Method and apparatus for object tracking for automatic controls in video devices

• US 6,226,388 B1
• Filed: 01/05/1999
• Issued: 05/01/2001
• Est. Priority Date: 01/05/1999
• Status: Expired due to Term

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Lab of America Incorporated (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Qian, Richard J., Sampsell, Jeffrey B.
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): NAKHJAVAN, SHERVIN K
• Application Number:
  US09/225,187
• Time in Patent Office: 847 Days
• Field of Search: 382/103, 382/107, 382/162, 382/164, 382/166, 382/167, 382/168, 382/169, 382/190, 382/195, 382/199, 382/224, 382/225, 382/260, 382/282, 382/286, 382/291, 382/305 , 382/307, 382/309, 382/311, 348/169, 348/575, 348/577, 348/671, 348/672, 345/326, 345/327, 345/328, 345/333, 345/335, 345/520, 345/523, 345/507, 345/30, 345/33
• US Class Current: 382/103
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters

Abstract

A method and apparatus for tracking of objects in video images. The tracking process includes the steps of: receiving an initial image with the object to be tracked; performing a color histogram on the initial image in the region where the object is located; receiving the next frame of the video sequence and specifying candidate regions in that image; using color histogram analysis on the candidate regions to find a match performing motion analysis to correct the analysis and to provide a prediction for the next frame; and, identifying and providing the tracked object'"'"'s image for output. Apparatus that can use this method can be either video capture or video display. In video capture, a user interface allows the user to designate the object to be tracked during capture. The tracking module than controls the capture system to track that object. In video display systems, a user interface allows the user to identify the object in the display that should be tracked. The tracking module then adjusts the display to track that object.

Claims

1. A method for tracking objects in video images, comprising the steps of:

a) determining an initial position of an object to be tracked;

b) storing a reference color histogram for said object, wherein the reference color histogram is registered in two-dimensional chromaticity space;

c) receiving an incoming frame of video data;

d) selecting a number of candidate regions in said incoming frame;

e) comparing initial color histograms of each of said candidate regions and said reference color histograms;

f) predicting and correcting said object motion using a linear filter; and

g) identifying said tracked object from one of said candidate regions, using histogram intersection between the initial color histogram and the reference color histogram.

2. The method as claimed in claim 1, wherein said determining step is accomplished by a user interface.

3. The method as claimed in claim 1, wherein said linear filter further comprises a Kalman filter.

4. The method as claimed in claim 1, wherein said video image is provided by an image capture device.

5. The method as claimed in claim 4, wherein said image capture device is a video camera.

6. The method as claimed in claim 1, wherein said video image is provided by an image display device.

7. The method as claimed in claim 6, wherein said image display device is a computer.

8. The method as claimed in claim 1, wherein said number of candidate regions is a predetermined number.

9. The method as claimed in claim 1, wherein said number of candidate regions is determined adaptively.

10. A processor having a memory, the processor configured to perform the tasks of:

determining an initial position of an object to be tracked;

storing a reference color histogram for said object, wherein the reference color histogram is registered in two-dimensional chromaticity space;

receiving an incoming frame of video data;

selecting a number of candidate regions in said incoming frame;

comparing initial color histograms of each of said candidate regions and said reference color histograms;

predicting and correcting said object motion using a linear filter; and

identifying said tracked object from one of said candidate regions, using histogram intersection between the initial color histogram and the reference color histogram.