Imaging exposure control method and apparatus, device and storage medium

Patent metadata

Field	Value
Publication number	US-12335629-B2
Application number	US-202217885035-A
Country	US
Kind code	B2
Filing date	Aug 10, 2022
Priority date	Nov 25, 2021
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

An imaging exposure control method and apparatus, a device and a storage medium, which relate to the field of artificial intelligence technologies, such as machine learning technologies and intelligent imaging technologies, are disclosed. An implementation includes performing semantic segmentation on a preformed image to obtain semantic segmentation images of at least two semantic regions; estimating an exposure duration of each semantic region based on the semantic segmentation image and the preformed image; and controlling exposure of each semantic region during imaging based on the exposure duration of each semantic region.

First claim

What is claimed is:

1. An imaging exposure control method, comprising:
performing semantic segmentation on a preformed image to obtain semantic segmentation images of at least two semantic regions, each semantic region corresponds to one object;
estimating an exposure duration of each semantic region based on the semantic segmentation images and the preformed image; and
controlling liquid crystal shutters in a liquid crystal shutter matrix corresponding to each semantic region during imaging to perform exposure of each semantic region based on the exposure duration of each semantic region, so as to obtain an image in which different objects can correspond to different exposure duration.

2. The method according to claim 1 , wherein the performing semantic segmentation on the preformed image to obtain semantic segmentation images of at least two semantic regions comprises:
performing the semantic segmentation on the preformed image using a pre-trained semantic segmentation model to obtain the semantic segmentation images of the at least two semantic regions.

3. The method according to claim 1 , wherein the estimating the exposure duration of each semantic region based on the semantic segmentation images and the preformed image comprises:
estimating the exposure duration of each semantic region based on the semantic segmentation images and the preformed image using a pre-trained exposure duration estimating model.

4. The method according to claim 1 , further comprising: before the controlling liquid crystal shutters in a liquid crystal shutter matrix corresponding to each semantic region during imaging to perform the exposure based on the exposure duration of each semantic region,
determining the liquid crystal shutters in the matrix corresponding to each semantic region based on the semantic segmentation image and the liquid crystal shutter matrix.

5. The method according to claim 1 , further comprising: before the performing semantic segmentation on the preformed image to obtain semantic segmentation images comprising at least two semantic regions,
generating the preformed image in a focusing and/or photometry process.

6. The method according to claim 1 , wherein each of the liquid crystal shutters in the liquid crystal shutter matrix is independently controlled and switched between a light transmitting state and a light non-transmitting state, and each of the liquid crystal shutters corresponds to one or more pixel regions in an imaging element.

7. An electronic device, comprising:
at least one processor; and
a memory connected with the at least one processor communicatively;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform an imaging exposure control method comprising:
performing semantic segmentation on a preformed image to obtain semantic segmentation images of at least two semantic regions, each semantic region corresponds to one object;
estimating an exposure duration of each semantic region based on the semantic segmentation images and the preformed image; and
controlling liquid crystal shutters in a liquid crystal shutter matrix corresponding to each semantic region during imaging to perform exposure of each semantic region based on the exposure duration of each semantic region, so as to obtain an image in which different objects can correspond to different exposure duration.

8. The electronic device according to claim 7 , wherein the performing semantic segmentation on the preformed image to obtain semantic segmentation images of at least two semantic regions comprises:
performing the semantic segmentation on the preformed image using a pre-trained semantic segmentation model to obtain the semantic segmentation images of the at least two semantic regions.

9. The electronic device according to claim 7 , wherein the estimating the exposure duration of each semantic region based on the semantic segmentation images and the preformed image comprises:
estimating the exposure duration of each semantic region based on the semantic segmentation images and the preformed image using a pre-trained exposure duration estimating model.

10. The electronic device according to claim 7 , wherein the method further comprises: before the controlling liquid crystal shutters in a liquid crystal shutter matrix corresponding to each semantic region during imaging to perform the exposure based on the exposure duration of each semantic region,
determining the liquid crystal shutters in the matrix corresponding to each semantic region based on the semantic segmentation image and the liquid crystal shutter matrix.

11. The electronic device according to claim 7 , wherein the method further comprises: before the performing semantic segmentation on the preformed image to obtain semantic segmentation images comprising at least two semantic regions,
generating the preformed image in a focusing and/or photometry process.

12. A non-transitory computer readable storage medium with computer instructions stored thereon, wherein the computer instructions are used for causing a computer to perform an imaging exposure control method comprising:
performing semantic segmentation on a preformed image to obtain semantic segmentation images of at least two semantic regions, each semantic region corresponds to one object;
estimating an exposure duration of each semantic region based on the semantic segmentation images and the preformed image; and
controlling liquid crystal shutters in a liquid crystal shutter matrix corresponding to each semantic region during imaging to perform exposure of each semantic region based on the exposure duration of each semantic region, so as to obtain an image in which different objects can correspond to different exposure duration.

13. The non-transitory computer readable storage medium according to claim 12 , wherein the performing semantic segmentation on the preformed image to obtain semantic segmentation images of at least two semantic regions comprises:
performing the semantic segmentation on the preformed image using a pre-trained semantic segmentation model to obtain the semantic segmentation images of the at least two semantic regions.

14. The non-transitory computer readable storage medium according to claim 12 , wherein the estimating the exposure duration of each semantic region based on the semantic segmentation images and the preformed image comprises:
estimating the exposure duration of each semantic region based on the semantic segmentation images and the preformed image using a pre-trained exposure duration estimating model.

15. The non-transitory computer readable storage medium according to claim 12 , wherein the method further comprises: before the controlling liquid crystal shutters in a liquid crystal shutter matrix corresponding to each semantic region during imaging to perform the exposure based on the exposure duration of each semantic region,
determining the liquid crystal shutters in the matrix corresponding to each semantic region based on the semantic segmentation image and the liquid crystal shutter matrix.

16. The non-transitory computer readable storage medium according to claim 12 , wherein the method further comprises: before the performing semantic segmentation on the preformed image to obtain semantic segmentation images comprising at least two semantic regions,
generating the preformed image in a focusing and/or photometry process.

17. An imaging apparatus, comprising:
an electronic device, comprising: at least one processor; and a memory c

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Wei Shengyu
• Du Yuning
• Cui Cheng
• Guo Ruoyu
• Dong Shuilong
• Lu Bin
• Gao Tingquan
• Liu Qiwen
• Hu Xiaoguang
• Yu Dianhai
• Ma Yanjun

Classifications

• G06T2207/20081

  Training; Learning · CPC title

• G02F1/13306

  Circuit arrangements or driving methods for the control of single liquid crystal cells (G02F1/132, G02F1/133382 take precedence) · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/80

  Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration · CPC title

• H04N23/61

  based on recognised objects · CPC title