IP Library Granted Patent US 12,196,841
Granted Patent B2
US 12,196,841 · App. 17/594,278 · Granted Jan 14, 2025

Ghost object identification for automobile radar tracking

Inventors: Pengbo Li (Auburn Hills, MI); Okechukwu Sidney Igbokwe (Rochester Hills, MI); Kyle Kolasinski (Howell, MI); Kirk North (Kingsville, CA); Adam Gagorik (Royal Oak, MI)
Assignee: Continental Autonomous Mobility US, LLC
G01S13/06G01S7/354G01S13/931
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 12,196,841
App. No.
17/594,278
Granted
Jan 14, 2025
Kind
B2
Abstract

Ghost Object Identification For Automobile Radar Tracking A method of classifying an object detected by a radar device (R) includes identifying two dynamic objects (O) and one stationary object from sensor data detected by at least one sensor; determining a plurality of confidences based on a comparison of the separation distance between each object and a range of each object to the sensor. The method also determining a highest confidence value among them; comparing the highest confidence to a p re-defined threshold; and increasing a corresponding ghost probability, when the highest confidence value is higher than a predetermined threshold or decreasing the corresponding ghost probability, when the highest confidence value is not higher than the predetermined threshold. The method also includes marking the object as a ghost object when a probability of a less confident object is higher than an upper threshold and setting a ghost probability to zero when the less confident object is lower than a lower threshold.

Claims (18)

1. A method classifying an object detected by a radar device, the method comprising:

detecting a ghost object, a real object, and a reflective object from sensor data of the radar device;

determining, from among the ghost object, the real object, and the reflective object, a first colinear object and a second colinear object that are colinear with the radar device based on an azimuth angle of the radar device, the first colinear device being closer in range to the radar device than the second colinear device;

determining, from among the ghost object, the real object, and the reflective object, a non-colinear object that is not colinear with the radar device, the first colinear object, and the second colinear object based on the azimuth angle of the radar device;

determining a first separation distance between the first colinear object to the second colinear object, a first range between the first colinear object and the radar device, and a second range between the second colinear object and the radar device;

determining a second separation distance between the first colinear object and the non-colinear object and a third range between the non-colinear object and the radar device;

determining whether the second separation distance is equal to: (i) the first separation distance, (ii) half the first separation distance, or (iii) twice the second range minus the first range and the third range; and

identifying the ghost object at a location from the radar device based on a result of determining whether the second separation distance is equal to: (i) the first separation distance, (ii) half the first separation distance, or (ii) twice the second range minus the first range and the third range.

2. A radar device comprising:

a hardware processor; and

hardware memory in communication with the hardware processor, the hardware memory storing instructions that when executed on the hardware processor cause the hardware processor to perform operations comprising:

detecting a ghost object, a real object, and a reflective object from sensor data of the radar device;

determining, from among the ghost object, the real object, and the reflective object, a first colinear object and a second colinear object that are colinear with the radar device based on an azimuth angle of the radar device, the first colinear device being closer in range to the radar device than the second colinear device;

determining, from among the ghost object, the real object, and the reflective object, a non-colinear object that is not colinear with the radar device, the first colinear object, and the second colinear object based on the azimuth angle of the radar device;

determining a first separation distance between the first colinear object to the second colinear object, a first range between the first colinear object and the radar device, and a second range between the second colinear object and the radar device;

determining a second separation distance between the first colinear object and the non-colinear object and a third range between the non-colinear object and the radar device;

determining whether the second separation distance is equal to: (i) the first separation distance, (ii) half the first separation distance, or (iii) twice the second range minus the first range and the third range; and

identifying the ghost object at a location from the radar device based on a result of determining whether the second separation distance is equal to: (i) the first separation distance, (ii) half the first separation distance, or (iii) twice the second range minus the first range and the third range.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 6, 2022
From: CONTINENTAL AUTOMOTIVE SYSTEMS, INC.
To: CONTINENTAL AUTONOMOUS MOBILITY US, LLC.
Reel/Frame 061100/0217 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 8, 2022
From: LI, PENGBO; LGBOKWE, OKECHUKWU SIDNEY; KOLASINSKI, KYLE; NORTH, KIRK; GAGORIK, ADAM
To: CONTINENTAL AUTOMOTIVE SYSTEMS, INC.
Reel/Frame 058927/0498 →
Continuity (2)
Provisional Application 62830971 · Apr 8, 2019
Related Publication 20220163649A1 · May 26, 2022
References Cited (40)
US 4970518A · Cole, Jr. · 1990 [cited by applicant]
US 5877721A · Tsang et al. · 1999 [cited by applicant]
US 20090033549A1 · Jin et al. · 2009 [cited by applicant]
US 20130314272A1 · Gross et al. · 2013 [cited by applicant]
US 20140368375A1 · Baftiu et al. · 2014 [cited by applicant]
US 20160161605A1 · Liu · 2016 [cited by examiner]
US 20160209211A1 · Song · 2016 [cited by examiner]
US 20170031013A1 · Halbert et al. · 2017 [cited by applicant]
US 20170261602A1 · Olshansky et al. · 2017 [cited by applicant]
US 20180292506A1 · Bjorkengren · 2018 [cited by applicant]
US 20180341012A1 · Takada · 2018 [cited by applicant]
US 20190084566A1 · Park · 2019 [cited by examiner]
US 20200018821A1 · Matsuo et al. · 2020 [cited by applicant]
CN 106043297A · 2016 [cited by applicant]
CN 107037432A · 2017 [cited by applicant]
CN 107132531A · 2017 [cited by applicant]
CN 109559525A · 2019 [cited by applicant]
DE 102004058844A1 · 2006 [cited by applicant]
DE 102012108023A1 · 2014 [cited by applicant]
DE 102016215505A1 · 2018 [cited by applicant]
EP 1418444A1 · 2004 [cited by examiner]
EP 3299841A1 · 2018 [cited by applicant]
GB 1231794A · 1971 [cited by applicant]
JP H11328600A · 1999 [cited by applicant]
JP 2005257515A · 2005 [cited by applicant]
JP 2006242695A · 2006 [cited by applicant]
JP 2009074804A · 2009 [cited by applicant]
JP 2015105836A · 2015 [cited by applicant]
JP 2016148547A · 2016 [cited by applicant]
JP 2017096840A · 2017 [cited by applicant]
JP 2018200173A · 2018 [cited by applicant]
KR 20170140005A · 2017 [cited by applicant]
WO 2007094064A1 · 2007 [cited by applicant]
WO 2018142629A1 · 2018 [cited by applicant]
Notice of Reasons for Refusal drafted Mar. 31, 2023, for the counterpart Japanese Patent Application No. 2021-559662. [cited by applicant]
Notice of Reasons for Refusal drafted Sep. 11, 2023, for the counterpart Japanese Patent Application No. 2021-559662. [cited by applicant]
International Search Report and the Written Opinion of the International Searching Authority mailed on Jul. 16, 2020 for the counterpart PCT Application No. PCT/US2020/027202. [cited by applicant]
Notice of Reasons for Refusal dated Oct. 14, 2022 for the counterpart Japanese Patent Application No. 2021-559662. [cited by applicant]
Hyun Et El. “Moving and Stationary Target Detection Scheme using Coherent Integration and Subtraction for Automotive FMCW Radar Systems”, 2017 IEEE Radar Conference (RadarConf), May 8-12, 2017, pp. 476-481, IEEE. [cited by applicant]
Office Action dated Mar. 28, 2024 from corresponding Chinese patent application No. 202080027137.X. [cited by applicant]