Motion Blur Recognition in Night Vehicle Images Using Brightness Ratios

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Images captured by vehicle-mounted devices in night scenes often suffer from motion blur due to increased exposure time, which adversely affects the execution of machine vision tasks.

Innovation Solution

Perform edge detection to determine a bounding box for a moving object, utilize a preset brightness distribution ratio range to recognize motion blur, and perform predetermined processing on the image based on the target motion blur recognition result, without reducing exposure time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If exposure time is increased to capture night scenes, then image brightness is improved, but motion blur occurs

Engineering Contradiction:
Improveimage brightnessVSAvoidimage quality
Core Design Contradiction:
Illumination intensityVSReliability

Solution Approach 1:

The patent segments the image processing task into multiple stages: edge detection to identify moving objects, brightness distribution analysis to recognize motion blur regions, and selective processing to distinguish between actual moving objects and motion blur artifacts. This segmentation allows the system to handle different image regions with appropriate processing strategies.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter being analyzed from temporal (exposure time) to spatial (brightness distribution pattern). By analyzing the brightness distribution ratio within detected moving object regions, the system can identify motion blur characteristics without altering the exposure time, thus maintaining image brightness while enabling motion blur detection.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If exposure time is reduced to eliminate motion blur, then motion blur is weakened, but signal-to-noise ratio and brightness deteriorate

Engineering Contradiction:
Improvemotion blur reductionVSAvoidimage brightness
Core Design Contradiction:
ReliabilityVSIllumination intensity

Solution Approach 1:

The patent converts the harmful effect of motion blur into a useful indicator for detection. By analyzing the characteristic brightness distribution patterns created by motion blur, the system can identify and process motion blur regions specifically, transforming what was previously a degradation into a detectable feature that enables targeted processing.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

3Illumination intensity

If motion blur recognition is performed without reducing exposure time, then image brightness is maintained, but accurate distinction between moving objects and motion blur is required

Engineering Contradiction:
Improveimage brightnessVSAvoidmotion blur detection accuracy
Core Design Contradiction:
Illumination intensityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent performs preliminary edge detection to identify potential moving object regions before conducting brightness distribution analysis. This preliminary action narrows down the analysis scope to only those regions that contain moving objects, making the subsequent motion blur detection more accurate and efficient by avoiding analysis of static background regions.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4712048A1Image processing method and apparatus, computer-readable storage medium, and electronic device
Publication Date: 2026.03.18 BEIJING HORIZON INFORMATION TECH CO LTD
  • EP4712048A1 patent drawingFigure 1~3
  • EP4712048A1 patent drawingFigure 4~5
  • EP4712048A1 patent drawingFigure 6~7

AI summary

Embodiments of this disclosure disclose an image processing method and apparatus, a computer readable storage medium, and an electronic device. The method includes: performing edge detection on a to-be-processed image, to determine a bounding box for a moving object in the to-be-processed image; obtaining a target motion blur recognition result of the moving object based on a preset brightness distribution ratio range and brightness values of pixels in a region enclosed by the bounding box; and performing predetermined processing on the to-be-processed image based on the target motion blur recognition result. According to the embodiments of this disclosure, adverse effects caused by motion blur can be avoided, helping to ensure execution effects of a machine vision task.