Method and system for computing parking occupancy

1. A method for computing street parking occupancy for a street segment, comprising

running a baseline occupancy module for the street segment using at least map data and image data to compute a baseline occupancy;

running a continuous time occupancy module for the street segment using at least the baseline occupancy and historical data to compute a continuous time occupancy; and

running a forecast occupancy module for the street segment using the continuous time occupancy module and at least real-time data to compute a forecast occupancy,

wherein the baseline occupancy model comprises a car recognition module that outputs a plurality of georeferenced features corresponding to cars detected in the image data, and

wherein the baseline occupancy module further comprises a center line module, wherein the center line module outputs at least georeferenced oriented features corresponding to a middle of the street segment.

2. The method according to claim 1 , wherein the baseline occupancy module further comprises a parked car identification module that uses the outputs of the car recognition module and the center line module to compute a plurality of georeferenced features corresponding to cars and wherein each feature corresponding to a car further comprises a probability that the car is parked, and wherein the parked car identification module filters out at least one of:

cars that are moving;

cars that are parked on private property; and

cars that are parked on private parking lots.

3. The method according to claim 2 , wherein the baseline occupancy module computes a section capacity value comprising at least a number of cars that can park in the street segment with lower and upper bounds of said number of cars that can park in the street segment.

4. The method according to claim 3 , wherein the street parking occupancy for the street segment obtained by the forecast occupancy module is displayed with a map by the mobile device.

5. The method according to claim 1 , wherein the historical data comprises at least one of:

historical movement data, comprising at least one of:

floating car data;

tracking data from navigation service providers; and

mobile network data; and

historical event data, comprising at least one of:

parking assistance application data;

parking payment provider data;

parking management system data; and

car sharing company data.

6. The method according to claim 1 , wherein the continuous time occupancy module comprises a parking event identification module that outputs a plurality of park-in and park-out events on the street segment based on the historical data.

7. The method according to claim 1 , wherein the continuous time occupancy module outputs a model that provides a measure of parking availability for the street segment and a time.

8. The method according to claim 7 , wherein the continuous time occupancy module takes into account variable types including at least one of:

location and vicinity characteristics;

time and date; and

number of parking events in the recent history.

9. The method according to claim 7 , wherein the continuous time occupancy module computes an output using at least one of:

statistical filtering methods; and

spatial point processes.

10. The method according to claim 1 , wherein the forecast occupancy module outputs a predicted availability of parking spaces in the street segment at a future time.

11. The method according to claim 1 , further comprising running a readjustment module using at least new data to provide an output, and wherein the output of the readjustment module is used as a further input into the continuous time occupancy module.

12. A system that computes street parking occupancy of a street segment, comprising:

a server, comprising:

a memory component storing instructions and configured to store at least image data, map data and historical data; and

a processing component configured to execute the instructions to at least:

run a baseline occupancy module for the street segment using at least the map data and the image data to compute a baseline occupancy;

run a continuous time occupancy module for the street segment using at least the baseline occupancy and the historical data to compute a continuous time occupancy; and

run a forecast occupancy module for the street segment using at least the continuous time occupancy and real-time data to compute a forecast occupancy,

wherein the baseline occupancy module outputs at least an estimate of a percentage of available parking spots for the street segment and an error rate of the estimate.

13. The system according to claim 12 , wherein the server is configured to communicate the forecast occupancy with one or more mobile devices in response to a request for the street parking occupancy of the street segment.

14. The system according to claim 13 , wherein the server is configured to send updates to the mobile device when the forecast occupancy changes.

15. The system according to claim 13 , wherein the mobile device is configured to send the server data relating to parking events, wherein the server is configured to process the data sent by the mobile device and to incorporate the data into at least one of

the historical data; and

the real-time data, and

wherein the server is configured to re-compute at least one of the continuous time occupancy module and the forecast occupancy module based on the data sent by the mobile device.

16. The system according to claim 13 , wherein the mobile device further comprises a graphical display and wherein the server is configured to send a graphical representation of parking availability obtained by the forecast occupancy module to the graphical display.

17. The system according to claim 16 , wherein the graphical representation comprises a heatmap.

18. A method for computing street parking occupancy for a street segment, comprising

running a baseline occupancy module for the street segment using at least map data and image data to compute a baseline occupancy;

running a continuous time occupancy module for the street segment using at least the baseline occupancy and historical data to compute a continuous time occupancy; and

running a forecast occupancy module for the street segment using the continuous time occupancy module and at least real-time data to compute a forecast occupancy;

wherein the baseline occupancy module outputs at least an estimate of a percentage of available parking spots for the street segment and an error rate of the estimate.