Automatic video monitoring system which selectively saves information

• US 7,023,469 B1
• Filed: 04/15/1999
• Issued: 04/04/2006
• Est. Priority Date: 04/30/1998
• Status: Expired due to Term

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Olson, Thomas J.
• Primary Examiner(s): WONG, ALLEN C
• Application Number:
  US09/292,265
• Time in Patent Office: 2,546 Days
• Field of Search: 348/152, 348/154, 348/143, 348/700, 382/104, 379/40, 707/218, 340/565, 701/207, 345/474
• US Class Current: 348/152
• CPC Class Codes: G08B 13/196 using television cameras
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A system (10) for automatically monitoring an area includes a camera unit (12) having therein a video camera (23) and an image processing section (27). The image processing section saves a reference image from the video camera, compares subsequent images to the reference image, and detects and tracks change regions in the subsequent images. For each change region, the image processing section saves a path of movement of the change region, and a selected image of the change region. Selection is carried out so as to optimize the selected image, for example so that a detected person is facing and close to the video camera. The camera unit is network-ready (14), so that a remote workstation (13) can access the images and other information saved in the camera unit.

Claims

1. A method of monitoring an area, comprising the steps of:

periodically detecting an image of the area;

identifying and tracking a moving object in a succession of the detected images;

automatically selecting a portion of a single image of the succession of detected images for each identified moving object using selection criteria;

saving the selected portion of the single image of the succession of detected images for each identified object; and

discarding and not saving detected images of the succession of the detected images other than said single image of each identified object.

2. A method according to claim 1, wherein said step of automatically selecting is carried out by using image selection criteria which are intended to lead to the selection of an image in which the face of a detected person is visible and large.

3. A method according to claim 2, wherein said step of automatically selecting includes the steps of:

saving one of the detected images as a reference image;

carrying out said step of identifying by evaluating images detected subsequent to the reference image in order to identify therein each change region where the evaluated image differs from the reference image;

determining a bounding box subset of the single image for a given change region in each image of a set of images in which the given change region appears; and

selecting the selected portion of the single image for the given change region by discarding images from the set in which a lowermost side of the bounding box is higher than in other images of the set, and by selecting from the remaining images of the set an image in which a size of the bounding box is larger than in the other remaining images of the set.

4. A method according to claim 1, wherein said step of automatically selecting is carried out using image selection criteria which cause a current image to be selected over a prior image if a lowermost point of a detected change region is lower in the current image than in the prior image.

5. A method according to claim 4, wherein said step of automatically selecting is carried out using image selection criteria which cause a current image to be selected over a prior image if a detected change region has increased in size relative to a prior image.

6. A method according to claim 1, wherein said selecting step is carried out in response to detection of the absence of a previously detected object.

7. A method according to claim 1, wherein said selecting step is carried out in response to detection of a situation in which an object has remained within a predefined region of the area for a specified time interval.

8. A method according to claim 1, wherein said selecting step is carried out in response to a determination that a previously moving object has become stationary.

9. A method according to claim 1, wherein said selecting step is carried out in response to a determination a previously stationary object has started moving.

10. A method according to claim 1, wherein said saving step is carried out by determining a bounding box subset of the single image just large enough to completely contain a corresponding detected object and saving a portion of a detected image corresponding to the bounding box.

11. A method according to claim 10, including the step of saving one of the detected images as a reference image at a first resolution, and wherein said step of saving the selected portion of the single image is carried out by saving the bounding box enclosing the selected portion of the single image at a second resolution which is higher than the first resolution.

12. A method according to claim 1, including the step of saving one of the detected images as a reference image having a first resolution, wherein said step of saving the selected portion of the single image is carried out by determining a bounding box subset of the single image just large enough to completely contain a corresponding detected object and saving at a second resolution the bounding box enclosing the selected portion of the single image, the second resolution being greater than the first resolution, and including the step of displaying the reference image at the first resolution, displaying the bounding box enclosing the selected portion of the single image within the reference image at the first resolution, and displaying the bounding box enclosing the selected portion of the single image separately from the reference image and at the second resolution.

13. An apparatus for monitoring an area, comprising:

a detector which is operative to periodically detect an image of the area; and

an image processing section which is responsive to the detector, said image processing section being operative to;

identify and track a moving object in a succession of the detected images;

automatically select a portion of a single image of the succession of detected images for each identified object utilizing selection criteria;

save the selected portion of the single image of the succession of detected images for each identified object; and

discard and not save detected images other than said single image of the succession of detected images for each identified object.

14. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

use image selection criteria which are intended to lead to the selection of an image in which the face of a detected person is visible and large.

15. An apparatus according to claim 14, wherein:

said image processing section being further operative to;

save one of the detected images as a reference image;

identify a moving object by evaluating images detected subsequent to the reference image in order to identify therein each change region where the evaluated image differs from the reference image;

determine a bounding box subset of the selected image for a given change region in each image of a set of images in which the given change region appears; and

select the selected portion of the single image for the given change region by discarding images from the set in which a lowermost side of the bounding box is higher than in other images of the set, and by selecting from the remaining images of the set an image in which a size of the bounding box is larger than in the other remaining images of the set.

16. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

automatically select an image using image selection criteria which cause a current image to be selected over a prior image if a lowermost point of a detected change region is lower in the current image than in the prior image.

17. An apparatus according to claim 16, wherein:

said image processing section being further operative to;

automatically select an image out using image selection criteria which cause a current image to be selected over a prior image if a detected change region has increased in size relative to a prior image.

18. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

select an image in response to detection of the absence of a previously detected object.

19. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

select an image in response to detection of a situation in which an object has remained within a predefined region of the area for a specified time interval.

20. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

select an image in response to a determination that a previously moving object has become stationary.

21. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

select an image in response to a determination a previously stationary object has started moving.

22. An apparatus according to claim 13, wherein:

said image processing section being further operative to;

save said selected portion of the single image by determining a bounding box subset of the single image just large enough to completely contain a corresponding detected object and saving a portion of a detected image corresponding to the bounding box.

23. An apparatus according to claim 22, wherein:

said image processing section being further operative to;

save one of the detected images as a reference image at a first resolution; and

save the selected portion of the single image by saving a bounding box enclosing the selected portion of the single image at a second resolution which is higher than the first resolution.

24. An apparatus according to claim 13, further comprising:

a display device; and

wherein said image processing section being connected to the display device and being further operative to;

save one of the detected images as a reference image having a first resolution;

save the selected portion of the single image by saving a bounding box subset of the single image enclosing a corresponding detected object at a second resolution which is higher than the first resolution;

display via said display device said reference image at the first resolution and said bounding box enclosing the selected portion of the single image within said reference image at said first resolution, and

display via said display device said bounding box separately from said reference image at said second resolution.

25. A method of monitoring an area, comprising the steps of:

periodically detecting an image of the area;

identifying and tracking a moving object in a succession of the detected images;

automatically selecting a portion of single image of the succession of detected images for each identified object using selection criteria;

saving the selected portion of the single image of the succession of detected images for each identified object; and

discarding and not saving detected images other than said single image of the succession of detected images for each identified object; and

automatically saving a series of Cartesian coordinate pairs which identifies the path of movement of the object, said information being retained after the object is no longer present in newly detected images.

26. A method according to claim 25, including the steps of saving an identification of an event associated with the detected object, saving one of the detected images as a reference image, displaying the reference image, displaying on the reference image the path of movement of the object, and displaying on the reference image the identification of the event at a location on the reference image corresponding to a location of the event.

27. An apparatus according to claim 25, further comprising:

a display device;

wherein said image processing section being connected to said display device and being further operative to;

save an identification of an event associated with said detected object;

save one of the detected images as a reference image; and

display via said display device said reference image, said path of movement of the object within said reference image, and said identification of said event on said reference image at a location on the reference image corresponding to a location of the event.

28. An apparatus for monitoring an area, comprising:

a detector which is operative to periodically detect an image of the area; and

an image processing section which is responsive to the detector and which is operative to;

identify and track a moving object in a succession of the detected images;

save the selected portion of the single image of the succession of detected images for each identified object; and

discard and not save detected images other than said single image of the succession of detected images for each identified object;

automatically save a series of Cartesian coordinate pairs which identifies the path of movement of each moving object, and to retain the information after the moving object ceases to be present in current detected images.