Active presence detection with depth sensing
In vision-based authentication platforms for secure resources such as computer systems, false positives and/or false negatives in the detection of walk-away events are reduced or eliminated by incorporating depth information into tracking authenticated system operators.
1. A computer-implemented method for monitoring use of a secure system, the method comprising:
defining a detection zone extending from an operator terminal of the secure system to a depth boundary spaced apart from the operator terminal and corresponding to a distance from the operator terminal beyond which an operator cannot interact with the secure system;
detecting one or more operators associated with the secure system;
for each of the operators, (i) authenticating the operator and initiating a session for the operator on the operator terminal, (ii) detecting a walk-away event of the operator using a depth-sensing camera system co-located with the operator terminal based on the operator being detected beyond the depth boundary, and (iii) responsive to the walk-away event is being detected, starting a re-entry timer associated with the operator;
upon expiration of the re-entry timer associated with a respective operator, closing the session of the respective operator and logging the respective operator out of the secure system;
detecting a face within the detection zone using the depth-sensing camera system;
determining that the face corresponds to the respective operator; and
when the re-entry timer associated with the respective operator has not expired and the detected face corresponds to the respective operator, re-validating the session for the respective operator on the operator terminal without requiring additional authentication.
2. The method of claim 1 , further comprising:
determining if the detected face corresponds to an operator associated with an unexpired re-entry timer; and
comparing the detected face only to face exemplars of operators having unexpired re-entry timers.
3. The method of claim 1 , wherein detecting a walk-away event comprises using the depth-sensing camera to track a distance from the operator terminal to the operator and determining when the distance extends beyond a walk-away threshold distance.
4. The method of claim 3 , wherein the walk-away threshold distance within the detection zone is smaller than the distance to the distance of the depth boundary of the detection zone.
5. The method of claim 1 , wherein detecting the face within the detection zone using the depth-sensing camera system comprises:
using the depth-sensing camera system to acquire images of one or more objects;
using the depth-sensing camera to measure distances from the operator terminal to the one or more objects; and
computationally determining whether any of the one or more objects is within the detection zone and is a face.
6. The method of claim 5 , wherein computationally determining whether any of the one or more objects is within the detection zone and is a face comprises:
using a face-finding algorithm to detect faces in the images and thereafter computationally determining, based on the distances measured using the depth-sensing camera, which, if any, of the detected faces are present within the detection zone while excluding detected faces disposed at distances, measured using the depth-sensing camera, which are beyond the depth boundary.
7. The method of claim 1 , wherein each operator is authenticated via at least one of a password, authentication card, or token.
8. The method of claim 1 , wherein detecting the face within the detection zone comprises analyzing relative depth information measured with the depth-sensing camera to discriminate between faces and two-dimensional images thereof.
9. The method of claim 1 , further comprising, after authenticating each user, acquiring one or more face exemplars of the user using the depth-sensing camera system and saving the one or more face exemplars.
10. The method of claim 9 , further comprising indexing the face exemplars based, at least in part, on face posture as determined from three-dimensional information contained therein.
11. An access-control system for monitoring use of a secure system, the system comprising:
a depth-sensing camera system co-located with an operator terminal of the secure system; and
a computational facility including a processor and associated memory, the memory storing instructions, for execution by the processor, for:
defining a detection zone extending from an operator terminal of the secure system to a depth boundary spaced apart from the operator terminal and corresponding to a distance from the operator terminal beyond which an operator cannot interact with the secure system;
detecting one or more operators associated with the secure system;
for each of the operators, (i) authenticating the operator and initiating a session for the operator on the operator terminal, (ii) detecting a walk-away event of the operator using the depth-sensing camera system based on the operator being detected beyond the depth boundary, and (iii) responsive to the walk-away event being detected, starting a re-entry timer associated with the operator;
upon expiration of the re-entry timer associated with a respective operator, closing the session of the respective operator and logging the respective operator out of the secure system;
detecting a face within the detection zone using the depth-sensing camera system;
determining that the face corresponds to the respective operator; and
when the re-entry timers associated with the respective operator has not expired and the detected face corresponds to the respective operator, reactivating re-validating the session for the respective operator on the operator terminal without requiring additional authentication.
12. The system of claim 11 , wherein the instructions stored in the memory are further for determining if the detected face corresponds to an operator associated with an unexpired re-entry timer and comparing the detected face only to face exemplars of operators having unexpired re-entry timers.
13. The system of claim 11 , wherein the instructions stored in the memory for detecting a walk-away event comprise instructions for using the depth-sensing camera to track a distance from the operator terminal to the operator and determining when the distance extends beyond a walk-away threshold distance.
14. The system of claim 13 , wherein the walk-away threshold distance within the detection zone is smaller than the distance to the distance of the depth boundary of the detection zone.
15. The system of claim 11 , wherein the instructions stored in the memory for detecting the face within the detection zone using the depth-sensing camera system comprise instructions for:
using the depth-sensing camera system to acquire images of one or more objects;
using the depth-sensing camera to measure distances from the operator terminal to the one or more objects; and
computationally determining whether any of the one or more objects is within the detection zone and is a face.
16. The system of claim 15 , wherein the instructions for computationally determining whether any of the one or more objects is within the detection zone and is a face comprise instructions for:
using a face-finding algorithm to detect faces in the images and thereafter computationally determining, based on the distances measured using the depth-sensing camera, which, if any, of the detected faces are present within the detection zone while excluding detected faces disposed at distances, measured using the depth-sensing camera, which are beyond the depth boundary.
17. The system of claim 11 , wherein each operator is authenticated via at least one of a password, authentication card, or token.
18. The system of claim 11 , wherein the instructions stored in the memory for detecting the face within the detection zone comprise instructions for analyzing relative depth information measured with the depth-sensing camera to discriminate between faces and two-dimensional images thereof.
19. The system of claim 11 , wherein the instructions stored in the memory further comprise instructions for, after authenticating each user, acquiring one or more face exemplars of the user using the depth-sensing camera system and saving the one or more face exemplars.
20. The system of claim 19 , wherein the instructions stored in the memory further comprise instructions for indexing the face exemplars based, at least in part, on face posture as determined from three-dimensional information contained therein.