IP Library Granted Patent US 12,254,607
Granted Patent B2
US 12,254,607 · App. 17/576,302 · Granted Mar 18, 2025

Image processing method and apparatus implementing the same

Inventors: Luis Eduardo García Capel (Singapore, SG); Bo Mu (San Jose, CA)
Assignee: OMNIVISION TECHNOLOGIES, INC.
G06T5/92G06T5/00G06T5/50G06T7/337G06T2207/20016G06T2207/20208G06T2207/20221
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 12,254,607
App. No.
17/576,302
Granted
Mar 18, 2025
Kind
B2
Abstract

An image processing method and a device configured to implement the same are disclosed. The method comprises: obtaining optical input from a hybrid imaging device, wherein an obtained optical input comprises a first component and a second component that temporally corresponds to the first component; wherein the first component of the obtained optical input corresponds to a first temporal resolution, while the second component of the obtained optical input corresponds to a second temporal resolution higher than that of the first component; performing image restoration operation on a first subset of the first component of the obtained optical input in accordance with data from the second component of the obtained optical input; and performing image fusion operation to generate fused image data from an output of the image restoration operation and a second subset of the first component of the obtained optical input.

Claims (64)

1. A method of image processing, comprising:

obtaining optical input from a hybrid imaging device,

wherein an obtained optical input comprises a first component and a second component having motion related information corresponding to the first component;

wherein the first component of the obtained optical input corresponds to a first temporal resolution, while the second component of the obtained optical input corresponds to a second temporal resolution higher than that of the first component;

performing image restoration operation on a first subset of the first component of the obtained optical input in accordance with data from the second component of the obtained optical input, wherein the first subset of the first component of the obtained optical input comprises a first exposure frame having a first exposure duration; and

performing image fusion operation to generate fused image data from an output of the image restoration operation and a second subset of the first component of the obtained optical input, wherein the second subset of the first component of the obtained optical input comprises a second exposure frame having a second exposure duration, and the second exposure duration is shorter than the first exposure duration,

wherein the first subset and the second subset of the first component of the obtained optical input temporally offset each other.

2. The method of claim 1 ,

wherein the first subset of the first component of the obtained optical input has a longer temporal duration than the second subset thereof.

3. The method of claim 1 ,

wherein the obtaining of optical input by a hybrid image system comprises acquiring optical input by a hybrid imaging device that comprises integrated first type sensor component and second type sensor component;

wherein the first component of the optical input corresponds to the first type sensor component;

wherein the second component of the optical input corresponds to the second type sensor component.

4. The method of claim 3 ,

wherein the first type sensor component has a first pixel resolution;

wherein the second type sensor component has a second pixel resolution less than the first pixel resolution.

5. The method of claim 3 ,

wherein the first type sensor component comprises frame-based image sensor; wherein the second type sensor component comprises event-based vision sensor.

6. The method of claim 1 ,

wherein performing image restoration operation comprises performing at least one of a de-blurring operation or a rolling shutter distortion correction (RSDC) operation on the first subset of the first component.

7. The method of claim 6 ,

wherein the image restoration operation is performed in accordance with a first portion of the second component of the obtained optical input that temporally corresponds to the first subset of the first component of the obtained optical input.

8. The method of claim 7 , further comprising:

performing additional image restoration operation on the second subset of the first component of the obtained optical input in accordance with a second portion of the second component of the obtained optical input.

9. The method of claim 8 ,

wherein the additional image restoration operation comprises performing RSDC operation on the second subset of the first component of the obtained optical input.

10. The method of claim 1 , further comprising:

performing temporal alignment operation on the first subset of the first component of the obtained optical input in accordance with data from the second component of the obtained optical input.

11. The method of claim 10 , wherein the temporal alignment operation is performed in accordance with a first portion of the second component that temporally corresponds to the first subset of the first component of the obtained optical input.

12. The method of claim 11 , wherein the temporal alignment operation is performed further in accordance with a second portion of the second component that temporally corresponds to the second subset of the first component of the obtained optical input.

13. An image processing system, comprising:

a hybrid imaging device configured to obtain optical input,

wherein an obtained optical input comprises a first component and a second component having motion related information corresponding to the first component,

wherein the second component corresponds to a temporal resolution that is higher than that of the first component; and

a processing device in signal communication with the hybrid imaging device, the processing device comprising:

an image restoration circuit configured to process a first subset of the first component of the obtained optical input in accordance with data from the second component of the obtained optical input, wherein the first subset of the first component of the obtained optical input comprises a first exposure frame having a first exposure duration; and

an image fusion circuit configured to generate fused image data based on output of the image restoration circuit and a second subset of the first component of the obtained optical input, wherein the second subset of the first component of the obtained optical input comprises a second exposure frame having a second exposure duration, and the second exposure duration is shorter than the first exposure duration,

wherein the first subset and the second subset of the first component of the obtained optical input temporally offset each other.

14. The device of claim 13 ,

wherein the hybrid imaging device comprises a first type sensor component and a second type sensor component;

wherein the first component of the optical input corresponds to the first type sensor component;

wherein the second component of the optical input corresponds to the second type sensor component.

15. The device of claim 14 ,

wherein the image restoration circuit is configured to respectively process both the first component of the optical input from the first type sensor and the second component of the optical input from the second type sensor.

16. The device of claim 15 ,

wherein the first type sensor component has a first pixel resolution and a first temporal resolution;

wherein the second type sensor component has a second pixel resolution less than the first pixel resolution and a second temporal resolution greater than the first temporal resolution.

17. The device of claim 16 ,

wherein the first type sensor component comprises an array of frame-based image sensor cells; and

wherein the second type sensor component comprises an array of event-based vision sensor cells interleavingly inserted among the first type sensor cells.

18. The device of claim 13 ,

wherein the first subset of the first component of the obtained optical input has a longer temporal duration than the second subset thereof.

19. The device of claim 13 ,

wherein the image restoration circuit is configured to perform at least one of a de-blurring operation or a rolling shutter distortion correction (RSDC) operation on the first subset of the first component.

20. The device of claim 19 ,

wherein the image restoration circuit is configured to operate in accordance with a first portion of the second component of the obtained optical input that temporally corresponds to the first subset of the first component of the obtained optical input.

21. The device of claim 20 , further comprising:

an additional image restoration circuit configured to process the second subset of the first component of the obtained optical input in accordance with a second portion of the second component of the obtained optical input.

22. The method of claim 21 ,

wherein the additional image restoration circuit is configured to perform RSDC operation on the second subset of the first component of the obtained optical input.

23. The device of claim 13 , further comprising:

a temporal alignment circuit signal communicatively arranged between the image restoration circuit and the image fusion circuit, configured to perform temporal alignment operation on the first subset of the first component of the obtained optical input in accordance with data from the second component of the obtained optical input.

24. The device of claim 23 ,

wherein the temporal alignment circuit is further configured to perform temporal alignment operation on the second subset of the first component of the obtained optical input.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 24, 2022
From: GARCÍA CAPEL, LUIS EDUARDO; MU, BO
To: OMNIVISION TECHNOLOGIES, INC.
Reel/Frame 058737/0904 →
Continuity (1)
Related Publication 20230230212A1 · Jul 20, 2023
References Cited (16)
US 11665427B2 · Hubel · 2023 [cited by examiner]
US 20090278857A1 · Wajs · 2009 [cited by examiner]
US 20150103222A1 · Choi · 2015 [cited by examiner]
US 20170163892A1 · Mihic · 2017 [cited by examiner]
US 20190139205A1 · El-Khamy · 2019 [cited by examiner]
US 20200045227A1 · Jiang · 2020 [cited by examiner]
US 20200249017A1 · Török · 2020 [cited by examiner]
US 20210090222A1 · Lee · 2021 [cited by examiner]
US 20210174092A1 · Zhao · 2021 [cited by examiner]
US 20210195082A1 · Peng · 2021 [cited by examiner]
US 20220198628A1 · Dinh · 2022 [cited by examiner]
Davide Scaramuzza, “Tutorial on event cameras”; Institute of Informatics—Institute of Neuroinformatics, 2020, pp. 1-113. [cited by applicant]
J. Han et al., “Neuromorphic Camera Guided High Dynamic Range Imaging,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1727-1736. [cited by applicant]
Chen, Guanying, et al. “HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset.” arXiv preprint arXiv:2103.14943 (2021); pp. 1-10. [cited by applicant]
Lin, Songnan, et al. “Learning Event-Driven Video Deblurring and Interpolation.” European Conference on Computer Vision. vol. 3. (2020); pp. 1-16. [cited by applicant]
Pan, L., Scheerlinck, C., Yu, X., Hartley, R., Liu, M., & Dai, Y. (2019). “Bringing a blurry frame alive at high frame-rate with an event camera,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Re… [cited by applicant]