Association of concurrent tracks using graph crossings

A system for sensing objects:

• a network computer, comprising:
• a memory that stores at least instructions;
• and
• one or more processors that are configured to execute instructions, wherein the instructions perform actions, including:
• employing two or more signal beams to scan a plurality of paths across an object, wherein two or more sensors separately detect signals from the two or more signal beams reflected by the object;
• generating a plurality of trajectories based on the separately detected signals, wherein each trajectory is associated with one or more events that correspond to the separately detected signals;
• determining one or more crossing points based on a portion of the plurality of trajectories that intersect each other during the scan of the object, wherein one or more unambiguous crossing points associated with one or more candidate trajectories that are in common with each other are obtained based on an absence of other crossing points occurring within a time range tolerance value;
• generating one or more graphs based on the portion of trajectories and the one or more crossing points, wherein each edge in the one or more graphs corresponds to a crossing point, and wherein each node in the one or more graphs corresponds to a trajectory;
• comparing the one or more graphs to determine one or more matched graphs that share a common topology;
• determining one or more common trajectories based on the one or more matched graphs;
• and
• determining one or more features of the object based on the one or more common trajectories;
• and
• one or more client computers, comprising:
• a memory that stores at least instructions;
• and
• one or more processors configured to execute instructions, wherein the instructions perform actions, including, providing the two or more signal beams to scan the plurality of paths across the object.

A network computer for sensing objects, comprising:

• a memory that stores at least instructions;
• and
• one or more processors configured to execute instructions, wherein the instructions perform actions, including:
• employing two or more signal beams to scan a plurality of paths across an object, wherein two or more sensors separately detect signals from the two or more signal beams reflected by the object;
• generating a plurality of trajectories based on the separately detected signals, wherein each trajectory is associated with one or more events that correspond to the separately detected signals;
• determining one or more crossing points based on a portion of the plurality of trajectories that intersect each other during the scan of the object, wherein one or more unambiguous crossing points associated with one or more candidate trajectories that are in common with each other are obtained based on an absence of other crossing points occurring within a time range tolerance value;
• generating one or more graphs based on the portion of trajectories and the one or more crossing points, wherein each edge in the one or more graphs corresponds to a crossing point, and wherein each node in the one or more graphs corresponds to a trajectory;
• comparing the one or more graphs to determine one or more matched graphs that share a common topology;
• determining one or more common trajectories based on the one or more matched graphs, wherein each common trajectory is associated with a same path across the object and a separate sensor;
• and
• determining one or more features of the object based on the one or more common trajectories.

A processor readable non-transitory storage media that includes instructions for sensing objects, wherein execution of the instructions by one or more processors on one or more network computers performs actions, comprising:

• employing two or more signal beams to scan a plurality of paths across an object, wherein two or more sensors separately detect signals from the two or more signal beams reflected by the object;
• generating a plurality of trajectories based on the separately detected signals, wherein each trajectory is associated with one or more events that correspond to the separately detected signals;
• determining one or more crossing points based on a portion of the plurality of trajectories that intersect each other during the scan of the object, wherein one or more unambiguous crossing points associated with one or more candidate trajectories that are in common with each other are obtained based on an absence of other crossing points occurring within a time range tolerance value;
• generating one or more graphs based on the portion of trajectories and the one or more crossing points, wherein each edge in the one or more graphs corresponds to a crossing point, and wherein each node in the one or more graphs corresponds to a trajectory;
• comparing the one or more graphs to determine one or more matched graphs that share a common topology;
• determining one or more common trajectories based on the one or more matched graphs, wherein each common trajectory is associated with a same path across the object and a separate sensor;
• and
• determining one or more features of the object based on the one or more common trajectories.