Image Fusion Using Intensity Mapping Functions to Mitigate Ghosting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image fusion techniques often result in ghosting or blurring due to local motion between successive images captured under different conditions, such as varying exposures or using different imaging devices, which affects the quality of high dynamic range (HDR) image generation and picture detail in low light conditions.
Innovation Solution
The use of intensity mapping functions (IMFs) to predict and fuse image pixel values, either by applying IMF-generated values when within a certain range or using actual values from secondary images when IMF values are not applicable, and the generation of consistency-based weighting factors to de-emphasize regions with relative motion, thereby reducing ghosting artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If multiple images are captured under different conditions (varying exposures, different imaging devices), then the dynamic range and picture detail are improved, but ghosting or blurring occurs due to local motion between successive images
Solution Approach 1:
The patent applies preliminary action by predicting what the reference image pixels should be based on secondary images before performing the fusion operation. This prediction step, using intensity mapping functions, prepares the data in advance to account for motion differences, allowing the fusion to proceed with corrected values that prevent ghosting artifacts while maintaining improved picture detail from multiple captures
2Reliability
If intensity mapping functions are used to predict pixel values, then ghosting artifacts are reduced, but the complexity of the image processing increases
Solution Approach 1:
The patent applies parameter changes by transforming pixel intensity values through intensity mapping functions that adjust brightness parameters. Instead of complex spatial transformations or motion compensation algorithms, the solution changes the intensity parameters directly using learned mapping relationships from training data, simplifying the processing while effectively reducing ghosting artifacts
Data Source
AI summary
Techniques to improve image fusing operations using intensity mapping functions (IMFs) are described. In one approach, when a reference image's pixel values are within its' IMF's useful range, they may be used to generate predicted secondary image pixel values. When the reference image's pixel values are not within the IMF's useful range, actual values from a captured secondary image may be used directly or processed further to generate predicted secondary image pixel values. The predicted and actual pixel values may be used to construct predicted secondary images that may be fused. In another approach, the consistency between pixel pairs may be used to generate consistency-based weighting factors that may be used during image fusion operations.