Path detection for tolling system using vehicle identifier correlation

1. A method performed by a computing system, the method comprising:

receiving from a first detection system, a plurality of identity tokens, the plurality of identity tokens including different types of identity tokens, the first detection system having a plurality of different types of detection instruments;

receiving from a second detection system, a number of identity tokens, the second detection system having a plurality of different types of detection instruments;

using information from the first detection system and the second detection system, creating correlation information that correlates different types of identity tokens;

using information from the first detection system and the second detection system, determining path likelihood for a plurality of moving objects passing through the first detection system and the second detection system, wherein determining path likelihood comprises determining a set of possible paths between two detection nodes and assigning a likelihood value to each possible path based at least in part on transmit times of the nodes along the possible paths; and

updating the correlation information using the path likelihood for the plurality of moving objects.

2. The method of claim 1 , wherein determining path likelihood comprises using a directed hypergraph representing real world roadways.

3. The method of claim 2 , wherein nodes of the hypergraph represent a one-way path between two points on the real world roadways.

4. The method of claim 3 , wherein metadata for each node includes a start point, an end point, and a time of transit range.

5. The method of claim 2 , wherein nodes corresponding to paths that have detection equipment are designated as detection nodes.

6. The method of claim 3 , wherein edges of the hypergraph represent connections between two paths.

7. The method of claim 1 , wherein the detection system includes a plurality of detection instruments, each of the plurality of detection instruments being configured to detect a different type of identity token.

8. The method of claim 7 , wherein the detection instruments include at least one of: a Radio Frequency Identifier (RFID) reader, an image sensor, and a network interface system.

9. The method of claim 1 , wherein the types of identity token include at least one of: a license plate number, an RFID number, and a network address.

10. A computing system comprising:

a processor; and

a memory comprising machine readable instructions that when executed by the processor, cause the system to:

receive from a first detection system, a plurality of identity tokens, the plurality of identity tokens including different types of identity tokens, the first detection system having a plurality of different types of detection instruments;

receive from a second detection system, a number of identity tokens, the second detection system having a plurality of different types of detection instruments;

create correlation information that correlates different types of identity tokens that correspond to a plurality of moving objects passing through the first detection system and the second detection system, based on data received from the first detection system and the second detection system;

determine path likelihood for a plurality of moving objects passing through the first detection system and the second detection system, based on data received from the first detection system and the second detection system, wherein determining path likelihood comprises determining a set of possible paths between two detection nodes and assigning a likelihood value to each possible path based at least in part on transit times of the nodes along the possible paths; and

update the correlation information using the path likelihood for the plurality of moving objects.

11. The system of claim 10 , wherein determining path likelihood comprises using a directed hypergraph representing real world roadways.

12. The system of claim 11 , wherein nodes of the hypergraph represent a one-way path between two points on the real world roadways.

13. The system of claim 12 , wherein metadata for each node includes a start point, an end point, and a time of transit range.

14. The method of claim 11 , wherein nodes corresponding to paths that have detection equipment are designated as detection nodes.

15. The system of claim 12 , wherein edges of the hypergraph represent connections between two paths.

16. A method performed by a computing system, the method comprising:

receiving, from a plurality of detection systems, identity tokens of different types for a plurality of moving objects, each of the identity tokens corresponding to a detection event within a detection volume;

recording a number of occurrences for each of the identity tokens;

recording a number of co-occurrences for instances in which two different identity tokens pass through a detection volume during a detection time window;

identifying correlations between different types of identity tokens with each other based on a threshold ratio between occurrences and co-occurrences;

determining path likelihood for the plurality of moving objects by determining a set of possible paths between two detection nodes and assigning a likelihood value to each possible path based at least in part on transit times of the nodes along the possible paths; and

updating the correlations based on the determined path likelihoods between two different detection systems.

17. The method of claim 16 , wherein updating correlations comprises increasing correlation between two identity tokens if there is a high path likelihood between two correlated identity tokens being detected together at two different detection systems at different times.

18. The method of claim 16 , wherein updating correlations comprises decreasing correlation between two identity tokens if there is no likely path between the two identity tokens being detected at two different detection systems at different times.