Object identification in a moving video image

• US 6,205,231 B1
• Filed: 05/10/1995
• Issued: 03/20/2001
• Est. Priority Date: 05/10/1995
• Status: Expired due to Fees

• Current Assignee: Identive Corporation
• Original Assignee: Identive Corporation
• Inventors: Emberson, David R., Meyer, Donald E., Isadore-Barreca, Anthony J., Himelstein, Mark I.
• Primary Examiner(s): BELLA, MATTHEW C
• Application Number:
  US08/435,439
• Time in Patent Office: 2,141 Days
• Field of Search: 382/103, 382/107, 382/199, 382/313, 382/316, 382/173, 382/190
• US Class Current: 382/103
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: H04N 19/20 using video object coding

Abstract

A moving object identification method (10) for identifying and tracing an object (20) within a video image (14) such that the object (20) can act as a hot spot (30) as for an interactive computer/user interface (70). A plurality of tags (28) define the edges (26) of the object (20) and a plurality of hot spot borders (32) define the hot spot (30) such that the hot spot (30) and the object (20) generally coincide. A physical tag (28b) is optionally used to position the tags (28). Sensitivity to disappearance of the edges (26) is adjustable according to the relative size of a subtag (68) to the corresponding tag (28).

Claims

1. A method of identifying an object in a digitized moving video image such that the object can be acted on by a computer, comprising placing a plurality of tags at user selected points on the object in a video frame, each tag containing an edge of the object and the plurality of tags generally defining the object;

automatically detecting the edges of the object;

relating each tag to an edge by repositioning the tag to center the tag on the edge;

tracking the object in subsequent frames of the moving video image by determining the locations of said tags in said subsequent video frames, wherein said plurality of tags define an area of the object corresponding to a hot spot, and said tracking of the object comprises tracking the hot spot, and wherein said hot spot comprises an area of the object bounded by lines interconnecting said plurality of tags.

2. A method of identifying an object in a digitized moving video image such that the object can be acted on by a computer, comprising placing a plurality of tags at user selected points on the object in a video frame, each tag containing an edge of the object and the plurality of tags generally defining the object;

automatically detecting the edges of the object;

relating each tag to an edge by repositioning the tag to center the tag on the edge;

tracking the object in subsequent frames of the moving video image by determining the locations of said tags in said subsequent video frames, wherein a tag comprises a first two dimensional array of pixels within a video frame, and each tag contains a subtag comprising a second smaller two-dimensional array of pixels centered within the first array; and

wherein said re-positioning of the tag to center the tag on an edge comprises positioning the subtag on the edge.

3. The method of claim 2 further comprising defining a sensitivity zone comprising the portion of a tag not included within the subtag.

4. The method of claim 3, wherein said automatically detecting an edge of the object comprises applying an edge mask to the video image, and determining an edge by detecting changes in luminance.

5. The method of claim 4, wherein said edge mask comprises a third array of pixels, and said detecting changes in luminance comprises detecting luminance differences within the third array which exceed a predetermined threshold.

6. The method of claim 2 further comprising ceasing to track a tag;

in the moving video and recording the tag as being lost when an edge of the object within the tag becomes sufficiently short to be within the subtag but not within the first array of pixels which contain the subtag.

7. A method for identifying and tracking an object in a moving video image such that the object can be acted on by a computer, comprising placing a tag at a user-selected point on the object within a video frame, the tag comprising an array of pixels and said placing comprising selecting a point for the tag such that the tag contains an edge of the object;

repositioning the tag such that the array of pixels comprising the tag is centered on the edge;

selecting a region of interest within the tag corresponding to a portion of the tag which coincides with the object;

repeating said placing and selecting steps to place a plurality of tags on the object;

defining a hot spot comprising an area bounded by lines interconnecting the tags, the hot spot comprising a clickable area which enables the object to be acted upon by the computer; and

tracking the object over successive frames by tracking and storing the locations of each of the tags from frame to frame.

8. The method of claim 7, wherein said tracking comprises determining the average luminosity within a tag within the region of interest and within an area outside of the region of interest and determining a luminosity difference, and identifying a tag to be lost when the luminosity difference decreases below a predetermined value.

9. The method of claim 7, wherein said tracking comprises determining average values for color components of pixels within the region of interest of a tag, and tracking the tag until the averages values change by a predetermined amount.

10. The method of claim 9, wherein said tracking comprises defining a subtag within tag comprising a smaller array of pixels centered within the tag and containing said edge;

and considering the tag to be lost when the size of the edge changes due to motion of the object such that the edge is located within the subtag but not within the area of the tag not constituted by the subtag.