System And Process For Detecting, Tracking And Counting Human Objects of Interest

• US 20110169917A1
• Filed: 11/09/2010
• Published: 07/14/2011
• Est. Priority Date: 01/11/2010
• Status: Abandoned Application

• Current Assignee: Shoppertrak RCT Corporation (Johnson Controls International plc)
• Original Assignee: Shoppertrak RCT Corporation (Johnson Controls International plc)
• Inventors: Farias, Jane, McNeill, David Patrick, Miglani, Rahul, Stephen, Anne Marie, Zaturenskiy, Mikhail, Kastilahn, William C., Wang, Zhiqian
• Application Number:
  US12/942,108
• Publication Number:
  US 20110169917A1
• Time in Patent Office: Days
• US Class Current: 348/46
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30242 Counting objects in image
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: H04N 13/204 using stereoscopic image cameras stereoscopic photography G03B35/00
• CPC Class Codes: H04N 2213/005 Aspects relating to the "3D+depth" image format
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

A system is disclosed that includes: at least one image capturing device at the entrance to obtain images; a reader device; and a processor for extracting objects of interest from the images and generating tracks for each object of interest, and for matching objects of interest with objects associated with RFID tags, and for counting the number of objects of interest associated with, and not associated with, particular RFID tags.

Claims

1. A system for separately counting and tracking defined objects and anonymous objects, including:

an image capturing device for capturing object data associated with both defined objects and anonymous objects that pass an entrance;

a reader device for capturing tag data for RFID tags associated with defined objects that pass the entrance;

a counting system for receiving object data and tag data, generating track records based on the object data and sequence records based on the tag data, identifying matching track records and sequence records and track records that do not match a sequence record, wherein the track records that match sequence records are associated with defined objects and the track records that do not match a sequence record are associated with anonymous objects, counting the defined objects and anonymous objects; and

tracking defined objects and anonymous objects.

2. The system described in claim 1, wherein the image capturing device is video-based.

3. The system described in claim 1, wherein the image capturing device includes a stereo camera.

4. The system described in claim 1, wherein the image capturing device includes two or more sensors.

5. The system described in claim 1, wherein the RFID tags may be active RFID tags.

6. The system described claim 5, wherein the RFID tags transmit their tag information at a fixed time interval.

7. The system described claim 6, wherein the fixed time interval is between 1 and 10 times per second.

8. The system described claim 1, wherein the RFID tag is self-powered.

9. The system described claim 1, wherein the RFID tag uses passive technology.

10. The system described claim 1, wherein the RFID tag uses ultrasonic signals.

11. The system described claim 1, wherein the RFID tag uses infrared signals.

12. The system described claim 1, wherein the counting system is in wired communication with the image capturing device or the reader device.

13. The system described claim 1, wherein the counting system is wirelessly connected to the image capturing device or the reader device.

14. The system described in claim 1, wherein the counting system, the image capturing device and the reader device are integrated into a single device.

15. The system described in claim 1, wherein the image capturing device and the reader device are mounted near an entrance to an enclosed space.

16. The system described in claim 1, wherein defined objects and anonymous objects are reported separately.

17. A method for counting and tracking defined objects and anonymous objects, comprising the steps of:

capturing object data with an image capturing device, wherein the object data is associated with both defined objects and anonymous objects that pass an entrance;

capturing tag data for RFID tags with a reader device, wherein the tag data is associated with defined objects that pass the entrance;

receiving object data and tag data at a counting system and generating track records based on the object data and sequence records based on the tag data;

identifying matching track records and sequence records, wherein matching track records and sequence records are representative of the defined objects and track records that do not match a sequence record are representative of the anonymous objects;

counting the defined objects and the anonymous objects; and

tracking the defined objects and the anonymous objects.

18. The method described in claim 17, wherein the image capturing device is video-based.

19. The method described in claim 17, wherein the image capturing device, the reader device and the counting system are wirelessly connected.

20. A method for separating defined objects and anonymous objects, comprising the following steps:

capturing object data with an image capturing device, wherein the object data is associated with both defined objects and anonymous objects that pass an entrance;

capturing tag data for RFID tags with a reader device, wherein the tag data is associated with defined objects that pass the entrance;

receiving object data and tag data at a counting system and generating track records based on the object data and sequence records based on the tag data, wherein each of the track records and sequence records include information indicative of a start time and an end time for the respective track record or sequence record;

identifying track records that overlap temporally with sequence records;

iteratively determining which overlapping track records and sequence records best match one another until all of the sequence records and track records have best matches or it is determined that no match exists; and

wherein track records that best match sequence records are defined objects and track records that do not match sequence records are anonymous objects.