Utilizing camera to assist with indoor pedestrian navigation

1. A method implemented by a processor of a mobile device for estimating a current location of the mobile device within an indoor facility, the mobile device having a first camera mounted on a first side of the mobile device, the method comprising:

receiving a first sequence of image frames captured by the first camera, the first sequence of image frames being captured when the first camera is substantially faced toward a ceiling of the indoor facility;

for each pair of consecutive image frames in the first sequence:

identifying a transformation based on identifying changes between the pair of image frames in an image analysis of the image frames, and

correlating the transformation with an estimated change in position of the mobile device;

obtaining a first sequence of displacements based on the estimated changes in position of the mobile device for the pairs of consecutive image frames in the first sequence;

receiving a second sequence of image frames captured by a second camera of the mobile device, the second camera being mounted on a second side of the mobile device opposite to the first side, each image frame of the second sequence being captured substantially simultaneously as a corresponding image frame of the first sequence;

for each pair of consecutive image frames in the second sequence:

identifying a transformation based on identifying changes between the image frames in an image analysis of the image frames; and

correlating the transformation with an estimated change in position of the mobile device; and

obtaining a second sequence of displacements based on the estimated changes in position of the mobile device for the pairs of consecutive image frames in the second sequence; and

determining the current location of the mobile device within the indoor facility based on an initial location of the mobile device and the first and second sequences of displacements.

2. The method of claim 1 , wherein a transformation between a pair of consecutive image frames comprises at least one of a translation and a rotation between the image frames.

3. The method of claim 1 , further comprising obtaining, for each image frame in the first sequence, an accelerometer reading associated with the image frame, the accelerometer reading being taken at a time of capturing the image frame.

4. The method of claim 3 , further comprising determining, for each image frame in the first sequence, a tilt of the mobile device relative to the ceiling of the indoor facility at a time when the image frame was captured, the tilt of the mobile device determined based on the accelerometer reading associated with the image frame.

5. The method of claim 1 , wherein the current location of the mobile device within the indoor facility is determined based on the initial location of the mobile device and at least one of the first sequence of displacements and the second sequence of displacements.

6. The method of claim 1 , further comprising:

for each pair of consecutive image frames in the first sequence:

obtaining motion data from one or more motion sensors associated with the mobile device, the motion data indicating an estimated direction of motion of the mobile device during a time interval between capture times of the pair of image frames,

wherein the first sequence of displacements is obtained based on the estimated changes in position of the mobile device and the obtained motion data associated with the consecutive pairs of image frames in the first sequence.

7. The method of claim 6 , wherein each displacement in the first sequence of displacements is obtained by weighting the estimated change in position of the mobile device and the obtained motion data associated with a pair of consecutive image frames.

8. The method of claim 6 , wherein the one or more motion sensors include at least one of an accelerometer, a gyroscope and a magnetometer.

9. The method of claim 1 , wherein the image frames of the first sequence are captured at regular time intervals.

10. A mobile device, comprising:

a first camera on a first side of the mobile device;

a memory;

a processor coupled the first camera and the memory, wherein the processor is configured to:

receive a first sequence of image frames captured by the first camera, the first sequence of image frames being captured when the first camera is substantially faced toward a ceiling of the indoor facility;

for each pair of consecutive image frames in the first sequence:

identify a transformation based on identifying changes between the pair of image frames in an image analysis of the image frames, and

correlate the transformation with an estimated change in position of the mobile device;

obtain a first sequence of displacements based on the estimated changes in position of the mobile device for the pairs of consecutive image frames in the first sequence;

receiving a second sequence of image frames captured by a second camera of the mobile device, the second camera being mounted on a second side of the mobile device opposite to the first side, each image frame of the second sequence being captured substantially simultaneously as a corresponding image frame of the first sequence;

for each pair of consecutive image frames in the second sequence:

identifying a transformation based on identifying changes between the image frames in an image analysis of the image frames; and

correlating the transformation with an estimated change in position of the mobile device; and

obtaining a second sequence of displacements based on the estimated changes in position of the mobile device for the pairs of consecutive image frames in the second sequence;

and

determine the current location of the mobile device within the indoor facility based on an initial location of the mobile device and the first and second sequences of displacements.

11. The mobile device of claim 10 , wherein a transformation between a pair of consecutive image frames comprises at least one of a translation and a rotation between the image frames.

12. The mobile device of claim 10 , wherein the processor is further configured to obtain, for each image frame in the first sequence, an accelerometer reading associated with the image frame, the accelerometer reading being taken at a time of capturing the image frame.

13. The mobile device of claim 12 , wherein the processor is further configured to determine, for each image frame in the first sequence, a tilt of the mobile device relative to the ceiling of the indoor facility at a time when the image frame was captured, the tilt of the mobile device determined based on the accelerometer reading associated with the image frame.

14. The mobile device of claim 10 , wherein the current location of the mobile device within the indoor facility is determined based on the initial location of the mobile device and at least one of the first sequence of displacements and the second sequence of displacements.

15. The mobile device of claim 10 , wherein the processor is further configured to:

for each pair of consecutive image frames in the first sequence:

obtain motion data from one or more motion sensors associated with the mobile device, the motion data indicating an estimated direction of motion of the mobile device during a time interval between capture times of the pair of image frames,

wherein the first sequence of displacements is obtained based on the estimated changes in position of the mobile device and the obtained motion data associated with the consecutive pairs of image frames in the first sequence.

16. The mobile device of claim 15 , wherein each displacement in the first sequence of displacements is obtained weighting the estimated change in position of the mobile device and the obtained motion data associated with a pair of consecutive image frames.

17. The mobile device of claim 15 , wherein the one or more motion sensors include at least one of an accelerometer, a gyroscope and a magnetometer.

18. The mobile device of claim 10 , wherein the image frames of the first sequence are captured at regular time intervals.

19. A non-transitory computer-readable medium storing processor-executable instructions which, when executed, perform a method for estimating a current location of a mobile device within an indoor facility, the mobile device having a first camera mounted on a first side of the mobile device, the method comprising:

receiving a first sequence of image frames captured by the first camera, the first sequence of image frames being captured when the first camera is substantially faced toward a ceiling of the indoor facility;

for each pair of consecutive image frames in the first sequence:

identifying a transformation based on identifying changes between the pair of image frames in an image analysis of the image frames, and

correlating the transformation with an estimated change in position of the mobile device;

obtaining a first sequence of displacements based on the estimated changes in position of the mobile device for the pairs of consecutive image frames in the first sequence;

receiving a second sequence of image frames captured by a second camera of the mobile device, the second camera being mounted on a second side of the mobile device opposite to the first side, each image frame of the second sequence being captured substantially simultaneously as a corresponding image frame of the first sequence;

for each pair of consecutive image frames in the second sequence:

identifying a transformation based on identifying changes between the image frames in an image analysis of the image frames; and

correlating the transformation with an estimated change in position of the mobile device; and

obtaining a second sequence of displacements based on the estimated changes in position of the mobile device for the pairs of consecutive image frames in the second sequence; and

determining the current location of the mobile device within the indoor facility based on an initial location of the mobile device and the first and second sequences of displacements.

20. A method implemented by a processor of a mobile device for facilitating navigation within an indoor facility, the mobile device having a first camera mounted on a first side of the mobile device, the method comprising:

receiving a first sequence of image frames captured by the first camera, the first sequence of image frames being captured when the first camera is substantially faced toward a ceiling of the indoor facility;

for each pair of consecutive image frames in the first sequence:

identifying a transformation based on identifying changes between the pair of image frames in an image analysis of the image frames;

correlating the transformation with a first estimated direction of motion of the mobile device during a time interval between capture times of the pair of image frames in the first sequence;

receiving a second sequence of image frames captured by a second camera of the mobile device, the second camera being mounted on a second side of the mobile device opposite to the first side, each image frame of the second sequence being captured substantially simultaneously as a corresponding image frame of the first sequence;

for each pair of consecutive image frames in the second sequence:

identifying a transformation based on identifying changes between the image frames in an image analysis of the image frames; and

correlating the transformation with a second estimated direction of motion of the mobile device during a time interval between captures times of the pair of image frames in the second sequence;

obtaining motion data from one or more motion sensors associated with the mobile device, the motion data indicating a third estimated direction of motion of the mobile device during the time interval; and

determining a direction of motion of the mobile device during the time interval based on at least one of the first, second, and third estimated directions; and

determining a trajectory of the mobile device within the indoor facility corresponding to the first and second sequences of images frames based on a sequence of the determined directions of motion for the pairs of consecutive image frames in the first and second sequences.