Indoor positioning method based on image visual features and electronic device

1. An indoor positioning method based on image visual features executable by a client, comprising:

matching a Wi-Fi signal strength value of a Wi-Fi tag closest to a current location of a mobile device with a signal strength list in a map database to obtain a first location of a first Wi-Fi tag with the greatest matching degree;

matching a speeded up robust features (SURF) descriptor of an image of the Wi-Fi tag closest to the current location of the mobile device with SURF descriptors recorded in the signal strength list in the map database to discover an image of a Wi-Fi tag with the greatest matching degree, thereby obtaining a second location of a second Wi-Fi tag corresponding to the image of the Wi-Fi tag with the greatest matching degree;

obtaining a three location of a three Wi-Fi tag according to a homography matrix corresponding to the image of the Wi-Fi tag with the largest matching degree and an empirical value of a positioning error; and

obtaining positioning information of the mobile device according to the first location, the second location and the third location.

2. The method of claim 1 , further comprising:

obtain the first location of the first Wi-Fi tag with the greatest matching degree according to the number of Wi-Fi access points (APs) and the signal strength values recorded in the signal strength list.

3. An indoor positioning method based on image visual features executable by a client, comprising:

when a mobile device moves near one of Wi-Fi tags, collecting signal strength values of Wi-Fi signals of Wi-Fi APs near the Wi-Fi tag;

matching the signal strength values of the Wi-Fi tag with a signal strength list in a map database;

obtain a first location of a first Wi-Fi tag with the greatest matching degree according to the matching result of the signal strength values;

calculating a SURF descriptor of an image of the Wi-Fi tag;

matching the SURF descriptor with SURF descriptors recorded in the map database;

discovering an image of a Wi-Fi tag with the highest matching degree in the map database according to the matching result of the SURF descriptors and obtaining a second location of a second Wi-Fi tag according to the SURF descriptors recorded in the map database;

calculating a homography matrix based on the image of the Wi-Fi tag with the greatest matching degree;

calculating current coordinates of a third Wi-Fi tag according to the homography matrix and a positioning error value to obtain a third location of the third Wi-Fi tag; and

obtaining positioning information of the mobile device according to the first location, the second location and the third location.

4. The method of claim 3 , wherein further comprising:

matching the signal strength values of the Wi-Fi tag with the signal strength list in the map database using a matching formula represented as:

M

⁡

(

x

,

y

)

=

∏

i

=

1

N

(

1

+

λ

)

⁢

exp

(

-

(

(

x

i

-

y

i

)

x

i

-

α

)

2

)

=

(

1

+

λ

)

N

⁢

∏

i

=

1

N

exp

(

-

(

(

x

i

-

y

i

)

x

i

-

α

)

2

)

;

where N is the number of the Wi-Fi APs within a signal range of the Wi-Fi tag, x is a signal strength value between a Wi-Fi AP and a Wi-Fi tag in the map database, y is a signal strength value between a Wi-Fi AP and a Wi-Fi tag collected in a positioning phase, and λ, and α are measured values.

5. The method of claim 3 , further comprising:

matching the SURF descriptor with the SURF descriptors stored in the map database using a K-nearest neighbor (KNN) algorithm.

6. The method of claim 3 , wherein each of the signal strength values in the signal strength list in the map database is greater than a preset value.

7. The method of claim 3 , further comprising:

calculating the homography matrix according to three-dimensional coordinates of 4 vertices of the image of the Wi-Fi tag in space.

8. The method of claim 3 , wherein the step of calculating the SURF descriptor of the image of the Wi-Fi tag further comprises:

selecting the center point of the image of the Wi-Fi tag as a SURF point of the image;

taking a square box around the SURF point;

dividing the square box into 16 sub-regions, wherein each of the sub-region contains 25 pixels;

counting the sum of the pixel values in the horizontal direction, the sum of the absolute values of the pixel values in the horizontal direction, the sum of the pixel values in the vertical direction and the sum of the absolute values of the pixel values in the vertical direction of the 25 pixels through Haar wavelet transformation, to obtain the SURF descriptor.

9. An electronic device, comprising:

a wireless signal matching module, configured to match a Wi-Fi signal strength value of a Wi-Fi tag closest to a current location of a mobile device with a signal strength list in a map database to obtain a first location of a first Wi-Fi tag with the greatest matching degree;

a SURF descriptor matching module, configured to match a SURF descriptor of an image of the Wi-Fi tag closest to the current location of the mobile device with SURF descriptors recorded in the signal strength list in the map database to discover an image of a Wi-Fi tag with the greatest matching degree, thereby obtaining a second location of a second Wi-Fi tag corresponding to the image of the Wi-Fi tag with the greatest matching degree; and

a coordinate matching module, configured to obtain a three location of a three Wi-Fi tag according to a homography matrix corresponding to the image of the Wi-Fi tag with the largest matching degree and an empirical value of a positioning error;

wherein positioning information of the mobile device is obtained according to the first location, the second location and the third location.

10. The device of claim 9 , wherein the wireless signal matching module obtains the first location of the first Wi-Fi tag with the greatest matching degree according to the number of Wi-Fi APs and the signal strength values recorded in the signal strength list.