IP Library Granted Patent US 12,456,305
Granted Patent B2
US 12,456,305 · App. 18/133,835 · Granted Oct 28, 2025

Systems and methods for identifying tailgating

Inventors: Joy Mazumder (Etobicoke, CA); Shashank Saurav (Toronto, CA); Javed Siddique (York, CA); Mohammed Sohail Siddique (Milton, CA)
Assignee: Geotab Inc.
G06V20/58G06V10/44
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 12,456,305
App. No.
18/133,835
Granted
Oct 28, 2025
Kind
B2
Abstract

Systems, methods, models, and training data for models are discussed, for determining vehicle positioning, and in particular identifying tailgating. Simulated training images showing vehicles following other vehicles, under various conditions, are generated using a virtual environment. Models are trained to determine following distance between two vehicles. Trained models are used to in detection of tailgating, based on determined distance between two vehicles. Results of tailgating are output to warn a driver, or to provide a report on driver behavior.

Claims (61)

1 . A system for identifying tailgating between a first vehicle and second vehicle, the system comprising:

at least one image capture device positioned at the second vehicle;

at least one processor;

at least one non-transitory processor-readable storage medium communicatively coupled to the at least one processor and storing processor-executable instructions which when executed by the at least one processor cause the system to:

capture, by the at least one image capture device, image data including at least at least one image, each image in the image data including a representation of a first vehicle from a perspective of a second vehicle behind the first vehicle;

apply, by the at least one processor, a following distance determination model to determine a following distance between the first vehicle and the second vehicle;

estimate, by the at least one processor, a first stopping distance for the first vehicle;

estimate, by the at least one processor, a second stopping distance for the second vehicle;

determine, by the at least one processor, whether the following distance is within a tailgating distance criteria, wherein the following distance is within the tailgating distance criteria if the second stopping distance is greater than the first stopping distance plus the following distance, and the following distance is outside the tailgating distance criteria if the second stopping distance is not greater than the first stopping distance plus the following distance;

identify, by the at least one processor, that the second vehicle is not tailgating the first vehicle if the following distance is outside of the tailgating distance criteria; and

identify, by the at least one processor, that the second vehicle is tailgating the first vehicle if tailgating criteria are met, wherein the tailgating criteria includes the following distance being within the tailgating distance criteria.

2 . The system of claim 1 , wherein the processor-executable instructions further cause the system to:

identify, by the at least one processor, a left-distance indicating a horizontal distance of the first vehicle from a left boundary of the at least one image;

identify, by the at least one processor, a right-distance indicating a horizontal distance of the first vehicle from a right boundary of the at least one image;

determine, by the at least one processor, a difference between the left-distance and the right-distance;

determine, by the at least one processor, whether the difference between the left-distance and the right-distance is within a horizontal distance criteria, wherein the tailgating criteria includes the difference between the left-distance and the right-distance being within the horizontal distance criteria; and

identify, by the at least one processor, that the second vehicle is not tailgating the first vehicle if the determined difference is outside of the horizontal distance criteria.

3 . The system of claim 2 , wherein:

the processor-executable instructions which cause the system to identify the left-distance cause the at least one processor to: identify a horizontal distance between a left edge of a bounding box delineating the first vehicle in the at least one image and a left edge of the at least one image; and

the processor-executable instructions which cause the system to identify the right-distance cause the at least one processor to: identify a horizontal distance between a right edge of a bounding box delineating the first vehicle in the at least one image and a right edge of the at least one image.

4 . The system of claim 1 , wherein:

the processor-executable instructions which cause the at least one processor to estimate the first stopping distance cause the at least one processor to estimate the first stopping distance as a minimum distance for the first vehicle to stop; and

the processor-executable instructions which cause the at least one processor to estimate the second stopping distance cause the at least one processor to estimate the second stopping distance as a maximum distance for the second vehicle to stop.

5 . A method for identifying tailgating between a first vehicle and second vehicle comprising:

capturing, by at least one image capture device positioned at the second vehicle, image data including at least at least one image, each image in the image data including a representation of a first vehicle from a perspective of a second vehicle behind the first vehicle;

applying, by at least one processor, a following distance determination model to determine a following distance between the first vehicle and the second vehicle;

estimating, by the at least one processor, a first stopping distance for the first vehicle;

estimating, by the at least one processor, a second stopping distance for the second vehicle;

determining, by the at least one processor, whether the following distance is within a tailgating distance criteria, wherein the following distance is within the tailgating distance criteria if the second stopping distance is greater than the first stopping distance plus the following distance, and the following distance is outside the tailgating distance criteria if the second stopping distance is not greater than the first stopping distance plus the following distance;

identifying, by the at least one processor, that the second vehicle is not tailgating the first vehicle if the following distance is outside of the tailgating distance criteria; and

identifying, by the at least one processor, that the second vehicle is tailgating the first vehicle if tailgating criteria are met, wherein the tailgating criteria includes the following distance being within the tailgating distance criteria.

6 . The method of claim 5 , further comprising:

identifying, by the at least one processor, a left-distance indicating a horizontal distance of the first vehicle from a left boundary of the at least one image;

identifying, by the at least one processor, a right-distance indicating a horizontal distance of the first vehicle from a right boundary of the at least one image;

determining, by the at least one processor, a difference between the left-distance and the right-distance;

determining, determining whether the difference between the left-distance and the right-distance is within a horizontal distance criteria, wherein the tailgating criteria includes the difference between the left-distance and the right-distance being within the horizontal distance criteria; and

identifying, by the at least one processor, that the second vehicle is not tailgating the first vehicle if the determined difference is outside of the horizontal distance criteria.

7 . The method of claim 6 , wherein:

identifying the left-distance comprises identifying, by the at least one processor, a horizontal distance between a left edge of a bounding box delineating the first vehicle in the at least one image and a left edge of the at least one image; and

identifying the right-distance comprises identifying, by the at least one processor, a horizontal distance between a right edge of a bounding box delineating the first vehicle in the at least one image and a right edge of the at least one image.

8 . The method of claim 5 , wherein:

estimating the first stopping distance comprises estimating the first stopping distance as a minimum distance for the first vehicle to stop; and

estimating the second stopping distance comprises estimating the second stopping distance as a maximum distance for the second vehicle to stop.

9 . The method of claim 5 wherein estimating the second stopping distance comprises estimating the second stopping distance based on speed data representing speed of the second vehicle.

10 . The method of claim 5 wherein estimating the first stopping distance and the second stopping distance comprises estimating the first stopping distance and the second stopping distance based on at least one factor selected from a list of factors consisting of:

vehicle speed;

vehicle weight;

road coefficient of friction;

weather data; and

driver response time.

11 . The method of claim 5 , further comprising outputting, by a user interface device positioned at the second vehicle, an alert of identified tailgating to a driver of the second vehicle.

12 . The method of claim 5 , further comprising transmitting, by at least one communication interface, a notification of identified tailgating to a management device.

13 . The system of claim 1 wherein the processor-executable instructions which cause the at least one processor to estimate the second stopping distance cause the at least one processor to estimate the second stopping distance based on speed data representing speed of the second vehicle.

14 . The system of claim 1 wherein the processor-executable instructions which cause the at least one processor to estimate the first stopping distance and the second stopping distance cause the at least one processor to estimate the first stopping distance and the second stopping distance based on at least one factor selected from a list of factors consisting of:

vehicle speed;

vehicle weight;

road coefficient of friction;

weather data; and

driver response time.

15 . The system of claim 1 , further comprising a user interface device at the second vehicle, wherein the processor executable instructions further cause the system to output, by the user interface device, an alert of identified tailgating to a driver of the second vehicle.

16 . The system of claim 1 , further comprising at least one communication interface, wherein the processor-executable instructions further cause the at least one communication interface to transmit a notification of identified tailgating to a management device.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 12, 2023
From: SIDDIQUE, JAVED; SIDDIQUE, MOHAMMED SOHAIL
To: GEOTAB INC.
Reel/Frame 064227/0157 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 12, 2023
From: MAZUMDER, JOY; SAURAV, SHASHANK
To: GEOTAB INC.
Reel/Frame 063304/0936 →
Continuity (2)
Provisional Application 63456179 · Mar 31, 2023
Related Publication 20240331399A1 · Oct 3, 2024
References Cited (95)
US 6950788B2 · Faghri · 2005 [cited by examiner]
US 7505841B2 · Sun et al. · 2009 [cited by applicant]
US 7676087B2 · Dhua et al. · 2010 [cited by applicant]
US 9405970B2 · Israel · 2016 [cited by applicant]
US 9489635B1 · Zhu · 2016 [cited by applicant]
US 9734717B1 · Surpi · 2017 [cited by examiner]
US 10276212B2 · Richardson · 2019 [cited by applicant]
US 10395540B2 · Surpi · 2019 [cited by applicant]
US 10431089B1 · Nguyen · 2019 [cited by applicant]
US 10496891B2 · Sai · 2019 [cited by applicant]
US 10728420B2 · Popa · 2020 [cited by applicant]
US 10766489B2 · Tuncali · 2020 [cited by examiner]
US 10818109B2 · Palmer et al. · 2020 [cited by applicant]
US 10997434B2 · Kurian et al. · 2021 [cited by applicant]
US 11017244B2 · Xue · 2021 [cited by applicant]
US 11257272B2 · Rowell et al. · 2022 [cited by applicant]
US 11336867B2 · Meier et al. · 2022 [cited by applicant]
US 11373411B1 · Goh · 2022 [cited by applicant]
US 11521009B2 · Peake et al. · 2022 [cited by applicant]
US 11544935B2 · Chen · 2023 [cited by applicant]
US 11615628B2 · Tsurumi · 2023 [cited by applicant]
US 11643102B1 · Calmer et al. · 2023 [cited by applicant]
US 11683579B1 · Symons et al. · 2023 [cited by applicant]
US 11704910B2 · Endo et al. · 2023 [cited by applicant]
US 11758096B2 · Shah et al. · 2023 [cited by applicant]
US 11866055B1 · Srinivasan et al. · 2024 [cited by applicant]
US 11989001B1 · Eihattab et al. · 2024 [cited by applicant]
US 11989949B1 · Mazumder · 2024 [cited by examiner]
US 11995546B1 · Srinivasan et al. · 2024 [cited by applicant]
US 12125222B1 · Ivascu · 2024 [cited by examiner]
US 20050090983A1 · Isaji et al. · 2005 [cited by applicant]
US 20050125121A1 · Isaji et al. · 2005 [cited by applicant]
US 20050259033A1 · Levine · 2005 [cited by examiner]
US 20060273922A1 · Bhogal · 2006 [cited by examiner]
US 20100110176A1 · Aoyama · 2010 [cited by applicant]
US 20120119894A1 · Pandy · 2012 [cited by examiner]
US 20120239268A1 · Chen · 2012 [cited by examiner]
US 20130057397A1 · Cutler · 2013 [cited by examiner]
US 20130107051A1 · Maruoka et al. · 2013 [cited by applicant]
US 20140195093A1 · Litkouhi · 2014 [cited by examiner]
US 20140222280A1 · Salomonsson · 2014 [cited by examiner]
US 20160019791A1 · Lin · 2016 [cited by applicant]
US 20160167514A1 · Nishizaki et al. · 2016 [cited by applicant]
US 20160170487A1 · Saisho · 2016 [cited by applicant]
US 20160280132A1 · Palanimuthu · 2016 [cited by examiner]
US 20160343145A1 · Israel · 2016 [cited by applicant]
US 20170261747A1 · Acklin · 2017 [cited by examiner]
US 20170305419A1 · Liebinger Portela · 2017 [cited by examiner]
US 20170326981A1 · Masui et al. · 2017 [cited by applicant]
US 20170327037A1 · Prakah-Asante · 2017 [cited by examiner]
US 20170369055A1 · Saigusa · 2017 [cited by examiner]
US 20180001899A1 · Shenoy · 2018 [cited by examiner]
US 20190001977A1 · Lin et al. · 2019 [cited by applicant]
US 20190232961A1 · Baier · 2019 [cited by examiner]
US 20190256105A1 · Parat et al. · 2019 [cited by applicant]
US 20190389487A1 · Gowda · 2019 [cited by examiner]
US 20200020121A1 · Rawashdeh · 2020 [cited by applicant]
US 20200238991A1 · Aragon et al. · 2020 [cited by applicant]
US 20200342760A1 · Vassilovski · 2020 [cited by examiner]
US 20210224560A1 · Kim et al. · 2021 [cited by applicant]
US 20210356696A1 · Kamada et al. · 2021 [cited by applicant]
US 20210365696A1 · He · 2021 [cited by examiner]
US 20210366144A1 · Magistri et al. · 2021 [cited by applicant]
US 20210370969A1 · Hegde · 2021 [cited by examiner]
US 20220009488A1 · Li · 2022 [cited by examiner]
US 20220172396A1 · Okuma · 2022 [cited by applicant]
US 20220244142A1 · Breton · 2022 [cited by applicant]
US 20220245955A1 · Freeman et al. · 2022 [cited by applicant]
US 20220371534A1 · Zheng · 2022 [cited by examiner]
US 20220379889A1 · Akella · 2022 [cited by examiner]
US 20230038842A1 · Ruichi · 2023 [cited by applicant]
US 20230102113A1 · Magistri · 2023 [cited by applicant]
US 20230159031A1 · Hu et al. · 2023 [cited by applicant]
US 20230169793A1 · Ogino · 2023 [cited by applicant]
US 20230206466A1 · Todoran et al. · 2023 [cited by applicant]
US 20230227058A1 · Julian et al. · 2023 [cited by applicant]
US 20230273033A1 · Kim et al. · 2023 [cited by applicant]
US 20230286498A1 · Oguri et al. · 2023 [cited by applicant]
US 20230290002A1 · Yang et al. · 2023 [cited by applicant]
US 20230382380A1 · Herrero Zarzosa · 2023 [cited by applicant]
US 20230394843A1 · Lee · 2023 [cited by examiner]
US 20240005675A1 · Lelowicz et al. · 2024 [cited by applicant]
US 20240059291A1 · Saylor · 2024 [cited by examiner]
CN 110745140B · 2021 [cited by applicant]
CN 115035251A · 2022 [cited by applicant]
EP 3855409A1 · 2021 [cited by applicant]
JP H04205825A · 1992 [cited by applicant]
JP 4205825B2 · 2009 [cited by applicant]
KR 20120021445A · 2012 [cited by applicant]
KR 20220119396A · 2022 [cited by applicant]
WO 2021253245A1 · 2021 [cited by applicant]
Extended European Search Report for European Application No. 24165655.2, mailed Aug. 27, 2024, 134 pages. [cited by applicant]
Meftah et al., “A Virtual Simulation Environment Using Deep Learning for Autonomous Vehicles Obstacle Avoidance,” 2020 IEEE International Conference on Intelligence and Security Informatics (ISI), 2020, 7 Pages. [cited by applicant]
Extended European Search Report for European Application No. 24165653.7, mailed Sep. 12, 2024, 8 pages. [cited by applicant]
Tram et al (“Vehicle to Vehicle Distance Estimation Using Camera based Visible Light Communications”, IEEE 2017, pp. 517-519) (Year: 2017). [cited by applicant]