Image-based object tracking system in 3D space using controller having multiple color clusters
First Claim
1. An image-based object tracking system, comprising:
- a controller, the controller comprising two or more color clusters;
a camera, configured to capture real-time images of the controller; and
a processing unit, for receiving the real-time images of the controller and executing an object tracking algorithm so as to provide real-time display of processed image contents from the captured images of the controller on a monitor screen;
wherein the processing unit configured for;
performing color learning on the controller using a learning box and a color learning algorithm;
upon determining color learning being successful, storing the color learning results of the controller, and starting object tracking of the controller using the color learning results; and
upon determining that color relearning of the controller is required, repeating the performing color learning step, otherwise showing a learning error message;
capturing images of the controller;
separating and splitting the controller and the background by color differences using the color learning results;
providing color labeling and color filtering to the controller and the background; and
performing an object pairing procedure on the controller, and upon determining that the object pairing of the controller is successful, performing output of the object features of the controller;
wherein the controller is configured to be directly interacting with the displayed processed image content on the monitor screen.
2 Assignments
0 Petitions
Accused Products
Abstract
Image-based object tracking system includes at least a controller with two or more color clusters, an input button, a processing unit with a camera, an object tracking algorithm and a display. Camera is configured to capture images of the controller, the processing unit is connected to display to display processed image contents, the controller is directly interacting with displayed processed image content. The controller can have two or three color clusters located on a side surface thereof and two color clusters having concentric circular areas located at a top surface thereof, the color of the first color cluster can be the same as or different from the color of the third color cluster. An object tracking method with or without scale calibration is also provided, which includes color learning and color relearning, image capturing, separating and splitting of the controller and the background, object pairing procedure steps on the controller.
-
Citations
20 Claims
-
1. An image-based object tracking system, comprising:
-
a controller, the controller comprising two or more color clusters; a camera, configured to capture real-time images of the controller; and a processing unit, for receiving the real-time images of the controller and executing an object tracking algorithm so as to provide real-time display of processed image contents from the captured images of the controller on a monitor screen; wherein the processing unit configured for; performing color learning on the controller using a learning box and a color learning algorithm; upon determining color learning being successful, storing the color learning results of the controller, and starting object tracking of the controller using the color learning results; and upon determining that color relearning of the controller is required, repeating the performing color learning step, otherwise showing a learning error message; capturing images of the controller; separating and splitting the controller and the background by color differences using the color learning results; providing color labeling and color filtering to the controller and the background; and performing an object pairing procedure on the controller, and upon determining that the object pairing of the controller is successful, performing output of the object features of the controller; wherein the controller is configured to be directly interacting with the displayed processed image content on the monitor screen. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An object tracking method, comprising the steps of
performing color learning on a first controller using a learning box and a color learning algorithm; -
upon determining color learning being successful, storing the color learning results of the first controller, determining if there are more than one controller, and if so, configuring the total number of controllers to be N, and performing color learning on each controller using the learning box and the color learning algorithm, and upon determining color learning being successful on the Nth controller, storing the color learning results, and starting object tracking of each controller using the color learning results; and upon determining that color relearning of each controller is deemed to be required, repeating from the performing color learning step, otherwise showing a learning error message; capturing images of each controller; separating and splitting each controller and the background by color differences using the color learning results; providing color labeling and color filtering to each controller and the background; performing an object pairing procedure on each controller, and upon determining that the object pairing of each controller is successful, performing output of the object features of each controller; and performing scale calibration upon determining that scale calibration is required. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17, 18, 19)
-
-
20. An object tracking method, comprising the steps of:
-
performing color learning on a controller using a learning box and a color learning algorithm; upon determining color learning being successful, storing the color learning results of the controller, and starting object tracking of the controller using the color learning results; and upon determining that color relearning of the controller is required, repeating the performing color learning step, otherwise showing a learning error message; capturing images of the controller; separating and splitting the controller and the background by color differences using the color learning results; providing color labeling and color filtering to the controller and the background; and performing an object pairing procedure on the controller, and upon determining that the object pairing of the controller is successful, performing output of the object features of the controller.
-
Specification