Exposure Time Adjustment via Motion Cluster Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image capture technologies face challenges in preventing motion blur when capturing images with moving objects or cameras, as they often rely on general exposure time adjustments that may not prioritize the most relevant motion clusters in the scene.

Innovation Solution

An apparatus and method that process consecutive image frames to determine a motion field, segment it into clusters, select the most relevant cluster based on motion information, and adjust exposure time accordingly to avoid motion blur, allowing for more precise control over exposure settings based on the importance of moving objects in the scene.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If exposure time is adjusted automatically or manually to avoid motion blur, then motion blur is reduced, but the adjustment may not prioritize the most relevant motion clusters in the scene

Engineering Contradiction:
Improvemotion blurVSAvoidexposure time adjustment precision
Core Design Contradiction:
Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The patent segments the motion field into multiple motion clusters based on motion characteristics. Each cluster represents a region with similar motion patterns. The system then evaluates the relevance of each cluster and adjusts exposure time specifically for the most relevant cluster, rather than applying a uniform exposure adjustment across the entire image. This segmentation allows precise targeting of exposure adjustment to where it is most needed.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by making different parts of the image have different exposure characteristics. Instead of a single uniform exposure time for the entire image, the system determines separate exposure times for different motion clusters. Regions with significant motion receive shorter exposure times to prevent blur, while static or less important regions can have longer exposure times for better lighting. This creates spatially varying exposure quality optimized for local conditions.

Inventive Principle:
Principle #3Local quality

2Object-affected harmful factors

If general exposure time adjustments are applied to the entire image, then motion blur is reduced overall, but image quality may deteriorate in static or less important regions

Engineering Contradiction:
Improvemotion blurVSAvoidimage quality
Core Design Contradiction:
Object-affected harmful factorsVSManufacturing precision

Solution Approach 1:

The patent divides the image into distinct motion clusters based on motion field analysis. Each cluster is then processed independently for exposure time determination. This segmentation enables the system to apply different exposure settings to different regions, preventing the need to compromise overall image quality to address motion blur in specific areas.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements local quality by allowing each motion cluster to have its own optimized exposure time. Static regions or regions with minimal motion can use longer exposure times for better lighting and detail, while moving objects receive shorter exposure times to eliminate motion blur. This localized optimization ensures that image quality is not sacrificed in static regions to fix motion blur in dynamic regions.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3308536B1Determination of exposure time for an image frame
Publication Date: 2020.04.15 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3308536B1 patent drawingFigure 1
  • EP3308536B1 patent drawingFigure 2A
  • EP3308536B1 patent drawingFigure 2B

AI summary

An apparatus for adjusting an exposure time for an image frame is presented. The apparatus comprises at least one processing unit and at least one memory. The at least one memory stores program instructions that, when executed by the at least one processing unit, cause the apparatus to process at least one image frame, select at least one region of interest from the at least one image frame, process at least two consecutive image frames to determine a motion field, segment the motion field into at least one motion cluster, select based on the at least one region of interest and the at least one motion cluster, the most relevant motion cluster, and adjust the exposure time based on motion information of the selected most relevant motion cluster.