Image-Based Object Tracking System and Image-Based Object Tracking Method

• US 20140191951A1
• Filed: 01/10/2014
• Published: 07/10/2014
• Est. Priority Date: 01/10/2013
• Status: Active Grant

• Current Assignee: ULSee Inc.
• Original Assignee: CyWee Group Ltd.
• Inventors: Ye, Zhou, Hsiao, Hsin-Wei, Lu, Ying-Ko, Jeng, Sheng-Weng, Chang, Chih-Ming, Hsu, Yi-Chia
• Granted Patent: US 9,317,136 B2
• Time in Patent Office: Days
• US Class Current: 345/156
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

An image-based object tracking system and an image-based object tracking method are provided. The image-based object tracking system includes an object, a camera, a computing device, and a display device. A color stripe is disposed on the surface of the object. The color stripe divides the surface of the object into a first section and a second section. The camera is configured to capture real-time images of the object. Further, the object tracking algorithm is stored in the computing device. The display device includes a display screen and is electrically connected to the computing device, and the display screen is configured to display the real-time images of the object. By using the image-based object tracking system provided in the invention, the object can be tracked accurately and efficiently without interference with the image of the background.

Claims

1. An image-based object tracking system, comprising:

an object, on a surface of the object is disposed with a color stripe, the color stripe dividing the surface of the object into a first section and a second section;

a camera, configured to capture real-time images of the object;

a computing device, an object tracking algorithm is stored in the computing device; and

a display device, comprising a display screen and electrically connected to the computing device, and the display screen configured to display the real-time images of the object;

wherein, when the computing device starts the operation of the object tracking algorithm, the computing device performs the following steps;

(i) checking whether color characteristics of the object stored in a database of the computing device, otherwise starting a step of color learning to store the color characteristics of the object in the database of the computing device;

(ii) creating an object tracking window; and

(iii) when the image of the object enters into the object tracking window, tracking the position of the object based on the color characteristics of the object stored in the database.

2. The image-based object tracking system of claim 1, wherein a length of the first section is less than a length of the second section.

3. The image-based object tracking system of claim 1, wherein the surface of the object is rendered in a single color except for the color stripe.

4. The image-based object tracking system of claim 1, wherein in the step (i), the step of color learning comprises:

showing a color learning window on the display screen;

moving the object so as to make the image of the object being located in the color window;

extracting the color characteristics of the object and storing the color characteristics in the database.

5. The image-based object tracking system of claim 1, wherein the step (ii) comprises:

executing a face tracking step so as to track a user'"'"'s face; and

creating an object tracking window, the object tracking window circling the user'"'"'s face;

wherein a length and a width of the object tracking window are greater than a length and a width of the user'"'"'s face, respectively.

6. The image-based object tracking system of claim 1, wherein the step (iii) comprises:

based on the color characteristics of the object stored in the database, splitting the image of the object and the image of a background in which the object exists;

labeling the first section and the second section of the object;

pairing the first section and the second section; and

tracking the position of the object.

7. The image-based object tracking system of claim 2, wherein the step (iii) comprises:

based on the color characteristics of the object stored in the database, splitting the image of the object and the image of a background in which the object exists;

labeling the first section and the second section of the object;

pairing the first section and the second section, so as to verify the second section as a body, and verify the first section as a tip; and

tracking the position of the object.

8. The image-based object tracking system of claim 1, wherein the object further comprises a motion sensor and a first wireless transmission unit, and the computing device further comprises a second wireless transmission unit, the first wireless transmission unit is configured to transmit data generated by the motion sensor to the second wireless transmission unit.

9. The image-based object tracking system of claim 1, wherein the computing device is a mobile phone, a tablet PC, or a personal computer.

10. An image-based object tracking method, comprising the steps of:

(a) capturing real-time images of an object by a camera;

(b) checking whether color characteristics of the object is stored in a database of a computing device, otherwise starting a step of color learning to store the color characteristics of the object in the database of the computing device, wherein a color stripe is disposed on the surface of the object, the color stripe divides the surface of the object into a first section and a second section;

(c) creating an object tracking window; and

(d) when the image of the object enters into the object tracking window, tracking the position of the object based on the color characteristics of the object stored in the database.

11. The image-based object tracking method of claim 10, wherein in the step (b), the step of color learning comprises:

showing a color learning window;

moving the object so as to make the image of the object being located in the color window;

extracting color characteristics of the object and storing the color characteristics in the database.

12. The image-based object tracking method of claim 10, wherein the step (c) comprises:

executing a face tracking step so as to track a user'"'"'s face; and

creating an object tracking window, the object tracking window circling the user'"'"'s face, and a length and a width of the object tracking window are greater than a length and a width of the user'"'"'s face, respectively.

13. The image-based object tracking method of claim 10, wherein the step (d) comprises:

based on the color characteristics of the object stored in the database, splitting the image of the object and the image of a background in which the object exists;

labeling the first section and the second section of the object, so as to label the second section as a body, and label the first section as a tip;

pairing the first section and the second section; and

tracking the position of the object.

14. The image-based object tracking method of claim 10, wherein a length of the first section is less than a length of the second section, and the step (d) comprises:

based on the color characteristics of the object stored in the database, splitting the image of the object and the image of a background in which the object exists;

labeling the first section and the second section of the object;

pairing the first section and the second section, so as to verify the second section as a body, and verify the first section as a tip; and

tracking the position of the object.