Prioritization of facial recognition matches based on likely route
Prioritizing facial recognition matches includes obtaining identification information and a facial image for each visitor entering the monitored environment, the monitored environment having a plurality of cameras at known locations including entry and exit points; obtaining itineraries of the visitors. Itineraries of the visitors are obtained, and based on the entry points and the itineraries of the visitors, likely routes of the visitors are determined through the monitored environment. Responsive to receiving an image captured by a first camera at a first location at an image capture time, the database records are sorted for facial recognition matching with the image from the first camera based on the visitors whose routes are likely to place the visitors in proximity to the first camera at the time of image capture.
1. A method for prioritizing facial recognition matches, comprising:
obtaining identification information and a facial image for each visitor entering a monitored environment, the monitored environment having a plurality of cameras at known locations throughout the monitored environment including entry and exit points;
obtaining itineraries of the visitors;
based on the entry points and the itineraries of the visitors, determining likely routes of the visitors through the monitored environment; and
responsive to receiving an image captured by a first camera at a first location at an image capture time, sorting visitor database records for facial recognition matching with the image from the first camera based on the visitors whose routes are likely to place the visitors in proximity to the first camera at the time of image capture.
2. The method of claim 1 , wherein determining likely routes of the visitors through the monitored environment further comprises: using the entry points of each of the visitors, exit points and departure times to calculate routes that the visitors are likely to take through the monitored environment.
3. The method of claim 2 , further comprising receiving changes to exit points assigned to the visitors in real time and recalculating the routes that the visitors are likely to take through the monitored environment.
4. The method of claim 1 , wherein sorting the visitor database further comprises:
analyzing the likely routes of the visitors to determine a position probability of each of the visitors being in proximity to the location of the first camera at the time of image capture; and
prioritizing visitor records in the visitor database for facial recognition matching with the image from the first camera based on the visitors determined to have highest position probabilities.
5. The method of claim 4 , further comprising augmenting the position probabilities based on the likely routes of the visitors using information retrieved from social networking websites.
6. The method of claim 1 further comprising:
once a match is found in the visitor database for the first image captured by the first camera, identifying the visitor in the image based on the identification information associated with the matching image; and
responsive to determining if the identified visitor has a route that is likely to place the visitor in proximity to the first camera at the time of image capture, marking the identified visitor in the visitor database as verified for being detected at an anticipated location at an anticipated time.
7. The method of claim 1 , further comprising: once one of the visitors is identified in the first image, presenting the identified visitor or collective profiles of identified visitors with personalized content, wherein the personalized content comprises at least one of personalized advertisements and flight screen status.
8. The method of claim 1 , further comprising: for each of the visitors who has a route that is likely to place the visitor in proximity to the first camera around the time of image capture, but has yet to be identified, marking the visitor as unverified in the visitor database; and searching for the unverified visitor using cameras in other locations within the monitored environment.
9. The method of claim 1 , further comprising: once visitors are detected exiting the monitored environment through one of the entry and exit points, marking the visitor as exited and removing or lowering the visitors' priority in the visitor database.
10. A system, comprising:
a memory;
a processor coupled to the memory; and
a software component executed by the processor that is configured to:
obtain identification information and a facial image for each visitor entering a monitored environment, the monitored environment having a plurality of cameras at known locations throughout the monitored environment including entry and exit points;
obtain itineraries of the visitors;
based on the entry points and the itineraries of the visitors, determine likely routes of the visitors through the monitored environment; and
responsive to receiving an image captured by a first camera at a first location at an image capture time, sort visitor database records for facial recognition matching with the image from the first camera based on the visitors whose routes are likely to place the visitors in proximity to the first camera at the time of image capture.
11. The system of claim 10 , wherein the software component is further configured to determine likely routes of the visitors through the monitored environment by: using the entry points of each of the visitors, exit points and departure times to calculate routes that the visitors are likely to take through the monitored environment.
12. The system of claim 11 , wherein the software component is further configured to: receive changes to exit points assigned to the visitors in real time and recalculate the routes that the visitors are likely to take through the monitored environment.
13. The system of claim 10 , wherein the software component is further configured to:
analyze the likely routes of the visitors to determine a position probability of each of the visitors being in proximity to the location of the first camera at the time of image capture; and
prioritize visitor records in the visitor database for facial recognition matching with the image from the first camera based on the visitors determined to have highest position probabilities.
14. The system of claim 13 , wherein the position probabilities are augmented based on the likely routes of the visitors using information retrieved from social networking websites.
15. The system of claim 10 , wherein the software component is further configured to:
once a match is found in the visitor database for the first image captured by the first camera, identify the visitor in the image based on the identification information associated with the matching image; and
responsive to determining if the identified visitor has a route that is likely to place the visitor in proximity to the first camera at the time of image capture, mark the identified visitor in the visitor database as verified for being detected at an anticipated location at an anticipated time.
16. The system of claim 10 , wherein once one of the visitors is identified in the first image, the identified visitor or collective profiles of identified visitors is presented with personalized content, wherein the personalized content comprises at least one of personalized advertisements and flight screen status.
17. The system of claim 10 , wherein for each of the visitors who has a route that is likely to place the visitor in proximity to the first camera around the time of image capture, but has yet to be identified, the visitor is marked as unverified in the visitor database; and searched for the unverified visitor using cameras in other locations within the monitored environment.
18. The system of claim 10 , wherein once visitors are detected exiting the monitored environment through one of the entry and exit points, the visitor is marked as exited and remove or lower the visitors' priority in the visitor database.
19. A tangible, non-transitory computer-readable medium comprising program instructions for prioritizing facial recognition matches, the program instructions comprising:
obtaining identification information and a facial image for each visitor entering a monitored environment, the monitored environment having a plurality of cameras at known locations throughout the monitored environment including entry and exit points;
obtaining itineraries of the visitors;
based on the entry points and the itineraries of the visitors, determining likely routes of the visitors through the monitored environment; and
responsive to receiving an image captured by a first camera at a first location at an image capture time, sorting visitor database records for facial recognition matching with the image from the first camera based on the visitors whose routes are likely to place the visitors in proximity to the first camera at the time of image capture.