Object tracking method

• US 8,532,337 B2
• Filed: 03/31/2011
• Issued: 09/10/2013
• Est. Priority Date: 10/29/2010
• Status: Active Grant

• Current Assignee: Altek Corporation
• Original Assignee: Altek Corporation
• Inventors: Chang, Yin-Pin, Chang, Wen-Yan, Chou, Hong-Long
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): HEIDEMANN, JASON E
• Application Number:
  US13/077,013
• Publication Number:
  US 20120106783A1
• Time in Patent Office: 894 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/248 involving reference images or patches

Abstract

An object tracking method includes steps of obtaining multiple first classifications of pixels within a first focus frame in a first frame picture, wherein the first focus frame includes an object to be tracked and has a first rectangular frame in a second frame picture; performing a positioning process to obtain a second rectangular frame; and obtaining color features of pixels around the second rectangular frame sequentially and establishing multiple second classifications according to the color feature. The established second classifications are compared with the first classifications sequentially to obtain an approximation value, compared with a predetermined threshold. The second rectangular frame is progressively adjusted, so as to establish a second focus frame. By analyzing color features of the pixels of the object and with a classification manner, the efficacy of detecting a shape and size of the object so as to update information of the focus frame is achieved.

Claims

1. An object tracking method, comprising:

performing a classification process in a first frame picture, so as to obtain multiple first classifications of pixels within a first focus frame, wherein the first focus frame has a first rectangular frame therein, and the classification process comprises;

obtaining the color feature of each of the pixels within the first focus frame;

calculating multiple weight values according to the color features respectively and correspondingly; and

establishing the first classifications for the weight values from large to small, with the first rectangular frame being set in a pixel range covered by the first classification having the largest weight value among the weight values;

performing a positioning process according to the first rectangular frame in a second frame picture, so as to obtain a second rectangular frame;

obtaining a color feature of each of the pixels around the second rectangular frame sequentially, and establishing multiple second classifications according to the color features;

calculating an approximation of the second classification and the corresponding first classification sequentially, so as to obtain an approximation value respectively;

comparing each approximation value sequentially to determine whether the approximation value is larger than a predetermined threshold;

if yes, progressively adjusting the second rectangular frame to a pixel range covered by the second classifications; and

if no, stopping adjusting the second rectangular frame, so as to establish a second focus frame.

2. The object tracking method according to claim 1, wherein the positioning process comprises:

searching a position having weight values approximate to the first rectangular frame in the second frame picture according to the pixel range covered by the first rectangular frame; and

setting the position as the second rectangular frame.

3. The object tracking method according to claim 1, wherein the positioning process comprises:

positioning a position having weight values approximate to the first rectangular frame in the second frame picture according to the pixel range covered by the first rectangular frame;

setting the position as the second rectangular frame, and obtaining multiple weight values of pixels within the second rectangular frame;

calculating an included angle according to a vector relation of the weight values of the first rectangular frame and the second rectangular frame; and

rotating the second rectangular frame according to the included angle.