CAMERA APPARATUS AND METHOD FOR TRACKING OBJECT IN THE CAMERA APPARATUS

• US 20140003661A1
• Filed: 07/01/2013
• Published: 01/02/2014
• Est. Priority Date: 06/29/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Pyo-Jae, Na, Jin-Hee, Sohn, Jae-Sik, Yoon, Young-Kwon, Kwon, Jung-Tae
• Granted Patent: US 9,171,378 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30244 Camera pose
• 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: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/632 for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters
• CPC Class Codes: H04N 23/843 Demosaicing, e.g. interpolating colour pixel values

Abstract

A camera apparatus capable of tracking a target object based on motion of a camera sensed by a motion sensor and a method for tracking an object in the camera apparatus are provided. The method includes, if input image data is inputted, sensing motion of a camera which captures the input image data, generating camera motion data corresponding to motion of the camera, estimating a pose or motion of the camera based on the camera motion data, and tracking translation of a target object based on at least one of the estimated pose or motion of the camera and the input image data.

Claims

1. A method for tracking an object in a camera apparatus, the method comprising:

if input image data is inputted, sensing motion of a camera which captures the input image data;

generating camera motion data corresponding to motion of the camera;

estimating a pose or motion of the camera based on the camera motion data; and

tracking translation of a target object based on at least one of the estimated pose or motion of the camera and the input image data.

2. The method of claim 1, before tracking the translation of the target object, further comprising:

performing a first tracking process of tracking the translation of the target object based on the input image data; and

performing a second tracking process of tracking the translation of the target object based on the estimated pose or motion of the camera,

wherein the tracking the translation of the target object comprises selecting one of the first tracking process and the second tracking process to track the translation of the target object.

3. The method of claim 1, further comprising:

incorporating and displaying a target object identifier indicating a position to which the target object is translated, in preview image data which is a result of outputting the input image data.

4. The method of claim 3, further comprising:

determining whether the target object is present in a Region Of Interest (ROI), based on a result of tracking the translation of the target object based on the pose or motion of the camera.

5. The method of claim 4, further comprising:

if the target object is present in the ROI, incorporating and displaying the target object identifier indicating a position to which the target object is translated, in the preview image data.

6. The method of claim 4, further comprising:

when the tracking of the target object based on the input image data is not possible even if the target object is present in the ROI, tracking the position of the target object based on the motion or pose of the camera.

7. The method of claim 4, further comprising:

if the target object is not present in the ROI, indicating that the target object is not present in the ROI by using the preview image data.

8. The method of claim 1, before tracking the translation of the target object, further comprising:

performing a first tracking process of tracking the translation of the target object based on the input image data;

performing a second tracking process of tracking the translation of the target object based on the estimated pose or motion of the camera;

comparing a result of the first tracking process with a result of the second tracking process to estimate actual motion of the target object; and

determining a ratio of selecting the result of the first tracking process to the result of the second tracking process based on the estimated actual motion.

9. The method of claim 8, further comprising:

transforming position data comprising a position of the target object in a previous frame and a position of the target object in a current frame by using interpolation or a filter to generate a target object identifier; and

incorporating and displaying the target object identifier in preview image data.

10. A camera apparatus comprising:

an imaging unit configured to receive an image and transform the input image into input image data;

an image processor configured to track a target object from the input image data;

a motion sensor configured to sense motion of a camera which captures the input image data; and

a motion processor configured to generate camera motion data according to the sensed motion of the camera,

wherein the image processor comprises a motion tracker configured to estimate a pose and motion of the camera based on the camera motion data, and estimate translation of the target object based on the estimated pose and motion of the camera.

11. The camera apparatus of claim 10, wherein the image processor tracks translation of the target object through at least one of a first tracking operation of tracking the translation of the target object based on the input image data and a second tracking operation of tracking the translation of the target object based on the estimated pose or motion of the camera.

12. The camera apparatus of claim 10, wherein the image processor incorporates a target object identifier indicating a position to which the target object is translated, in preview image data that is a result of outputting the input image data.

13. The camera apparatus of claim 12, wherein the image processor determines whether the target object is in a Region Of Interest (ROI), based on a result of tracking the translation of the target object based on the pose or motion of the camera.

14. The camera apparatus of claim 13, wherein the image processor incorporates the target object identifier indicating a position to which the target object is translated, in preview image data that is a result of tracking the target object, if the target object is present in the ROI.

15. The camera apparatus of claim 13, wherein the image processor tracks the position of the target object based on the motion or pose of the camera, when tracking of the target object based on the input image data is not possible even if the target object is present in the ROI.

16. The camera apparatus of claim 13, further comprising a display configured to display the preview image data,

wherein the image processor controls the display to indicate that the target object is not present in the ROI by using the preview image data, if the target object is not present in the ROI.

17. The camera apparatus of claim 10, wherein the image processor performs a first tracking operation of tracking the translation of the target object based on the input image data and a second tracking operation of tracking the translation of the target object based on the estimated pose or motion of the camera, compares a result of the first tracking process with a result of the second tracking process to estimate actual motion of the target object, and determines a ratio of selecting the result of the first tracking process to the result of the second tracking process based on the estimated actual motion.

18. The camera apparatus of claim 17, wherein the image processor transforms position data comprising a position of the target object in a previous frame and a position of the target object in a current frame by using interpolation or a filter to generate a target object identifier, and incorporates the generated target object identifier in preview image data.