US Patent 11184556 Camera vision system overlap management without network coordination

A system of cameras includes a first camera and a second camera. The first camera captures a first image with a first total number of objects and a first total number of edge objects. The second camera captures a second image with a second total number of objects and a second total number of edge objects. A controller determines the total number of objects by summing the first total number of objects and the second total number of objects and subtracting the first total number of edge objects. In another implementation, the first camera and the second camera can have a coordinate system used to assign coordinates to objects identified in a first image from the first camera and a second image from the second camera. A controller can compare the coordinates of the objects to identify duplicates to determine an accurate total number of objects.