Target localization utilizing wireless and camera sensor fusion
According to some implementations, an estimate of a target's location can be calculated by correlating Wi-Fi and video location measurements. This spatio-temporal correlation combines the Wi-Fi and video measurements to determine an identity and location of an object. The accuracy of the video localization and the identity from the Wi-Fi network provide an accurate location of the Wi-Fi identified object.
1. A method comprising:
obtaining, by a computing device, image data associated with an object;
estimating, by the computing device, a first location of the object based on the image data and a first probability grid, where the image data is used to generate a value for each cell of the first probability grid that indicates a probability that a first probability grid cell is occupied by the object;
obtaining, by the computing device, wireless signal data from a device;
estimating, by the computing device, a second location of the device based on the wireless signal data and a second probability grid, where the wireless signal data is used to generate a value for each cell of the second probability grid that indicates a probability that a second probability grid cell is occupied by the device; and
multiplying each of the first probability grid cells with respective cells of the second probability grid to determine which two corresponding grid cells produce a largest probability across the first and second probability grids; and
estimating, by the computing device, a current location of the device based on corresponding grid cells that produce the largest probability.
2. The method of claim 1 , where estimating the first location of the object based on the image data comprises:
transforming the image data through a ground plane homography projection.
3. The method of claim 1 , wherein the image data comprises images captured by different cameras having overlapping fields of view.
4. The method of claim 1 , wherein estimating the first location of the object comprises calculating an object track corresponding to the object.
5. The method of claim 1 , wherein obtaining wireless signal data from the device includes obtaining device identification information from the wireless signal data.
6. A system comprising:
one or more processors; and
a computer-readable medium including one or more sequences of instructions which,
when executed by the one or more processors, causes:
obtaining image data associated with an object;
estimating a first location of the object based on the image data and a first probability grid, where the image data is used to generate a value for each cell of the first probability grid that indicates a probability that a first probability grid cell is occupied by the object;
obtaining wireless signal data from a device;
estimating a second location of the device based on the wireless signal data and a second probability grid, where the wireless signal data is used to generate a value for each cell of the second probability grid that indicates a probability that a second probability grid cell is occupied by the device;
multiplying each of the first probability grid cells with respective cells of the second probability grid to determine which two corresponding grid cells produce a largest probability across the first and second probability grids; and
estimating a current location of the device based on the corresponding grid cells that produce the largest probability.
7. The system of claim 6 , wherein the instructions that cause estimating the first location of the object based on the image data comprise instructions that cause transforming the image data through a ground plane homography projection.
8. The system of claim 6 , wherein the image data comprises images captured by different cameras having overlapping fields of view.
9. The system of claim 6 , wherein the instructions that cause estimating the first location of the object comprise instructions that cause calculating an object track corresponding to the object.
10. The system of claim 6 , wherein the instructions that cause obtaining wireless signal data from the device comprise instructions that cause obtaining device identification information from the wireless signal data.
11. A non-transitory computer-readable medium including one or more sequences of instructions which, when executed by one or more processors, causes:
obtaining image data associated with an object;
estimating a first location of the object based on the image data and a first probability grid, where the image data is used to generate a value for each cell of the first probability grid that indicates a probability that a first probability grid cell is occupied by the object;
obtaining wireless signal data from a device;
estimating a second location of the device based on the wireless signal data and a second probability grid, where the wireless signal data is used to generate a value for each cell of the second probability grid that indicates a probability that a second probability grid cell is occupied by the device;
multiplying each of the first probability grid cells with respective cells of the second probability grid to determine which two corresponding grid cells produce a largest probability across the first and second probability grids; and
estimating a current location of the device based on the corresponding grid cells that produce the largest probability.
12. The non-transitory computer-readable medium of claim 11 , wherein the instructions that cause estimating the first location of the object based on the image data comprise instructions that cause transforming the image data through a ground plane homography projection.
13. The non-transitory computer-readable medium of claim 11 , wherein the image data comprises images captured by different cameras having overlapping fields of view.
14. The non-transitory computer-readable medium of claim 11 , wherein the instructions that cause estimating the first location of the object comprise instructions that cause calculating an object track corresponding to the object.
15. The non-transitory computer-readable medium of claim 11 , wherein the instructions that cause obtaining wireless signal data from the device comprise instructions that cause obtaining device identification information from the wireless signal data.