Object recognition and tracking system

• US 6,754,368 B1
• Filed: 07/27/2001
• Issued: 06/22/2004
• Est. Priority Date: 02/01/1999
• Status: Expired due to Term

• Current Assignee: Magnolia Star Pty Ltd.
• Original Assignee: Beonic Corporation Pty Limited
• Inventors: Cohen, Peter
• Primary Examiner(s): Johns, Andrew W.
• Application Number:
  US09/890,241
• Time in Patent Office: 1,061 Days
• Field of Search: 382/100, 382/103, 382/104, 382/191, 382/286, 382/291, 382/318, 348/135, 348/143, 348/144, 348/148, 348/149, 348/150, 348/152, 348/153, 348/159, 342/23, 342/27, 367/93, 250/203.1, 250/203.2, 250/DIG.1
• US Class Current: 382/103
• CPC Class Codes: G01S 13/04 Systems determining presence of a target based on relative movement of target G01S13/56
• CPC Class Codes: G01S 13/66 Radar-tracking systems; Analogous systems
• CPC Class Codes: G01S 13/70 for range tracking only
• CPC Class Codes: G01S 13/87 Combinations of radar systems, e.g. primary radar and secondary radar
• CPC Class Codes: G01S 13/89 for mapping or imaging
• CPC Class Codes: G01S 7/4008 of transmitters
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

An object recognition and tracking system having detector arrays (60, 70), each detector array (60, 70) including a first type of detector (95) and a second type of detector (96). The first type of detector (95) detects the presence of an object such as by changing contrast boundaries and hence objects (91, 92) that move in a detector space (90) and the second type of detector (96) focuses in on the defined object (91, 92) and to recognize, identify or record it. The detectors (95, 96) may be video, radar, microwave, radio frequency, infrared, millimeter wave, or transponder interrogators or a combination of these. Tracking of objects (91, 92) between adjoining detector spaces (90, 90) may also be done.

Claims

1. An object recognition and tracking system including at least one detector array, the or each detector array including a first type of detector and a second type of detector, the first type of detector being adapted to detect the presence of an object in a detector space and to define the object'"'"'s position, the second type of detector being adapted to use the defined object position to identify or recognize the object or to count or to record the presence of the object if it is of a selected type, the first detector and the second detector being the same detector, the second detector focussing or operating at a higher resolution than the first detector.

2. An object recognition and tracking system as in claim 1 wherein the presence of an object as determined by the first detector may be detected by a change in contrast boundaries or by a change in pattern or by movement and hence to detect objects that move within the detector space.

3. An object recognition and tracking system as in claim 1 wherein the detector array is adapted to use a portion of the electromagnetic spectrum selected from radar, microwave, radio frequency, infrared, microwave, millimeter wave or light or to use sonar or some other detection system.

4. An object recognition and tracking system as in claim 1 wherein the first and second types of detectors are provided by a single video detector the observed image of which is handled in two different ways, in a first way the observed image may be digitised and the sequential images scanned to detect changes in the digitised image over successive frames which would indicate the presence of an object and in a second way the same digital image can then be analysed in more detail in a particular region of the detector space.

5. An object recognition and tracking system as in claim 1 wherein the second type of detector is adapted to use subsequent or previous frames to improve the recognition or result with respect to the object of interest.

6. An object recognition and tracking system as in claim 1 wherein one or more of characteristics such as mass, height, shape, contrast, brightness, colour, patterns, velocity, heat, reflectivity, signature are used to define and identify an object.

7. An object recognition and tracking system as in claim 1 further including artificial intelligence to assist with defining or identifying an object.

8. An object recognition and tracking system as in claim 1 further including a third stage of the system performed by a tracking engine being adapted to track a defined object.

9. An object recognition and tracking system as in claim 1 further including multiple detector arrays and multiple detector spaces.

10. An object recognition and tracking system as in claim 9 further including means to communicate between detector arrays to hand over tracking of a selected object from one detector space.

11. An object recognition and tracking system as in claim 10 wherein the means to communicate between detector arrays includes means to pass information to successive detectors or other third party devices requiring such information to activate as necessary programmed actions without human intervention.

12. An object recognition and tracking system as in claim 1 further including means to take into account the angle of the object from the detector array.

13. An object recognition and tracking system as in claim 1 wherein the or each detector array is mounted substantially over its respective detection space.

14. An object recognition and tracking system as in claim 1 wherein the or each detector array is mounted to a side of its respective detection space.

15. An object recognition and tracking system as in claim 1 used for counting people in supermarkets or the like or for traffic traveling along a road, for security monitoring and surveillance applications and to determine patterns or trends from seemingly random movements over time such as when walking through a shop or display areas.

16. An object recognition and tracking system as in claim 1 used on a moving vehicle to detect objects which are relatively stationary with respect to the vehicle.