Vision chip architecture for simultaneous output of multi-target positions

In this paper, we describe new vision chip architecture, which enables simultaneous output of multi-target positions. This architecture selects targets that don't overlap at each other in the direction of the column and extracts the target positions simultaneously. Thanks to this simultaneous output, the vision chip based on the architecture can obtain many target positions at high-speed. On that point, this vision chip will be useful in wide field of applications in the future.