Method to reject false positives detecting and tracking image objects

• US 8,836,799 B2
• Filed: 07/16/2012
• Issued: 09/16/2014
• Est. Priority Date: 03/30/2012
• Status: Expired due to Fees

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Kim, Taesu, Cho, Hyun-Mook, Koo, Hyung-Il
• Primary Examiner(s): SELBY, GEVELL V
• Application Number:
  US13/550,531
• Publication Number:
  US 20130258141A1
• Time in Patent Office: 792 Days
• Field of Search: 348/208.14, 348/222.1, 348/226.1
• US Class Current: 348/208.14
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: H04N 23/70 Circuitry for compensating brightness variation in the scene

Abstract

Methods, apparatuses, systems, and computer-readable media for rejecting false positive detection and tracking of image objects are presented. According to one or more aspects, a computing device may implement embodiments of the invention to use the movement of the mobile device for distinguishing false positives from true movement of the mobile device depicted in the field of view of the camera. In one embodiment, the actual movement of the mobile device may be measured using multi-modal sensor data from inertial sensors such as accelerometers and gyroscopes. In another embodiment, the actual movement of the device is calculated using the global movement of the mobile phone with reference to other objects in the field of view of the camera.

Claims

1. A method for rejecting information using a mobile device, the method comprising:

obtaining a video frame using a camera coupled to the mobile device;

detecting an at least one portion of the video frame at least partially representing a feature;

identifying a first shift associated with the at least one portion of the video frame;

identifying a second shift associated with an entire video frame, wherein the second shift associated with the entire video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

determining a disparity between the first shift and the second shift;

determining flickering in a detection of the feature by determining that the disparity is higher than a predetermined threshold; and

rejecting the at least one portion of the video frame at least partially representing the feature as a false positive detection due to flickering.

2. The method of claim 1, further comprising overlaying a video according to the first shift for displaying on a display unit if the disparity is lower than the predetermined threshold.

3. The method of claim 1, wherein identifying the second shift associated with the entire video frame further comprises using motion detected from an inertial sensor coupled to the mobile device.

4. The method of claim 3, wherein the inertial sensor is at least one from a group comprising of a gyroscope and an accelerometer.

5. A method for tracking at least one portion of a video, the method comprising:

obtaining a video frame using a camera coupled to a mobile device;

identifying a shift associated with the video frame, wherein the shift associated with the video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

determining an at least one possible location for the at least one portion of the video frame representing a feature based on the shift associated with the video frame; and

tracking the at least one portion of the video frame at the at least one possible location.

6. The method of claim 5, further comprising rejecting the at least one portion of the video frame partially representing the feature as a false positive detection of the feature if the at least one portion of the video frame is detected outside the at least one possible location for the at least one portion of the video frame.

7. The method of claim 5, further comprising overlaying the video according to the shift.

8. The method of claim 5, wherein identifying the shift associated with the video frame further comprises using motion detected from an inertial sensor coupled to the mobile device.

9. The method of claim 8, wherein the inertial sensor is at least one from a group comprising of a gyroscope and an accelerometer.

10. A device, comprising:

a processor;

a camera coupled to the processor;

a display unit coupled to the processor; and

a non-transitory computer readable storage medium coupled to the processor, wherein the non-transitory computer readable storage medium comprises code executable by the processor comprising;

obtaining a video frame using the camera coupled to the device;

detecting an at least one portion of the video frame at least partially representing a feature;

identifying a first shift associated with the at least one portion of the video frame;

identifying a second shift associated with an entire video frame, wherein the second shift associated with the entire video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

determining a disparity between the first shift and the second shift;

determining flickering in a detection of the feature by determining that the disparity is higher than a predetermined threshold; and

rejecting the at least one portion of the video frame at least partially representing the feature as a false positive detection due to flickering.

11. The device of claim 10, further comprising overlaying a video according to the first shift for displaying on the display unit if the disparity is lower than the predetermined threshold.

12. The device of claim 10, wherein identifying the second shift associated with the entire video frame further comprises using an inertial sensor coupled to the device.

13. The device of claim 12, wherein the inertial sensor is at least one from a group comprising of a gyroscope and an accelerometer.

14. A device, comprising:

a processor;

a camera coupled to the processor;

a display unit coupled to the processor; and

a non-transitory computer readable storage medium coupled to the processor, wherein the non-transitory computer readable storage medium comprises code executable by the processor comprising;

obtaining a video frame using the camera coupled to the device for tracking an at least one portion of the video frame;

identifying a shift associated with the video frame, wherein the shift associated with the video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

determining an at least one possible location for the at least one portion of the video frame representing a feature based on the shift associated with the video frame; and

tracking the at least one portion of the video frame at the at least one possible location.

15. The code of claim 14, further comprising rejecting the at least one portion of the video frame partially representing the feature as a false positive detection of the feature if the at least one portion of the video frame is detected outside the at least one possible location for the at least one portion of the video frame.

16. The code of claim 14, further comprising overlaying a video according to the shift.

17. The code of claim 14, wherein identifying the shift associated with the video frame further comprises using motion detected from an inertial sensor coupled to the device.

18. The code of claim 17, wherein the inertial sensor is at least one from a group comprising of a gyroscope and an accelerometer.

19. A non-transitory computer readable storage medium coupled to a processor, wherein the non-transitory computer readable storage medium comprises a computer program executable by the processor comprising:

obtaining a video frame using a camera coupled to a mobile device;

detecting an at least one portion of the video frame at least partially representing a feature;

identifying a first shift associated with the at least one portion of the video frame;

identifying a second shift associated with an entire video frame, wherein the second shift associated with the entire video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

determining a disparity between the first shift and the second shift;

determining flickering in a detection of the feature by determining that the disparity is higher than a predetermined threshold; and

rejecting the at least one portion of the video frame at least partially representing the feature as a false positive detection due to flickering.

20. A non-transitory computer readable storage medium coupled to a processor, wherein the non-transitory computer readable storage medium comprises a computer program executable by the processor comprising:

obtaining a video frame using a camera coupled to a mobile device, for tracking an at least one portion of the video frame;

identifying a shift associated with the video frame, wherein the shift associated with the video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

determining an at least one possible location for the at least one portion of the video frame representing a feature based on the shift associated with the video frame; and

tracking the at least one portion of the video frame at the at least one possible location.

21. An apparatus for rejecting information comprising:

means for obtaining a video frame using a camera coupled to a mobile device;

means for detecting an at least one portion of the video frame at least partially representing a feature;

means for identifying a first shift associated with the at least one portion of the video frame;

means for identifying a second shift associated with an entire video frame, wherein the second shift associated with the entire video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

means for determining a disparity between the first shift and the second shift;

means for determining flickering in a detection of the feature by determining that the disparity is higher than a predetermined threshold; and

means for rejecting the at least one portion of the video frame at least partially representing the feature as a false positive detection due to flickering.

22. An apparatus for tracking comprising:

means for obtaining a video frame using a camera coupled to a mobile device for tracking an at least one portion of the video;

means for identifying a shift associated with the video frame, wherein the shift associated with the video frame is identified using motion calculated from portions of the video frame that are distinct from the at least one portion of the video frame;

means for determining an at least one possible location for the at least one portion of the video frame representing a feature based on the shift associated with the video frame; and

means for tracking the at least one portion of the video frame at the at least one possible location.