IP Library Granted Patent US 12,475,522
Granted Patent B2
US 12,475,522 · App. 18/316,214 · Granted Nov 18, 2025

Methods and apparatus for scalable processing

Inventors: Te-Won Lee (San Diego, CA); Edwin Chongwoo Park (San Diego, CA)
Assignee: SoftEye, Inc.
G06T1/60G06T1/20G06V40/166G06V40/172H04N23/651H04N25/78
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 12,475,522
App. No.
18/316,214
Granted
Nov 18, 2025
Kind
B2
Abstract

Methods and apparatus for scalable processing. Conventional image sensors read image data in a sequential row-by-row manner. However, image data may be more efficiently processed at different scales. For example, computer vision processing at a first scale may be used to determine whether subsequent processing with more resolution is helpful. Various embodiments of the present disclosure readout image data according to different scales; scaled readouts may be processed using scale specific computer vision algorithms to determine next steps. In addition to scaled readouts of image data, some variants may also provide commonly used data and/or implement pre-processing steps.

Claims (38)

1 . A camera module, comprising:

an array of photosites arranged by rows and columns; and

output logic configured to provide:

a first scaled readout of the array of the photosites for a first exposure and a first integral image of the first scaled readout, and

a second scaled readout of the array of the photosites for the first exposure and a second integral image of the first scaled readout, where the first scaled readout and the second scaled readout comprise destructive photosite discharges.

2 . The camera module of claim 1 , where the first scaled readout is provided before the second scaled readout and the second scaled readout includes the first scaled readout.

3 . The camera module of claim 2 , where the first integral image is provided before the second integral image and the second integral image includes the first integral image.

4 . The camera module of claim 3 , where the first integral image is provided before the second integral image and the second integral image does not include the first integral image.

5 . The camera module of claim 4 , where the output logic comprises a memory buffer.

6 . A method comprising:

capturing light information via an array of photosites in a single exposure;

reading the array to obtain a first scaled readout using a first destructive photosite discharges of a first set of photosites of the array of photosites;

calculating a first scaled integral image from the first scaled readout;

reading the array to obtain a second scaled readout using a second destructive photosite discharges of a second set of photosites of the array of photosites; and

calculating a second scaled integral image from the second scaled readout.

7 . The method of claim 6 , where the first scaled integral image is characterized by a reduced precision.

8 . The method of claim 7 , where the reduced precision is 16-bits.

9 . The method of claim 7 , where the first scaled integral image is limited to a maximum patch size.

10 . The method of claim 6 , where the first scaled readout is a subset of the second scaled readout.

11 . The method of claim 10 , where the first scaled integral image and the second scaled integral image are characterized by a reduced precision.

12 . A camera module, comprising:

an array of photosites arranged by rows and columns; and

output logic configured to provide a first scaled readout of the array of the photosites for a first exposure and a first integral image of the first scaled readout, where the first scaled readout is characterized by a bit-reversed addressing.

13 . The camera module of claim 12 , where the first integral image is characterized by a reduced precision.

14 . The camera module of claim 12 , where the output logic comprises a bus.

15 . The camera module of claim 12 , where the output logic comprises a memory buffer.

16 . The camera module of claim 12 , where the first integral image is characterized by the bit-reversed addressing.

17 . The camera module of claim 13 , where:

the first scaled readout of the array of the photosites comprises a readout of a first subset of photosites of the array of the photosites based on a scale parameter, and

the reduced precision of the first integral image corresponds to the scale parameter.

18 . The camera module of claim 1 , where:

the first scaled readout of the array of the photosites is stored in a first readout memory buffer,

the second scaled readout of the array of photosites is stored in a second readout memory buffer, and

the output logic is configured to output the first readout memory buffer prior to completing storing the second scaled readout in the second readout memory buffer.

19 . The camera module of claim 1 , where:

the first scaled readout of the array of the photosites is stored in a first readout memory buffer and a second readout memory buffer at a set of addresses, and

the second scaled readout of the array of photosites is stored in the second readout memory buffer skipping the set of addresses.

20 . The method of claim 6 , where reading the array to obtain the second scaled readout comprises skipping first photosites of the array of photosites previously read to obtain a first scaled readout.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 20, 2024
From: LEE, TE-WON; PARK, EDWIN CHONGWOO
To: SOFTEYE, INC.
Reel/Frame 068652/0108 →
Continuity (2)
Provisional Application 63340470 · May 11, 2022
Related Publication 20230368326A1 · Nov 16, 2023
References Cited (56)
US 9344649B2 · Bock · 2016 [cited by examiner]
US 9471153B1 · Ivanchenko · 2016 [cited by applicant]
US 9619105B1 · Dal Mutto · 2017 [cited by applicant]
US 9741169B1 · Holz · 2017 [cited by applicant]
US 10366508B1 · Liu et al. · 2019 [cited by applicant]
US 10390003B1 · Liu et al. · 2019 [cited by applicant]
US 10410328B1 · Liu et al. · 2019 [cited by applicant]
US 11611705B1 · Chen · 2023 [cited by applicant]
US 20040143380A1 · Stam · 2004 [cited by examiner]
US 20130106681A1 · Eskilsson et al. · 2013 [cited by applicant]
US 20150049017A1 · Weber et al. · 2015 [cited by applicant]
US 20150130959A1 · Kao · 2015 [cited by examiner]
US 20150338915A1 · Publicover et al. · 2015 [cited by applicant]
US 20160274762A1 · Lopez et al. · 2016 [cited by applicant]
US 20170142313A1 · Gren · 2017 [cited by examiner]
US 20170249009A1 · Parshionikar · 2017 [cited by applicant]
US 20180368074A1 · Gong et al. · 2018 [cited by applicant]
US 20190050685A1 · Kaminski et al. · 2019 [cited by applicant]
US 20190324529A1 · Stellmach et al. · 2019 [cited by applicant]
US 20190362557A1 · Lacey et al. · 2019 [cited by applicant]
US 20200382717A1 · Chiu et al. · 2020 [cited by applicant]
US 20210072831A1 · Edwards · 2021 [cited by applicant]
US 20210201661A1 · Jazaery et al. · 2021 [cited by applicant]
US 20210248427A1 · Guo et al. · 2021 [cited by applicant]
US 20210373657A1 · Connor et al. · 2021 [cited by applicant]
US 20220101593A1 · Rockel et al. · 2022 [cited by applicant]
US 20220326367A1 · Matuszak et al. · 2022 [cited by applicant]
US 20220391697A1 · Mousavi et al. · 2022 [cited by applicant]
US 20230038159A1 · Holland et al. · 2023 [cited by applicant]
US 20230049339A1 · Ganguly et al. · 2023 [cited by applicant]
US 20230118074A1 · Park et al. · 2023 [cited by applicant]
US 20230305632A1 · Lee et al. · 2023 [cited by applicant]
US 20230333384A1 · Zhu et al. · 2023 [cited by applicant]
US 20230368326A1 · Lee et al. · 2023 [cited by applicant]
US 20230368328A1 · Lee et al. · 2023 [cited by applicant]
US 20230370752A1 · Lee et al. · 2023 [cited by applicant]
U.S. Appl. No. 11/847,266, filed Dec. 19, 2023, Lee et al. [cited by applicant]
U.S. Appl. No. 18/745,027, filed Jun. 17, 2024, SoftEye, Inc. [cited by applicant]
U.S. Appl. No. 18/745,233, filed Jun. 17, 2024, SoftEye, Inc. [cited by applicant]
U.S. Appl. No. 18/745,353, filed Jun. 17, 2024, SoftEye, Inc. [cited by applicant]
U.S. Appl. No. 18/745,462, filed Jun. 17, 2024, SoftEye, Inc. [cited by applicant]
Vaswani et al., “Attention Is All You Need,” 31st Conference on Neural Information Processing Systems (NIPS 2017). [cited by applicant]
U.S. Appl. No. 18/061,203, filed Dec. 2, 2022, Te-Won Lee. [cited by applicant]
U.S. Appl. No. 18/061,226, filed Dec. 2, 2022, Te-Won Lee. [cited by applicant]
U.S. Appl. No. 18/061,257, filed Dec. 2, 2022, Te-Won Lee. [cited by applicant]
U.S. Appl. No. 18/185,362, filed Mar. 16, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 18/185,364, filed Mar. 16, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 18/185,366, filed Mar. 16, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 18/316,181, filed May 11, 2023, Te-Won Lee. [cited by applicant]
U.S. Appl. No. 18/316,203, filed May 11, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 18/316,206, filed May 11, 2023, Te-Won Lee. [cited by applicant]
U.S. Appl. No. 18/316,214, filed May 11, 2023, Te-Won Lee. [cited by applicant]
U.S. Appl. No. 18/316,218, filed May 11, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 18/316,221, filed May 11, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 18/316,225, filed May 11, 2023, Edwin Chongwoo Park. [cited by applicant]
U.S. Appl. No. 63/491,733, filed Mar. 22, 2023, Edwin Chongwoo Park. [cited by applicant]