IP Library › Granted Patent US 12,315,319
Granted Patent B2
US 12,315,319 · App. 18/318,226 · Granted May 27, 2025

Tailgating detection using multimodal entry data

Inventors: Abhijeet Shenoi (San Francisco, CA); Sagar Kashinath Honnungar (Mountain View, CA)
Assignee: HAKIMO INC.
G07C9/15G06T7/70G06V20/41G06V20/52G06V40/168G06V40/172G07C9/00571G06T2207/10016G06T2207/30201G06T2207/30232
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,315,319
App. No.
18/318,226
Granted
May 27, 2025
Kind
B2
Abstract

An electronic device and method for tailgating detection is provided. The electronic device receives data from an access control system for a physical entry point. When an event that indicates an access grant is detected, entry information for a period is collected. The information includes a set of authentications provided by the access control system. The electronic device receives a video from at least one imaging device, extracts object detection information from the video, and determines cost information based on a comparison of a time of each entry and a time of each authentication. Thereafter, the electronic device determines a correspondence between a subset of the entries and the authentications based on the cost information. The electronic device detects, from entries included in the object detection information, one or more entries that are different from the subset as tailgating entries. An output device renders tailgating information based on such entries.

Claims (87)

1. An electronic device, comprising:

circuitry configured to:

receive data from an access control system for a physical entry point;

detect, based on the data, an event that indicates a grant to access a physical area via the physical entry point;

receive entry information that indicates a set of authentications provided by the access control system within a defined period from a time of the detection of the event;

receive a video from at least one imaging device;

extract, from a portion of the video, object detection information that indicates a set of entries that corresponds to the defined period;

determine cost information based on a difference between a time of each entry of the set of entries and a time of each authentication of the set of authentications;

execute a matching operation on the cost information;

determine a minimum cost association between each authentication of the set of authentications and a corresponding entry of the set of entries based on the executed matching operation;

determine a correspondence between a subset of the set of entries and the set of authentications based on the minimum cost association;

detect, from the set of entries, one or more entries that are different from the subset as one or more tailgating entries; and

control an output device to render tailgating information based on the one or more tailgating entries.

2. The electronic device according to claim 1 , wherein

the physical entry point is a door or a gate, and

the defined period corresponds to a duration for which the door or the gate stays open from the time of the detection of the event.

3. The electronic device according to claim 1 , wherein each authentication of the set of authentications is one of a radio frequency-based authentication, a fingerprint-based authentication, a face-based authentication, an iris-based authentication, a voice-based authentication, a hand gesture-based authentication, a touch-based authentication, a password-based authentication, or an identifier (ID) based authentication.

4. The electronic device according to claim 1 , wherein the circuitry is further configured to:

receive an input comprising a threshold time difference; and

determine the cost information further based on a comparison of the difference with the threshold time difference.

5. The electronic device according to claim 1 , wherein

the cost information is a cost matrix between the set of authentications and the set of entries, and

the cost matrix includes the difference between the time of each entry of the set of entries and the time of each authentication of the set of authentications.

6. The electronic device according to claim 1 , wherein the matching operation corresponds to a Hungarian matching algorithm.

7. The electronic device according to claim 1 , wherein

the set of authentications corresponds to a set of objects, and

each object of the set of objects is a vehicle in which a person is a rider of the vehicle.

8. The electronic device according to claim 1 , wherein

the set of authentications corresponds to a set of objects, and

each object of the set of objects is a person.

9. The electronic device according to claim 1 , wherein the circuitry is further configured to:

detect, with respect to a location of an input interface of a lock system of the physical entry point, a position of a body portion of a person associated with each entry of the set of entries,

wherein the detection of the position of the body portion is based on the video; and

detect at least one entry of the one or more tailgating entries based on the position of the body portion of the at least one entry.

10. The electronic device according to claim 1 , wherein the circuitry is further configured to:

extract a facial image of a person associated with each entry of the set of entries from at least one frame of the video;

determine an identifier associated with the person based on the set of authentications;

extract face information associated with the person from a database based on the identifier;

compare the facial image with the face information; and

detect at least one entry of the one or more tailgating entries based on the comparison of the facial image with the face information.

11. The electronic device according to claim 1 , wherein the circuitry is further configured to:

retrieve a list of blacklisted objects associated with the physical area;

determine an entry of the one or more tailgating entries further based on an association of the entry with at least one item in the list of blacklisted objects; and

control the access control system to restrict an access for the entry based on the association.

12. The electronic device according to claim 1 , wherein the circuitry is further configured to:

extract visual attributes of a person associated with each entry of the set of entries based on an analysis of at least one frame of the video;

determine a whitelisted entry profile for the physical area; and

disregard an entry of the person as the one or more tailgating entries based on a determination that the visual attributes of the person match attributes included in the whitelisted entry profile.

13. The electronic device according to claim 1 , wherein the circuitry is further configured to:

determine, based on an analysis of at least one frame of the video, one or more unsafe items that a person associated with an entry of the one or more tailgating entries possesses; and

control the output device to render information about the determined one or more unsafe items.

14. A method, comprising:

in an electronic device:

receiving data from an access control system for a physical entry point;

detecting, based on the data, an event that indicates a grant to access a physical area via the physical entry point;

receiving entry information comprising a set of authentications provided by the access control system within a defined period from a time of the detection of the event;

receiving a video from at least one imaging device;

extracting, from a portion of the video, object detection information comprising a set of entries that corresponds to the defined period;

determining cost information based on a difference between a time of each entry of the set of entries and a time of each authentication of the set of authentications;

executing a matching operation on the cost information;

determining a minimum cost association between each authentication of the set of authentications and a corresponding entry of the set of entries based on the executed matching operation;

determining a correspondence between a subset of the set of entries and the set of authentications based on the minimum cost association;

detecting, from the set of entries, one or more entries that are different from the subset as one or more tailgating entries; and

controlling an output device to render tailgating information based on the one or more tailgating entries.

15. The method according to claim 14 , wherein the matching operation corresponds to a Hungarian matching algorithm.

16. The method according to claim 14 , further comprising:

detecting, with respect to a location of an input interface of a lock system of the physical entry point, a position of a body portion of a person associated with each entry of the set of entries,

wherein the detection of the position of the body portion is based on the video, and

detecting at least one entry of the one or more tailgating entries based on the position of the body portion of the at least one entry.

17. The method according to claim 14 , further comprising:

extracting a facial image of a person associated with each entry of the set of entries from at least one frame of the video;

determining an identifier associated with the person based on the set of authentications;

extracting face information associated with the person from a database based on the identifier;

comparing the facial image with the face information; and

detecting at least one entry of the one or more tailgating entries based on the comparison of the facial image with the face information.

18. A non-transitory computer-readable medium having stored thereon, computer-executable instructions that, when executed by an electronic device, causes the electronic device to perform operations, the operations comprising:

receiving data from an access control system for a physical entry point;

detecting, based on the data, an event that indicates a grant to access a physical area via the physical entry point;

receiving entry information comprising a set of authentications provided by the access control system within a defined period from a time of the detection of the event;

receiving a video from at least one imaging device;

extracting, from a portion of the video, object detection information comprising a set of entries that corresponds to the defined period;

determining cost information based on a difference between a time of each entry of the set of entries and a time of each authentication of the set of authentications;

executing a matching operation on the cost information;

determining a minimum cost association between each authentication of the set of authentications and a corresponding entry of the set of entries based on the executed matching operation;

determining a correspondence between a subset of the set of entries and the set of authentications based on the minimum cost association;

detecting, from the set of entries, one or more entries that are different from the subset as one or more tailgating entries; and

controlling an output device to render tailgating information based on the one or more tailgating entries.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 16, 2023
From: SHENOI, ABHIJEET; HONNUNGAR, SAGAR KASHINATH
To: HAKIMO INC.
Reel/Frame 063656/0216 →
Continuity (1)
Related Publication 20240386766A1 · Nov 21, 2024
References Cited (18)
US 6720874B2 · Fufido · 2004 [cited by examiner]
US 7382895B2 · Bramblet · 2008 [cited by examiner]
US 7999847B2 · Donovan · 2011 [cited by examiner]
US 8330814B2 · Matsuda · 2012 [cited by examiner]
US 9142106B2 · Jerhotova · 2015 [cited by examiner]
US 10235854B2 · Trani · 2019 [cited by examiner]
US 10373408B2 · Trani · 2019 [cited by examiner]
US 10957137B2 · Baumgarte · 2021 [cited by examiner]
US 11200767B2 · Boyes · 2021 [cited by examiner]
US 11315374B2 · Arrufat Ribas · 2022 [cited by examiner]
US 11482088B1 · Russo · 2022 [cited by examiner]
US 11798340B1 · Xu · 2023 [cited by examiner]
US 20070268145A1 · Bazakos · 2007 [cited by examiner]
US 20080285802A1 · Bramblet et al. · 2008 [cited by applicant]
US 20230050055A1 · Houston · 2023 [cited by examiner]
JP 2006120086A · 2006 [cited by applicant]
JP 2010152552A · 2010 [cited by applicant]
Intublog, intuVision VA—Tailgate Detection, © Copyright 2006-2023—https://www.intuvisiontech.com/solutions/person-tailgating. [cited by applicant]
Cited By (2)
US 12,682,711 US 12,731,450