IP Library Granted Patent US 12,316,927
Granted Patent B2
US 12,316,927 · App. 18/314,737 · Granted May 27, 2025

Behind the windshield camera-based perception system for autonomous traffic violation detection

Inventors: Patrick L. McGuire (Oakland, CA); Ahmad Lemar (Union City, CA); Randal B. Chinnock (Ashford, CT); Joseph Virzi (Fremont, CA); Vaibhav Ghadiok (Mountain View, CA)
Assignee: Hayden AI Technologies, Inc.
H04N23/11B60R11/04H04N7/181H04N23/51H04N23/54H04N23/56H04N23/90B60R2011/0026G02B5/208
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 12,316,927
App. No.
18/314,737
Granted
May 27, 2025
Kind
B2
Abstract

Disclosed herein are systems and apparatus for detecting a traffic violation. In one embodiment, a system for detecting a traffic violation comprises a context camera assembly and a license plate recognition (LPR) camera assembly. The context camera assembly can comprise a context camera housing containing a context camera, a context camera mount configured to mount the context camera housing to an interior of a carrier vehicle, and a context camera skirt coupled to and protruding outwardly from the context camera housing. The license LPR camera assembly can comprise an LPR camera housing containing one or more LPR cameras, an LPR camera mount configured to mount the LPR camera housing to the interior of the carrier vehicle, and one or more LPR camera skirts coupled to and protruding outwardly from the LPR camera housing.

Claims (30)

1. A perception system for detecting a traffic violation, comprising:

a context camera assembly, comprising:

a context camera housing containing a context camera configured to capture videos of a traffic violation event,

a context camera mount coupled to the context camera housing and configured to mount the context camera housing to an interior of a carrier vehicle, and

a context camera skirt coupled to and protruding outwardly from the context camera housing, wherein the context camera skirt is configured to block unwanted ambient light;

a license plate recognition (LPR) camera assembly, comprising:

an LPR camera housing containing one or more LPR cameras configured to capture videos containing one or more license plates of one or more vehicles involved in the traffic violation event,

an LPR camera mount coupled to the LPR camera housing and configured to mount the LPR camera housing to the interior of the carrier vehicle at an angle, laterally, with respect to a windshield of the carrier vehicle, and

at least one LPR camera skirt coupled to and protruding outwardly from the LPR camera housing, wherein the at least one LPR camera skirt comprises a first camera skirt lateral side and a second camera skirt lateral side, wherein a length of the first camera skirt lateral side is not the same as the length of the second camera skirt lateral side, wherein the at least one LPR camera skirt is configured to block unwanted light; and

a control unit communicatively coupled to the context camera and the one or more LPR cameras and configured to receive videos captured by at least one of the context camera and the one or more LPR cameras and transmit the videos wirelessly to another device.

2. The perception system of claim 1 , wherein the LPR camera assembly further comprises a daytime LPR camera and a nighttime LPR camera.

3. The perception system of claim 2 , wherein the nighttime LPR camera is an infrared (IR) camera.

4. The perception system of claim 2 , wherein the LPR camera assembly further comprises a plurality of infrared (IR) lights to illuminate an event scene.

5. The perception system of claim 4 , wherein the plurality of IR lights are arranged to surround or partially surround the nighttime LPR camera.

6. The perception system of claim 4 , wherein the plurality of IR lights are configured to be arranged as an IR light array.

7. The perception system of claim 4 , wherein emission of IR light by the plurality of IR lights is synchronized with a rate with which the nighttime LPR camera captures video frames or images.

8. The perception system of claim 7 , wherein the plurality of IR lights are periodically powered off to avoid overheating, wherein the powering off of the plurality IR lights is controlled by a control circuit comprising a current limiter, a capacitor, and at least one bipolar junction transistor.

9. A license plate recognition (LPR) camera assembly, comprising:

an LPR camera housing containing one or more LPR cameras configured to capture videos containing one or more license plates of one or more vehicles involved in a traffic violation event;

an LPR camera mount coupled to the LPR camera housing and configured to mount the LPR camera housing to an interior of a carrier vehicle at an angle, laterally, with respect to a windshield of the carrier vehicle;

a plurality of infrared (IR) lights configured to illuminate an event scene of the traffic violation event; and

at least one LPR camera skirt coupled to and protruding outwardly from the LPR camera housing, wherein the at least one LPR camera skirt comprises a first camera skirt lateral side and a second camera skirt lateral side, wherein a length of the first camera skirt lateral side is not the same as the length of the second camera skirt lateral side, wherein the at least one LPR camera skirt is configured to prevent unwanted light from interfering with the videos captured by the one or more LPR cameras.

10. The LPR camera assembly of claim 9 , wherein the one or more LPR cameras comprises a daytime LPR camera configured to capture videos in a visible spectrum and a nighttime LPR camera configured to capture videos in an IR spectrum.

11. The LPR camera assembly of claim 9 , wherein the plurality of IR lights are arranged in an array.

12. The LPR camera assembly of claim 9 , wherein the plurality of IR lights are arranged to surround or partially surround at least one of the LPR cameras.

13. The LPR camera assembly of claim 9 , wherein the at least one LPR camera skirt comprises an outer LPR camera skirt and an inner LPR camera skirt at least partially shrouded or surrounded by the outer LPR camera skirt.

14. The LPR camera assembly of claim 13 , wherein the outer LPR camera skirt comprises a first outer camera skirt lateral side and a second outer camera skirt lateral side, and wherein a length of the first outer camera skirt lateral side is greater than the length of the second outer camera skirt lateral side.

15. The LPR camera assembly of claim 14 , wherein the inner LPR camera skirt comprises a first inner camera skirt lateral side and a second inner camera skirt lateral side, and wherein a length of the first inner camera skirt lateral side is greater than the length of the second inner camera skirt lateral side.

16. The LPR camera assembly of claim 15 , wherein the length of the first inner camera skirt lateral side is less than the length of the first outer camera skirt lateral side.

17. The LPR camera assembly of claim 9 , further comprising an IR bandpass filter covering the plurality of IR lights.

Assignments (3)
SECURITY INTEREST Recorded Oct 27, 2025
From: HAYDEN AI TECHNOLOGIES INC.
To: BANK OF MONTREAL
Reel/Frame 072691/0585 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2024
From: MCGUIRE, PATRICK L.; LEMAR, AHMAD; CHINNOCK, RANDAL B.; VIRZI, JOSEPH; GHADIOK, VAIBHAV
To: HAYDEN AI TECHNOLOGIES, INC.
Reel/Frame 066116/0021 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 10, 2023
From: MCGUIRE, PATRICK L.; LEMAR, AHMAD; CHINNOCK, RANDAL B.; VIRZI, JOSEPH; GHADIOK, VAIBHAV
To: HAYDEN AI TECHNOLOGIES, INC.
Reel/Frame 063594/0105 →
Continuity (3)
Division 18068721 · Dec 20, 2022
Provisional Application 63383958 · Nov 16, 2022
Related Publication 20240163533A1 · May 16, 2024
References Cited (96)
US 6741405B1 · Chen · 2004 [cited by examiner]
US 9070289B2 · Saund et al. · 2015 [cited by applicant]
US 10296794B2 · Ratti · 2019 [cited by applicant]
US 10726274B1 · Hasegawa et al. · 2020 [cited by applicant]
US 11003919B1 · Ghadiok et al. · 2021 [cited by applicant]
US 11164014B1 · Ghadiok et al. · 2021 [cited by applicant]
US 11322017B1 · Ghadiok et al. · 2022 [cited by applicant]
US 11361558B2 · Seo · 2022 [cited by applicant]
US 11688182B2 · Ghadiok et al. · 2023 [cited by applicant]
US 11689787B1 · McGuire et al. · 2023 [cited by applicant]
US 20020072847A1 · Trajkovic et al. · 2002 [cited by applicant]
US 20050035926A1 · Takenaga · 2005 [cited by examiner]
US 20100081200A1 · Rajala et al. · 2010 [cited by applicant]
US 20100253832A1 · Duparre · 2010 [cited by examiner]
US 20120148092A1 · Ni et al. · 2012 [cited by applicant]
US 20120212617A1 · Wang · 2012 [cited by examiner]
US 20120242786A1 · Sasagawa · 2012 [cited by examiner]
US 20130266188A1 · Bulan et al. · 2013 [cited by applicant]
US 20140007762A1 · Gavish et al. · 2014 [cited by applicant]
US 20140036076A1 · Nerayoff et al. · 2014 [cited by applicant]
US 20140160283A1 · Hofman · 2014 [cited by examiner]
US 20140300738A1 · Mueller · 2014 [cited by examiner]
US 20140311456A1 · Richter et al. · 2014 [cited by applicant]
US 20150025800A1 · An · 2015 [cited by examiner]
US 20150042804A1 · Okuda · 2015 [cited by examiner]
US 20150248595A1 · Khan et al. · 2015 [cited by applicant]
US 20160232410A1 · Kelly · 2016 [cited by examiner]
US 20170291548A1 · Kim · 2017 [cited by examiner]
US 20180172454A1 · Ghadiok et al. · 2018 [cited by applicant]
US 20180240336A1 · Kareev et al. · 2018 [cited by applicant]
US 20180242404A1 · Wehninck · 2018 [cited by examiner]
US 20190137280A1 · Ghadiok et al. · 2019 [cited by applicant]
US 20190197369A1 · Law et al. · 2019 [cited by applicant]
US 20200063866A1 · Reinhart et al. · 2020 [cited by applicant]
US 20200177767A1 · Kelly et al. · 2020 [cited by applicant]
US 20200204713A1 · Potter · 2020 [cited by examiner]
US 20200247330A1 · Tokunaga · 2020 [cited by examiner]
US 20200272032A1 · Takenouchi · 2020 [cited by examiner]
US 20200326777A1 · Shoushtari · 2020 [cited by examiner]
US 20200380270A1 · Cox et al. · 2020 [cited by applicant]
US 20210166145A1 · Omari et al. · 2021 [cited by applicant]
US 20210209941A1 · Maheshwari et al. · 2021 [cited by applicant]
US 20210237737A1 · Al-Nuaimi et al. · 2021 [cited by applicant]
US 20210241003A1 · Seo · 2021 [cited by applicant]
US 20210306537A1 · Solar · 2021 [cited by examiner]
US 20210370846A1 · Jo · 2021 [cited by examiner]
US 20220147745A1 · Ghadiok et al. · 2022 [cited by applicant]
CN 2277104 · 1998 [cited by applicant]
CN 106560861 · 2017 [cited by applicant]
CN 110197589 · 2019 [cited by applicant]
CN 110321823 · 2019 [cited by applicant]
CN 110717433 · 2020 [cited by applicant]
CN 111368687 · 2020 [cited by applicant]
CN 111492416 · 2020 [cited by applicant]
CN 111666853 · 2020 [cited by applicant]
JP 4805763 · 2008 [cited by applicant]
KR 100812397 · 2008 [cited by applicant]
WO WO2010081200 · 2010 [cited by applicant]
WO WO2014007762 · 2014 [cited by applicant]
WO WO2020063866 · 2020 [cited by applicant]
WO WO2020177767 · 2020 [cited by applicant]
WO WO2022099237 · 2022 [cited by applicant]
WO WO2024107471 · 2024 [cited by applicant]
“Consulting services in Computer Vision and AI” accessed on May 8, 2023, online. [cited by applicant]
“Safety Vision Announces Smart Automated Bus Lane Enforcement (SABLETM) Solution,” [cited by applicant]
Bo, T. et al., “Common Phase Error Estimation in Coherent Optical OFDM Systems Using Best-fit Bounding Box,” [cited by applicant]
Bo, T. et al., “Common Phase Estimation in Coherent OFDM System Using Image Processing Technique,” [cited by applicant]
Bo, T. et al., “Image Processing Based Common Phase Estimation for Coherent Optical Orthogonal Frequency Division Multiplexing System,” [cited by applicant]
Canizo, M. et al. “Multi-Head CNN-RNN for multi time series anomaly detection: An industrial case study,” [cited by applicant]
Chen, S. et al., “A Dense Feature Pyramid Network-Based Deep Learning Model for Road Marking Instance Segmentation Using MLS Point Clouds,” [cited by applicant]
Chhaya, S. et al., “Basic Geometric Shape and Primary Colour Detection Using Image Processing On MATLAB,” [cited by applicant]
Clearlane, “Automated Bus Lane Enforcement System”, [cited by applicant]
Clearlane, “The Safe Fleet Automated Bus Lane Enforcement (ABLE)”, [cited by applicant]
Evanko, K. “Siemens Mobility launches first-ever mobile bus lane enforcement solution in New York,” [cited by applicant]
Fan, Y. et al., “A Coarse-to-Fine Framework for Multiple Pedestrian Crossing Detection,” [cited by applicant]
Franklin, R. “Traffic Signal Violation Detection using Artificial Intelligence and Deep Learning,” [cited by applicant]
Github Repository, Our Camera, <https://github.com/Bellspringsteen/OurCamera> (last visited Sep. 25, 2023). [cited by applicant]
Glenn, J., Adaptive Morphological Feature-Based Object Classifier for a Color Imaging System, [cited by applicant]
Hsu, K., et al. “Augmented Multiple Instance Regression for Inferring Object Contours in Bounding Boxes,” [cited by applicant]
Huval, B. et al. “An Empirical Evaluation of Deep Learning on Highway Driving,” [cited by applicant]
Liu, X. “Vehicle-Related Scene Understanding Using Deep Learning,” [cited by applicant]
Nehemiah, A et al. “Deep Learning for Automated Driving with MATLAB,” [cited by applicant]
Novak, L., “Vehicle Detection and Pose Estimation for Autonomous Driving,” Prague, May 2017. [cited by applicant]
Oh, J. et al., “Context-based Abnormal Object Detection Using the Fully-connected Conditional Random Fields,” [cited by applicant]
Paquet, E. et al., “Description of shape information for 2-D and 3-D objects,” [cited by applicant]
Safe Fleet. “Whitepaper: Vendor Interoperability for ABLE,” [cited by applicant]
Sengupta, S., “Semantic Mapping of Road Scenes,” Oxford Brookes University, Oct. 2014. [cited by applicant]
Siemens Mobility Inc., “Ratification of Completed Procurement Actions” New York City Transit and Siemens Mobility Inc., [cited by applicant]
Siemens Mobility Traffic Solutions, “Enforcement Solutions For Safe and Efficient Cities,” [cited by applicant]
Spencer, B. et al. “NYC extends Brooklyn bus lane enforcement,” [cited by applicant]
Sullivan, T. “Transit Bus Surveillance Solutions,” [cited by applicant]
Tonge, A. et al., “Traffic Rules Violation Detection using Deep Learning,” [cited by applicant]
Viorel, C., “Some Aspects Concerning Geometric Forms Automatically Find Images and Ordering Them Using Robot Studio Simulation,” [cited by applicant]
Wu, C. et al. “Adjacent Lane Detection and Lateral Vehicle Distance Measurement Using Vision-Based Neuro-Fuzzy Approaches,” [cited by applicant]
Zhao Z. et al., “Deep Reinforcement Learning Based Lane Detection and Localization,” [cited by applicant]
Zhou, C. et al., “Predicting the Passenger Demand on Bus Services for Mobile Users,” [cited by applicant]
Cited By (1)
US 12,437,553