Reconfigurable sensor array

An object tracking method, comprising:

• receiving a first (x,y) coordinate within a space for a sensor from a position sensor, wherein:
• the first (x,y) coordinate corresponds with a new physical location of the sensor within the space;
• the sensor is configured to capture frames of a global plane for at least a portion of the space, wherein:
• the global plane represents (x,y) coordinates for the at least a portion of the space;
• each frame comprises a plurality of pixels;
• and
• each pixel from the plurality of pixels is associated with a pixel location comprising a pixel row and a pixel column;
• and
• the position sensor is configured to output (x,y) coordinates corresponding with the physical location of the sensor within the space;
• determining translation coefficients for the sensor based on a difference between the first (x,y) coordinate and a second (x,y) coordinate, wherein the second (x,y) coordinate corresponds with a previous physical location of the sensor within the space;
• updating a homography that is associated with the sensor by applying the translation coefficients to the homography, wherein:
• the homography comprises coefficients that translate between pixel locations in a frame from the sensor and (x,y) coordinates in the global plane;
• and
• the homography is associated with sensor located at the second (x,y) coordinate within the space;
• and
• storing the updated homography.

A computer program comprising executable instructions stored in a non-transitory computer readable medium that when executed by a processor causes the processor to:

• receive a first (x,y) coordinate within a space for a sensor from a position sensor, wherein:
• the first (x,y) coordinate corresponds with a new physical location of the sensor within the space;
• the sensor is configured to capture frames of a global plane for at least a portion of the space, wherein:
• the global plane represents (x,y) coordinates for the at least a portion of the space;
• each frame comprises a plurality of pixels;
• and
• each pixel from the plurality of pixels is associated with a pixel location comprising a pixel row and a pixel column;
• and
• the position sensor is configured to output (x,y) coordinates corresponding with the physical location of the sensor within the space;
• determine translation coefficients for the sensor based on a difference between the first (x,y) coordinate and a second (x,y) coordinate, wherein the second (x,y) coordinate corresponds with a previous physical location of the sensor within the space;
• update a homography that is associated with the sensor by applying the translation coefficients to the homography, wherein:
• the homography comprises coefficients that translate between pixel locations in a frame from the sensor and (x,y) coordinates in the global plane;
• and
• the homography is associated with sensor located at the second (x,y) coordinate within the space;
• and
• store the updated homography.