Contextual visual dataspaces

Patent metadata

Field	Value
Publication number	US-11025865-B1
Application number	US-201113163558-A
Country	US
Kind code	B1
Filing date	Jun 17, 2011
Priority date	Jun 17, 2011
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

A method is disclosed. The method receives a two dimensional or a three dimensional computer generated representation of an area, receives a plurality of images of the area captured by one or more video cameras, detects a first moving object in the plurality of images, generates a computer representation of the first moving object, correlates the images of the area captured by the one or more video cameras with the two dimensional or three dimensional computer generated representation of the area, and displays the computer representation of the first moving object in the two dimensional or the three dimensional computer generated representation of the area.

First claim

What is claimed is:

1. A method comprising:
receiving a two dimensional or a three dimensional computer generated representation of an area;
receiving a plurality of images of the area captured by one or more video cameras;
detecting a first moving object in the plurality of images, wherein detecting the first moving object comprises performing a foreground detection process on the plurality of images to determine image pixels;
providing a computer generated avatar representing the first moving object;
correlating the images of the area captured by the one or more video cameras with the two dimensional or three dimensional computer generated representation of the area;
displaying the computer generated avatar in the two dimensional or the three dimensional computer generated representation of the area;
performing a background modeling process on the plurality of images to identify static background;
determining background image pixels;
matching the image pixels to the background image pixels;
identifying unmatched image pixels as foreground pixels;
converting the foreground pixels into one or more sets of foreground blobs to represent at least the first moving object;
classifying the one or more sets of foreground blobs; and
identifying ground point of the one or more sets of foreground blobs.

2. The method of claim 1 , wherein correlating the images captured by the one or more video cameras with the two dimensional or three dimensional computer generated representation of the area comprises:
identifying at least one ground point in the plurality of images associated with the first moving object; and
mapping the at least one ground point to a corresponding point in the two dimensional or the three dimensional computer generated representation of the area.

3. The method of claim 1 , further comprising:
determining a traveling path of the first moving object from the plurality of images; and
updating a position of the computer generated avatar in the two dimensional or the three dimensional computer generated representation of the area based on the traveling path.

4. The method of claim 1 , further comprising:
classifying the first moving object as a person or a vehicle.

5. The method of claim 4 , wherein generating a computer representation of the first moving object comprises:
generating a computer representation of the person.

6. The method of claim 4 , wherein providing a computer generated avatar comprises:
providing a computer generated avatar of the vehicle.

7. The method of claim 1 , further comprising:
detecting a second moving object in the plurality of images; determining a traveling path of the first moving object;
determining a traveling path of the second moving object; and
providing a warning when the first moving object is on a collision course with the second moving object.

8. The method of claim 1 , wherein the area is for parking vehicles and the first moving object is a vehicle leaving a parking spot.

9. The method of claim 8 , further comprising:
providing an alert when the vehicle leaves the parking spot.

10. The method of claim 8 , further comprising:
providing a driving direction to the parking spot.

11. The method of claim 1 , wherein the two dimensional or the three dimensional computer generated representation of the area depicts a stationary object.

12. The method of claim 11 , further comprising:
determining a traveling path of the first moving object; and
providing a warning when the first moving object approaches the stationary object.

13. The method of claim 12 , wherein the stationary object is a building and the first moving object is a person.

14. The method of claim 12 , wherein the stationary object is a building and the first moving object is a vehicle.

15. The method of claim 1 , further comprising:
receiving global positioning coordinates of a second moving object in the area; determining traveling path of the first moving object;
determining traveling path of the second moving object based on the changes in the global positioning coordinates of the second moving object; and
providing a warning if the first moving object is on a collision course with the second moving object.

16. The method of claim 1 , further comprising:
receiving global positioning coordinates of the first moving; detecting a second moving object in the plurality of images; receiving global positioning coordinates of the second moving object;
determining traveling path of the first moving object based on the changes in the global positioning coordinates of the first moving object and based on the location of the first moving object in the plurality of images;
determining traveling path of the second moving object based on the changes in the global positioning coordinates of the second moving object and based on the location of the second moving object in the plurality of images; and
providing a warning if the first moving object is on a collision course with the second moving object.

17. The method of claim 1 further comprises:
performing a background modeling process on the plurality of images to identify static background; and
determining background image pixels.

18. The method of claim 17 , wherein detecting the first moving object comprises performing a foreground detection process on the plurality of images to determine image pixels.

19. The method of claim 18 further comprises:
matching the image pixels to the background image pixels; and identifying unmatched image pixels as foreground pixels.

20. The method of claim 19 further comprises:
converting the foreground pixels into one or more sets of foreground blobs to represent at least the first moving object; and
classifying the one or more sets of foreground blobs.

21. The method of claim 20 further comprises identifying ground point of the one or more sets of foreground blobs.

22. The method of claim 21 , wherein correlating the images of the area captured by the one or more video cameras with the two dimensional or three dimensional computer generated representation of the area comprises mapping the identified ground point to a corresponding ground point in the two dimensional or three dimensional computer generated representation of the area.

23. The method of claim 20 further comprises creating an appearance model for the one or more sets of foreground blobs.

24. The method of claim 23 , wherein creating an appearance model for the one or more sets of foreground blobs is performed with histograms.

25. The method of claim 1 , wherein the two dimensional or a three dimensional computer generated representation of an area is generated using one or more detection sources.

26. The method of claim 25 , wherein the one or more detection sources is an image-based object detection and localization detection source, a radar detection source, a sonar detection source, or a light detection and ranging (LIDAR) detection source.

27. A method comprising:
receiving a two dimensional or a three dimensional computer generated representation of an area;
receiving a plurality of images of the area captured by one or more video cameras;
detecting a first moving object in the plurality of images, wherein detecting the first moving object comprises performing a foreground detection process on the plurality of images to determine image pixels;
providing

Assignees

• Medasani Swarup S
• Owechko Yuri
• Kim Kyungnam
• Krayner Alexander
• Hrl Lab Llc

Inventors

• Medasani Swarup S
• Owechko Yuri
• Kim Kyungnam
• Krayner Alexander

Classifications

• H04N7/181 Primary

  for receiving images from a plurality of remote sources · CPC title