encoded transmission identified therein.

2. The method according to claim 1, wherein the encoded transmissions are transmitted from one or more mobile computing devices.

3. The method according to claim 1, wherein the object is a face.

4. The method according to claim 1, further comprising recording the sequence of images with a video camera.

5. The method according to claim 1, wherein said outputting labels at least one region of interest in the sequence of images with an identity corresponding to the encoded transmission.

6. The method according to claim 1, further comprising directing when the active devices transmit the encoded transmissions that are recorded in the sequence of images.

7. The method according to claim 6, further comprising:

filtering regions of interest in the sequence of images based on one or more filtering criteria to detect encoded transmissions from active devices; and

decoding the encoded transmissions to associate the regions of interest with an identity corresponding to the encoded transmissions.

8. The method according to claim 7, wherein said filtering maps a detected color arrangement to a black and white image.

9. The method according to claim 8, wherein the detected color arrangement records infrared frequencies.

10. The method according to claim 7, wherein said decoding decodes digital coded message data.

11. The method according to claim 7, wherein said decoding decodes one of time and frequency coded message data.

12. The method according to claim 7, wherein said decoding decodes message data after sequentially polling by one of an active device or a message bit.

13. The method according to claim 1, wherein the encoded transmission are detected according to assigned parameters that specify one or more of correct luminosity, size, shape, and distance.

14. The method according to claim 1, further comprising:

receiving motion information from active devices in the field of view of the camera;

associating the movement information from the active devices with the movement of the detected regions of interest between images in the sequence of images;

outputting the sequence of images while identifying at least some of the regions of interest using the motion information.

15. A method for identifying objects in a sequence of images, comprising:

receiving the sequence of images recorded using a camera having a field of view;

receiving motion information from active devices in the field of view of the camera;

detecting regions of interest in the sequence of images including at least some the objects;

associating the movement information from the active devices with the movement of the detected regions of interest between images in the sequence of images;

outputting the sequence of images while identifying at least some of the regions of interest using the motion information.

16. The method according to claim 15, further comprising:

locating in the detected regions of interest encoded transmissions from active devices positioned in the field of view of the camera; and

outputting the sequence of images while identifying at least some of the regions of interest using encoded transmission identified therein.

17. The method according to claim 16, wherein the encoded transmissions are transmitted from one or more mobile computing devices.

18. A method for identifying objects in a sequence of images, comprising:

receiving the sequence of images recorded using a camera having a field of view;

receiving motion information from active devices in the field of view of the camera;

detecting regions of interest in the sequence of images including at least some the objects;

locating in the detected regions of interest encoded transmissions from active devices positioned in the field of view of the camera;

associating the movement information from the active devices with the movement of the detected regions of interest between images in the sequence of images;

outputting the sequence of images while identifying at least some of the regions of interest using encoded transmission identified therein and at least some other of the regions of interest using the motion information.

19. The method according to claim 18, wherein the encoded transmissions are transmitted from one or more mobile computing devices.

20. The method according to claim 19, wherein the encoded transmissions are transmitted by the mobile computing devices as infrared transmissions.