IP Library Granted Patent US 12,475,711
Granted Patent B2
US 12,475,711 · App. 17/815,083 · Granted Nov 18, 2025

Object detection device

Inventors: Yuusuke Yokoi (Kariya, JP); Kazunori Nogi (Toyota, JP); Yuma Hoshikawa (Toyota, JP)
Assignees: DENSO CORPORATION; TOYOTA JIDOSHA KABUSHIKI
G06V20/58G01S13/867G01S13/931G06V10/80G08G1/16G06V2201/07
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 12,475,711
App. No.
17/815,083
Granted
Nov 18, 2025
Kind
B2
Abstract

An object detection device detects objects around an own vehicle by fusing a plurality of pieces of target information obtained by detecting the objects as targets using a plurality of detection sensors with different detection accuracies, and includes a crowd determination unit that determines that a target other than a reference target detected in a predetermined crowd region based on the reference target selected from the targets is a crowd target; a region setting unit that sets a search region so as to include a crowd determination region in which the reference target and the crowd target are detected; and an object determination unit that determines an object indicated by a target in the search region by fusing the target information for the search region.

Claims (9)

1 . An object detection device that detects objects around an own vehicle by fusing a plurality of pieces of target information obtained by detecting the objects as targets using a plurality of detection sensors with different detection accuracies, the object detection device comprising a storage medium storing instructions and a processor, wherein the processor executes the instructions to cause performance of operations comprising:

selecting a reference target from targets detected by a particular detection sensor with higher separability among the plurality of detection sensors, the reference target being selected from the targets detected by the particular detection sensor as opposed to from other targets detected by one or more other detection sensors of the plurality of detection sensors because the particular detection sensor has higher separability than the one or more other detection sensors;

setting a predetermined crowd region based on the reference target;

determining whether a target detected in the predetermined crowd region is a crowd target, the target being different from the reference target, wherein the determining of whether the target detected in the predetermined crowd region is a crowd target includes excluding a target that is determined to be inappropriate to form a corresponding crowd together with the reference target, based on at least one of a movement state and a type of the target;

setting a search region so as to include the predetermined crowd region in which the reference target and the crowd target are detected, wherein the search region is set in a region that includes the reference target and the crowd target, but does not include targets other than the reference target and the crowd target; and

determining an object in the search region by fusing the target information for the search region.

2 . The object detection device according to claim 1 , wherein the operations further comprise selecting, as the reference target, a target closest to the own vehicle and detected in a future moving track of the own vehicle.

3 . The object detection device according to claim 1 , wherein the operations further comprise selecting, as a representative target, a target with the highest risk of collision with the own vehicle among the targets detected in the predetermined crowd region, and fuses the target information while prioritizing the representative target over targets other than the representative target in the predetermined crowd region.

4 . The object detection device according to claim 2 , wherein the operations further comprise selecting, as a representative target, a target with the highest risk of collision with the own vehicle among the targets detected in the predetermined crowd region, and fuses the target information while prioritizing the representative target over targets other than the representative target in the predetermined crowd region.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 9, 2022
From: YOKOI, YUUSUKE; NOGI, KAZUNORI; HOSHIKAWA, YUMA
To: DENSO CORPORATION; TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 061050/0238 →
Priority Claims (1)
JP 2020-011990 · Jan 28, 2020 · national
Continuity (2)
Continuation PCTJP2021002660 · Jan 26, 2021
Related Publication 20220366702A1 · Nov 17, 2022
References Cited (22)
US 6337637B1 · Kubota · 2002 [cited by examiner]
US 8352173B2 · Greene · 2013 [cited by examiner]
US 10088551B2 · Kwakkernaat · 2018 [cited by examiner]
US 10235768B2 · Sasaki · 2019 [cited by examiner]
US 10679506B2 · Szulc · 2020 [cited by examiner]
US 11222541B2 · Ikeda · 2022 [cited by examiner]
US 11987271B2 · Yamamoto · 2024 [cited by examiner]
US 20030174054A1 · Shimomura · 2003 [cited by examiner]
US 20080019567A1 · Takagi · 2008 [cited by examiner]
US 20090303078A1 · Mochizuki · 2009 [cited by examiner]
US 20140139369A1 · Baba · 2014 [cited by applicant]
US 20150161796A1 · Choi · 2015 [cited by examiner]
US 20170174227A1 · Tatourian · 2017 [cited by examiner]
US 20170336504A1 · Kai · 2017 [cited by examiner]
US 20170356993A1 · Lee · 2017 [cited by examiner]
US 20180350083A1 · Fang · 2018 [cited by examiner]
US 20190236958A1 · Fang et al. · 2019 [cited by applicant]
US 20190263398A1 · Matsunaga · 2019 [cited by examiner]
JP 2008065634A · 2008 [cited by applicant]
JP 2014122873A · 2014 [cited by applicant]
JP 201759095A · 2017 [cited by applicant]
WO 2018002985A1 · 2018 [cited by applicant]