IP Library › Granted Patent US 12,695,856
Granted Patent B2
US 12,695,856 · App. 18/761,915 · Granted Jul 28, 2026

Systems and methods for adapting a display depth of an object around a vehicle

Inventor: Hiroshi Yasuda (San Carlos, CA)
Assignees: Toyota Research Institute, Inc.; Toyota Jidosha Kabushiki Kaisha
H04N13/128G06T7/50G06T7/73G06V10/764G06V20/58H04N13/167H04N13/302B60K35/23B60K35/81B60K2360/164G06T2207/30196G06T2207/30261G06V2201/08
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 12,695,856
App. No.
18/761,915
Filed
Jul 2, 2024
Granted
Jul 28, 2026
Kind
B2
Art Unit
2488
USPC
348/51
Abstract

Systems, methods, and other embodiments described herein relate to identifying objects and adapting display depth of a three-dimensional (3D) display for an object that increases situational awareness. In one embodiment, a method includes identifying objects within a field-of-view (FOV) using real depth that is detected by a vehicle. The method also includes positioning the objects within layers using the real depth and a display depth. The method also includes altering the display depth for the objects with a separation degree between the layers using a safety parameter, the display depth is associated with coordinate points of a display. The method also includes receiving a driving command according to the display depth.

Claims (51)

1 . An adaptation system comprising:

a memory storing instructions that, when executed by a processor, cause the processor to:

identify objects within a field-of-view (FOV) using real depth that is detected by a vehicle;

position the objects within layers using the real depth and a display depth;

alter the display depth for the objects with a separation degree between the layers using a safety parameter, the display depth is associated with coordinate points of a display having the display depth associated with a y-axis and the real depth associated with an x-axis, and the separation degree is distorted, and the display depth is associated with a quadrangular space; and

receive a driving command according to the display depth.

2 . The adaptation system of claim 1 , wherein the instructions to alter the display depth further include instructions to:

increase the separation degree between another vehicle and a pedestrian of the objects along the coordinate points, wherein the another vehicle and the pedestrian are ahead of the vehicle; and

the another vehicle and the pedestrian occupy different layers among the layers;

wherein the quadrangular space is associated with a comfort zone and the objects are in a background of a scene on the display.

3 . The adaptation system of claim 2 further including instructions to:

position the another vehicle at an increased distance from the vehicle on the coordinate points and maintain the pedestrian at a constant point on the coordinate points.

4 . The adaptation system of claim 1 , wherein the instructions to alter the display depth further include instructions to:

increase the separation degree between two of the objects for the display depth having different classifications and located ahead of the vehicle along the coordinate points; and

the two of the objects occupying different layers among the layers.

5 . The adaptation system of claim 1 , wherein the layers are continuous for mapping the objects within an image frame on the display and the vehicle incorporates the display within one of a heads-up display (HUD) and an infotainment system.

6 . The adaptation system of claim 1 , wherein the display is a three-dimensional (3D) display having optical components, and the optical components give the objects a 3D depth according to the display depth and the separation degree.

7 . The adaptation system of claim 1 , wherein the safety parameter is a time-to-collision to the objects computed by a machine learning (ML) model and the real depth is a physical depth of the objects located away from the vehicle.

8 . A non-transitory computer-readable medium comprising: instructions that when executed by a processor cause the processor to:

identify objects within a field-of-view (FOV) using real depth that is detected by a vehicle;

position the objects within layers using the real depth and a display depth;

alter the display depth for the objects with a separation degree between the layers using a safety parameter, the display depth is associated with coordinate points of a display having the display depth associated with a y-axis and the real depth associated with an x-axis, and the separation degree is distorted, and the display depth is associated with a quadrangular space; and

receive a driving command according to the display depth.

9 . The non-transitory computer-readable medium of claim 8 , wherein the instructions to alter the display depth further include instructions to:

increase the separation degree between another vehicle and a pedestrian of the objects along the coordinate points, wherein the another vehicle and the pedestrian are ahead of the vehicle; and

the another vehicle and the pedestrian occupy different layers among the layers;

wherein the quadrangular space is associated with a comfort zone and the objects are in a background of a scene on the display.

10 . The non-transitory computer-readable medium of claim 9 further including instructions to:

position the another vehicle at an increased distance from the vehicle on the coordinate points and maintain the pedestrian at a constant point on the coordinate points.

11 . The non-transitory computer-readable medium of claim 8 , wherein the instructions to alter the display depth further include instructions to:

increase the separation degree between two of the objects for the display depth having different classifications and located ahead of the vehicle along the coordinate points; and

the two of the objects occupying different layers among the layers.

12 . The non-transitory computer-readable medium of claim 8 , wherein the layers are continuous for mapping the objects within an image frame on the display and the vehicle incorporates the display within one of a heads-up display (HUD) and an infotainment system.

13 . The non-transitory computer-readable medium of claim 8 , wherein the display is a three-dimensional (3D) display having optical components, and the optical components give the objects a 3D depth according to the display depth and the separation degree.

14 . A method comprising:

identifying objects within a field-of-view (FOV) using real depth that is detected by a vehicle;

positioning the objects within layers using the real depth and a display depth;

altering the display depth for the objects with a separation degree between the layers using a safety parameter, the display depth is associated with coordinate points of a display having the display depth associated with a y-axis and the real depth associated with an x-axis, and the separation degree is distorted, and the display depth is associated with a quadrangular space; and

receiving a driving command according to the display depth.

15 . The method of claim 14 , wherein altering the display depth further includes:

increasing the separation degree between another vehicle and a pedestrian of the objects along the coordinate points, wherein the another vehicle and the pedestrian are ahead of the vehicle; and

the another vehicle and the pedestrian occupy different layers among the layers;

wherein the quadrangular space is associated with a comfort zone and the objects are in a background of a scene on the display.

16 . The method of claim 15 further comprising:

positioning the another vehicle at an increased distance from the vehicle on the coordinate points and maintaining the pedestrian at a constant point on the coordinate points.

17 . The method of claim 14 , wherein altering the display depth further includes:

increasing the separation degree between two of the objects for the display depth having different classifications and located ahead of the vehicle along the coordinate points; and

the two of the objects occupying different layers among the layers.

18 . The method of claim 14 , wherein the layers are continuous for mapping the objects within an image frame on the display and the vehicle incorporates the display within one of a heads-up display (HUD) and an infotainment system.

19 . The method of claim 14 , wherein the display is a three-dimensional (3D) display having optical components, and the optical components give the objects a 3D depth according to the display depth and the separation degree.

20 . The method of claim 14 , wherein the safety parameter is a time-to-collision to the objects computed by a machine learning (ML) model and the real depth is a physical depth of the objects located away from the vehicle.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 5, 2026
From: TOYOTA RESEARCH INSTITUTE, INC.
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 075537/0967 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 5, 2024
From: YASUDA, HIROSHI
To: TOYOTA RESEARCH INSTITUTE, INC.; TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 068182/0646 →
Continuity (1)
Related Publication 20260012563A1 · Jan 8, 2026
References Cited (22)
US 5793900A · Nourbakhsh · 1998 [cited by examiner]
US 10810774B2 · Lee · 2020 [cited by examiner]
US 11288553B1 · Murad · 2022 [cited by examiner]
US 12027113B1 · Broggi · 2024 [cited by examiner]
US 20040109004A1 · Bastos et al. · 2004 [cited by applicant]
US 20130044104A1 · Bouie · 2013 [cited by applicant]
US 20150067008A1 · Kamath · 2015 [cited by examiner]
US 20160325680A1 · Curtis · 2016 [cited by examiner]
US 20200249689A1 · Tatsubori · 2020 [cited by examiner]
US 20200358961A1 · Kimura · 2020 [cited by examiner]
US 20210099686A1 · Panchagnula et al. · 2021 [cited by applicant]
US 20230144893A1 · Chan · 2023 [cited by applicant]
US 20230245373A1 · Xiong et al. · 2023 [cited by applicant]
US 20230344975A1 · Ryu · 2023 [cited by examiner]
CN 110378243A · 2019 [cited by applicant]
CN 117853611A · 2024 [cited by applicant]
EP 1859410A1 · 2007 [cited by applicant]
WO 2012074361A1 · 2012 [cited by applicant]
Lang et al., “Nonlinear Disparity Mapping for Stereoscopic 3D,” ACM Transactions on Graphics, vol. 29, No. 4, article No. 75, pp. 1-10. [cited by applicant]
Bai et al., “Monocular Outdoor Semantic Mapping with a Multi-task Network,” 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, 2019, pp. 1992-1997. [cited by applicant]
Wang et al., “Automatic Layer Separation using Light Field Imaging,” arXiv:1506.04721, Jun. 15, 2015, pp. 1-9. [cited by applicant]
Fang et al., “GroupTransNet: Group Transformer Network for RGB-D Salient Object Detection,” arXiv:2203.10785, Journal of Latex Class Files, vol. 14, No. 8, Aug. 2021, pp. 1.11. [cited by applicant]