Person/object image and screening

• US 8,300,890 B1
• Filed: 06/25/2009
• Issued: 10/30/2012
• Est. Priority Date: 01/29/2007
• Status: Active Grant

• Current Assignee: IntelliVision Technologies Corp. (Melrose Industries Plc)
• Original Assignee: IntelliVision Technologies Corp. (Melrose Industries Plc)
• Inventors: Gaikwad, Deepak, Gope, Chandan, Nathan, Vaidhi, Walimbe, Radhika
• Primary Examiner(s): PERUNGAVOOR, SATHYANARAYA V
• Application Number:
  US12/459,073
• Time in Patent Office: 1,223 Days
• Field of Search: 382/103
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• 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: H04N 5/144 Movement detection for video coding H04N19/503; analysis of motion in general G06T7/20
• CPC Class Codes: H04N 5/272 Means for inserting a foreground image in a background image, i.e. inlay, outlay

Abstract

A first set of unknown pixels is determined for which being located in the foreground portion does not in-and-of-itself determine the pixel to be part of the foreground. A second set of unknown pixels is determined for which being in a current background portion does not in-and-of-itself determine the pixel to be part of the background. A determination is made for the first and second set of unknown pixels whether the pixel is part of the background or foreground based on temporal data. Extracting an image of the foreground that does not include the current background based on the determination of whether the pixel is part of the foreground, the current background, and temporal data. In an embodiment, the system can use multiple types of sensors to determine whether an entity is a likely security risk.

Claims

1. A hardware system comprising:

one or more sensors, which includes a sensor to capture video frames;

a processor system having one or more processors;

a memory system storing one or more machine instructions, which when implemented cause the processor system to perform a method including at least;

processing data from the sensors;

determining, via the processor system, whether a pixel is part of a foreground portion of an image based on a current video frame;

determining, via the processor system, a first set of unknown pixels for which being located in the foreground portion does not in-and-of-itself determine the pixel to be part of the foreground;

determining, via the processor system, whether the pixel is part of a current background portion of the image based on the current video frame;

determining, via the processor system, a second set of unknown pixels for which being in a current background portion does not in-and-of-itself determine the pixel to be part of the background;

determining, via the processor system, for the first and second set of unknown pixels whether the pixel is part of the background or foreground is based on temporal data; and

extracting, via the processor system, an image of the foreground that does not elude the current background based on the determining of whether the pixel is part of the foreground, based on the determining of whether the pixel is part of the current background and based on the temporal data.

2. The system of claim 1 further comprising a hardware output system, the memory system storing one or more instructions for joining data from two or more sensors, and fusing the sensor data into a format for viewing data from both sensors simultaneously on a monitor, and

sending the sensor data to the monitor.

3. The system for claim 1, the system being capable of connecting and providing add-on solutions including one more of remote processing, recording, face detection or search solutions.

4. The system of claims 1, the one or more sensors including at least a camera, the system having a flexible architecture for providing add-on solutions inside the camera or outside camera on a network.

5. The system of claim 1 the memory system storing one or more machine instructions, which when implemented, cause a processor and one or more units to detect whether an event is a security risk, manage events, and search events.

6. The system of claim 1 the one or more sensors including multiple sensor system, the memory system storing one or more instructions, which when implemented by the processor, cause the process to join output from multiple sensors of the sensor system to form a panorama view for a wide angle coverage.

7. The system of claim 1, the method further including at least:

determining a motion associated with regions of the image; and

determining which pixels are background pixels based on whether the motion is within a range of values of motion that is expected to be associated with the background.

8. The system of claim 1, the foreground being one or more images of one or more people and determining the foreground pixel includes at least determining whether the pixels have a coloring that is expected to be associated with the one or more people.

9. The system of claim 8, the coloring including a hue associated with skin.

10. The system of claim 1, the method further including at least determining regions to be part of the background, based on the regions having a motion that is less than a particular amount, and updating the background based on the determining of the regions.

11. The system of claim 10, the method further including at least the updating of the background including changing pixel values of background pixels to indicate changes in lighting associated with the background.

12. The system of claim 1,

the extracting of the image of the foreground including a first phase and a second phase,

the first phase including at least

classifying pixels having a first range of motion values as background pixels

classifying pixels having a second of range of motion values as foreground pixels, the first range does not overlap the second range,

undetermined pixels, which are pixels having a motion value that is not in the first range and not in the second range, are not classified as background or foreground as part of the first phase;

and

during the second phase, classifying the undetermined pixels as background or foreground based one or more other criteria.

13. The system of claim 1, further comprising:

determining a complexity for one or more regions of a scene, and

adjusting one more criteria for determining whether a pixel is a background or foreground pixel, based on the complexity.

14. The system of claim 1, the method further including at least

determining whether the data indicates a security threat,

tracking a particular entity,

activating an alert in response to determining that the data indicates a security threat, and

storing the data.