IP Library Granted Patent US 12,192,620
Granted Patent B2
US 12,192,620 · App. 17/576,677 · Granted Jan 7, 2025

System and method for opportunistic imaging

Inventors: Andreas U. Kuehnle (Villa Park, CA); Zheng Li (Irvine, CA)
Assignee: RM ACQUISITION, LLC
H04N23/667B60W40/02B60W40/08H04N7/183H04N7/188B60W2420/403
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 12,192,620
App. No.
17/576,677
Granted
Jan 7, 2025
Kind
B2
Abstract

A system for opportunistic imaging includes an imaging device that generates data comprising a plurality of sequential image frames. The system also includes a control module that causes the imaging device to generate standard-resolution image frames at a standard-frame rate and a standard-resolution, such that there is a processing time lull between the generation of sequential standard-resolution image frames. The control module also causes the imaging device to generate one or more burst-resolution image frames at a burst-frame rate and a burst-resolution within the processing time lull.

Claims (35)

1. A system for opportunistic imaging, comprising:

an imaging device configured to generate data comprising a plurality of sequential image frames; and

a control module configured to:

cause the imaging device to generate standard-resolution image frames at a standard-frame rate and a standard-resolution, wherein the standard frame rate delineates a reserved processing time that includes a processing time lull that the control module has reserved for processing the standard-resolution image frames but in which the control module is not processing the sequential standard-resolution image frames; and

cause the imaging device to generate one or more burst-resolution image frames at a burst-frame rate and a burst-resolution within the processing time lull, wherein the burst-resolution image frames are generated via pixel sampling at a fraction of the standard resolution.

2. The system of claim 1 , wherein the burst-resolution image frames are generated such that corresponding reconstructed image frames can be generated, at the standard-resolution and higher, from the burst-resolution image frames via image reconstruction.

3. The system of claim 1 , wherein the processing time lull is idle time between the image processing time reserved by the control module for generating the standard-resolution image frames.

4. The system of claim 1 , wherein each of the burst-resolution image frames are generated by pixel sampling corresponding image frames at random, non-overlapping, pixel locations.

5. The system of claim 4 , wherein the random, non-overlapping, pixel locations are stored in a predetermined look-up table and each burst-resolution image frame is associated with a key to the lookup table.

6. The system of claim 1 , wherein the imaging device is mounted to a vehicle surface via a wobbly mount.

7. A method for opportunistic imaging, comprising:

generating, via an imaging device, sequential standard-resolution image frames at a standard-frame rate and a standard-resolution, wherein the standard frame rate delineates a reserved processing time that includes a processing time lull that a control module has reserved for processing the standard-resolution image frames but in which the control module is not processing the standard-resolution image frames; and

generating, via the imaging device, sequential burst-resolution image frames at a burst-frame rate and a burst-resolution within the processing time lull, wherein the burst-resolution image frames are generated via pixel sampling at a fraction of the standard resolution.

8. The method of claim 7 , wherein the burst-resolution image frames are generated such that corresponding reconstructed image frames can be generated, at the standard-resolution and higher, from the burst-resolution image frames via image reconstruction.

9. The method of claim 7 , wherein the processing time lull is idle time between the image processing time reserved for generating the standard-resolution image frames.

10. The method of claim 7 , wherein each of the burst-resolution image frames are generated by pixel sampling corresponding image frames at random, non-overlapping pixel locations.

11. The system of claim 10 , wherein the random, non-overlapping pixel locations are stored in a predetermined look-up table and each burst-resolution image frame is associated with a key to the lookup table.

12. The method of claim 11 , further comprising:

transmitting the burst-resolution image frames and the look-up table to a remote computer system; and

generating, at the remote computer system, corresponding reconstructed image frames from the burst-resolution image frames via image reconstruction based on the look-up table.

13. An on-vehicle event detection and reporting system, comprising:

a vehicle mounted imaging device configured to capture data comprising a plurality of sequential image frames;

an event detection system configured to detect vehicle and/or driver related events based on the captured video data;

an image control module configured to, at least in response to the detected vehicle and/or driver related events:

cause the imaging device to generate standard-resolution image frames at a standard-frame rate and a standard-resolution, wherein the standard frame rate delineates a reserved processing time that includes a processing time lull that the control module has reserved for processing the standard-resolution image frames but in which the control module is not processing the sequential standard-resolution image frames, and

cause the imaging device to generate one or more burst-resolution image frames at a burst-frame rate and a burst-resolution within the processing time lull, wherein the burst-resolution image frames are generated via pixel sampling at a fraction of the standard resolution.

14. The system of claim 13 , wherein the burst-resolution image frames are generated such that corresponding reconstructed image frames can be generated from the burst-resolution image frames via image reconstruction.

15. The system of claim 14 , further comprising: a remote system configured to receive the burst-resolution image frames and to generate the corresponding reconstructed image frames therefrom via image reconstruction.

16. The system of claim 13 , wherein the processing time lull is idle time between the image processing time reserved by the control module for generating the standard-resolution image frames.

17. The system of claim 13 , wherein each of the burst-resolution image frames are generated by pixel sampling corresponding image frames at random, non-overlapping pixel locations.

18. The system of claim 17 , wherein the random, non-overlapping pixel locations are stored in a predetermined look-up table and each burst-resolution image frame is associated with a key to the lookup table.

19. The system of claim 18 , further comprising:

a remote system configured to receive the burst-resolution image frames and to generate corresponding reconstructed image frames therefrom via image reconstruction and based on the look-up table.

20. The system of claim 13 ,

wherein the imaging device is mounted to the vehicle via a wobbly mount, and wherein the burst-resolution image frames are generated such that corresponding super-resolution image frames can be generated from the burst-resolution image frames via image reconstruction.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 24, 2024
From: BENDIX COMMERCIAL VEHICLE SYSTEMS LLC
To: RM ACQUISITION, LLC
Reel/Frame 067824/0004 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 18, 2022
From: KUEHNLE, ANDREAS U.; LI, ZHENG
To: BENDIX COMMERCIAL VEHICLE SYSTEMS LLC
Reel/Frame 058676/0845 →
Continuity (1)
Related Publication 20230232098A1 · Jul 20, 2023
References Cited (14)
US 8095791B2 · Suwabe · 2012 [cited by applicant]
US 20030147640A1 · Voss · 2003 [cited by examiner]
US 20140184858A1 · Yu · 2014 [cited by examiner]
US 20150287435A1 · Land · 2015 [cited by examiner]
US 20160323508A1 · Ayalasomayajula · 2016 [cited by examiner]
US 20170085796A1 · Rangam · 2017 [cited by examiner]
US 20180217953A1 · Cross et al. · 2018 [cited by applicant]
US 20180367752A1 · Donsbach · 2018 [cited by examiner]
US 20200186712A1 · Högasten · 2020 [cited by examiner]
US 20230007282A1 · Hu · 2023 [cited by examiner]
CN 106685934A · 2017 [cited by applicant]
CN 110297711A · 2019 [cited by applicant]
Mardani et al., “Rank Minimization for Subspace Tracking from Incomplete Date”, University of Minnesota, ICASSP 2013, Vancouver, Canada, May 18, 2013, URL: https://www.ece.rochester.edu/˜qmateosb/pubs/orm/orm_ICASSP13.p… [cited by applicant]
Mercier et al., “Big Data and HPC collcation: Using HPC idle resources for Big Data Analytics”, 2017 IEEE International Conference on Big Data (Bigdata), pp. 347-352. [cited by applicant]