Video monitoring and surveillance systems capable of handling asynchronously multiplexed video

• US 20030123702A1
• Filed: 12/28/2001
• Published: 07/03/2003
• Est. Priority Date: 12/28/2001
• Status: Active Grant

• Current Assignee: Antonio J. Colmenarez, Miroslav Trajkovic, Srinivas Gutta
• Original Assignee: Antonio J. Colmenarez, Miroslav Trajkovic, Srinivas Gutta
• Inventors: Trajkovic, Miroslav, Gutta, Srinivas, Colmenarez, Antonio J.
• Granted Patent: US 6,999,613 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/295 Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
• CPC Class Codes: G08B 13/1961 Movement detection not involving frame subtraction, e.g. motion detection on the basis of luminance changes in the image
• CPC Class Codes: G08B 13/19645 Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

Aspects of the present invention can be configured to demultiplex an asynchronously multiplexed video signal, which comprises images from a number of different cameras. Image matching techniques are used to assign input images with states. After a period, the number of states will generally equal the number of input cameras. The states may be modeled through any number of techniques, such as histogram analysis, clustering, and hidden Markov model analysis. Input images are assigned to states, and the input images are output as being associated with the states. Zone surveillance may be performed on a series of images from one or more of the states. Any events that occur can be distinguished and reported.

Claims

1. A method, comprising:

matching an input image with one of a plurality of states, the input image determined from a signal comprising images from a plurality of cameras; and

assigning the input image to one of the states when the input image matches the one state.

2. The method of claim 1, wherein:

the method further comprises the steps of;

determining an input image from the signal comprising images from a plurality of cameras; and

determining input image information from the input image;

the step of matching further comprises the step of comparing the input image information with state image information corresponding to each of at least one states; and

the step of assigning further comprises the step of assigning the input image to one of the states when the input image information matches state image information of the one state.

3. The method of claim 2, wherein:

the step of comparing comprises the steps of;

determining if at least one state exists; and

adding a new state that corresponds to the input image when at least one state does not exist; and

the step of assigning comprises the step of;

assigning the input image to the new state.

4. The method of claim 2, wherein:

the step of comparing comprises the step of;

when the input image information does not match any of the information for each of the at least one states, adding a new state that corresponds to the input image; and

the step of assigning comprises the step of;

assigning the input image to the new state.

5. The method of claim 2, wherein the at least one state comprises a plurality of states and wherein the method further comprises the step of performing training to determine the plurality of states.

6. The method of claim 2, further comprising the step of outputting the input image, the input image output as being associated with the one state.

7. The method of claim 2, wherein the images on the signal are determined asynchronously.

8. The method of claim 7, further comprising the step of multiplexing the images onto the signal, the step of multiplexing performed wherein a sequence of switching between cameras is not predetermined.

9. The method of claim 2, wherein the images on the signal are determined synchronously.

10. The method of claim 2, further comprising the steps of:

outputting the input image, the step of outputting associating the input image with the one state;

determining if an event is occurring on the input image, the step of determining comparing previous images associated with the one state with a present image.

11. The method of claim 2, wherein the input image information matches state image information of the one state when a metric comparing the input image information and the state image information of the one state falls within a predetermined value.

12. The method of claim 2, wherein:

the step of determining input image information from the input image comprises the step of determining a histogram from the input image;

the step of comparing comprises the step of comparing the histogram of the input image with histograms corresponding to each of at least one states; and

the step of assigning comprises the step of assigning the input image to one of the states when the histogram of the input image matches the histogram of the one state within a predetermined error.

13. The method of claim 2, wherein:

the step of determining input image information from the input image comprises the step of determining a plurality of features from the input image;

the step of comparing comprises the step of comparing the features of the input image with each of a plurality of features corresponding to the at least one states; and

the step of assigning comprises the step of assigning the input image to one of the states when the features of the input image match the features of the one state within a predetermined error.

14. The method of claim 13, wherein each of the states comprises a state of a Hidden Markov Model (HMM).

15. A system comprising:

a memory that stores computer readable code; and

a processor operatively coupled to said memory, said processor configured to implement said computer readable code, said computer readable code configured to;

determine an input image from a signal comprising images from a plurality of cameras;

determine input image information from the input image;

compare the input image information with state image information corresponding to each of at least one states; and

assign the input image to one of the states when the input image information matches state image information of the one state.

16. An article of manufacture comprising:

a computer readable medium having computer readable program code means embodied thereon, said computer readable program code means comprising;

a step to determine an input image from a signal comprising images from a plurality of cameras;

a step to determine input image information from the input image;

a step to compare the input image information with state image information corresponding to each of at least one states; and

a step to assign the input image to one of the states when the input image information matches state image information of the one state.