IP Library › Granted Patent US 12,243,281
Granted Patent B2
US 12,243,281 · App. 17/802,451 · Granted Mar 4, 2025

System, an arrangement, a computer software module arrangement, a circuitry arrangement and a method for improved image processing utilizing two entities

Inventors: Yun Li (Lund, SE); Fredrik Dahlgren (Lund, SE); Héctor Caltenco (Oxie, SE); Alexander Hunt (Tygelsjö, SE); Saeed Bastani (Dalby, SE)
Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (publ)
G06V10/20G06T7/11G06T9/002G06V10/96G06T2207/20012G06T2207/20081G06T2207/20084
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 12,243,281
App. No.
17/802,451
Granted
Mar 4, 2025
Kind
B2
Abstract

A system comprising a first image processing arrangement and a second image processing arrangement, wherein the first image processing arrangement comprises a controller configured to: a) receive an image; b) select a task and a task identifier associated with task data; c) compress the image based on the task data; and d) transmit the compressed image to the second image processing arrangement for processing, and wherein the second image processing arrangement comprises a controller configured to: e) receive the compressed image and task identifier; f) retrieve task parameters associated with the task identifier; g) process the compressed image based on the task parameters; h) determine results and i) transmit the at least indications of the determined results to the first image processing arrangement, and the controller of the first image processing arrangement is further configured to: j) receive at least indications of a result of the processing from the second image processing arrangement; and k) indicate the result.

Claims (114)

1. A system comprising a first image processing arrangement and a second image processing arrangement, wherein the first image processing arrangement comprises a controller configured to:

a) receive an image;

b) select a task and a task identifier associated with task data;

c) compress the image based on the task data; and

d) transmit the compressed image to the second image processing arrangement for processing, and wherein the second image processing arrangement comprises a controller configured to:

e) receive the compressed image and task identifier;

f) retrieve task parameters associated with the task identifier;

g) process the compressed image based on the task parameters;

h) determine results and

i) transmit the at least indications of the determined results to the first image processing arrangement, and the controller of the first image processing arrangement is further configured to:

j) receive at least indications of a result of the processing from the second image processing arrangement; and

k) indicate the result.

2. The image processing arrangement according to claim 1 , wherein the image data file is in raw format.

3. The image processing arrangement according to claim 1 , wherein the controller of the first image processing arrangement is further configured to b) select the task in communication with the controller of the second image processing arrangement and wherein the controller of the second image processing arrangement is further configured to select the task in communication with the controller of the first image processing arrangement.

4. The image processing arrangement according to claim 1 , wherein the controller of the first image processing arrangement is further configured to c) compress the image utilizing a compressing neural network.

5. The image processing arrangement according to claim 1 , wherein the controller of the second image processing arrangement is further configured to g) process the compressed image utilizing a processing neural network.

6. The image processing arrangement according to claim 5 , wherein the processing neural network comprises a decompression neural network and a task performing neural network.

7. The image processing arrangement according to claim 4 ,

wherein the controller of the second image processing arrangement is further configured to g) process the compressed image utilizing a processing neural network, and

wherein the controller of the first image processing arrangement and the controller of the second image processing arrangement are further configured to train the compressing neural network and the processing neural network respectively end-to-end.

8. The image processing arrangement according to claim 7 , wherein the controller of the first image processing arrangement and the controller of the second image processing arrangement are further configured to train the compressing neural network and the processing neural network respectively end-to-end by minimizing the bit rate and the task accuracy loss.

9. The image processing arrangement according to claim 7 , wherein the controller of the first image processing arrangement and the controller of the second image processing arrangement are further configured to train the compressing neural network and the processing neural network respectively end-to-end by minimizing the distortion of the image, the bit rate and the task accuracy loss.

10. The image processing arrangement according to claim 1 , wherein the processing is object detection.

11. The image processing arrangement according to claim 1 , wherein the first image processing arrangement is an optical see-through device.

12. The image processing arrangement according to claim 1 , wherein the second image processing arrangement is a smartphone or a computer.

13. The image processing arrangement according to claim 1 , wherein the image processing arrangement is arranged to be used in image retrieval, industrial use, robotic vision and/or video surveillance.

14. A method for image processing in a system comprising a first image processing arrangement and a second image processing arrangement, wherein the method comprises in the first image processing arrangement:

a) receiving an image;

b) selecting a task and a task identifier associated with task data;

c) compressing the image based on the task data; and

d) transmitting the compressed image to the second image processing arrangement for processing, and wherein the method comprises in the second image processing arrangement:

e) receiving the compressed image and task identifier;

f) retrieving task parameters associated with the task identifier;

g) processing the compressed image based on the task parameters;

h) determining results and

i) transmitting the at least indications of the determined results to the first image processing arrangement, and the method further comprises in the first image processing arrangement:

j) receiving at least indications of a result of the processing from the second image processing arrangement; and

k) indicating the result.

15. An image processing arrangement for image processing in an image processing arrangement system comprising a first image processing arrangement and a second image processing arrangement, the image processing arrangement comprising circuitry for processing images comprising:

a) a circuitry for receiving an image in the first image processing arrangement;

b) a circuitry for selecting a task and a task identifier associated with task data in the first image processing arrangement;

c) a circuitry for compressing the image based on the task data in the first image processing arrangement; and

d) a circuitry for transmitting the compressed image to the second image processing arrangement for processing;

e) a circuitry for receiving the compressed image and task identifier in the second image processing arrangement;

f) a circuitry for retrieving task parameters associated with the task identifier in the second image processing arrangement;

g) a circuitry for processing the compressed image based on the task parameters in the second image processing arrangement;

h) a circuitry for determining results and

i) a circuitry for transmitting the at least indications of the determined results to the first image processing arrangement;

j) a circuitry for receiving at least indications of a result of the processing from the second image processing arrangement in the first image processing arrangement; and

k) a circuitry for indicating the result.

16. A first image processing arrangement comprising a controller configured to:

a) receive an image;

b) select a task and a task identifier associated with task data;

c) compress the image based on the task data; and

d) transmit the compressed image to the second image processing arrangement for processing;

j) receive at least indications of a result of the processing from the second image processing arrangement; and

k) indicate the result.

17. A method for image processing in a first image processing arrangement, said method comprising:

a) receiving an image;

b) selecting a task and a task identifier associated with task data;

c) compressing the image based on the task data; and

d) transmitting the compressed image to the second image processing arrangement for processing;

j) receiving at least indications of a result of the processing from the second image processing arrangement; and

k) indicating the result.

18. An arrangement comprising circuitry for image processing in a first image processing arrangement, said arrangement comprising circuitry comprising:

a) a circuitry for receiving an image;

b) a circuitry for selecting a task and a task identifier associated with task data;

c) a circuitry for compressing the image based on the task data; and

d) a circuitry for transmitting the compressed image to the second image processing arrangement for processing;

j) a circuitry for receiving at least indications of a result of the processing from the second image processing arrangement; and

k) a circuitry for indicating the result.

19. A second image processing arrangement comprising a controller configured to:

e) receive a compressed image and a task identifier from a first image processing arrangement;

f) retrieve task parameters associated with the task identifier;

g) process the compressed image based on the task parameters;

h) determine results; and

i) transmit at least indications of the determined results to the first image processing arrangement.

20. A method for image processing in a second image processing arrangement, said method comprising:

e) receiving a compressed image and a task identifier from a first image processing arrangement;

f) retrieving task parameters associated with the task identifier;

g) processing the compressed image based on the task parameters;

h) determining results; and

i) transmitting at least indications of the determined results to the first image processing arrangement.

21. An arrangement comprising circuitry for image processing in a second image processing arrangement, said arrangement comprising circuitry comprising:

e) a circuitry for receiving a compressed image and a task identifier from a first image processing arrangement;

f) a circuitry for retrieving task parameters associated with the task identifier;

g) a circuitry for processing the compressed image based on the task parameters;

h) a circuitry for determining results; and

i) a circuitry for transmitting at least indications of the determined results to the first image processing arrangement.

22. A non-transitory computer-readable medium carrying computer instructions that when loaded into and executed by a controller of an image processing arrangement enables the image processing arrangement to implement a method for image processing in a system comprising a first image processing arrangement and a second image processing arrangement, wherein the method comprises in the first image processing arrangement:

a) receiving an image;

b) selecting a task and a task identifier associated with task data;

c) compressing the image based on the task data; and

d) transmitting the compressed image to the second image processing arrangement for processing, and wherein the method comprises in the second image processing arrangement:

e) receiving the compressed image and task identifier;

f) retrieving task parameters associated with the task identifier;

g) processing the compressed image based on the task parameters;

h) determining results and

i) transmitting the at least indications of the determined results to the first image processing arrangement, and the method further comprises in the first image processing arrangement:

j) receiving at least indications of a result of the processing from the second image processing arrangement; and

k) indicating the result.

23. A non-transitory computer-readable medium carrying computer instructions that when loaded into and executed by a controller of an image processing arrangement enables the image processing arrangement to implement a method for image processing in a first image processing arrangement, said method comprising:

a) receiving an image;

b) selecting a task and a task identifier associated with task data;

c) compressing the image based on the task data; and

d) transmitting the compressed image to the second image processing arrangement for processing;

j) receiving at least indications of a result of the processing from the second image processing arrangement; and

k) indicating the result.

24. A non-transitory computer-readable medium carrying computer instructions that when loaded into and executed by a controller of an image processing arrangement enables the image processing arrangement to implement a method for image processing in a second image processing arrangement, said method comprising:

e) receiving a compressed image and a task identifier from a first image processing arrangement;

f) retrieving task parameters associated with the task identifier;

g) processing the compressed image based on the task parameters;

h) determining results; and

i) transmitting at least indications of the determined results to the first image processing arrangement.

Assignments (1)
NUNC PRO TUNC ASSIGNMENT Recorded Aug 25, 2022
From: BASTANI, SAEED; CALTENCO, HECTOR; DAHLGREN, FREDRIK; HUNT, ALEXANDER; LI, YUN
To: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
Reel/Frame 060903/0847 →
Continuity (1)
Related Publication 20230100728A1 · Mar 30, 2023
References Cited (27)
US 10984560B1 · Appalaraju · 2021 [cited by examiner]
US 20130194617A1 · Link · 2013 [cited by examiner]
US 20180063538A1 · Bernal et al. · 2018 [cited by applicant]
US 20180174047A1 · Bourdev et al. · 2018 [cited by applicant]
US 20180199039A1 · Trepte · 2018 [cited by applicant]
US 20190158884A1 · Tsai et al. · 2019 [cited by applicant]
US 20190327486A1 · Liao · 2019 [cited by examiner]
US 20200143457A1 · Manmatha · 2020 [cited by examiner]
US 20210110191A1 · Gruteser · 2021 [cited by examiner]
US 20220189155A1 · Wu · 2022 [cited by examiner]
US 20240290055A1 · El Essaili · 2024 [cited by examiner]
CN 110149456A · 2019 [cited by examiner]
CN 118489253A · 2024 [cited by examiner]
EP 2595113A2 · 2013 [cited by examiner]
WO 2018150083A1 · 2018 [cited by applicant]
WO 2020008104A1 · 2020 [cited by applicant]
L. Baroffio, M. Cesana, A. Redondi and M. Tagliasacchi, “Performance evaluation of object recognition tasks in visual sensor networks,” 2014 26th International Teletraffic Congress (ITC), Karlskrona, Sweden, 2014, pp. 1… [cited by examiner]
Ahn J, Park J, Park D, Paek J, Ko J. Convolutional neural network-based classification system design with compressed wireless sensor network images. PLoS One. May 8, 2018;13(5):e0196251. doi: 10.1371/journal.pone.019625… [cited by examiner]
Q. Wang, L. Shen and Y. Shi, “Recognition-Driven Compressed Image Generation Using Semantic-Prior Information,” in IEEE Signal Processing Letters, vol. 27, pp. 1150-1154, 2020, doi: 10.1109/LSP.2020.3004967. (Year: 2020… [cited by examiner]
European Communication issued Sep. 25, 2024 in connection with European Application No. 20711518.9, 16 pages. [cited by applicant]
PCT International Search Report, mailed Nov. 26, 2020, in connection with International Application No. PCT/EP2020/055525, all pages. [cited by applicant]
PCT Written Opinion, mailed Nov. 26, 2020, in connection with International Application No. PCT/EP2020/055525, all pages. [cited by applicant]
Galteri, L, et al., “Video Compression for Object Detection Algorithms”, 2018 24th International Conference on Pattern Recognition (ICPR), Bejing, China, Aug. 20-24, 2018, pp. 3007-3012. [cited by applicant]
Balle, J. et al., “End-To-End Optimized Image Compression”, published as a conference paper at ICLR 2017, arXiv:1611.01704v3 [cs.CV] Mar. 3, 2017, pp. 1-27. [cited by applicant]
Balle, J., et al., “Variational Image Compression with a Scale Hyperprior”, Published as a conference paper at ICLR 2018, arXiv:1802.01436v2 [eess.IV] May 1, 2018, pp. 1-23. [cited by applicant]
Torfason, R., et al., “Towards Image Understanding from Deep Compression Without Decoding”, published as a conference paper at ICLR 2018, arXiv:1803.06131v1 [cs.CV] Mar. 16, 2018, pp. 1-17. [cited by applicant]
Shen, Qui et al., “Coded Vision: Towards Joint Image Understanding and Compression via End-to-End Learning”, Intelligent Virtual Agent. IVA 2015. LNCS; [Lecture Notes in Computer Science; Lect. Notes Computer], Sep. 19,… [cited by applicant]
Cited By (1)
US 12,567,976