ROI-Weighted Histogram Equalization for IR Contrast Enhancement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IR imaging systems face challenges in enhancing image contrast while preserving important details and maintaining low resource utilization, particularly in low SWaP-C devices, as existing techniques like PLTEQ and CLAHE either obscure important details or require excessive computing resources.
Innovation Solution
ROI-Weighted Plateau Equalization (RW-PLTEQ) enhances image contrast by defining a user-defined Region of Interest (ROI) with weighted histogram bins, attenuating or scaling non-ROI bins to prioritize important details, using a Cumulative Distribution Function (CDF) for transformation, and incorporating digital filtering and non-uniformity correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If Plateau Equalization (PLTEQ) is used to enhance image contrast, then image contrast is improved, but important details are obscured and unimportant details are enhanced
Solution Approach 1:
The patent applies local quality by creating a weighted histogram where bins corresponding to the Region of Interest (ROI) are assigned higher weights than bins outside the ROI. This is achieved by calculating weight factors based on the proportion of pixels in each bin that fall within the ROI, thereby prioritizing the enhancement of important details located in the ROI while de-emphasizing less important areas.
Solution Approach 2:
The patent segments the image into a Region of Interest (ROI) and non-ROI areas, then segments the histogram into bins corresponding to different intensity ranges. By separately weighting and processing these segments, the method selectively enhances contrast in the ROI while preserving overall image quality and avoiding the enhancement of unimportant background details.
2Loss of information
If the ROI is reduced to a relatively small area to enhance important details, then important details are better enhanced, but the resulting image is blown out with many full black and full white pixels
Solution Approach 1:
The patent changes the parameter of histogram bin weighting by introducing weight factors that dynamically adjust the contribution of different histogram bins to the cumulative distribution function. By setting weight factors greater than 1.0 for bins within the ROI and weight factors less than 1.0 for bins outside the ROI, the method enhances contrast in important areas while maintaining stable pixel distribution and avoiding blown-out images.
3Loss of information
If Contrast Limited Adaptive Histogram Equalization (CLAHE) is used to allow multiple CE regions of interest, then important details in multiple regions are enhanced, but computing resources required are excessive for low SWaP-C devices
Solution Approach 1:
The patent applies partial action by focusing the enhancement process only on the Region of Interest (ROI) rather than processing the entire image with full computational intensity. By calculating weight factors only for bins corresponding to the ROI and using a simplified weighted histogram approach, the method achieves effective contrast enhancement in important areas while requiring significantly fewer computing resources than full CLAHE implementation.
4Illumination intensity
If the histogram is clipped with a plateau limit to avoid over enhancement, then contrast is controlled, but the enhancement of unimportant details and obscuring of important details is not prevented
Solution Approach 1:
The patent combines local quality with histogram clipping by applying the plateau limit selectively based on the spatial location of histogram bins. Bins corresponding to the ROI are allowed to reach higher contrast levels while bins outside the ROI are more heavily clipped. This spatially-aware clipping strategy maintains contrast control while preserving important details in the ROI.
Data Source
AI summary
A method of image enhancement, the method comprising: obtaining image data representing an image comprising a plurality of pixels, each having a pixel intensity value, the image further comprising a region of interest; analyzing image data associated with the region of interest and gathering relevant statistics thereon; analyzing image data associated with the image as a whole and gathering relevant statistics thereon; accumulating a histogram based on the intensity value of pixels in the image as a whole; defining histogram bins of interest that correspond to a range of pixel intensity values from within the region of interest; attenuating histogram bins outside of the bins of interest OR multiplying bins of interest by a scaling factor; using the attenuated or scaled histogram to create a cumulative distribution function; and using the cumulative distribution function to produce a contrast enhanced image.