IP Library Granted Patent US 12,407,943
Granted Patent B1
US 12,407,943 · App. 18/475,752 · Granted Sep 2, 2025

Reducing throughput of paired cameras

Inventors: Volkmar Uhlig (Cupertino, CA); John Hayes (Mountain View, CA); Riaz Ali (Mountain View, CA); Shaun M. Pacheco (Santa Clara, CA); Justin N. Erickson (San Francisco, CA); James S. Cross (San Francisco, CA); Daniel D. Schmidt (Seattle, WA); Akash J. Sagar (Redwood City, CA)
Assignee: Applied Intuition, Inc.
H04N23/80H04N1/32106H04N2101/00H04N2201/325
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 12,407,943
App. No.
18/475,752
Granted
Sep 2, 2025
Kind
B1
Abstract

Reducing throughput of paired cameras, including: selecting, by a first camera of an autonomous vehicle, a first area of focus for a first frame generated by the first camera; selecting, by a second camera of the autonomous vehicle, a second area of focus for a second frame generated by the second camera by matching the first area of focus for the first frame; generating, by the first camera from the first frame, a first downsampled frame and a first cropped frame, wherein the first cropped frame is based on the first area of focus; and generating, by the second camera from the second frame, a second downsampled frame and a second cropped frame, wherein the second cropped frame is based on the second area of focus.

Claims (35)

1. A method, comprising:

selecting, by a first camera of an autonomous vehicle, a first area of focus for a first frame generated by the first camera;

selecting, by a second camera of the autonomous vehicle, a second area of focus for a second frame generated by the second camera by matching the first area of focus for the first frame;

generating, by the first camera from the first frame, a first downsampled frame and a first cropped frame, wherein the first cropped frame is based on the first area of focus; and

generating, by the second camera from the second frame, a second downsampled frame and a second cropped frame, wherein the second cropped frame is based on the second area of focus.

2. The method of claim 1 , wherein selecting the second area of focus comprises selecting, based on one or more models, as the second area of focus, a portion of the second frame matching the first area of focus.

3. The method of claim 1 , wherein the first camera and the second camera are in a stereoscopic configuration.

4. The method of claim 1 , further comprising:

providing, to an automation computing system of the autonomous vehicle, the first downsampled frame and the first cropped frame instead of the first frame; and

providing, to the automation computing system of the autonomous vehicle, the second downsampled frame and the second cropped frame instead of the second frame.

5. The method of claim 4 , wherein the first downsampled frame and the first cropped frame are provided via a first data link having the first camera at a first end and the automation computing system at a second end, and wherein the second downsampled frame and the second cropped frame are provided via a second data link having the second camera at a third end and the automation computing system at a fourth end.

6. The method of claim 1 , wherein the first camera and the second camera are included in a pair of cameras of the autonomous vehicle, and wherein the autonomous vehicle comprises a plurality of pairs of cameras including the pair of cameras.

7. The method of claim 6 , wherein each pair of cameras of the plurality of pairs of cameras correspond to a different facing of the autonomous vehicle.

8. The method of claim 1 , wherein selecting the first area of focus comprises selecting, as the first area of focus, an area of the first frame having a highest spatial density.

9. The method of claim 1 , wherein selecting the first area of focus comprises selecting, as the first area of focus, an area of the first frame having a highest object density.

10. The method of claim 1 , wherein selecting the first area of focus comprises selecting, as the first area of focus, an area of the first frame having one or more of: a degree of motion exceeding a threshold or a highest degree of motion.

11. An autonomous vehicle, comprising:

an automation computing system;

a first camera configured to:

select a first area of focus for a first frame generated by the first camera;

generate a first downsampled frame and a first cropped frame, wherein the first cropped frame is based on the first area of focus;

a second camera configured to:

select a second area of focus for a second frame generated by the second camera by matching the first area of focus for the first frame; and

generate a second downsampled frame and a second cropped frame, wherein the second cropped frame is based on the second area of focus.

12. The autonomous vehicle of claim 11 , wherein selecting the second area of focus comprises selecting, based on one or more models, as the second area of focus, a portion of the second frame matching the first area of focus.

13. The autonomous vehicle of claim 11 , wherein the first camera and the second camera are in a stereoscopic configuration.

14. The autonomous vehicle of claim 11 :

wherein the first camera is further configured to provide, to an automation computing system of the autonomous vehicle, the first downsampled frame and the first cropped frame instead of the first frame; and

wherein the second camera is further configured to provide, to the automation computing system of the autonomous vehicle, the second downsampled frame and the second cropped frame instead of the second frame.

15. The autonomous vehicle of claim 14 , wherein the first downsampled frame and the first cropped frame are provided via a first data link having the first camera at a first end and the automation computing system at a second end, and wherein the second downsampled frame and the second cropped frame are provided via a second data link having the second camera at a third end and the automation computing system at a fourth end.

16. The autonomous vehicle of claim 11 , wherein the first camera and the second camera are included in a pair of cameras of the autonomous vehicle, and wherein the autonomous vehicle comprises a plurality of pairs of cameras including the pair of cameras.

17. The autonomous vehicle of claim 16 , wherein each pair of cameras of the plurality of pairs of cameras correspond to a different facing of the autonomous vehicle.

18. The autonomous vehicle of claim 11 , wherein selecting the first area of focus comprises selecting, as the first area of focus, an area of the first frame having a highest spatial density.

19. The autonomous vehicle of claim 11 , wherein selecting the first area of focus comprises selecting, as the first area of focus, an area of the first frame having a highest object density.

20. The autonomous vehicle of claim 11 , wherein selecting the first area of focus comprises selecting, as the first area of focus, an area of the first frame having one or more of: a degree of motion exceeding a threshold or a highest degree of motion.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 18, 2024
From: GHOST AUTONOMY, INC.
To: APPLIED INTUITION, INC.
Reel/Frame 068982/0647 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 28, 2023
From: UHLIG, VOLKMAR; HAYES, JOHN; ALI, RIAZ; PACHECO, SHAUN M; ERICKSON, JUSTIN N; CROSS, JAMES S; SCHMIDT, DANIEL D; SAGAR, AKASH J
To: GHOST AUTONOMY INC.
Reel/Frame 065057/0659 →
Continuity (1)
Continuation 17676569 · Feb 21, 2022
References Cited (29)
US 9602806B1 · Stafford · 2017 [cited by examiner]
US 10489912B1 · Brailovskiy · 2019 [cited by examiner]
US 10582186B1 · Baldwin · 2020 [cited by examiner]
US 10832418B1 · Karasev et al. · 2020 [cited by applicant]
US 11805316B2 · Hayes · 2023 [cited by examiner]
US 11849225B2 · Uhlig · 2023 [cited by examiner]
US 11909944B1 · Uhlig · 2024 [cited by examiner]
US 20050146621A1 · Tanaka · 2005 [cited by examiner]
US 20140146185A1 · Kannermark · 2014 [cited by examiner]
US 20170237937A1 · Motohashi · 2017 [cited by examiner]
US 20180070023A1 · Oh · 2018 [cited by examiner]
US 20190279440A1 · Ricci · 2019 [cited by examiner]
US 20190289282A1 · Briggs · 2019 [cited by examiner]
US 20190325580A1 · Lukac · 2019 [cited by examiner]
US 20200175326A1 · Shen · 2020 [cited by examiner]
US 20210099643A1 · Agrawal · 2021 [cited by examiner]
US 20210327092A1 · Jiang · 2021 [cited by examiner]
US 20210350137A1 · Imes · 2021 [cited by examiner]
US 20220050890A1 · Karantzis · 2022 [cited by examiner]
US 20220180131A1 · Oblak · 2022 [cited by examiner]
US 20220182551A1 · Fang · 2022 [cited by examiner]
US 20220188560A1 · Dharia · 2022 [cited by examiner]
US 20220210305A1 · Feng · 2022 [cited by examiner]
US 20220301188A1 · Yoon et al. · 2022 [cited by applicant]
US 20220365210A1 · Lind · 2022 [cited by examiner]
US 20220385816A1 · Jung · 2022 [cited by examiner]
US 20220388535A1 · Singh et al. · 2022 [cited by applicant]
US 20220392036A1 · Feng · 2022 [cited by examiner]
US 20230269491A1 · Uhlig et al. · 2023 [cited by applicant]