Image Compositing Apparatus Motion Vector Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image compositing technologies face challenges in creating clear composite images of moving subjects while minimizing blur and multiple images in still regions, as they often rely on either global or local motion vectors alone, which are insufficient for handling complex motion scenarios.
Innovation Solution
An image compositing apparatus and method that calculates both global and local motion vectors, generates corrected reference images based on these vectors, and determines composition ratios to effectively composite images, with the global motion vector composition ratio being higher in moving regions to maintain subject trajectory clarity and suppress blur in still regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If only global motion vector is used for image compositing, then camera shake can be eliminated, but moving subjects cannot be clearly distinguished from background
Solution Approach 1:
The patent segments the image into multiple blocks and calculates motion vectors for each block independently. This allows differentiation between global camera motion (affecting all blocks) and local subject motion (affecting specific blocks), resolving the contradiction by treating different regions with appropriate motion compensation
Solution Approach 2:
The patent applies different composition ratios to different regions based on motion analysis. Blocks with motion vectors significantly different from the global motion vector are identified as containing moving subjects and receive different weighting, preserving subject trajectory while maintaining background stability
2Loss of information
If only local motion vector is used for image compositing, then moving subjects can be tracked, but camera shake cannot be effectively eliminated
Solution Approach 1:
The patent merges global motion vector compensation with local motion vector compensation by compositing multiple corrected images with different weights. The final composite image combines the stability from global correction with the subject tracking from local correction, resolving the contradiction between camera shake elimination and subject trajectory preservation
3Reliability
If multiple corrected images are composited with equal weights, then both global and local motion can be compensated, but blur and multiple images occur in still regions
Solution Approach 1:
The patent dynamically changes the composition ratio parameter based on motion analysis results. For blocks identified as containing moving subjects, a higher weight is given to the locally-corrected image to preserve trajectory. For still background regions, a higher weight is given to the globally-corrected image to eliminate camera shake and prevent blur, thus resolving the contradiction between motion compensation accuracy and image clarity
Data Source
AI summary
A moving region information calculation unit calculates moving region information from a global motion vector and a local motion vector. An image correction unit generates a corrected reference image obtained by correcting a reference image based on the global motion vector and a corrected reference image obtained by correcting the reference image based on the local motion vector. A composition unit composites a base image with the corrected reference images with composition ratios determined based on the moving region information. The composition ratio of the corrected reference image corrected based on the global motion vector is higher than the composition ratio of the corrected reference image corrected based on the local motion vector in a region having the moving region information indicative of a moving region.