IP Library › Granted Patent US 12,400,301
Granted Patent B2
US 12,400,301 · App. 18/472,702 · Granted Aug 26, 2025

Image generation method and apparatus, device, and storage medium

Inventors: Guangliang Cheng (Hong Kong, CN); Jianping Shi (Hong Kong, CN); Yuji Yasui (Tokyo, JP); Hideki Matsunaga (Tokyo, JP); Kaname Tomite (Tokyo, JP)
Assignees: SENSETIME GROUP LIMITED; HONDA MOTOR CO., LTD.
G06T5/70G06T3/40G06T7/0002
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 12,400,301
App. No.
18/472,702
Granted
Aug 26, 2025
Kind
B2
Abstract

An image generation method includes the following steps. Illumination lamps on a target object in an original image are detected; the original image is converted into an image to be processed that is in a specific scene; in the image to be processed, at least one illumination lamp of which operation state does not match scene information of the specific scene is determined as an object to be replaced; a replacement image including the object to be replaced of which operation state matches the scene information is determined according to the scene information and the object to be replaced; and the image in a region occupied by the object to be replaced in the image to be processed is replaced with the replacement image to generate a target image.

Claims (73)

1. A method of image generation, executed by an electronic device and comprising:

detecting illumination lamps on a target object in an original image;

converting the original image into an image to be processed that is under a specific scene;

determining, in the image to be processed, at least one illumination lamp of which operation state does not match scene information of the specific scene as an object to be replaced;

determining, according to the scene information and the object to be replaced, a replacement image comprising the object to be replaced of which operation state matches the scene information; and

replacing an image of a region occupied by the object to be replaced in the image to be processed with the replacement image to generate a target image.

2. The method of claim 1 , wherein determining, according to the scene information and the object to be replaced, the replacement image comprising the object to be replaced of which the operation state matches the scene information, comprises:

determining attribute information of the object to be replaced;

searching a preset image library for a target preset image comprising a preset object of which attribute matches the attribute information of the object to be replaced; and

determining the searched target preset image as the replacement image, wherein an operation state of the preset object in the replacement image matches the scene information.

3. The method of claim 2 , further comprising:

determining a distance between the object to be replaced and a device collecting the original image;

wherein searching the preset image library for the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced comprises:

searching, according to category information of the object to be replaced and the determined distance, the preset image library for the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced.

4. The method of claim 3 , wherein determining the distance between the object to be replaced and the device collecting the original image comprises:

determining size information of the object to be replaced according to the category information of the object to be replaced; and

determining the distance between the device collecting the original image and the object to be replaced according to the size information and a size of the object to be replaced in the image to be processed.

5. The method of claim 2 , wherein in response to the target preset image not being searched in the preset image library, the method further comprises:

generating the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced; and

determining the generated target preset image as the replacement image.

6. The method of claim 5 , wherein generating the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced comprises:

determining an operation parameter of the preset object according to the distance between the object to be replaced and the device collecting the original image; and

generating the target preset image comprising the preset object according to the determined operation parameter.

7. The method of claim 6 , wherein the operation parameter of the preset object is light intensity of the illumination lamp;

wherein determining the operation parameter of the preset object according to the distance between the object to be replaced and the device collecting the original image comprises: determining the light intensity of the illumination lamp at a turned-on state; and determining the light intensity of the illumination lamp matching the distance according to the distance and the light intensity of the illumination lamp at the turned-on state, and

wherein generating the target preset image comprising the preset object according to the determined operation parameter comprises: generating, according to the light intensity matching the distance, the target preset image comprising the preset object with the light intensity matching the distance.

8. The method of claim 5 , wherein after the target preset image is generated, the method further comprises:

storing the target preset image in the preset image library.

9. The method of claim 1 , wherein replacing the image of the region occupied by the object to be replaced in the image to be processed with the replacement image to generate the target image comprises:

determining size information of the replacement image;

determining an area of the region occupied by the object to be replaced in the image to be processed;

adjusting the size information of the replacement image according to the area to obtain an adjusted image; and

replacing the image of the region occupied by the object to be replaced with the adjusted image to generate a candidate image; and

smoothing the candidate image to generate the target image.

10. The method of claim 1 , wherein the target object comprises a traveling device and a street lamp.

11. A non-transitory computer storage medium, having a computer executable instruction stored thereon, wherein the computer executable instruction, when being executed, enables to implement the following:

detecting illumination lamps on a target object in an original image;

converting the original image into an image to be processed that is under a specific scene;

determining, in the image to be processed, at least one illumination lamp of which operation state does not match scene information of the specific scene as an object to be replaced;

determining, according to the scene information and the object to be replaced, a replacement image comprising the object to be replaced of which operation state matches the scene information; and

replacing an image of a region occupied by the object to be replaced in the image to be processed with the replacement image to generate a target image.

12. An electronic device, comprising a memory and a processor, wherein the memory stores a computer executable instruction; and the processor is configured to execute the computer executable instruction stored on the memory to:

detect illumination lamps on a target object in an original image;

convert the original image into an image to be processed that is under a specific scene;

determine, in the image to be processed, at least one illumination lamp of which operation state does not match scene information of the specific scene as an object to be replaced;

determine, according to the scene information and the object to be replaced, a replacement image comprising the object to be replaced of which operation state matches the scene information; and

replace an image of a region occupied by the object to be replaced in the image to be processed with the replacement image to generate a target image.

13. The electronic device of claim 12 , wherein the operation of determining, according to the scene information and the object to be replaced, the replacement image comprising the object to be replaced of which the operation state matches the scene information comprises:

determining attribute information of the object to be replaced;

searching a preset image library for a target preset image comprising a preset object of which attribute matches the attribute information of the object to be replaced; and

determining the searched target preset image as the replacement image, wherein an operation state of the preset object in the replacement image matches the scene information.

14. The electronic device of claim 13 , wherein the processor is further configured to execute the computer executable instruction stored on the memory to:

determine a distance between the object to be replaced and a device collecting the original image; and

search, according to category information of the object to be replaced and the determined distance, the preset image library for the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced.

15. The electronic device of claim 14 , wherein the operation of determining the distance between the object to be replaced and the device collecting the original image comprises:

determining size information of the object to be replaced according to the category information of the object to be replaced; and

determining the distance between the device collecting the original image and the object to be replaced according to the size information and a size of the object to be replaced in the image to be processed.

16. The electronic device of claim 13 , wherein the processor is further configured to execute the computer executable instruction stored on the memory to: in response to the target preset image not being searched in the preset image library,

generate the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced; and

determine the generated target preset image as the replacement image.

17. The electronic device of claim 16 , wherein the operation of generating the target preset image comprising the preset object of which the attribute matches the attribute information of the object to be replaced comprises:

determining an operation parameter of the preset object according to the distance between the object to be replaced and the device collecting the original image; and

generating the target preset image comprising the preset object according to the determined operation parameter.

18. The electronic device of claim 17 , wherein the operation parameter of the preset object is light intensity of the illumination lamp;

wherein the operation of determining the operation parameter of the preset object according to the distance between the object to be replaced and the device collecting the original image comprises: determining the light intensity of the illumination lamp at a turned-on state; and determining the light intensity of the illumination lamp matching the distance according to the distance and the light intensity of the illumination lamp at the turned-on state, and

wherein the operation of generating the target preset image comprising the preset object according to the determined operation parameter comprises: generating, according to the light intensity matching the distance, the target preset image comprising the preset object with the light intensity matching the distance.

19. The electronic device of claim 16 , wherein the processor is further configured to execute the computer executable instruction stored on the memory to: after the target preset image is generated, store the target preset image in the preset image library.

20. The electronic device of claim 12 , wherein the operation of replacing the image of the region occupied by the object to be replaced in the image to be processed with the replacement image to generate the target image comprises:

determining size information of the replacement image;

determining an area of the region occupied by the object to be replaced in the image to be processed;

adjusting the size information of the replacement image according to the area to obtain an adjusted image; and

replacing the image of the region occupied by the object to be replaced with the adjusted image to generate a candidate image; and

smoothing the candidate image to generate the target image.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 22, 2023
From: CHENG, GUANGLIANG; SHI, JIANPING; YASUI, YUJI; MATSUNAGA, HIDEKI; TOMITE, KANAME
To: SENSETIME GROUP LIMITED; HONDA MOTOR CO., LTD.
Reel/Frame 064997/0334 →
Priority Claims (1)
CN 202110351897.2 · Mar 31, 2021 · national
Continuity (2)
Continuation PCTCN2022074085 · Jan 26, 2022
Related Publication 20240013348A1 · Jan 11, 2024
References Cited (27)
US 10157332B1 · Gray · 2018 [cited by examiner]
US 20150002672A1 · Hayakawa et al. · 2015 [cited by applicant]
US 20170161938A1 · Imber · 2017 [cited by examiner]
US 20170244908A1 · Flack · 2017 [cited by applicant]
US 20180247201A1 · Liu · 2018 [cited by examiner]
US 20200020102A1 · Dai · 2020 [cited by examiner]
US 20210019453A1 · Yang · 2021 [cited by examiner]
US 20210027083A1 · Cohen · 2021 [cited by examiner]
US 20210042950A1 · Wantland · 2021 [cited by examiner]
US 20210150681A1 · Sytnik · 2021 [cited by examiner]
US 20210295571A1 · Sun · 2021 [cited by examiner]
US 20220101577A1 · Chakrabarty · 2022 [cited by examiner]
US 20220284078A1 · Jakkula · 2022 [cited by examiner]
US 20230206568A1 · Du · 2023 [cited by examiner]
CN 102360490A · 2012 [cited by applicant]
CN 108122276A · 2018 [cited by applicant]
CN 110418095A · 2019 [cited by applicant]
CN 111738968A · 2020 [cited by applicant]
CN 111951157A · 2020 [cited by applicant]
CN 112348737A · 2021 [cited by applicant]
CN 113096000A · 2021 [cited by applicant]
JP 2010246166A · 2010 [cited by applicant]
WO 2020039838A1 · 2020 [cited by applicant]
WO 2020220807A1 · 2020 [cited by applicant]
Notice of Allowance of the Japanese application No. 2023-559731, issued on Jul. 16, 2024, 6 pages with English translation. [cited by applicant]
International Search Report in the international application No. PCT/CN2022/074085, mailed on Mar. 29, 2022, 7 pages with English translation. [cited by applicant]
Written Opinion of the International Search Authority in the international application No. PCT/CN2022/074085, mailed on Mar. 29, 2022, 10 pages with English translation. [cited by applicant]